@article {pmid41134096,
year = {2025},
author = {Lu, T and Jiang, S and Liu, X and Lu, Z and Sadaqat, M and Chen, C and Zuo, X and Tahir Ul Qamar, M},
title = {Pan-genome analysis and functional characterisation of the terpene synthase (TPS) gene family in five varieties of yellowhorn (Xanthoceras sorbifolium).},
journal = {Functional plant biology : FPB},
volume = {52},
number = {10},
pages = {},
doi = {10.1071/FP24349},
pmid = {41134096},
issn = {1445-4416},
mesh = {*Alkyl and Aryl Transferases/genetics/metabolism ; Phylogeny ; *Multigene Family ; *Genome, Plant/genetics ; *Sapindaceae/genetics/enzymology ; *Plant Proteins/genetics/metabolism ; Gene Expression Regulation, Plant ; Stress, Physiological/genetics ; },
abstract = {The terpene synthase (TPS) gene family is integral to the biosynthesis of terpenoids, which are vital for plant defence, development, and interaction with the environment. Yellowhorn (Xanthoceras sorbifolium) has gained attention for its bioactive compounds, particularly terpenoids, which have applications in pharmaceuticals, biofuels, and cosmetics. This study provides a comprehensive pan-genome-wide analysis of the TPS gene family across five yellowhorn varieties (Xg11, Xzs4, Xwf8, Xjg, and Xzg2). A total of 257 TPS genes were identified and characterised, showing diversity in their evolutionary patterns. Phylogenetic analysis revealed distinct clades corresponding to functional classes of TPS genes. Conserved domains and motifs of these genes were analysed to highlight their structural characteristics. Furthermore, expression profiling under abiotic stresses, including cold and drought, was conducted, revealing the roles of specific TPS genes in stress tolerance. Tissue-specific expression analysis demonstrated the involvement of TPS genes in key physiological processes across different plant organs. This research advances our understanding of the TPS gene family in yellowhorn, with implications for improving crop resilience and biotechnological applications.},
}

*Alkyl and Aryl Transferases/genetics/metabolism
Phylogeny
*Multigene Family
*Genome, Plant/genetics
*Sapindaceae/genetics/enzymology
*Plant Proteins/genetics/metabolism
Gene Expression Regulation, Plant
Stress, Physiological/genetics

@article {pmid41133102,
year = {2025},
author = {Shi, Y and Liu, L and Wu, J and Gao, M and Sheng, K and Hou, W and Li, X and Wang, H},
title = {Whole-genome sequencing and analysis of a novel strain Streptococcus oralis CRC211 from colorectal tumor.},
journal = {Microbiome research reports},
volume = {4},
number = {3},
pages = {33},
pmid = {41133102},
issn = {2771-5965},
abstract = {Aim: This study provides a comprehensive genomic characterization of Streptococcus oralis CRC211, a novel bacterial strain isolated from colorectal tumor tissue. Methods: Whole-genome sequencing and comparative genomic analyses were performed. Results: The high-quality assembled genome (15.03 Mb, 40.94% guanine-cytosine content) contains 2 prophage regions spanning 160.5 kb, which may facilitate the horizontal transfer of virulence genes. Functional annotation identified 3,674 genes, with significant enrichment in metabolic pathways (amino acid and carbohydrate metabolism) and virulence factors (116 genes in Virulence Factors Batabase), including adhesins and biofilm-associated proteins that likely promote tumor colonization. Comparative genomic analysis revealed that CRC211 shares 92.29% average nucleotide identity with reference Streptococcus oralis strains, while pan-genome analysis demonstrated an open genome structure with 1,222 conserved core genes. In addition, the strain also carries 75 antimicrobial resistance genes, underscoring its potential clinical relevance. Notably, the genomic profile indicates adaptations for nutrient acquisition and immune evasion in the tumor microenvironment. Conclusion: These findings establish CRC211 as a colorectal cancer (CRC)-associated strain with distinct genomic features that may contribute to tumor progression. The study provides critical insights into its possible oncogenic mechanisms and highlights potential applications in mic ases,indels - changerobiota-based diagnostics or therapeutics for colorectal cancer.},
}

@article {pmid41132938,
year = {2025},
author = {Wang, J and Zhou, Q and Liu, Y and Li, R and Lan, L and Zhao, J and Yang, Z and Jia, Y and Hu, H},
title = {Editorial: Exploring structural variants in plant pangenomics: innovations and applications.},
journal = {Frontiers in plant science},
volume = {16},
number = {},
pages = {1700222},
pmid = {41132938},
issn = {1664-462X},
}

@article {pmid41132369,
year = {2025},
author = {Huang, Z and Ren, Q and Du, X and Cao, S and Li, Y},
title = {Epidemiological and comparative genomic analysis of pathogenic Glaesserella parasuis from livestock agriculture in Shandong, China.},
journal = {Frontiers in microbiology},
volume = {16},
number = {},
pages = {1698342},
pmid = {41132369},
issn = {1664-302X},
abstract = {Glaesserella parasuis (G. parasuis) is the causative agent of Glässer's disease, posing a significant economic threat to the livestock agriculture. The present study aimed to investigate the prevalence of G. parasuis in six regions of Shandong Province, China, from June 2023 to November 2024, and to analyze the whole genome of G. parasuis isolates using whole genome sequencing (WGS). This study conducted a comprehensive analysis of the isolates, encompassing antibiotic resistance profiling, virulence gene detection, multilocus sequence typing (MLST), prophage detection, and pan-genome analysis. The prevalence of G. parasuis ranged from 10.8 to 26.5% across different cities in Shandong Province, exhibiting significant seasonal variation (p < 0.01). Among the 45 isolates, serovar 4 accounted for the highest proportion (40%). Antibiotic resistance testing revealed that 55.6% of isolates demonstrated multidrug-resistance (MDR). WGS analysis revealed that 18 distinct sequence types (STs) were identified across the 45 isolates, including 13 newly discovered STs. Notably, all isolates possessed complete prophage sequences. Pan-genome and phylogenetic analysis of 145 G. parasuis strains indicated that G. parasuis possesses an open pan-genome with genetic diversity. In summary, these data enhance our understanding of the molecular characteristics and epidemiological risks of G. parasuis in Shandong Province, China, particularly regarding livestock agriculture.},
}

@article {pmid41131485,
year = {2025},
author = {Sorin, V and Naji, MM and Birbes, C and Grohs, C and Escouflaire, C and Fritz, S and Eché, C and Marcuzzo, C and Suin, A and Donnadieu, C and Gaspin, C and Iampietro, C and Milan, D and Drouilhet, L and Tosser-Klopp, G and Boichard, D and Klopp, C and Sanchez, MP and Boussaha, M},
title = {Application of a French cattle pangenome, from structural variant discovery to association studies on key phenotypes.},
journal = {Genetics, selection, evolution : GSE},
volume = {57},
number = {1},
pages = {61},
pmid = {41131485},
issn = {1297-9686},
abstract = {BACKGROUND: The current cattle reference genome assembly, a pseudo-linear sequence produced using sequences from a single Hereford cow, represents a limitation when performing genetic studies, especially when investigating the whole spectrum of genetic variations within the species. Detecting structural variations (SVs) poses significant challenges when relying solely on conventional methods of sequencing read mapping to the current bovine genome assembly.

RESULTS: In this study, we used long-reads (LR) and bioinformatic tools to construct a comprehensive bovine pangenome, using as a backbone the Hereford ARS-UCD1.2 reference genome assembly, and incorporating genetic diversity of 64 good quality de novo genome assemblies representing 14 French dairy and beef cattle breeds. Using a combination of complementary approaches, we explored the pangenome graph and identified 2.563 Gb of sequences common to all samples, and cumulated 0.295 Gb of variable sequences. Notably, we discovered 0.159 Gb of novel sequences not present in the current reference genome assembly. Our analysis also revealed 109,275 SVs, of which 84,612 were bi-allelic. These included 27,171 insertions and 24,592 deletions, while the remaining 32,849 SVs corresponded to alternate allele sequences defined as sequence substitutions between the reference genome and the sample sequence. Genome-wide association studies using SNPs and a panel of 221 SVs, shared between the pangenome and the EuroGMD chip, revealed well-known QTLs across the genome for the Holstein, Montbéliarde and Normande breeds. Among those, a QTL on chromosome 11 presents an SV with a highly significant effect on stature in the Holstein breed. This SV is a 6.2 kb deletion affecting the 5'UTR, first exon and part of the first intron of the MATN3 gene, suggesting a potential regulatory and coding effect.

CONCLUSIONS: Our study provides new insights into the genetic diversity of 14 French dairy and beef breeds and highlights the utility of pangenome graphs in capturing structural variation. The identified SV associated with stature highlights the importance of integrating SVs into GWAS for a more comprehensive understanding of complex traits.},
}

@article {pmid41126024,
year = {2025},
author = {Man, Q and Li, W and Gao, S and Liu, F and Sun, S and Liu, X and Lin, B and Wang, L and Ding, M and Chen, X and Cui, J},
title = {Pan-genome identification and expression analysis of the ARF gene family in potato.},
journal = {BMC plant biology},
volume = {25},
number = {1},
pages = {1435},
pmid = {41126024},
issn = {1471-2229},
support = {SG2012016//Hebei province detoxigenic potato breeding technology innovation center/ ; SG2012016//Hebei province detoxigenic potato breeding technology innovation center/ ; SG2012016//Hebei province detoxigenic potato breeding technology innovation center/ ; SG2012016//Hebei province detoxigenic potato breeding technology innovation center/ ; SG2012016//Hebei province detoxigenic potato breeding technology innovation center/ ; SG2012016//Hebei province detoxigenic potato breeding technology innovation center/ ; SG2012016//Hebei province detoxigenic potato breeding technology innovation center/ ; SG2012016//Hebei province detoxigenic potato breeding technology innovation center/ ; SG2012016//Hebei province detoxigenic potato breeding technology innovation center/ ; SG2012016//Hebei province detoxigenic potato breeding technology innovation center/ ; SG2012016//Hebei province detoxigenic potato breeding technology innovation center/ ; SC2021028//Hebei Potato Seed Potato Industry Technology Research Institute/ ; SC2021028//Hebei Potato Seed Potato Industry Technology Research Institute/ ; SC2021028//Hebei Potato Seed Potato Industry Technology Research Institute/ ; SC2021028//Hebei Potato Seed Potato Industry Technology Research Institute/ ; SC2021028//Hebei Potato Seed Potato Industry Technology Research Institute/ ; SC2021028//Hebei Potato Seed Potato Industry Technology Research Institute/ ; SC2021028//Hebei Potato Seed Potato Industry Technology Research Institute/ ; SC2021028//Hebei Potato Seed Potato Industry Technology Research Institute/ ; SC2021028//Hebei Potato Seed Potato Industry Technology Research Institute/ ; SC2021028//Hebei Potato Seed Potato Industry Technology Research Institute/ ; SC2021028//Hebei Potato Seed Potato Industry Technology Research Institute/ ; 202206F013//Hebei (Chengde) Potato Seed Potato Industry Technology Research Institute improved innovation ability/ ; 202206F013//Hebei (Chengde) Potato Seed Potato Industry Technology Research Institute improved innovation ability/ ; 202206F013//Hebei (Chengde) Potato Seed Potato Industry Technology Research Institute improved innovation ability/ ; 202206F013//Hebei (Chengde) Potato Seed Potato Industry Technology Research Institute improved innovation ability/ ; 202206F013//Hebei (Chengde) Potato Seed Potato Industry Technology Research Institute improved innovation ability/ ; 202206F013//Hebei (Chengde) Potato Seed Potato Industry Technology Research Institute improved innovation ability/ ; 202206F013//Hebei (Chengde) Potato Seed Potato Industry Technology Research Institute improved innovation ability/ ; 202206F013//Hebei (Chengde) Potato Seed Potato Industry Technology Research Institute improved innovation ability/ ; 202206F013//Hebei (Chengde) Potato Seed Potato Industry Technology Research Institute improved innovation ability/ ; 202206F013//Hebei (Chengde) Potato Seed Potato Industry Technology Research Institute improved innovation ability/ ; 202206F013//Hebei (Chengde) Potato Seed Potato Industry Technology Research Institute improved innovation ability/ ; },
abstract = {BACKGROUND: The auxin response factor (ARF) is a key regulator involved in plant growth, development, and stress response. In this study, we systematically identified the ARF gene family using a pan-genomic approach based on 47 high-quality potato genomes.

RESULTS: Among the 28 members of the potato ARF pan-gene family, no core or private genes were identified. Only one gene was classified as near-core, while the remaining genes were considered non-essential. Ka/Ks analysis indicated that a single gene was under positive selection, whereas the rest of the family members were subject to purifying selection. Structural variations across the 21 potato genomes did not significantly alter the expression of ARF pan-gene family members, and no notable expression differences were detected. However, these structural variations did lead to changes in conserved domains in certain strains. RNA-seq analysis revealed differential expression of ARF family members under drought stress compared to control conditions, with variation in expression levels among different genes. Further investigation suggested that transcription factors are involved in regulating the expression of ARF gene family members.

CONCLUSIONS: Our findings revealed the function of the auxin response-factor family members in biological processes in potato, and provide a new theoretical reference for drought resistance-breeding in this important crop species.},
}

@article {pmid41117958,
year = {2025},
author = {Koech, N and Muoma, J and Banerjee, A and Okoth, P and Wekesa, C},
title = {Modular evolution and regulatory diversification of nodD-like LysR-type transcriptional regulators in α-Proteobacteria.},
journal = {Archives of microbiology},
volume = {207},
number = {12},
pages = {327},
pmid = {41117958},
issn = {1432-072X},
mesh = {*Bacterial Proteins/genetics/metabolism/chemistry ; *Transcription Factors/genetics/metabolism/chemistry ; *Gene Expression Regulation, Bacterial ; *Evolution, Molecular ; *Alphaproteobacteria/genetics/classification/metabolism ; Phylogeny ; Gene Transfer, Horizontal ; Genome, Bacterial ; Operon ; Symbiosis ; },
abstract = {The nodD gene encodes a LysR-type transcriptional regulator critical for nodulation gene expression in rhizobia, yet its evolutionary origin, structural plasticity, and regulatory reach beyond symbiosis remain incompletely resolved. Here we investigate the genomic organization, structural variation, and functional diversification of nodD and its homologs across α-proteobacteria with selected outgroups. Using orthogroup-based pangenome clustering, dated species trees, and gene-tree-species-tree reconciliation, we reconstruct the evolutionary trajectory of nodD, indicating emergence from ancient LTTRs deep in proteobacterial history. Reconciliation reveals widespread duplication and horizontal gene transfer (HGT), with several rhizobia showing notable duplication and exchange, and marine/non-rhizobial taxa contributing to a mosaic of nodD-like genes. Gene-neighborhood and operon analyses show conserved syntenic tendencies in classical rhizobia but extensive architectural divergence in free-living lineages, including frequent monocistronic anchors with extended upstream regions and, when polycistronic, enrichment for transporters and local metabolic enzymes within compact multi-regulator cassettes. Structural comparisons with AlphaFold and PyMOL confirm the canonical LTTR fold while uncovering species-specific deviations concentrated in effector-binding loops and interfaces. Motif discovery and genome-wide scanning identify targets involved in metabolism, stress responses, and transcriptional control, and network analysis reveals modular connectivity spanning core metabolism and accessory processes such as secondary metabolism, transport, and biofilm-associated functions. These findings portray nodD as a structurally conserved yet functionally flexible regulator repeatedly reshaped by duplication, HGT, and local genome context, extending nodD-like systems beyond symbiosis and broadening the regulatory landscape of bacterial LTTRs.},
}

*Bacterial Proteins/genetics/metabolism/chemistry
*Transcription Factors/genetics/metabolism/chemistry
*Gene Expression Regulation, Bacterial
*Evolution, Molecular
*Alphaproteobacteria/genetics/classification/metabolism
Phylogeny
Gene Transfer, Horizontal
Genome, Bacterial
Operon
Symbiosis

@article {pmid41115209,
year = {2025},
author = {Xue, Z and Wang, Y and Wang, X and Yuan, J and Wang, L and Zeng, J and Jin, X and Zhu, H and Wang, J},
title = {PangenomeX: a graph convolutional network-based pangenome framework for unbiased population-scale genomic variation analysis.},
journal = {Briefings in bioinformatics},
volume = {26},
number = {5},
pages = {},
doi = {10.1093/bib/bbaf550},
pmid = {41115209},
issn = {1477-4054},
support = {72293581//National Natural Science Foundation of China/ ; 72274152//National Natural Science Foundation of China/ ; 62402376//National Natural Science Foundation of China/ ; },
mesh = {Humans ; *DNA Copy Number Variations ; *Genomics/methods ; Polymorphism, Single Nucleotide ; *Genome, Human ; *Software ; Phylogeny ; Genetics, Population ; Whole Genome Sequencing ; },
abstract = {In population-scale genomic variation studies based on shallow whole genome sequencing, pangenomes have become an effective tool for identifying population-specific single-nucleotide polymorphisms and indels. Extending these advantages to copy number variation (CNV), however, remains challenging due to two unresolved issues. First, current pangenome frameworks exhibit pronounced population-representation bias arising from uneven sampling across populations. As the number of samples increases, the pangenome tends to capture variations primarily from majority populations while suppressing signals from minority populations. Second, in population-scale genomic variation analyses, common but benign population-specific copy number polymorphisms (CNPs) frequently obscure pathogenic CNVs. Existing pangenome frameworks lack dedicated mechanisms for representing CNPs and CNVs, limiting their ability to distinguish pathogenic CNVs from benign, population-specific CNPs. In this study, we present PangenomeX, a graph-convolutional pangenome framework tailored for low-coverage, population-scale CNV analysis. To address CNP representation, we embed known CNPs as prior knowledge into the pangenome graph and construct a CNV relationship network guided by a phylogenetic tree. A graph convolutional network (GCN) then learns the interactions between CNV and CNP nodes. To mitigate population-representation bias, the GCN aggregates information from only one- and two-hop neighborhoods, preserving local population context while preventing majority group signals from dominating. Evaluation on simulated cohorts and 561 real samples shows that PangenomeX distinguishes pathogenic CNVs from common population CNPs markedly better than existing methods. Overall, PangenomeX offers a methodological blueprint for large-cohort variant screening and provides a practical path for bringing graph-based genomics into clinical practice.},
}

Humans
*DNA Copy Number Variations
*Genomics/methods
Polymorphism, Single Nucleotide
*Genome, Human
*Software
Phylogeny
Genetics, Population
Whole Genome Sequencing

@article {pmid41114918,
year = {2025},
author = {Wei, ZY and Li, SX and Li, MH and Tang, J and Jiang, YQ and Lu, XY and Zhang, YM and Xue, JY},
title = {Pan-genomic insights into RLK family evolution and adaptation in Dioscorea alata.},
journal = {Plant molecular biology},
volume = {115},
number = {6},
pages = {114},
pmid = {41114918},
issn = {1573-5028},
}

@article {pmid41114504,
year = {2025},
author = {Bahati, SY and Maghembe, RS},
title = {Pangenome analysis of Tanzanian clinical Klebsiella pneumoniae reveals pandemic clones with high genome plasticity and versatile mobilome, virulome, and resistome profiles.},
journal = {Microbiology spectrum},
volume = {},
number = {},
pages = {e0194725},
doi = {10.1128/spectrum.01947-25},
pmid = {41114504},
issn = {2165-0497},
abstract = {Klebsiella pneumoniae is a rapidly evolving pathogen with a diverse pangenome whose mobilome and resistome remain elusive. Here, we aimed to delineate the pangenome of 198 isolates from Tanzanian regions. Raw Illumina reads retrieved from public repositories were assembled and analyzed using multilocus sequence typing, core-genome single nucleotide polymorphism (SNP)-based phylogeny, and capsular polysaccharide (K-locus) and lipopolysaccharide O-antigen (O-locus) typing. A total of 184 isolates were classified as Klebsiella pneumoniae sensu stricto, while 14 belonged to other species within the Klebsiella pneumoniae complex. We identified 90 sequence types (STs), including global high-risk ST45, ST39, ST336, ST14, ST1552, and ST17. KL24 and KL25 were the most common K-loci, while OL2α.1 and OL2α.2 were dominant O-loci. Pangenome analysis revealed 30,992 gene families, distributed as persistent (13.6%), shell (11.2%), and cloud (75.2%) genes, suggesting an open pangenome structure. Core-genome SNP-based phylogeny confirmed clonal expansion and lineage clustering. Virulence profiling showed yersiniabactin in 44% of isolates. Most genomes carried key fimbrial and iron uptake genes. Resistome analysis revealed near-universal presence of bla_CTX-M-15, oqxA/B, fosA6, sul2, and marA. Plasmid typing identified IncF-type (76%) and Col-type (54%) plasmids, while over 120 mobile genetic elements were detected, whose frequencies were on a huge spectrum of insertion sequences (e.g., IS5075 and MITEYpe1) and transposons (e.g., Tn5403 and Tn6082). Conclusively, Tanzanian K. pneumoniae strains exhibit extensive genomic plasticity, high-risk lineages, and a versatile mobilome, calling for national genomic surveillance to inform intervention strategies.IMPORTANCEThe Klebsiella pneumoniae complex comprises a diverse group of bacterial pathogens adapted to thrive over a wide range of environments. Isolates from clinical and environmental samples are implicated in nosocomial infections and multidrug resistance, with similar genome structures and inherent genes. Our study presents the first pangenome report underlying genomic plasticity of K. pneumoniae isolates from Tanzanian clinical specimens, demonstrating versatile clones, mobilome, and resistome profiles. Combining these profiles with the versatility of K and O structures, our study emphasizes the need for comprehensive multidisciplinary surveillance studies to optimize therapeutic and vaccine development.},
}

@article {pmid41110766,
year = {2025},
author = {Saint-Charles, A and Masliah-Planchon, J and Saberi-Ansari, E and Bellini, A and Bernkopf, M and Font de Mora, J and Salvá, RN and Van Roy, N and Goodman, A and Vicha, A and Attignon, V and Combaret, V and Beiske, K and Martinsson, T and Schoumans, J and Rossing, M and Tops, B and Westermann, F and Cotteret, S and Fischer, M and Birger, Y and Mazzocco, K and Chesler, L and Betts, D and Cowley, M and Capasso, M and Bobin, C and Iddir, Y and Zaidi, S and Carcaboso, AM and Vandermeulen, J and Loontiens, S and Gaarder, J and Ibrahim, RR and Rosswog, C and Hameiri-Grossman, M and Shichrur, K and Trahair, T and Barahona, P and Eggert, A and Deubzer, HE and Delattre, O and Pasqualini, C and George, S and Tytgat, G and Tweddle, DA and Taschner-Mandl, S and Schleiermacher, G},
title = {Harmonization of reporting for detection of ALK genetic alterations in neuroblastoma - a SIOPEN Biology study.},
journal = {The Journal of molecular diagnostics : JMD},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.jmoldx.2025.09.007},
pmid = {41110766},
issn = {1943-7811},
abstract = {In high-risk neuroblastoma, identification of ALK activating genetic alterations is considered for clinical decision-making in relapse or more recently frontline treatment. The accurate diagnosis of genetic alterations requires harmonization of molecular techniques and reporting especially when these are considered as inclusion criteria for clinical trials. Analysis and validation was preformed across the 21 SIOPEN (International Society of Paediatric Oncology Europe Neuroblastoma) molecular diagnostic laboratories, with 14 DNA samples harbouring distinct ALK alterations including ALK mutations in or outside hotspots in the tyrosine kinase domain (TKD) with variant allele frequencies (VAF) ranging from 1% to 91%, or ALK genomic amplification shared between the laboratories. Each laboratories employed their own established techniques: ALK amplifications were detected using either pan-genomic copy number techniques or fluorescence in situ hybridization and ALK mutations were characterized by Next Generation Sequencing (NGS) techniques. All laboratories correctly identified high-level ALK amplification and ALK mutations within the TKD hotspots with VAF >5%, with exception of 2 cases. Difference in interpretation and reporting was apparent for samples harbouring mutations with a VAF <5% or outside known hotspots. These results highlight the importance of standard operating procedures, standardized reporting, and the robustness of ALK genetic testing in the SIOPEN laboratories, as well as the need for expert discussions on atypical ALK alterations, to validate eligibility for ALK targeted treatment in clinical trials.},
}

@article {pmid41108646,
year = {2025},
author = {Jeon, JY and Allen, NM and Black, AN and DeWoody, JA},
title = {Short-Read Pangenomes and Their Potential Utility in Population and Conservation Genomics.},
journal = {Molecular ecology resources},
volume = {},
number = {},
pages = {e70060},
doi = {10.1111/1755-0998.70060},
pmid = {41108646},
issn = {1755-0998},
abstract = {As a collection of all the genetic variants in the gene pool, the pangenome is a concept that will become fundamental to conservation genomic studies. Unfortunately, most pangenomic approaches developed for humans and model organisms are financially impractical for conservation genomic studies of threatened or endangered species due to the high costs associated with deep sequencing multiple individuals using long-read platforms. Here, by integrating metagenomic and iterative map-then-assemble approaches, we (1) propose novel workflows to construct graph pangenomes from multiple low-coverage short-read datasets; (2) benchmark these short-read pangenomes (both linear and graph) against a previously published long-read graph pangenome of the barn swallow; and (3) evaluate the utility of our workflows in population and conservation genomics. Our results indicate that economical short-read graph pangenomes can recover the vast majority of the variants identified through expensive long-read graph approaches, and that these variants accurately detect important biological signals (e.g., spatial structure and independent taxonomic delineations). These results mean that researchers can utilize their limited, conservation-oriented funding to more fully characterize all the variants in a particular gene pool for population-level analyses.},
}

@article {pmid41107551,
year = {2025},
author = {Prodanov, T and Plender, EG and Seebohm, G and Meuth, SG and Eichler, EE and Marschall, T},
title = {Locityper enables targeted genotyping of complex polymorphic genes.},
journal = {Nature genetics},
volume = {},
number = {},
pages = {},
pmid = {41107551},
issn = {1546-1718},
support = {R01 HG002385/HG/NHGRI NIH HHS/United States ; R01 HG002385/HG/NHGRI NIH HHS/United States ; },
abstract = {The human genome contains many structurally variable polymorphic loci, including several hundred disease-associated genes, almost inaccessible for accurate variant calling. Here we present Locityper, a tool capable of genotyping such challenging genes using short-read and long-read whole-genome sequencing. For each target, Locityper recruits and aligns reads to locus haplotypes, for instance, extracted from a pangenome, and finds the likeliest haplotype pair by optimizing read alignment, insert size and read depth profiles. Across 256 challenging medically relevant loci, Locityper achieves a median quality value (QV) above 35 from both long-read and short-read data, outperforming state-of-the-art Illumina and PacBio HiFi variant calling pipelines by 10.9 and 1.7 points, respectively. Furthermore, Locityper provides access to hyperpolymorphic HLA genes and other gene families, including KIR, MUC and FCGR. With its low running time of 1 h 35 m per sample at eight threads, Locityper is scalable to biobank-sized cohorts, enabling association studies for previously intractable disease-relevant genes.},
}

@article {pmid41107550,
year = {2025},
author = {Ma, W and Chaisson, MJP},
title = {Genotyping sequence-resolved copy number variation using pangenomes reveals paralog-specific global diversity and expression divergence of duplicated genes.},
journal = {Nature genetics},
volume = {},
number = {},
pages = {},
pmid = {41107550},
issn = {1546-1718},
support = {U01HG010973//U.S. Department of Health & Human Services | NIH | National Human Genome Research Institute (NHGRI)/ ; },
abstract = {Copy number variable (CNV) genes are important in evolution and disease, yet their sequence variation remains a blind spot in large-scale studies. We present ctyper, a method that leverages pangenomes to produce allele-specific copy numbers with locally phased variants from next-generation sequencing samples. Benchmarking on 3,351 CNV genes and 212 challenging medically relevant (CMR) genes, ctyper captures 96.5% of phased variants with ≥99.1% correctness of copy number in CNV genes and 94.8% of phased variants in CMR genes. Ctyper takes 1.5 h to genotype a genome on one CPU. The ctyper genotypes give a 4.81-fold improvement in predictions of gene expression compared to known expression quantitative trait locus (eQTL) variants. Allele-specific expression quantified divergent expression in 7.94% of paralogs and tissue-specific biases in 4.68%. We found reduced expression of SMN2 due to SMN1 conversion, potentially affecting spinal muscular atrophy, and increased expression of translocated duplications of AMY2B. Overall, ctyper enables biobank-scale genotyping of CNV and CMR genes.},
}

@article {pmid41106384,
year = {2025},
author = {Liu, HS and Wang, WH and Song, YF and Yang, Y and Zhang, DY and Bai, WN and Zhang, BW},
title = {A pan-genome framework reveals structural variation and small RNA regulation underlying heterodichogamy in Pterocarya.},
journal = {Current biology : CB},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.cub.2025.09.017},
pmid = {41106384},
issn = {1879-0445},
abstract = {Heterodichogamy, characterized by reciprocal timing of male and female flowering, promotes disassortative mating yet remains poorly understood at the genomic level. Here, we investigated this mating system in Pterocarya, a genus within Juglandaceae, using a low-input pan-genome framework that integrates phased assemblies with population resequencing. We identified a deeply divergent 78-kb locus associated with mating morphs in P. stenoptera, marked by repeat-rich structural variants and containing a FAF-like gene linked to floral development. This region also produces small RNAs that potentially regulate key floral and hormonal pathways, suggesting pleiotropic trans-regulatory effects. Comparative analyses reveal that although the loci controlling heterodichogamy in Juglans, Carya, and Pterocarya are non-homologous, they appear to share convergent evolutionary solutions involving tandem repeats or transposable element (TE) insertions. Our study uncovers the genomic basis of heterodichogamy in Pterocarya and underscores the utility of pan-genome approaches for dissecting structural variation-associated traits.},
}

@article {pmid41101942,
year = {2025},
author = {Lim, SL and Chin, CH and Chiou, YJ and Hsu, MT and Chiang, PW and Chen, HJ and Tu, YC and Tzou, WS and Tang, SL},
title = {Unveiling Unusual Ecofunctional Traits of Endozoicomonas Species Through Comprehensive Comparative Genomics.},
journal = {Environmental microbiology},
volume = {27},
number = {10},
pages = {e70191},
doi = {10.1111/1462-2920.70191},
pmid = {41101942},
issn = {1462-2920},
support = {AS-IA-109-L05//Academia Sinica/ ; },
mesh = {*Genome, Bacterial ; Genomics ; Phylogeny ; Prophages/genetics ; Bacterial Proteins/genetics ; *Gammaproteobacteria/genetics ; Quorum Sensing ; },
abstract = {Endozoicomonas is an omnipresent marine bacterial genus, associated with various marine organisms, that contributes to host health, nutrient cycling and disease resistance. Nonetheless, its genomic features remain poorly characterised due to a paucity of high-quality genomes. In this study, we sequenced 5 novel Endozoicomonas strains and re-sequenced 1 known strain to improve genomic resolution. By integrating these 6 high-quality genomes with 31 qualified published genomes, our pan-genomic analysis revealed variation in genetic traits among clades. Notably, Endozoicomonas lacks quorum-sensing capabilities, suggesting resistance to quorum quenching mechanisms. It also lacks the capacity to synthesise and transport vitamin B12, indicating that it does not supply this nutrient to holobionts. Remarkably, Endozoicomonas genomes encode 92 identified giant proteins (15-65 kbp). These proteins cluster into three major groups associated with antimicrobial peptide synthesis, exotoxin production and cell adhesion. Additionally, we found that Endozoicomonas has acquired prophages from diverse sources via infection or other types of gene transfer. Notably, CRISPR-Cas sequences suggest evolutionary trajectories independent of both prophage acquisition and phylogenetic lineage, implying potential geographic influences or environmental pressures. This study provides new insights into the genomic diversity of Endozoicomonas and its genetic adaptations to diverse hosts.},
}

*Genome, Bacterial
Genomics
Phylogeny
Prophages/genetics
Bacterial Proteins/genetics
*Gammaproteobacteria/genetics
Quorum Sensing

@article {pmid41100528,
year = {2025},
author = {Deschner, D and Hill, JE},
title = {Identification of genes that differentiate Mannheimia haemolytica genotypes 1 and 2 using a pangenome approach.},
journal = {PloS one},
volume = {20},
number = {10},
pages = {e0325338},
doi = {10.1371/journal.pone.0325338},
pmid = {41100528},
issn = {1932-6203},
mesh = {*Mannheimia haemolytica/genetics/pathogenicity/classification ; Genotype ; *Genome, Bacterial ; Animals ; Cattle ; *Genes, Bacterial ; Bacterial Proteins/genetics ; },
abstract = {Mannheimia haemolytica is an opportunistic bacterial pathogen associated with the economically costly bovine respiratory disease. Two genotypes have been described, of which genotype 2 is more strongly associated with disease. Several previous studies have investigated the genomic differences between the genotypes and/or the major serotypes (1, 2 and 6) of M. haemolytica, however we still lack a clear basis for the greater disease association of genotype 2 (serotypes 1 and 6) and demonstrations of phenotypic differences are scarce. This work builds upon previous investigations to identify genes that differentiate the two genotypes with a particular focus on genes that may play a role in virulence and fitness in the respiratory tract microbiome. We identified 422 genotype differentiating genes in a collection of 206 unique M. haemolytica genomes (61 genotype 1, 145 genotype 2). Genotype differentiating genes included genotype-associated variants of a TonB-dependent siderophore receptor homolog, transferrin binding protein B, leukotoxin A, and IgA1 proteases. We also identified a genotype 1 associated lytic transglycosylase, and a genotype 2 specific highly immunogenic outer membrane lipoprotein. Genotype 2 genomes were significantly larger in size and contained more predicted protein coding genes than genotype 1 genomes. These results expand our knowledge of what differentiates the genotypes 1 and 2 of M. haemolytica and provides information that can be used as the basis for laboratory investigations of corresponding phenotypic differences.},
}

*Mannheimia haemolytica/genetics/pathogenicity/classification
Genotype
*Genome, Bacterial
Animals
Cattle
*Genes, Bacterial
Bacterial Proteins/genetics

@article {pmid41097617,
year = {2025},
author = {Abitayeva, G and Kurmangali, D and Baikonys, T and Bekshin, Z},
title = {Lacticaseibacillus paracasei subsp. paracasei 2LB: Identification of Genes to Assess the Safety and Probiotic Potential of the Strain.},
journal = {Foods (Basel, Switzerland)},
volume = {14},
number = {19},
pages = {},
doi = {10.3390/foods14193449},
pmid = {41097617},
issn = {2304-8158},
support = {АР19679863//This research has been funded by the Science Committee of the Ministry of Science and Higher Education of the Republic of Kazakhstan/ ; },
abstract = {In this study, we conducted a whole-genome analysis of the Lacticaseibacillus paracasei subsp. paracasei 2LB isolated from Kazakh traditional fermented milk (koumiss) to identify genes associated with the safety and probiotic potential of the strain. A comparative genomic analysis of the core and pan-genome of L. paracasei 2LB was performed. Functional annotation revealed the presence of genes putatively involved in metabolism, genetic information processing, and cellular processes. In terms of safety parameters, the stability of its genetic material, the absence of the ability to synthesize virulence factors, and genes responsible for antibiotic resistance were characterized. Also, in vitro studies of the L. paracasei 2LB strain showed resistance to stress factors and antimicrobial activity, and the presence of coding sequences encoding adhesion factors, bacteriocins, bile salts, pH, cold and heat shock, and osmotic stress was observed through genomic analysis. These results indicate that the L. paracasei 2LB strain is a potential probiotic candidate and demonstrate that whole-genome analysis is a useful method for assessing the quality and safety of probiotics.},
}

@article {pmid41097310,
year = {2025},
author = {Zhou, B and Nie, X and Mao, X and Chen, J and Chen, J and Ma, B and Wu, X},
title = {Novel ST-Specific Molecular Target-Based Method for Simultaneous and Quantitative Detection of Staphylococcus aureus ST7, ST188 and ST398.},
journal = {Molecules (Basel, Switzerland)},
volume = {30},
number = {19},
pages = {},
doi = {10.3390/molecules30193889},
pmid = {41097310},
issn = {1420-3049},
support = {20242BAB20333//Jiangxi Provincial Natural Science Foundation/ ; GSJK202401//Science and Technology Project of Jiangxi Provincial Administration for Market Regulation/ ; ZYK202403//Research Project of Jiangxi General Institute of Testing and Certification/ ; },
mesh = {*Staphylococcus aureus/genetics/isolation & purification/classification ; Food Microbiology ; Humans ; Staphylococcal Infections/microbiology/diagnosis ; Genome, Bacterial ; Limit of Detection ; Real-Time Polymerase Chain Reaction ; },
abstract = {Staphylococcus aureus is a globally crucial foodborne pathogen that can cause diarrhea, vomiting, and bloodstream infection in immunocompromised individuals. S. aureus has three predominant sequence types (STs) (ST7, ST188 and ST398) that are prevalent clones in both food and clinical cases. This study aimed to screen ST-specific targets for S. aureus ST7, ST188 and ST398, and then developed a novel rapid and accurate assay for the detection of these three predominant S. aureus STs in food. A total of 505 Staphylococcus strain genome sequences including 371 sequences of 58 different STs and 134 other non-target S. aureus ST genome sequences were subjected to pan-genome analysis; we successfully screened five novel ST-specific targets (group_10498 and group_10499 target for S. aureus ST7, group_9415 and group_9419 target for S. aureus ST188, group_9911 target for S. aureus ST398). The excellent specificity and sensitivity of all the targets were confirmed by PCR assays. Based on these molecular targets, mPCR and qPCR methods were developed for specifically identifying S. aureus' three predominant STs without non-target bacterial interference. The limits of detection (LODs) for the mPCR assay in artificially contaminated milk were determined to be 10[4] CFU/mL for ST7, 10[5] CFU/mL for ST188, and 10[4] CFU/mL for ST398, while the LODs achieved by the qPCR method were 8.6 × 10[2] CFU/mL, 1.2 × 10[2] CFU/mL, and 6.4 × 10[3] CFU/mL, respectively. The testing results for actual food samples suggested that the developed mPCR or qPCR assays could be used as an alternative to standard MLST analysis, for the rapid and reliable identification of S. aureus STs. The novel molecular detection technology established in this study provides an efficient and reliable detection method for the prevention and control of predominant S. aureus ST contamination in food and has important application potential and promotion prospects.},
}

*Staphylococcus aureus/genetics/isolation & purification/classification
Food Microbiology
Humans
Staphylococcal Infections/microbiology/diagnosis
Genome, Bacterial
Limit of Detection
Real-Time Polymerase Chain Reaction

@article {pmid41097292,
year = {2025},
author = {Buyuklyan, JA and Biryukov, MV and Zakalyukina, YV and Sacharov, AA},
title = {The Regulation of the Albomycin and Desferrioxamine E Biosynthesis in Streptomyces globisporus bja209.},
journal = {Molecules (Basel, Switzerland)},
volume = {30},
number = {19},
pages = {},
doi = {10.3390/molecules30193871},
pmid = {41097292},
issn = {1420-3049},
mesh = {*Streptomyces/metabolism/genetics ; *Anti-Bacterial Agents/biosynthesis/pharmacology ; *Deferoxamine/pharmacology ; Phylogeny ; Biosynthetic Pathways ; },
abstract = {We identified Streptomyces globisporus bja209 through a targeted screen of actinomycetes from natural habitats using an E. coli JW5503 ΔtolC DualRep2(c) reporter strain. This strain produced antibacterial compounds whose action depended on the growth medium. HPLC-MS and genomic analysis revealed two metabolites: albomycin δ2 (a translation inhibitor) and desferrioxamine E. The latter induced the SOS response. Desferrioxamine E exhibited a narrow spectrum of antagonistic activity against carbapenem-resistant A. baumannii and C. michiganensis, and its production was critically regulated by iron concentration. Notably, the structurally similar desferrioxamine B was inactive. Contrary to previous reports, pangenome analysis of published GenBank genomes revealed that albomycin BGC is restricted to specific S. globisporus strains and not present in other Streptomycetes phylogenetic clades. The C-1027 BGC was found in a large linear plasmid (165.5 kb) of the S. globisporus bja209 strain and also found exclusively on linear plasmids in some of the published S. globisporus genomes.},
}

*Streptomyces/metabolism/genetics
*Anti-Bacterial Agents/biosynthesis/pharmacology
*Deferoxamine/pharmacology
Phylogeny
Biosynthetic Pathways

@article {pmid41094142,
year = {2025},
author = {Loegler, V and Thiele, P and Teyssonnière, E and Tsouris, A and Brach, G and Cruaud, C and Payen, E and Engelen, S and Dunham, MJ and Hou, J and Friedrich, A and Schacherer, J},
title = {From genotype to phenotype with 1,086 near telomere-to-telomere yeast genomes.},
journal = {Nature},
volume = {},
number = {},
pages = {},
pmid = {41094142},
issn = {1476-4687},
abstract = {Unravelling the genetic basis of the remarkable phenotypic diversity observed in natural populations remains a central challenge in biology[1-4]. Despite major advances[5-19], no species has yet been characterized with a truly comprehensive atlas of genetic variation. Here we present an extensive genomic and phenotypic resource for the yeast Saccharomyces cerevisiae based on near telomere-to-telomere assemblies of 1,086 natural isolates. Leveraging these high-contiguity assemblies, we generated a highly complete species-wide structural variant atlas, gene-based pangenome and graph pangenome. By incorporating the full spectrum of genetic variation captured across the species, we conducted genome-wide association studies across 8,391 molecular and organismal traits[19-22]. The inclusion of structural variants and small insertion-deletion mutations improved heritability estimates by an average of 14.3% compared with analyses based only on single-nucleotide polymorphisms. Structural variants were more frequently associated with traits and exhibited greater pleiotropy than other variant types. Notably, the genetic architecture of molecular and organismal traits differed markedly. Together, this work provides a unique dataset that illuminates how diverse forms of genetic variation shape phenotypic diversity and lays the groundwork for integrative, genome-scale studies in other eukaryotic systems.},
}

@article {pmid41092514,
year = {2025},
author = {Goddard, M and Martín, JS and Molina-Mora, JA and Collado, L and Rodriguez, J and Galarce, N and Mella, A},
title = {Genetic diversity of Mycoplasma bovis isolated from bovine respiratory disease and bovine mastitis in Chile.},
journal = {Veterinary microbiology},
volume = {311},
number = {},
pages = {110752},
doi = {10.1016/j.vetmic.2025.110752},
pmid = {41092514},
issn = {1873-2542},
abstract = {Mycoplasma bovis, a major bacterial pathogen for cattle, is responsible for diseases such as pneumonia, mastitis, otitis, and arthritis, leading to substantial economic losses and animal welfare concerns. Despite its wide global distribution, there is limited information in South America. M. bovis has been reported as a mastitis agent in Chile, but its genetic diversity is poorly understood. Therefore, this study aimed to determine the genetic diversity of M. bovis isolates from Chilean dairy cattle (from bovine respiratory disease and mastitis cases) in the last two decades and evaluate their genetic relatedness with strains isolated in different countries using a whole genome sequencing approach. The M. bovis population in Chile was found to be highly homogeneous, with MLST and phylogenomic analysis identifying ST60 as the dominant clone, representing most of the isolates (97.8 %), while just one isolate was typed as ST12 (2.2 %). Phylogenomic analysis revealed close genetic relatedness among most Chilean isolates, showing a close genetic relationship with North American strains, forming a tight clade with Canadian ST60 strains, while the single Chilean ST12 isolate clustered with North American, Israeli, and European strains and clustered with the type strain (PG45) of this species. Moreover, the pangenome analysis confirms that M. bovis has an open pangenome, with a large range of accessory genes that remain largely unexplored and may hold key insights into its genome plasticity, thereby opening future research. The findings of this study provide the first insights into the Chilean population structure of M. bovis, contributing to the global epidemiology of this pathogen with a focus on South America. These results also open future research focused on the comprehensive characterization of this dominant clone, inspiring the scientific community to further exploration into the genetic diversity of M. bovis in Chile.},
}

@article {pmid41090561,
year = {2025},
author = {Zhang, T and Luo, D and Li, G and Wang, H and Cao, Q and Zhang, R and Li, Y and Zhu, Y and Ma, C and Liston, A and Sun, H and Qiao, Q},
title = {Multi-omics analyses shed lights on the evolution and fruit development of Chinese raspberries (Rubus spp.).},
journal = {Journal of integrative plant biology},
volume = {},
number = {},
pages = {},
doi = {10.1111/jipb.70052},
pmid = {41090561},
issn = {1744-7909},
support = {202301AS070071//Yunnan Fundamental Research Projects/ ; 202505AS350015//Yunnan Fundamental Research Projects/ ; 202501AS070177//Yunnan Fundamental Research Projects/ ; 32260094//National Natural Science Foundation of China/ ; 32372655//National Natural Science Foundation of China/ ; 82260739//National Natural Science Foundation of China/ ; 2024YFF1306702//National Key Research and Development Program of China/ ; },
abstract = {Rubus (raspberries and blackberries) is a large genus of over 700 species well known for its taxonomic challenges. Many of its species hold significant economic value as important edible and medicinal plants. Here, near-complete genomes for four wild diploid raspberry species were assembled, including R. ellipticus, R. niveus, as well as the highly heterozygous diploid red raspberry (R. idaeus), and its closely related species R. sachalinensis. Pan-genome analysis of Rubus identified 10,243 core gene families (64% of total), and highlights expansions of flavonoid/terpenoid pathways in Rubus, correlating with fruit bioactive compound diversity. Our discovery of shared ancestral components between R. idaeus and R. sachalinensis subgenomes provides evidence for their homoploid hybrid origin. The centromere sequence characteristics could serve as markers for subgenome assignment in R. idaeus and R. sachalinensis. Moreover, population genomic studies of 125 accessions from ca. 80 species uncovered widespread genetic introgression, particularly in red raspberries, with centromeric haplotype signatures tracing ancestral contributions to cultivated varieties. By integrating metabolome and transcriptome data, we explore the fruit quality regulatory network of Chinese raspberries. We identified a glutathione S-transferase gene that may inhibit the successful transport of anthocyanins into the vacuole and appears to be a limiting factor for the anthocyanin pigmentation in R. ellipticus fruits. In summary, this research sheds new light on the genetic intricacies of raspberry species and their cultivars, and provides a robust foundation for horticultural improvement and genomic selection in raspberry breeding.},
}

@article {pmid41087872,
year = {2025},
author = {Wang, Y and Meng, S and Bahetijiang, H and Li, H and Wang, T and Assabayev, T and Barkema, HW and Kastelic, JP and Han, B and Deng, Z},
title = {Phenotypic and genotypic characterization of ST103 serotype Ia Streptococcus agalactiae isolated from bovine mastitis in China.},
journal = {BMC microbiology},
volume = {25},
number = {1},
pages = {662},
pmid = {41087872},
issn = {1471-2180},
support = {31772813//National Natural Science Foundation of China/ ; G2022108009L//High-end Foreign Experts Recruitment Plan of China/ ; 6244052//Natural Science Foundation of Beijing, China/ ; },
abstract = {Streptococcus agalactiae is a contagious pathogen responsible for bovine mastitis, leading to significant economic losses in the global dairy industry. Our objectives were to determine the population structure, to profile the antimicrobial resistance and to investigate the pathogenicity and genes associated with pathogenicity in S. agalactiae isolated from Chinese dairy herds. A total of 266 milk samples were collected on three dairy farms in Ningxia (herd A) and Hebei provinces (herds B & C) with outbreaks of bovine mastitis from September 2020 to April 2021. There were 116 isolates identified as Streptococcus agalactiae by 16S rRNA sequencing. Twenty-seven S. agalactiae isolates were randomly selected using a stratified approach from the three farms for whole genome sequencing analysis and phenotypic analyses, including antimicrobial resistance profiling, identification of adhesion, invasion and virulence genes using in vitro bovine mammary epithelial cell models and in vivo Galleria mellonella models. Multilocus sequence typing and serotyping showed that all isolates belonged to sequence type ST103 and serotype Ia. In total, 34 genes were identified as virulence genes in Streptococcus species. Isolates from herd C had significantly higher virulence than those from herd B. Genome-wide association analysis revealed 166 virulence-related genes, 221 adhesion-related genes and 218 invasion-related genes. Furthermore, 47 genes were associated with pathogenicity in infecting G. mellonella. Resistance to tetracycline and macrolides was related to the presence of antimicrobial resistance genes tetO, tetM, and ermB. Pan-genome analyses revealed that 1,421 S. agalactiae isolates (27 from our study and 1,394 from the NCBI genome database) had 20,955 genes, including 666 and 20,289 genes in the core and accessory genomes, respectively. This study characterized the phenotypic and genotypic profiles for S. agalactiae, and identified associations between phenotypic traits and genetic determinants of virulence and antimicrobial resistance, providing new insights into controlling S. agalactiae mastitis in Chinese dairy herds.},
}

@article {pmid41087377,
year = {2025},
author = {Karouia, F and de Oliveira, LC and Hameed, A and Simpson, A and Singh, N and Rekha, PD and Mason, CE and Venkateswaran, K},
title = {Genomic characterization of Microbacterium meiriae sp. nov., a novel bacterium isolated from the International Space Station.},
journal = {Scientific reports},
volume = {15},
number = {1},
pages = {35770},
pmid = {41087377},
issn = {2045-2322},
support = {19-12829-26//National Aeronautics and Space Adminstration/ ; },
mesh = {Phylogeny ; RNA, Ribosomal, 16S/genetics ; *Genome, Bacterial ; *Microbacterium/genetics/isolation & purification/classification ; *Spacecraft ; Whole Genome Sequencing ; DNA, Bacterial/genetics ; Genomics/methods ; Russia ; },
abstract = {During the microbial surveillance of the International Space Station (ISS) in April 2018, four Gram-stain positive bacterial strains, designated as F6_8S_P_2B[T], F6_8S_P_3A, F6_8S_P_3B and F6_8S_P_3C, belonging to the genus Microbacterium were isolated from the walls of crew quarters. All four strains exhibited high 16S rRNA gene sequence similarity (> 99%), low average nucleotide identity (93%), and < 49.7% digital DNA: DNA hybridization values with the closest recognized Microbacterium paraoxydans DSM 15019[T], delineating new phylogenetic branches within the genus. Further whole-genome sequencing (WGS) and phylogenomic analysis revealed a close genetic relationship (> 98% ANI; > 83% dDDH) between the ISS strains and Microbacterium sp. LTR1 strain isolated from the larva skin of Lissotriton vulgaris from Tula region, Russia, which was misidentified as M. paraoxydans. The pangenomic analysis also shows high correlation between the ISS strains and their proximity to the type strain M. paraoxydans DSM 15019[T]. These analyses suggest that strain LTR1, previously characterized as M. paraoxydans, should be included in this new Microbacterium clade alongside the four novel ISS strains. Functional genome analysis revealed unique proteins associated with transcription, defense, and metabolism. The genome harbored toxin-antitoxin modules (e.g., VapBC, Phd/YuzE), stress response regulators (FrmR, YhcF), and genes involved in formaldehyde resistance and glycoside hydrolase activity. Secondary metabolite gene clusters included beta-lactone, terpene, and T3PKS. Notably, tetracycline resistance gene tet(42) was present, indicating potential clinical relevance. The ISS strains grew at 4-40 °C, 0.5-8% NaCl, and pH 6.0-9.0. Chemotaxonomic features included anteiso-C15:0 and anteiso-C17:0 as major fatty acids, MK-12 as the predominant menaquinone, and ornithine as the diagnostic diamino acid in B2β-type peptidoglycan. The genomic DNA G+C content was 70.03 mol%. The polyphasic taxonomy showed that the ISS isolates along with LTR1 represent distinct strains of a new Microbacterium species, herein named Microbacterium meiriae. The type strain is F6_8S_P_2B[T] (DSM 115935[T] = NRRL B-65668[T]).},
}

Phylogeny
RNA, Ribosomal, 16S/genetics
*Genome, Bacterial
*Microbacterium/genetics/isolation & purification/classification
*Spacecraft
Whole Genome Sequencing
DNA, Bacterial/genetics
Genomics/methods
Russia

@article {pmid41081913,
year = {2025},
author = {Amaresh, and Aswini, N and Krishnappa, G and Durai, AA and Manimekalai, R and Swamy, HKM and Pathy, TL and Vinayaka, and Dhanya, VG and Rathan, ND and Nandakumar, S and Shwetha, K and Sreenivasa, V and Maruthi, RT and Suresha, GS and Hemaprabha, G and Govindaraj, P},
title = {Next-generation molecular breeding tools to harness higher genetic gains in sugarcane.},
journal = {Planta},
volume = {262},
number = {5},
pages = {122},
pmid = {41081913},
issn = {1432-2048},
mesh = {*Saccharum/genetics ; *Plant Breeding/methods ; Genetic Variation ; Genome, Plant/genetics ; Genotype ; },
abstract = {Next-generation molecular tools with AI integration can accelerate genetic gain in sugarcane by enhancing variation, accuracy, and efficiency, enabling rapid development of high-yielding, high-quality, and climate-resilient varieties. Enhancing genetic gain is essential for sustainable sugar and bioenergy production, especially amid growing global reliance on renewable energy sources. Sugarcane and its byproducts serve as important feedstocks for both first and second-generation biofuels, and face several breeding challenges due to its genetic complexity, extended breeding cycles, and strong environmental interactions. The breeder's equation offers a quantitative framework to accelerate genetic improvement by optimizing four key components: additive genetic variation (σa), heritability (h[2]), selection intensity (i), and breeding cycle length (L). Additive genetic variation can be enhanced through genome-wide exploration, including genome, pan-genome, and super pangenome analyses, gene discovery, characterization, and the induction of novel variations. Precise estimation of heritability in sugarcane can be achieved through the large-scale characterization of germplasm, high-throughput phenotyping, and detailed genotype × environment interaction (G × E) studies. Selection intensity can be increased by expanding population sizes via genotypic, genomic, and in vitro selection, leveraging the law of large numbers, and adopting technologies that provide greater throughput, precision, and cost efficiency. Breeding cycle time can be significantly reduced using tools, such as marker-assisted selection, genomic selection, emerging doubled haploid strategies (though still challenging in polyploid crops like sugarcane), speed breeding, transgenic approaches, and genome editing technologies like CRISPR/Cas9 (including base and prime editing), TALENs. This review provides a comprehensive overview of each component of the breeder's equation in sugarcane breeding and highlights next-generation molecular strategies and tools aligned to these components. The integration of these advanced tools with artificial intelligence holds immense potential to enhance genetic gain and accelerate the development of high-yielding, high-quality, and climate-resilient sugarcane varieties.},
}

*Saccharum/genetics
*Plant Breeding/methods
Genetic Variation
Genome, Plant/genetics
Genotype

@article {pmid41079324,
year = {2025},
author = {Fontanet-Manzaneque, JB and Hernández, DM and Giordano, A and Caño-Delgado, AI},
title = {Sorghum as a monocot model for drought research.},
journal = {Frontiers in plant science},
volume = {16},
number = {},
pages = {1665967},
pmid = {41079324},
issn = {1664-462X},
abstract = {Climate change is intensifying drought events, posing a major threat to global food security. Sorghum bicolor (L.) Moench (Sorghum), a C4 monocot grass, is emerging as a valuable model for drought research due to its natural tolerance to water limitation and adaptability to semi-arid and arid environments. Sorghum cultivation requires significantly less water than major cereals such as rice, maize, and wheat, making it an attractive crop for sustaining agricultural productivity under water-limiting conditions. In fact, Sorghum uses up to 34% less water than rice in rainfed systems and up to 50% less under irrigation, with rice-to-Sorghum substitution potentially reducing water demand by 33%. Its lower water requirements, along with the compact growth of commonly used accessions such as TX430 and BTx623, make Sorghum a practical system for experimentation, particularly in genome editing studies. Maize, which shares close genetic similarity and also belongs to the Panicoideae subfamily, could particularly benefit from Sorghum-based insights. Sorghum also overcomes key limitations of model species such as Arabidopsis thaliana, offering greater relevance to monocot crops. Additionally, advances in metabolomics, transcriptomics, proteomics, phenomics, population genomics and pangenomics are expanding our understanding of the molecular and physiological mechanisms underlying Sorghum's drought resilience. Despite these advantages, challenges remain in transformation efficiency and the availability of genomic tools. This review highlights Sorghum's drought tolerance mechanisms, available omics and genetic tools, described drought-related genes and regulatory networks, and the limitations and progress in gene manipulation for climate-resilient crop development. Sorghum uniquely combines the advantages of a staple crop and a model organism, making it a powerful next-generation system for climate-resilient agriculture.},
}

@article {pmid41077207,
year = {2025},
author = {Qiao, P and Saleem, N and Zhao, J and Zhao, C and Zhang, M},
title = {Pan-genome analysis of the LATERAL ORGAN BOUNDARIES domain family in camelina and function investigation of LATERAL ORGAN BOUNDARIES domain 40 in fatty acid synthesis.},
journal = {International journal of biological macromolecules},
volume = {},
number = {},
pages = {148232},
doi = {10.1016/j.ijbiomac.2025.148232},
pmid = {41077207},
issn = {1879-0003},
abstract = {Camelina (Camelina sativa (L.) Crantz) is an allohexaploid oilseed crop with a cultivation history of about six thousand years, yet its pan-genome was poorly studied. Moreover, Lateral Organ Boundary Domain (LBD) transcription factor family remains uninvestigated. Here, we performed a pan-genome analysis of LBD genes across 13 camelina accessions, identifying 1487 members classified into 44 Core, 2 SoftCore, 15 Dispensable, and 21 Private orthologous groups. Camelina LBDs were classified into Class I (six subclasses) and Class II (two subclasses). Selection pressure analysis showed that compared with Core LBD genes and SoftCore genes, Dispensable genes have undergone obvious relaxed selection. Promoter analysis identified subclass-specific regulatory elements, with Class IIB significantly enriched in endosperm-specific expression motifs and Class IA1 associated with stress responses. Transcriptome profiling revealed some tissue-specific expression patterns, including potential roles of LBD40/41 in seed development. Functional validation demonstrated that AtLBD40 overexpression in Arabidopsis and camelina remodeled fatty acid composition by suppressing FAD3 and KCS18, thereby reducing the relative contents of 18:3 and 22:1. Arabidopsis lbd40-1 and lbd40-2 mutant analyses suggested a possible functional redundancy between LBD40 and LBD41. This study elucidates the dynamic evolution of the camelina LBD family and its pivotal role in regulating the fatty acid profile in seeds, establishing a foundation for targeted oil quality improvement in this versatile crop.},
}

@article {pmid41074924,
year = {2025},
author = {Zhou, Z and Xiang, W and Fang, C and Shen, H},
title = {Genomic and Pan-Genomic Characterization of Elizabethkingia meningoseptica Reveals Resistance Gene Profiles, Phylogenetic Clusters, and Functional Landscape.},
journal = {Current microbiology},
volume = {82},
number = {12},
pages = {546},
pmid = {41074924},
issn = {1432-0991},
mesh = {*Phylogeny ; *Genome, Bacterial ; Humans ; Flavobacteriaceae Infections/microbiology ; Anti-Bacterial Agents/pharmacology ; Genomics ; *Drug Resistance, Bacterial/genetics ; Polymorphism, Single Nucleotide ; Multigene Family ; *Chryseobacterium/genetics/drug effects/classification ; Bacterial Proteins/genetics ; Drug Resistance, Multiple, Bacterial/genetics ; },
abstract = {Elizabethkingia meningoseptica (E. meningoseptica) is a significant pathogen associated with various infections. This study aimed to analyze the general molecular and pan-genomic characteristics of E. meningoseptica. The 104 E. meningoseptica genomes were retrieved from NCBI, annotated using Prokka, and screened for antibiotic resistance genes via ABRicate. Core-genome single-nucleotide polymorphisms (SNPs) were identified using Parsnp, with phylogenetic trees constructed. Pan-genomic analysis employed BPGA for gene clustering at 80% identity, supplemented by COG and KEGG functional annotations. Among the 104 sequences, 86 were from human sources, 12 from nonhuman sources, and 6 had unknown origins. Phylogenetic analysis classified the strains into three clades (A, B, and C), with 95 strains (91.3%) in clade C. Nineteen resistance genes were identified, with 11 being carbapenem-resistance genes. Significant differences in the distribution of resistance genes were observed between human and non-human sources. Pan-genomic analysis revealed 8856 genes in total, including 2267 core genes, 4052 accessory genes, and 2537 unique genes. The median genomic G + C content was 36.9% (36.8%-37.0%). The pan-genome was still open but approaching closure. In COG functional classification, significant differences were found in "Information storage and processing", "cellular processes and signaling" and "Metabolism" between core genes and accessory/unique genes. Similar significant differences were also observed in KEGG functional classification, especially in Cellular Processes, Human Diseases, and Metabolism. This study provides valuable insights into the genomic characteristics of E. meningoseptica, which can contribute to understanding its evolution, pathogenicity, and drug resistance mechanisms.},
}

*Phylogeny
*Genome, Bacterial
Humans
Flavobacteriaceae Infections/microbiology
Anti-Bacterial Agents/pharmacology
Genomics
*Drug Resistance, Bacterial/genetics
Polymorphism, Single Nucleotide
Multigene Family
*Chryseobacterium/genetics/drug effects/classification
Bacterial Proteins/genetics
Drug Resistance, Multiple, Bacterial/genetics

@article {pmid41074769,
year = {2025},
author = {Tucker, SJ and Freel, KC and Eren, AM and Rappé, MS},
title = {Habitat-specificity in SAR11 is associated with a few genes under high selection.},
journal = {The ISME journal},
volume = {},
number = {},
pages = {},
doi = {10.1093/ismejo/wraf216},
pmid = {41074769},
issn = {1751-7370},
abstract = {The order Pelagibacterales (SAR11) is the most abundant group of heterotrophic bacteria in the global surface ocean, where individual sublineages likely play distinct roles in oceanic biogeochemical cycles. Yet, understanding the determinants of niche partitioning within SAR11 has been a formidable challenge due to the high genetic diversity within individual SAR11 sublineages and the limited availability of high-quality genomes from both cultivation and metagenomic reconstruction. Through an integrated metapangenomic analysis of 71 new SAR11 isolate genomes and a time-series of metagenomes from the prominent source of isolation, we reveal an ecological and phylogenetic partitioning of metabolic traits across SAR11 genera. We resolve distinct habitat preferences among genera for coastal or offshore environments of the tropical Pacific and identify a handful of genes involved in carbon and nitrogen metabolisms that appear to contribute to these contrasting lifestyles. Furthermore, we find that some habitat-specific genes experience high selective pressures, indicating that they are critical determinants of SAR11 fitness and niche differentiation. Together, these insights reveal the underlying evolutionary processes shaping niche-partitioning within sympatric and parapatric populations of SAR11 and demonstrate that the immense genomic diversity of SAR11 bacteria naturally segregates into ecologically and genetically cohesive units, or ecotypes, that vary in spatial distributions in the tropical Pacific.},
}

@article {pmid41074339,
year = {2025},
author = {Xu, Y and Sun, R and Zheng, Z and Ye, L and Peng, M and Chen, S},
title = {Genomic and phenotypic analysis of virulence, antimicrobial resistance, and transmission routes of Vibrio vulnificus from food and clinical sources in China.},
journal = {Food research international (Ottawa, Ont.)},
volume = {220},
number = {},
pages = {117148},
doi = {10.1016/j.foodres.2025.117148},
pmid = {41074339},
issn = {1873-7145},
mesh = {*Vibrio vulnificus/genetics/pathogenicity/drug effects/isolation & purification ; Animals ; China ; Humans ; Virulence/genetics ; *Food Microbiology ; Mice ; Seafood/microbiology ; *Vibrio Infections/transmission/microbiology ; Anti-Bacterial Agents/pharmacology ; Phenotype ; *Drug Resistance, Bacterial/genetics ; Virulence Factors/genetics ; Whole Genome Sequencing ; Microbial Sensitivity Tests ; Foodborne Diseases/microbiology ; Genome, Bacterial ; Genomics ; },
abstract = {Vibrio vulnificus is a zoonotic pathogen that imposes significant economic burdens on healthcare and aquaculture. It represents a serious public health threat by causing primary septicemia through the consumption of raw shellfish and secondary septicemia via wound exposure to contaminated seawater. In this study, we aimed to compare the genomic features and virulence of foodborne V. vulnificus isolates with clinical strains to assess their public health threat. V. vulnificus isolates from Shenzhen (24 from seafood and meat, 4 clinical) were subjected to Whole-genome sequencing (WGS) and phenotypic assays including antibiotic susceptibility testing, human serum resistance, and a mouse infection model to evaluate virulence. Our results show that only a few food-derived isolates harbored antibiotic resistance genes (ARGs) encoding resistance towards rifamycin, aminoglycoside, trimethoprim, phenicol, quinolone, sulfonamide, and tetracycline; whereas all isolates possessed an extensive array of virulence factors (VFs) related to motility, adherence, and exotoxins. Two-thirds of food isolates were serum resistant and were able to survive in human serum like clinical isolates. In vivo experiments further confirmed that food-derived isolates can cause mouse mortality comparable to a clinical isolate. Genomic analysis of 685 V. vulnificus genomes from different provinces of China (including 28 genomes sequenced in this study and 657 publicly available genomes in China) revealed that V. vulnificus has an open pan-genome and there is no clear separation between clinical isolates and food isolates, either in phylogeny or VF profiles. Phylogeographic analysis indicated that Guangdong and Zhejiang provinces might play a key role in spreading V. vulnificus nationally. Collectively, this study highlights foodborne V. vulnificus isolates exhibit virulence potential equivalent to clinical strains and underscores the need for strict food safety monitoring and interventions to prevent severe infections.},
}

*Vibrio vulnificus/genetics/pathogenicity/drug effects/isolation & purification
Animals
China
Humans
Virulence/genetics
*Food Microbiology
Mice
Seafood/microbiology
*Vibrio Infections/transmission/microbiology
Anti-Bacterial Agents/pharmacology
Phenotype
*Drug Resistance, Bacterial/genetics
Virulence Factors/genetics
Whole Genome Sequencing
Microbial Sensitivity Tests
Foodborne Diseases/microbiology
Genome, Bacterial
Genomics

@article {pmid41074336,
year = {2025},
author = {Huang, J and Zhang, Z and Li, Q and Chen, J and Mei, L and Qi, X and Chen, L and Zhang, J and Lv, C and Li, M and Chen, H and Zhang, Y and Wu, B and Yu, K and Zhang, Y and Zhan, L and Zhu, Y},
title = {Emergence and genomic characterization of Vibrio parahaemolyticus serotype O10:K4 from seafood-linked diarrheal cases in Zhejiang, China (2016-2023).},
journal = {Food research international (Ottawa, Ont.)},
volume = {220},
number = {},
pages = {117144},
doi = {10.1016/j.foodres.2025.117144},
pmid = {41074336},
issn = {1873-7145},
mesh = {*Vibrio parahaemolyticus/genetics/isolation & purification/classification/pathogenicity ; Humans ; *Seafood/microbiology ; China/epidemiology ; *Vibrio Infections/epidemiology/microbiology ; Whole Genome Sequencing ; Serogroup ; *Diarrhea/microbiology/epidemiology ; Genome, Bacterial ; Virulence Factors/genetics ; },
abstract = {Vibrio parahaemolyticus is a leading cause of seafood-associated gastroenteritis, posing increasing public health challenges globally. We conducted a large-scale molecular epidemiological analysis of 7932 clinical isolates collected from seafood-associated diarrheal patients in 69 sentinel hospitals across 11 prefecture-level cities in Zhejiang Province between 2016 and 2023. Whole-genome sequencing (WGS) was performed on 1261 representative isolates, supplemented by 11,555 publicly available genomes. We analyzed temporal serotype dynamics, antimicrobial resistance genes (ARGs), virulence factors, and pangenomic diversity, with an emphasis on the globally prevalent ST3 lineage. Notably, the O10:K4 serotype emerged as the second most common within ST3, increasing in prevalence from 40.0 % to 65.6 % over the study period. O10:K4 isolates exhibited a significantly higher frequency of tdh (96.3 % vs. 78.2 %) and complete T3SS2 effector gene clusters. Nearly all isolates harbored tet(35) and blaCARB-22, indicating widespread resistance. Comparative pangenome analysis revealed O10:K4-specific acquisitions in chemotaxis and LPS synthesis (e.g., per, mcpQ, fcl) and loss of key polyamine metabolism genes (aguA, puu operon). These findings suggest that the emergence and clonal expansion of the O10:K4 serotype represent a significant epidemiological shift characterized by enhanced virulence and multidrug resistance. Sustained genomic surveillance is imperative to guide seafood safety management and clinical interventions.},
}

*Vibrio parahaemolyticus/genetics/isolation & purification/classification/pathogenicity
Humans
*Seafood/microbiology
China/epidemiology
*Vibrio Infections/epidemiology/microbiology
Whole Genome Sequencing
Serogroup
*Diarrhea/microbiology/epidemiology
Genome, Bacterial
Virulence Factors/genetics

@article {pmid41071885,
year = {2025},
author = {VanGessel, CJ and Felderhoff, TJ and Prigozhin, DM and Cui, M and Pressoir, G and Healey, AL and Lovell, JT and Nalam, VJ and Nishimura, MT and Morris, GP},
title = {Ancient pangenomic origins of noncanonical NLR genes underlying the recent evolutionary rescue of a staple crop.},
journal = {Science advances},
volume = {11},
number = {41},
pages = {eady1667},
doi = {10.1126/sciadv.ady1667},
pmid = {41071885},
issn = {2375-2548},
mesh = {*NLR Proteins/genetics ; *Evolution, Molecular ; *Sorghum/genetics/parasitology ; Disease Resistance/genetics ; *Plant Proteins/genetics ; Animals ; Plant Diseases/genetics/parasitology ; *Crops, Agricultural/genetics ; Aphids ; Phylogeny ; },
abstract = {The recent adaptation of the cereal crop sorghum to a global aphid outbreak was a fortuitous case of evolutionary rescue, but the pangenomic and molecular basis is not known. We show that RMES1 disrupts phloem feeding via activation of conserved immunity networks, with a growth-to-defense transition mediated by phytohormone signaling and activated by nucleotide-binding site-leucine-rich repeat receptor (NLR) resistance genes on a structural variant. The causative NLRs [resistance to Melanaphis sorghi 1A (RMES1A) and RMES1B] lack signaling domains and have adenosine triphosphatase mutations expected to abrogate function, suggesting that RMES1 NLRs regulate immunity via a noncanonical mechanism. The RMES1 NLR family is ancient, orthologous to phloem-feeding resistance genes in rice and syntenic across the grass superpangenome. Thus, gene birth-and-death processes at an ancient gene cluster created rare standing variation and provided the adaptive allele for evolutionary rescue.},
}

*NLR Proteins/genetics
*Evolution, Molecular
*Sorghum/genetics/parasitology
Disease Resistance/genetics
*Plant Proteins/genetics
Animals
Plant Diseases/genetics/parasitology
*Crops, Agricultural/genetics
Aphids
Phylogeny

@article {pmid41068364,
year = {2025},
author = {Umer, MJ and Huang, L and Liu, H and Batool, R and Li, H and Li, S and Hong, Y and Wang, R and Yu, Q and Lu, Q and Varshney, RK and Chen, X},
title = {Integrative genomics and genetics from evolutionary insights to precision breeding in peanuts (Arachis Hypogaea L.).},
journal = {Functional & integrative genomics},
volume = {25},
number = {1},
pages = {206},
pmid = {41068364},
issn = {1438-7948},
support = {32172051, 32301869 and 32401893//The National Natural Science Foundation of China/ ; 32172051, 32301869 and 32401893//The National Natural Science Foundation of China/ ; 32172051, 32301869 and 32401893//The National Natural Science Foundation of China/ ; 2023A04J0776 and 2024A04J3870//Guangzhou Basic and Applied Basic Research Foundation/ ; 2023A04J0776 and 2024A04J3870//Guangzhou Basic and Applied Basic Research Foundation/ ; 2023B1212060038//Science and Technology Planning Project of Guangdong Province/ ; 2024B1212060003//Science and Technology Planning Project of Guangdong Province/ ; CARS-13//China Agriculture Research System of MOF and MARA/ ; 2019KJ136-02//Technology Special Fund of Guangdong Province Agriculture and Rural Affairs Department/ ; 2024-NPY-00-018//Special Funds for the Revitalization of Agriculture through Seed Industry under the Provincial Rural Revitalization Strategy/ ; R2020PY-JX004, R2020PY-JG005, R2021PY-QY003, R2022YJ-YB3025 and R2023PY-JG007//Special Fund for Scientific Innovation Strategy-Construction of High-level Academy of Agriculture Science/ ; XTXM202203//The Project of Collaborative Innovation Center of GDAAS/ ; 2023YFD1202800//National Key Research and Development Program of China/ ; 2021TX06N789//The Special Support Program of Guangdong Province/ ; 2022SDZG05//The Open Competition Program of Top Ten Critical Priorities of Agricultural Science and Technology Innovation for the 14th Five-Year Plan in Guangdong Province/ ; 2022B0202060004//Guangdong Provincial Key Research and Development Program-Modern Seed Industry/ ; 2023A1515010098 and 2024A1515010511//Basic and Applied Basic Research Foundation of Guangdong Province/ ; 202101, 202201 and 202306//The Foundation of Director of Crop Research Institute of Guangdong Academy of Agriculture Sciences/Open Fund of Guangdong Provincial Key Laboratory of Crop Genetic Improvement/ ; },
mesh = {*Arachis/genetics/metabolism/growth & development ; *Plant Breeding/methods ; *Genome, Plant ; *Genomics ; *Evolution, Molecular ; },
abstract = {Peanut (Arachis hypogaea L.), a globally important oilseed crop, increasingly challenged by rising edible oil demands as well as biotic and abiotic stresses. This review synthesizes recent advances in peanut genomics, evolutionary biology, and breeding technologies to address these challenges aimed at improving yield, oil quality, and resilience. Cultivated peanut is an allotetraploid (AABB), derived from hybridization of the diploid ancestors, A. duranensis and A. ipaensis followed by polyploidization. However, competing evolutionary models highlight unresolved aspects of its domestication history. Advances in sequencing have enabled the high-quality genome assembly of cultivated peanuts, facilitating the development of markers (SSRs, SNPs), trait dissection, and cross omics integration. Genomic studies reveal asymmetric subgenome evolution, chromosomal rearrangements, and structural variations associated with key traits like oil biosynthesis and stress adaptation. Markers assisted selection (MAS) and genomic selection (GS) now accelerate breeding by enabling accurate prediction of complex traits, including yield, disease resistance, and oil quality. Genome editing via CRISPR-Cas9 has transformed trait improvement by enabling accurate modifications in fatty acid desaturases (FAD2), allergen genes, and stress regulators. Multi-omics strategies like transcriptomics, proteomics, metabolomics, lipidomics, and single-cell atlases uncover cell-type specific networks governing pod development and drought responses. Despite progress, polyploid complexity, low transformation efficiency, and genotype-environment interactions remain bottlenecks. Future efforts must leverage pangenomes, machine learning, and high throughput phenotyping to bridge these gaps. This review highlights the potential of integrated genomics and precision breeding to develop high oleic, climate resilient peanut varieties, critical for global food and nutritional security.},
}

*Arachis/genetics/metabolism/growth & development
*Plant Breeding/methods
*Genome, Plant
*Genomics
*Evolution, Molecular

@article {pmid41068119,
year = {2025},
author = {Liu, S and Feng, B and Zhang, Z and Miao, J and Lai, X and Zhao, W and Xie, Q and Ye, X and Cao, C and Yu, P and Sun, J and Guo, J and Wang, Z and Wang, Q and Zhang, Z and Pan, Y},
title = {UPGG: expanding the taxonomic and functional diversity of the pig gut microbiome with an enhanced genome catalog.},
journal = {NPJ biofilms and microbiomes},
volume = {11},
number = {1},
pages = {196},
pmid = {41068119},
issn = {2055-5008},
support = {LZ23C170003//Zhejiang Provincial Natural Science Foundation of China/ ; LZ23C170003//Zhejiang Provincial Natural Science Foundation of China/ ; 2021YFD1200802,2023YFF1001100//National Key Research and Development Program of China/ ; 2021YFD1200802,2023YFF1001100//National Key Research and Development Program of China/ ; 32272832//National Natural Science Foundation of China/ ; 32272832//National Natural Science Foundation of China/ ; },
mesh = {Animals ; *Gastrointestinal Microbiome/genetics ; Swine/microbiology ; *Bacteria/genetics/classification/isolation & purification ; *Archaea/genetics/classification/isolation & purification ; Metagenome ; *Genome, Bacterial ; Interspersed Repetitive Sequences ; Phylogeny ; Metagenomics ; },
abstract = {The porcine gut microbiome is crucial for pig health and key to its production performance. However, genome-level analysis across multiple kingdoms remains limited. Here, we reconstructed the unified pig gastrointestinal genome (UPGG), including bacterial, archaeal, and annotated over 78 million non-redundant protein-coding genes using 5784 metagenome samples. We identified antibiotic resistance genes (ARGs) and mobile genetic elements (MGEs), and the distribution of 72,056 metabolic gene clusters within existing populations. We have constructed pan-genomes of 436 high-quality microbial species and, using these as references, discovered intraspecies genomic variations that revealed 23,350,975 single-nucleotide variants (SNVs). Finally, through comparative analysis of gut microbiome genomes conducted in this study, we observed that pigs may serve as a more suitable model than other animals for investigating human gut microbiota composition and functional patterns. In summary, we constructed a comprehensive reference catalog of the porcine gut microbiome and enhanced the understanding of the host-microbe coevolution.},
}

Animals
*Gastrointestinal Microbiome/genetics
Swine/microbiology
*Bacteria/genetics/classification/isolation & purification
*Archaea/genetics/classification/isolation & purification
Metagenome
*Genome, Bacterial
Interspersed Repetitive Sequences
Phylogeny
Metagenomics

@article {pmid41067298,
year = {2025},
author = {Trisakul, K and Sirichoat, A and Nithichanon, A and Rotcheewaphan, S and Phelan, J and Clark, TG and Faksri, K},
title = {Genomic insights into persistent infections, reinfections, and subspecies diversity of Mycobacteroides abscessus: A whole-genome sequencing study of Thai and global isolates.},
journal = {Infection, genetics and evolution : journal of molecular epidemiology and evolutionary genetics in infectious diseases},
volume = {},
number = {},
pages = {105838},
doi = {10.1016/j.meegid.2025.105838},
pmid = {41067298},
issn = {1567-7257},
abstract = {Mycobacteroides abscessus is a highly resistant pathogen with significant genetic diversity and complicating clinical management. This study used whole-genome sequencing to analyze genomic variations in seven serially collected isolates from three Thai patients, distinguishing between persistent infections and reinfections. Comparative analysis with 43 global isolates revealed subspecies-specific genetic diversity and distribution patterns. Among Thai isolates, two paired samples (P7.1-P7.2 and P15.1-P15.2) were persistent infections (same clone), while two (P8.1-P8.2 and P15.2-P15.3) were reinfections (different clones). Genome-wide comparisons revealed depth distribution patterns and gene cluster variations among different clones, whereas minimal divergence was observed within persistent infections. Although initial pan-genome analysis identified unique genes in same-clone pairs (P7.1 vs. P7.2 and P15.1 vs. P15.2), further validation using raw read mapping confirmed these genes were not truly unique. Analysis of global isolates showed subspecies-specific genetic variations. M. abscessus subsp. abscessus (MAB) and M. abscessus subsp. massiliense (MMAS) exhibited distinct genotypically drug resistance profiles, with unique core genes linked to adaptation and resistance mechanisms. STRING analysis identified 42 unique core genes in MAB, with 11 gene interactions-truB, prmC_2, and aguA_2 showing the highest interaction scores. In contrast, MMAS had 11 unique core genes with a single interaction between lgrD_4 and rnc. Subsequent validation using NCBI BLAST showed only fmt_2 and aguA_2 were truly unique to MAB. This study provides new insights into the genomic evolution of M. abscessus during persistent and reinfections and genetic variation among subspecies. The findings enhance understanding of M. abscessus epidemiology and may inform therapeutic and infection control.},
}

@article {pmid41064766,
year = {2025},
author = {Liu, C and Xu, H and Li, Z and Wang, Y and Zhang, J and Qiao, S and Zhang, H},
title = {From map to blueprint: the plant pan-genome unraveling genetic mysteries and powering precision breeding.},
journal = {Frontiers in plant science},
volume = {16},
number = {},
pages = {1673637},
pmid = {41064766},
issn = {1664-462X},
abstract = {With the rapid advancement of sequencing technologies and bioinformatics, coupled with significant progress in sequencing efficiency and reduced costs, substantial breakthroughs have been achieved in plant functional genomics, evolutionary genetics, and molecular breeding. However, as research deepens, accumulating evidence demonstrates that reference genomes derived from a single individual fail to adequately represent the genetic diversity of entire species. This limitation has catalyzed the emergence of the pan-genome concept. Pan-genome research now stands at the forefront of plant genomics, serving as a pivotal area of focus. Its application in plant studies has unveiled extensive genetic variations, identified numerous novel genes, and significantly enhanced our understanding of genetic diversity within relevant species. This review comprehensively summarizes recent progress in plant pan-genome research, construction methodologies, current applications in plant science, and key achievements. Finally, we outline future research directions, aiming to provide a reference for theoretical and applied pan-genome studies while offering novel perspectives for deciphering the genetic basis of plant breeding, evolutionary domestication, and phenotypic diversity.},
}

@article {pmid41060691,
year = {2025},
author = {Gao, F and Colles, FM and Ko, S and Luo, J and Sheppard, SK and Chen, M},
title = {Genomic epidemiology and the evolution of erm(B)-mediated macrolide resistance in Campylobacter.},
journal = {Microbial genomics},
volume = {11},
number = {10},
pages = {},
doi = {10.1099/mgen.0.001528},
pmid = {41060691},
issn = {2057-5858},
mesh = {*Campylobacter/genetics/drug effects/isolation & purification/classification ; *Macrolides/pharmacology ; Humans ; *Anti-Bacterial Agents/pharmacology ; Phylogeny ; Animals ; *Campylobacter Infections/epidemiology/microbiology ; *Drug Resistance, Bacterial/genetics ; China/epidemiology ; *Methyltransferases/genetics ; Genome, Bacterial ; Microbial Sensitivity Tests ; *Bacterial Proteins/genetics ; Gene Transfer, Horizontal ; Poultry/microbiology ; Evolution, Molecular ; },
abstract = {Campylobacter is a major foodborne bacterial pathogen that has become increasingly resistant to clinically important antimicrobials. Of particular concern is the emergence of erm(B)-mediated macrolide resistance, which has been increasingly documented across Campylobacter isolates from diverse ecological reservoirs. In this study, we investigated the genomic characteristics and epidemiology of erm(B)-carrying clinical Campylobacter isolates from Shanghai, alongside a globally representative dataset of all publicly available strains. Among clinical isolates obtained from a diarrhoeal outpatient surveillance programme between 2020 and 2023 in Shanghai, China, 16% (80/500) were erythromycin-resistant, with 23.8% (19/80) testing positive for erm(B). The genomes of these isolates were sequenced to identify erm(B) gene alleles. Phylogenetic analyses, pairwise comparisons of core and accessory genomes and examination of shared alleles revealed horizontal gene transfer as the predominant mechanism driving the transmission of erm(B) between isolates from various sources. Poultry was identified as a key reservoir for human infections caused by erm(B)-positive Campylobacter isolates. Comparative pangenome analyses of erm(B)-positive and negative isolates identified multiple accessory elements associated with erm(B) acquisition, among which the IS607 family transposon-associated tnpB gene exhibited sequence and structural homology to functional progenitors of CRISPR-Cas nucleases. These findings expand our understanding of the epidemiology of erm(B)-mediated macrolide resistance in Campylobacter and underscore the urgent need for enhanced antimicrobial stewardship in poultry production and targeted surveillance programmes to curb the spread of resistance.},
}

*Campylobacter/genetics/drug effects/isolation & purification/classification
*Macrolides/pharmacology
Humans
*Anti-Bacterial Agents/pharmacology
Phylogeny
Animals
*Campylobacter Infections/epidemiology/microbiology
*Drug Resistance, Bacterial/genetics
China/epidemiology
*Methyltransferases/genetics
Genome, Bacterial
Microbial Sensitivity Tests
*Bacterial Proteins/genetics
Gene Transfer, Horizontal
Poultry/microbiology
Evolution, Molecular

@article {pmid41060304,
year = {2025},
author = {Bueno de Mesquita, CP and Olm, MR and Bissett, A and Fierer, N},
title = {High strain-level diversity of Bradyrhizobium across Australian soils.},
journal = {The ISME journal},
volume = {},
number = {},
pages = {},
doi = {10.1093/ismejo/wraf222},
pmid = {41060304},
issn = {1751-7370},
abstract = {Global surveys of soil bacteria have identified several taxa that are nearly ubiquitous and often the most abundant members of soil bacterial communities. However, it remains unclear why these taxa are so abundant and prevalent across a wide range of soil types and environmental conditions. Here we use genome-resolved metagenomics to test the hypothesis that strain-level differences exist in these taxa that are not adequately captured with standard marker gene sequencing, and that distinct strains harbor unique traits that reflect adaptations to different soil environments. We analyzed data from 331 natural soils spanning Australia to assess strain differentiation in Bradyrhizobium, a dominant soil bacterial genus of ecological importance. We developed a workflow for strain-level bacterial analyses of complex soil metagenomes, combining genomes from pre-existing databases with new genomes generated via targeted assembly from metagenomes to detect 181 Bradyrhizobium strains across the soil collection. In addition to a high degree of phylogenetic variation, we observed substantial variation in pangenome content and inferred traits, highlighting the breadth of diversity within this widespread genus. Although members of the genus Bradyrhizobium were detected in >80% of samples, most individual strains were restricted in their distributions. The overall strain-level community composition of Bradyrhizobium varied significantly across geographic space and environmental gradients, and was particularly associated with differences in temperature, soil pH, and soil nitrate and metal concentrations. Our work provides a general framework for studying the strain-level ecology of soil bacteria and highlights the ecological and pangenomic diversity within this dominant soil bacterial genus.},
}

@article {pmid41059690,
year = {2025},
author = {Venkatachalam, S and Granskog, MA and Gonçalves-Araujo, R and Divine, DV and Vipindas, PV and Jabir, T and Shereef, A and Jain, A},
title = {Distinct bacterial community structures with abundant carbon degradation and sulfur metabolisms found in different sea-ice types from the Central Arctic Ocean.},
journal = {Microbiology spectrum},
volume = {},
number = {},
pages = {e0129125},
doi = {10.1128/spectrum.01291-25},
pmid = {41059690},
issn = {2165-0497},
abstract = {The rapid decline of sea ice in the relatively understudied Central Arctic Ocean has a significant impact on bacterial biodiversity and the ecological functions they support. We investigated the bacterial community composition and the associated metabolic functions from three geographically distinct sea-ice floes: first-year ice (FYI) at the North Pole and western Nansen Basin and second-year or multi-year ice (SYI/MYI) in the western Amundsen Basin. We resolved the sea-ice bacterial community diversity at species-level precision using a long-read amplicon (n = 18) and metagenomic (n = 3) sequencing approach. The amplicon sequencing highlighted marked differences in bacterial community structure driven by ice age, floe origin, and environmental factors, demonstrating pronounced vertical structuring among ice horizons. Bacterial taxa like Paraglaciecola psychrophila, Hydrogenophaga crassostreae, Octadecabacter arcticus, and Polaribacter irgensii mainly dominated the bottom layers of SYI/MYI, whereas species Actimicrobium antarcticum, Polaromonas cryoconiti, O. antarcticus, and Rhodoferax sp. dominated the FYI. Similarly, notable taxonomic differences were observed in bacterial taxa inhabiting the surface and interior layers of FYI and SYI/MYI (e.g., F. frigoris and Hydrogenophaga sp.). The metagenomic analysis showed the prevalence of sulfur cycling-associated (assimilatory and dissimilatory sulfur metabolism) and complex carbon degradation processes in sea ice. We also elucidated the potential ecological role of novel metagenome-assembled genomes belonging to the genus Aquiluna through phylogenomic and pangenomic analyses. Overall, our findings revealed novel insights on the distinct bacterial communities that inhabit ice horizons and their associated ecological functions correlating with sea-ice type, origin, and habitat characteristics in the Central Arctic Ocean.IMPORTANCEThe Arctic region is warming nearly four times faster than the global average, leading to the continuous replacement of its thick multi-year sea ice with thinner first-year ice. The reduction in Arctic sea-ice cover was previously shown to have cascading effects on sea-ice-associated microbial communities and their role in the functioning of the ecosystem. This study provides the first high-resolution, species-level insight into the bacterial community composition and metabolic potential across different sea-ice types in the Central Arctic Ocean-an understudied yet rapidly changing environment. By combining long-read amplicon and metagenomic sequencing, we uncover distinct bacterial assemblages and functional metabolic roles that were shaped by the ice age and other physicochemical properties. Our findings highlight the ecological importance of sea-ice associated bacterial communities and the prevalence of sulfur metabolism and carbon degradation processes in different sea-ice types found in the central Arctic Ocean through genome-resolved metagenomics.},
}

@article {pmid38617326,
year = {2025},
author = {Pell, ME and Blankenship, HM and Gaddy, JA and Davies, HD and Manning, SD},
title = {Genomic adaptation in group B Streptococcus following intrapartum antibiotic prophylaxis and childbirth.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.1101/2024.04.01.587590},
pmid = {38617326},
issn = {2692-8205},
support = {R01 HD090061/HD/NICHD NIH HHS/United States ; R01 AI134036/AI/NIAID NIH HHS/United States ; I01 BX005352/BX/BLRD VA/United States ; U01 CK000510/CK/NCEZID CDC HHS/United States ; U01CK000510/ACL/ACL HHS/United States ; },
abstract = {Through vaginal colonization, GBS causes severe outcomes including neonatal sepsis and meningitis. Although intrapartum antibiotic prophylaxis (IAP) has reduced neonatal disease rates, persistent GBS colonization has been observed in patients following prophylaxis. To determine whether IAP selects for genomic signatures that enhance GBS survival and persistence, a pangenome analysis was performed on 97 isolates from 58 participants before (prenatal) and after (postpartum) IAP/childbirth. Thirty-one of the 34 paired strains from participants with persistent colonization clustered together in the core gene phylogeny, suggesting that the strains recovered at the postpartum sampling were highly similar to those recovered at the prenatal visit. A core-gene mutation analysis identified mutations in 74% (n=23) of the 31 postpartum genomes when compared to the prenatal strains of the same multilocus sequence type recovered from the same individuals. Several strains had acquired mutations in the same colonization-associated genes, though two postpartum strains accounted for most of the mutations. These two outliers were classified as mutators based on high mutation rates and mutations within DNA repair system genes. Increased biofilm production was observed in half of the postpartum strains relative to the prenatal strains, which is supported by the presence of point mutations in genes associated with adherence. Together, these findings suggest that antibiotics may impose a selective pressure on GBS that selects for mutations and phenotypes that promote adaptation and survival in vivo . Enhanced survival in the genitourinary tract can lead to persistent colonization, increasing the likelihood of invasive disease in subsequent pregnancies and in newborns following IAP.},
}

@article {pmid41055944,
year = {2025},
author = {Saygin, H},
title = {Comparative genomics and ecological insights into Nonomuraea turcica sp. nov., an actinomycete from Black Sea island soil.},
journal = {International journal of systematic and evolutionary microbiology},
volume = {75},
number = {10},
pages = {},
doi = {10.1099/ijsem.0.006938},
pmid = {41055944},
issn = {1466-5034},
mesh = {*Phylogeny ; RNA, Ribosomal, 16S/genetics ; *Soil Microbiology ; DNA, Bacterial/genetics ; Base Composition ; Bacterial Typing Techniques ; *Genome, Bacterial ; Black Sea ; Sequence Analysis, DNA ; Islands ; Fatty Acids/chemistry/analysis ; Turkey ; Nucleic Acid Hybridization ; Genomics ; *Actinomycetales/classification/genetics/isolation & purification ; },
abstract = {A polyphasic study was undertaken to characterize strain G32[T], an actinomycete isolated from soil collected on Giresun Island (Black Sea, Turkey). 16S rRNA phylogeny placed the strain within the genus Nonomuraea, but ≤99.1% similarity to its nearest type strains, Nonomuraea turkmeniaca DSM 43926[T], Nonomuraea aridisoli KC333[T], Nonomuraea candida NRRL B-24552[T], Nonomuraea polychroma DSM 43925[T] and Nonomuraea endophytica DSM 45385[T], suggested that it potentially represents a novel taxon. The total genome size is about 12.66 Mb, and the digital G+C content is 69.6 mol%. The high-quality draft genome shared ≤92.16% average nucleotide identity and ≤47.0% digital DNA-DNA hybridization with the closest related type strains, corroborating species-level distinctness. Comparative genomics against four type strains, N. turkmeniaca DSM 43926[T], N. polychrom DSM 43925[T], N. aridisoli KC333[T] and N. endophytica DSM 45385[T], revealed an open pangenome of 24,056 orthologous families, of which G32[T] contributed 2,785 singletons. Copy-number expansion of aqpZ with four paralogues and efeB with three paralogues, together with the sole genome-wide occurrence of ACC-deaminase and an additional fhuDBC siderophore transporter, highlights adaptations to periodic salinity, iron limitation and rhizosphere contact in island soil. Chemotaxonomic markers (meso-diaminopimelic, madurose, MK-9(H4), iso-C16 : 0, iso-C16 : 0 2OH and C17 : 0 10-methyl) of the strain were consistent with the genus Nonomuraea, but phenotypic traits further differentiated the isolate from its relatives. Based on the evidence presented here, strain G32[T] represents a novel species of the genus Nonomuraea, for which the name Nonomuraea turcica sp. nov. is proposed. The type strain of the species is G32[T] (=KCTC 49887[T]=CGMCC 4.7873[T]).},
}

*Phylogeny
RNA, Ribosomal, 16S/genetics
*Soil Microbiology
DNA, Bacterial/genetics
Base Composition
Bacterial Typing Techniques
*Genome, Bacterial
Black Sea
Sequence Analysis, DNA
Islands
Fatty Acids/chemistry/analysis
Turkey
Nucleic Acid Hybridization
Genomics
*Actinomycetales/classification/genetics/isolation & purification

@article {pmid41053037,
year = {2025},
author = {White, B and Lux, T and Rusholme-Pilcher, R and Juhász, A and Kaithakottil, G and Duncan, S and Simmonds, J and Rees, H and Wright, J and Colmer, J and Ward, S and Joynson, R and Coombes, B and Irish, N and Henderson, S and Barker, T and Chapman, H and Catchpole, L and Gharbi, K and Bose, U and Okada, M and Handa, H and Nasuda, S and Shimizu, KK and Gundlach, H and Lang, D and Naamati, G and Legg, EJ and Bharti, AK and Colgrave, ML and Haerty, W and Uauy, C and Swarbreck, D and Borrill, P and Poland, JA and Krattinger, SG and Stein, N and Mayer, KFX and Pozniak, C and , and Spannagl, M and Hall, A},
title = {De novo annotation reveals transcriptomic complexity across the hexaploid wheat pan-genome.},
journal = {Nature communications},
volume = {16},
number = {1},
pages = {8538},
pmid = {41053037},
issn = {2041-1723},
support = {BB/M011216/1//RCUK | Biotechnology and Biological Sciences Research Council (BBSRC)/ ; BB/CCG1720/1//RCUK | Biotechnology and Biological Sciences Research Council (BBSRC)/ ; BBX011089/1//RCUK | Biotechnology and Biological Sciences Research Council (BBSRC)/ ; BB/X011003/1//RCUK | Biotechnology and Biological Sciences Research Council (BBSRC)/ ; BB/M011216/1//RCUK | Biotechnology and Biological Sciences Research Council (BBSRC)/ ; },
mesh = {*Triticum/genetics ; *Genome, Plant/genetics ; *Transcriptome/genetics ; *Polyploidy ; Molecular Sequence Annotation ; Gene Expression Regulation, Plant ; Gene Expression Profiling ; Genetic Variation ; Chromosomes, Plant/genetics ; },
abstract = {Wheat is the most widely cultivated crop in the world, with over 215 million hectares grown annually. The 10+ Wheat Genomes Project recently sequenced and assembled to chromosome-level the genomes of nine wheat cultivars, uncovering genetic diversity and selection within the pan-genome of wheat. Here, we provide a wheat pan-transcriptome with de novo annotation and differential expression analysis for these wheat cultivars across multiple tissues. Using the de novo annotations we identify cultivar-specific genes and define the core and dispensable genomes. Expression analysis across cultivars and tissues reveals conservation in expression between a large core set of homeologous genes, in addition to widespread changes in subgenome homeolog expression bias between cultivars and cultivar-specific expression profiles. We utilise both the newly constructed gene-based wheat pan-genome and pan-transcriptome, demonstrating variation in the prolamin superfamily and immune-reactive proteins across cultivars.},
}

*Triticum/genetics
*Genome, Plant/genetics
*Transcriptome/genetics
*Polyploidy
Molecular Sequence Annotation
Gene Expression Regulation, Plant
Gene Expression Profiling
Genetic Variation
Chromosomes, Plant/genetics

@article {pmid41051826,
year = {2025},
author = {McCallum, GE and Ho, SFS and Cummins, EA and Wildsmith, AJ and McInnes, RS and Weigel, C and Tong, LYS and Quick, J and van Schaik, W and Moran, RA},
title = {The Kocurious case of Noodlococcus: genomic insights into Kocuria rhizophila from characterisation of a laboratory contaminant.},
journal = {Microbial genomics},
volume = {11},
number = {10},
pages = {},
doi = {10.1099/mgen.0.001526},
pmid = {41051826},
issn = {2057-5858},
mesh = {*Genome, Bacterial ; Phylogeny ; Genomics ; *Micrococcaceae/genetics/classification/isolation & purification ; Whole Genome Sequencing ; Sequence Analysis, DNA ; },
abstract = {The laboratory contaminant strain Noodlococcus was named for its coccoid cells and unusual colony morphology, which resembled a pile of noodles. Along with laboratory characterisation and electron microscopy, we generated a complete Noodlococcus genome sequence using Illumina and Oxford Nanopore data. The genome consisted of a single, circular, 2,732,108 bp chromosome that shared 97.5% average nucleotide identity (ANI) with the Kocuria rhizophila type strain TA68. We identified genomic features involved in replication (oriC), carotenoid synthesis (crt) and genome defence (CRISPR-Cas) and discovered four novel mobile elements (ISKrh4-7). Despite its environmental ubiquity and relevance to food production, bioremediation and human medicine, there have been few genomic studies of the Kocuria genus. We conducted a comparative, phylogenetic and pangenomic examination of all 257 publicly available Kocuria genomes, with a particular focus on the 56 that were identified as K. rhizophila. We found that there are two phylogenetically distinct clades of K. rhizophila, with within-clade ANI values of 96.7-100.0% and between-clade values of 89.5-90.4%. The second clade, which we refer to as Kocuria pseudorhizophila, exhibited ANI values of <95% relative to TA68 and should constitute a separate species. Delineation of the two clades would be consistent with the rest of the genus, where all other species satisfy the 95% ANI threshold criteria. Differences in the K. rhizophila and K. pseudorhizophila pangenomes likely reflect phenotypic as well as evolutionary divergence. This distinction is relevant to clinical and industrial settings, as strains and genomes from both clades are currently used interchangeably, which may lead to reproducibility issues and phenotype-genotype discordance. Investigating an innocuous laboratory contaminant has therefore provided useful insights into the understudied species K. rhizophila, prompting an unexpected reassessment of its taxonomy.},
}

*Genome, Bacterial
Phylogeny
Genomics
*Micrococcaceae/genetics/classification/isolation & purification
Whole Genome Sequencing
Sequence Analysis, DNA

@article {pmid41051628,
year = {2025},
author = {Martínez-Zavaleta, MG and García-Contreras, R and Hoshiko, Y and Maeda, T and Zolkefli, N and Colín-Castro, CA and Hernández-Durán, M and Aguilar-Vega, L and Ortíz-Álvarez, J and Franco-Cendejas, R and López-Jácome, LE},
title = {Pseudomonas fragi or not? Beyond MALDI-TOF in the frontier of Pseudomonas diversity.},
journal = {Medical microbiology and immunology},
volume = {214},
number = {1},
pages = {48},
pmid = {41051628},
issn = {1432-1831},
mesh = {*Pseudomonas/classification/genetics/isolation & purification/drug effects ; Spectrometry, Mass, Matrix-Assisted Laser Desorption-Ionization ; Phylogeny ; Humans ; Whole Genome Sequencing ; *Pseudomonas Infections/microbiology ; Virulence Factors/genetics ; Anti-Bacterial Agents/pharmacology ; Genome, Bacterial ; Microbial Sensitivity Tests ; RNA, Ribosomal, 16S/genetics ; Computational Biology ; *Genetic Variation ; Bacterial Typing Techniques ; },
abstract = {Advanced platforms, such as whole genome sequencing (WGS), should be employed to enhance and refine microbial identification compared to phenotypic methods, including miniaturized biochemical tests and MALDI-TOF. The application of WGS has led to the reclassification of clinical bacterial pathogens previously misidentified by phenotypic techniques. In this study, eight clinical isolates initially identified as Pseudomonas fragi by VITEK MS were subjected to WGS and bioinformatics analysis. The results revealed one strain as Pseudomonas lundensis, while average nucleotide identity and phylogenetic reconstruction suggested that the remaining seven strains represent novel species within the Pseudomonas fluorescens superclade. The strains harbored four antimicrobial resistance genes conferring resistance to β-lactams, fluoroquinolones, phenicols, and tetracyclines, yet in vitro assays indicated susceptibility to carbapenems and intermediate susceptibility to colistin. Additionally, the strains possessed virulence factor genes associated with alginate biosynthesis, flagellar formation, pilus assembly, and iron uptake, with Type III Secretion System (T3SS)-related genes detected only in P. lundensis. Notably, the isolated Pseudomonas spp., exhibited multiple haplotypes, a closely related pan-genome, and similar phenotypic characteristics. These findings underscore the necessity of integrating multiple approaches, including molecular methods such as 16S rRNA gene amplification, sanger sequencing, and WGS, alongside traditional phenotypic techniques, to improve the accuracy of microbial identification in clinical settings.},
}

*Pseudomonas/classification/genetics/isolation & purification/drug effects
Spectrometry, Mass, Matrix-Assisted Laser Desorption-Ionization
Phylogeny
Humans
Whole Genome Sequencing
*Pseudomonas Infections/microbiology
Virulence Factors/genetics
Anti-Bacterial Agents/pharmacology
Genome, Bacterial
Microbial Sensitivity Tests
RNA, Ribosomal, 16S/genetics
Computational Biology
*Genetic Variation
Bacterial Typing Techniques

@article {pmid41051204,
year = {2025},
author = {Guillén-Navarro, D and Ochoa, SA and De La Rosa-Zamboni, D and Giono-Cerezo, S and Xicohtencatl-Cortes, J and Cruz-Córdova, A},
title = {Comparative genomics of carbapenem-resistant Acinetobacter baumannii isolated from pediatric patients in a tertiary care hospital.},
journal = {Microbiology spectrum},
volume = {},
number = {},
pages = {e0167625},
doi = {10.1128/spectrum.01676-25},
pmid = {41051204},
issn = {2165-0497},
abstract = {Acinetobacter baumannii is a short gram-negative bacillus, notable for its intrinsic multidrug resistance and genomic plasticity, which facilitates the acquisition of additional resistance genes via mobile genetic elements. Due to its increasing carbapenem resistance, the World Health Organization has classified it as a critical priority pathogen. This study performed a comparative genomic analysis of 20 carbapenem-resistant A. baumannii clinical strains isolated from the Hospital Infantil de México Federico Gómez (CRAB-HIMFG), alongside 11 genomes from other Mexican strains. The pangenome was determined to be open, and core genome single-nucleotide polymorphism-based analysis grouped the CRAB-HIMFG strains within CC758/IC5 and CC92/IC2. A novel sequence type (ST) in the MLST-Pasteur scheme was identified, related to ST[Pas]156, and in the MLST-Oxford scheme, associated with ST[Oxf]758 and ST[Oxf]1054. Virulence and resistance genes comprised 0.61% to 2.23% of the pangenome. Oxacillinase genes and efflux pumps primarily mediated carbapenem resistance, while virulence genes included those encoding biofilm and type IV pili. Capsule typing revealed a correlation with established international clones, IC2 and IC5. Plasmids exhibited high diversity, harboring maintenance modules and toxin-antitoxin systems, with the dissemination of resistance genes linked to insertion sequences. Biofilm formation and twitching motility were not always expressed, as they depend on additional environmental factors. Our study shows that comparative genomics is an essential tool to analyze clinically and epidemiologically significant genomes, providing critical insights into gene distribution, genomic architecture, and horizontal gene transfer mechanisms in microbial populations.IMPORTANCEIn recent years, a reported increase in the mortality rate associated with infections caused by A. baumannii, along with a rise in carbapenem resistance, poses a serious clinical challenge. The WHO considered this microorganism critical for research into alternative therapies and epidemiological surveillance. Despite advances in bioinformatics, genomic studies have yet to fully elucidate the structural rearrangements and secretion systems of A. baumannii. This knowledge gap hinders our understanding of its remarkable genomic plasticity and its ability to acquire and spread resistance and virulence genes through horizontal gene transfer.},
}

@article {pmid41050061,
year = {2025},
author = {Nyaga, DM and Zaied, RE and Silander, OK and Black, MA and O'Sullivan, JM},
title = {Beyond single references: pangenome graphs and the future of genomic medicine.},
journal = {Frontiers in genetics},
volume = {16},
number = {},
pages = {1679660},
pmid = {41050061},
issn = {1664-8021},
abstract = {Genomic medicine relies on single reference genomes that miss crucial genetic diversity, creating diagnostic gaps that disproportionately affect underrepresented populations. Pangenome graphs, collections of diverse genomes represented as interconnected genetic paths, offer a powerful alternative to the standard reference genome approach. Pangenome-based approaches capture the spectrum of human variation, dramatically improving how we detect complex structural variants, reconstruct haplotypes, and reduce bias in genetic studies. Projects like the Human Pangenome Reference Consortium have identified hundreds of megabases of missing genetic diversity, leading to remarkable improvements in variant detection across different populations. Yet, as pangenomes grow larger and computationally complex, they become more challenging to interpret clinically, creating a trade-off between comprehensiveness and usability. This review discusses the technical and conceptual advances enabling clinical applications of pangenomes in rare disease diagnosis. Realizing the future potential of pangenome graphs in genomic medicine will require innovative implementation strategies, thorough clinical testing, and user-friendly approaches.},
}

@article {pmid41042591,
year = {2025},
author = {Liu, Z and Pei, S and Ou, X and Li, X and Zhu, Y and Lu, Y and Zhang, M and Che, Y and Wu, K and Wang, X and Zhao, Y},
title = {Pan- and core genome analysis of Mycobacterium tuberculosis in high-resolution transmission and genetic diversity studies.},
journal = {Microbial genomics},
volume = {11},
number = {10},
pages = {},
doi = {10.1099/mgen.0.001460},
pmid = {41042591},
issn = {2057-5858},
mesh = {*Mycobacterium tuberculosis/genetics/classification/isolation & purification ; Humans ; *Genome, Bacterial ; *Tuberculosis/transmission/microbiology ; *Genetic Variation ; China/epidemiology ; Polymorphism, Single Nucleotide ; Phylogeny ; Genomics/methods ; Whole Genome Sequencing ; },
abstract = {The application of pan-genomics in understanding Mycobacterium tuberculosis complex (MTBC) transmission remains understudied, particularly in high-burden settings such as China. We constructed an M. tuberculosis complex pan-genome (MTB_pan) using 307 complete genomes representing all eight lineages from the National Center for Biotechnology Information (NCBI). Core and accessory genomes were analysed, lineage-associated genes were identified and functional annotations were assessed using Pfam domains. Transmission dynamics were evaluated by comparing pan-genome- and H37Rv-based approaches for isolates collected from China, focusing on alignment rates, clustering efficiency and SNP distances. The MTB_pan (5.75 Mb) consisted of 3,893 core and 958 accessory genes, with 176 accessory genes significantly associated with specific lineages. These genes were enriched in PE/PPE/PGRS families, mobile genetic elements (e.g. IS6110) and pentapeptide repeats. The median alignment rate based on MTB_pan reached 99.8%, which was significantly higher than that based on H37Rv. The clustering rate of isolates based on MTB_pan (19.93%) was higher than that based on H37Rv (18.90%). The pairwise SNP distances below 50 SNPs within lineage 2 decreased significantly, while those within lineage 4 showed no significant differences. Compared to a single reference genome, clustering using the pan-genome improved the identification of same-province transmission events. Therefore, the pan-genomic analysis is a more powerful analytical tool that enables the establishment of a high-resolution picture of tuberculosis transmission in different epidemiological settings, which will enable more precise outbreak mapping and support data-driven tuberculosis control strategies.},
}

*Mycobacterium tuberculosis/genetics/classification/isolation & purification
Humans
*Genome, Bacterial
*Tuberculosis/transmission/microbiology
*Genetic Variation
China/epidemiology
Polymorphism, Single Nucleotide
Phylogeny
Genomics/methods
Whole Genome Sequencing

@article {pmid41041811,
year = {2025},
author = {Shokrof, M and Abuelanin, M and Brown, CT and Mansour, TA},
title = {The Great Genotyper: a graph-based method for population genotyping of small and structural variants.},
journal = {GigaScience},
volume = {14},
number = {},
pages = {},
doi = {10.1093/gigascience/giaf112},
pmid = {41041811},
issn = {2047-217X},
support = {D22CLP-505//Morris Animal Foundation/ ; },
mesh = {Humans ; *Software ; *Genotyping Techniques/methods ; Gene Frequency ; Genotype ; *Genomic Structural Variation ; Genetics, Population/methods ; Computational Biology/methods ; High-Throughput Nucleotide Sequencing/methods ; Genome, Human ; },
abstract = {BACKGROUND: Long-read sequencing (LRS) enables high-quality structural variant (SV) discovery. SV genotypers utilize these precise call sets to improve the recall and precision of genotyping in short-read sequencing (SRS) samples. With the extensive growth in publicly available SRS datasets, it is now possible to calculate accurate population allele frequencies of SVs. However, reprocessing hundreds of terabytes of raw SRS data to genotype new variants is impractical for population-scale studies, a computational challenge known as the N+1 problem (i.e., the challenge of re-genotyping an entire cohort for one additional variant). Overcoming this computational bottleneck is essential for analyzing new SVs from the growing number of pangenomes, public genomic databases, and pathogenic variant discovery studies.

RESULTS: We propose the Great Genotyper, a population-scale genotyping workflow to address the N+1 problem. Applied to a human dataset, the workflow begins by preprocessing 4.2k short-read samples of a total of 183 TB raw data to create an 867-GB Counting Colored de Bruijn Graph (CCDG). The Great Genotyper uses this CCDG to genotype a list of phased or unphased variants, leveraging the CCDG population information to increase both precision and recall. The Great Genotyper offers the same accuracy as the state-of-the-art genotypers while achieving unprecedented performance. It took about 100 hours to genotype 4.5M variants across the 4.2k samples and calculate their population allele frequencies using 1 server with 32 cores and 145 GB of memory. The Great Genotyper opens the door to new ways to study SVs. For example, using the premade index, we demonstrate the Great Genotyper's application in finding pathogenic variants by calculating accurate allele frequency for novel SVs. Also, we used it to create a 4k reference panel by genotyping variants from the Human Pangenome Reference Consortium (HPRC). The new reference panel allows for SV imputation from genotyping microarrays. Moreover, we genotype the human GWAS Catalog and merge its variants with the 4k reference panel. We show 6,253 events of high linkage between the HPRC's SVs and nearby GWAS single-nucleotide polymorphisms, which can help in interpreting the effect of these SVs on gene functions. This analysis uncovers the detailed haplotype structure of the human fibrinogen locus and revives the pathogenic association of a 28-bp insertion in the FGA gene with thromboembolic disorders.

CONCLUSION: The Great Genotyper solves the N+1 problem for population-scale genotyping of small and structural variants, offering both high accuracy and efficiency. Its ability to rapidly re-genotype large cohorts paves the road for several new studies of SVs.},
}

Humans
*Software
*Genotyping Techniques/methods
Gene Frequency
Genotype
*Genomic Structural Variation
Genetics, Population/methods
Computational Biology/methods
High-Throughput Nucleotide Sequencing/methods
Genome, Human

@article {pmid41040191,
year = {2025},
author = {Sridharan, S and Lou, RN and Ferguson, S and Rocha, JL and De-Kayne, R and Mitchell, MW and Killilia, AN and Borda, V and Medina-Munoz, SG and Gravel, S and , and Henn, B and Sudmant, PH},
title = {Recurrent structural variation and recent turnover at the 17q21.31 locus in humans and great apes.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.1101/2025.08.15.670618},
pmid = {41040191},
issn = {2692-8205},
abstract = {The 17q21.31 locus in humans harbors several complex structural haplotypes including a ∼970kb inversion. Different inversion haplotypes have been associated with susceptibility to microdeletions causing Koolen-de Vries syndrome and variation in fecundity and recombination rates. Here, using 210 haplotype-resolved human genome assemblies and pangenome graph-based approaches we characterize 11 distinct structural haplotypes, several of which have not been previously described. Extending our analyses to a set of haplotype-resolved great-ape genomes, we characterize the structure of an independent inversion in chimpanzees which extends an additional 650kb, encompasses 5 additional genes, and is ∼2 million years younger than the human inversion. We further determine that gorillas exhibit an independent duplication of the KANSL1 gene which may predispose them to Koolen-de Vries syndrome causing microdeletions. Using short read sequencing data we characterize 17q21.31 haplotype diversity worldwide in ∼5174 individuals from 107 populations finding increased frequencies of KANSL1 duplication-containing haplotypes in both European and South Asian populations as well as 8 double recombination events between inverted and non-inverted haplotypes ranging in size from 20-180kb. Finally, using 626 ancient Eurasian human genomes we show the frequency of haplotypes containing KANSL1 duplications has increased ∼6-fold over the past 12 thousand years in Europe. Together, our results highlight the dynamics, complexity, and recurrent, independent evolution of a medically relevant locus across humans and great apes.},
}

@article {pmid41038457,
year = {2025},
author = {Karthik, K and Anbazhagan, S and Thomas, P and Manoharan, S},
title = {Genome sequencing and comparative genome analysis of Clostridium perfringens of animal origin.},
journal = {Microbial pathogenesis},
volume = {},
number = {},
pages = {108079},
doi = {10.1016/j.micpath.2025.108079},
pmid = {41038457},
issn = {1096-1208},
abstract = {Clostridium perfringens, a ubiquitous organism that has zoonotic potential, is associated with enteric diseases in humans and various animals, largely due to its potent toxin production and increasing antimicrobial resistance (AMR). The present study involved whole genome sequencing and comparative genomic analysis of four C. perfringens isolates (from pig, dog, and cattle) collected in Tamil Nadu, India, along with 133 global strains of animal origin. The phylogenomic analysis revealed six major clusters and no correlation associated with geographic origin or host were observed. Multilocus sequence typing (MLST) defined sequence types (STs) of two Indian isolates (ST126 and ST200) whereas the remaining two isolates were novel., Pangenome analysis indicated an open genome structure, with 18.28% core genes and 81.72% accessory genes. Virulent gene profiling identified widespread presence of plc, pfoA, and cpe, especially among dog isolates, suggesting potential zoonotic risks. wgMLST and MST analysis showed clustering of toxinotype F isolates from dogs and higher genetic diversity for other toxintypess. AMR gene analysis revealed tetracycline resistance as the most prevalent, with several strains harbouring multidrug resistance genes. This study underscores the genetic diversity, adaptive evolution, and One Health significance of C. perfringens in animals and highlights the importance of genomics in understanding host-specific virulence and resistance patterns for effective disease surveillance and control.},
}

@article {pmid41036850,
year = {2025},
author = {Montecillo, JAV and Yoo, HJ and Lee, Y-Y and Park, CM and Cho, A and Lee, H and Yoon, HY and Kim, JM and Lee, NY and Park, S-H and Park, NJ-Y and Han, HS and Seo, I and Chong, GO},
title = {Pangenome analysis of Lactobacillus mulieris strains reveals distinct subspecies clusters with defined ecological adaptations.},
journal = {Microbiology spectrum},
volume = {},
number = {},
pages = {e0201125},
doi = {10.1128/spectrum.02011-25},
pmid = {41036850},
issn = {2165-0497},
abstract = {Lactobacillus mulieris is a recently described species, reportedly isolated from human urine, vagina, and gut. Previous genomic studies of L. mulieris highlighted significant genetic diversity among its strains. To gain a deeper understanding of this genomic diversity, we conducted a comprehensive genomic comparison of 70 L. mulieris strains from diverse sources. Phylogenomic and genome relatedness analysis identified three distinct clades, each representing a potential subspecies cluster. Pangenome analysis revealed distinct gene clusters shaping the functional characteristics and unique ecological adaptations of each clade. Clade 1 demonstrated a generalist lifestyle, with strains isolated from diverse sources and enriched in serine/threonine protein kinases, suggesting adaptive versatility. Clade 2, predominantly composed of urinary isolates, displayed enrichment in genes facilitating nutrient acquisition and osmotic regulation, enabling survival in the nutrient-limited and high osmolarity conditions of the urinary tract. Clade 3, exclusively composed of vaginal isolates, exhibited significant enrichment in genes supporting glycogen metabolism, carbohydrate transport, and capsular polysaccharide biosynthesis-features indicative of adaptation to the vaginal environment. Collectively, our findings provide essential genomic insights into the ecological specialization of L. mulieris, shedding light on their genetic variability and adaptive traits within their respective ecological niches.IMPORTANCERecognizing the genomic diversity within Lactobacillus mulieris is essential for understanding its ecological specialization and adaptation strategies across distinct human-associated environments. By identifying three distinct clades with unique functional traits, our study highlights the critical role of niche-specific genetic adaptations in microbial survival. The presence of specialized gene functions within each clade underscores how evolutionary pressures shape bacterial resilience in different environments. Despite their coexistence in overlapping environments, these clades exhibit distinct genomic profiles that may influence their colonization potential and interactions with the host and within the host-associated microbiota. Our findings emphasize the need for a classification framework that accounts for these genetic and functional differences and the necessity for further investigation to understand their distinct roles and impact on human health.},
}

@article {pmid41036251,
year = {2025},
author = {Boussaha, M and Eché, C and Klopp, C and Grohs, C and Milhes, M and Suin, A and Bulach, T and Fourdin, R and Faraut, T and Kuchly, C and Fritz, S and Vernette, C and Naji, M and Sorin, V and Capitan, A and Gaspin, C and Milan, D and Boichard, D and Iampietro, C and Donnadieu, C},
title = {Whole genome short read data from 567 bulls of 14 breeds provides insight into genetic diversity of French cattle.},
journal = {Data in brief},
volume = {62},
number = {},
pages = {112049},
pmid = {41036251},
issn = {2352-3409},
abstract = {Technological developments in high-throughput sequencing and advances in bioinformatic analysis allowed to sequence and study a very large number of genomes from a single species (cattle). Analyzing this data set enabled to generate the corresponding genomic variant database, especially for single nucleotide polymorphisms (SNPs) and small insertion or deletion (Indels) variations. These variants and genotypes allowed to better characterize the genetic diversity of these breeds. In this work, we sequenced 567 bulls from 14 different breeds (Holstein, Montbéliarde, Normande, Brown Swiss, Simmental, Abondance, Tarentaise, Vosgienne, Blonde d'Aquitaine, Charolaise, Limousine, Aubrac, Flamande, Parthenaise). Each sample was sequenced at an approximately 15x depth on the Illumina Novaseq6000 platform. We detected 34,252,080 variants, 25,115,987 of which were already known in the Ensembl variation database version 110 and 9,136,093 were absent and were considered as novel variants. This data set represents a useful resource for the community to better identify SNPs or indels such as mutation anticipation and provides new insights into bovine genetic diversity.},
}

@article {pmid41032193,
year = {2025},
author = {Yetiman, AE and Horzum, M and Kanbur, E and Çadir, M and Bahar, D and Gürbüz, Ş and Karaman, MZ and Fidan, Ö and Kaya, M and Yetiman, S and Doğan, M and Akbulut, M},
title = {Pangenome Analysis and Genome-Guided Probiotic Evaluation of Cyclic Dipeptides Producing Levilactobacillus brevis DY55bre Strain from a Lactic Acid Fermented Shalgam to Assess Its Metabolic, Probiotic Potentials, and Cytotoxic Effects on Colorectal Cancer Cells.},
journal = {Probiotics and antimicrobial proteins},
volume = {},
number = {},
pages = {},
pmid = {41032193},
issn = {1867-1314},
support = {FBA-2025-14779//Bilimsel Araştırma Projeleri, Erciyes Üniversitesi/ ; },
abstract = {This study investigates the genetic, metabolic, and probiotic characteristics of Levilactobacillus brevis DY55bre, a strain isolated from the traditional Turkish fermented beverage, shalgam. Whole-genome sequencing revealed a circular genome of 2.485 Mb with a GC content of 45.72%, predicted 2791 genes, and multiple CRISPR-Cas systems. Pangenome analysis demonstrated an open structure, with 18.9% core genes and 103 strain-specific genes, highlighting its genetic diversity. The DY55bre exhibits heterofermentative carbohydrate metabolism due to the presence of the araBAD operon and the lack of 1-phosphofructokinase (pfK) and fructose-1,6-bisphosphate aldolase enzymes. Probiotic evaluation revealed firm survival under simulated gastrointestinal conditions, including resistance to acidic pH (as low as 3.0) and bile salts (up to 1%), along with significant adhesion to intestinal epithelial cell lines (HT29;59.3%, Caco-2;87%, and DLD-1;60.8%). The strain exhibited high auto-aggregation (84.55%) and cell surface hydrophobicity (56.69%), essential for gut colonization. Safety assessments confirmed its non-hemolytic nature and absence of horizontally acquired antibiotic resistance genes. Notably, GC-MS analysis identified bioactive cyclic dipeptides, Cyclo(D-Phe-L-Pro) and Cyclo(L-Leu-L-Pro), which demonstrated cytotoxic effects against colorectal cancer cell lines, with IC50 values of 7.71 mg/mL for HT29 and 3.19 mg/mL for DLD-1. The cell-free supernatant exhibited antimicrobial activity against pathogens, likely due to the synergistic effects of cyclic dipeptides, organic acids, and other metabolites. Antioxidant assays revealed significant ABTS[+] (76.63%) and DPPH (34.25%) radical scavenging activities, while cholesterol assimilation tests showed a 27.29% reduction. These findings position the DY55bre as a promising candidate for functional foods, nutraceuticals, and therapeutic applications, warranting further in vivo validation.},
}

@article {pmid41030232,
year = {2025},
author = {Evans, D and Friedman, B and Pung, K and Weber, B and Plumb, M and Garfin, J and Lees, C and Holzbauer, S and Lynfield, R and Wang, X},
title = {Insights on recurrent and sequential Clostridioides difficile infections from genomic surveillance in Minnesota, USA, 2019-2021.},
journal = {The Journal of infectious diseases},
volume = {},
number = {},
pages = {},
doi = {10.1093/infdis/jiaf505},
pmid = {41030232},
issn = {1537-6613},
abstract = {BACKGROUND: The frequent temporal recurrence of Clostridioides difficile infection (CDI) may be the result of relapse with the same strain or reinfection with a different strain. We used whole-genome sequencing (WGS) to assess the genetic diversity and molecular evolution of strains that caused recurrent or sequential CDI.

METHODS: We analyzed data from active population- and laboratory-based surveillance of CDI in Minnesota, USA. We performed WGS on isolates collected from 306 patients with multiple CDI events during 2019-2021. We identified multi-locus sequence types (MLSTs), nucleotide variants, and putative mobile genetic elements (MGEs) from WGS data to study the genetic similarity and evolution of those C. difficile genomes.

RESULTS: Among patients with multiple CDI events in the surveillance period, 198 (64.7%) had multiple infections of the same MLST, including 49.6% of patients with subsequent infections beyond the 8-week limit of the case definition for recurrent CDI Among 232 temporally defined events of recurrent CDI, 155 (66.8%) involved isolates of the same MLST. There were no statistically significant correlations between accumulated mutations and elapsed time between same-MLST CDI events. Analysis of sequential same-MLST C. difficile genomes showed evidence of gain or loss of putative mobile genetic elements (MGEs) in 45.6% of genome pairs.

CONCLUSIONS: Leveraging the largest CDI genomic dataset to date, our results confirm prior findings that recurrent CDI is a combination of reinfection and/or change in the ascendant strain in mixed infection, and relapse, while expanding knowledge on the evolution of pathogenic C. difficile strains in the human gastrointestinal tract.},
}

@article {pmid41028366,
year = {2026},
author = {MacNish, TR and Hu, H and Yuan, Y and Bayer, PE and Tay Fernandez, CG and Scheben, A and Golicz, AA and Edwards, D},
title = {Legume Pangenome Construction Using an Iterative Mapping and Assembly Approach.},
journal = {Methods in molecular biology (Clifton, N.J.)},
volume = {2977},
number = {},
pages = {1-14},
pmid = {41028366},
issn = {1940-6029},
mesh = {*Genome, Plant ; *Chromosome Mapping/methods ; *Fabaceae/genetics ; *Genomics/methods ; Sequence Analysis, DNA/methods ; High-Throughput Nucleotide Sequencing/methods ; },
abstract = {A pangenome is a collection of genomic sequences found in the entire species rather than a single individual. It allows comprehensive, species-wide characterization of genetic variations and mining of variable genes that may play important roles in phenotypes of interest. Advances in DNA sequencing technologies have facilitated genome sequence assembly and have made pangenome constructions routine. Here, we present a reference genome-based iterative mapping and assembly method to construct a pangenome for a legume species.},
}

*Genome, Plant
*Chromosome Mapping/methods
*Fabaceae/genetics
*Genomics/methods
Sequence Analysis, DNA/methods
High-Throughput Nucleotide Sequencing/methods

@article {pmid41023799,
year = {2025},
author = {Xing, J and Hao, J and Tang, C and Xie, S and Liu, K},
title = {A closed-loop method for precise genome size estimation using HiFi reads.},
journal = {BMC genomics},
volume = {26},
number = {1},
pages = {878},
pmid = {41023799},
issn = {1471-2164},
support = {2021YFA0909600//National Key Research and Development Program of China/ ; 2021YFA0909600//National Key Research and Development Program of China/ ; 2021YFA0909600//National Key Research and Development Program of China/ ; 31825007//National Natural Science Foundation of China/ ; 31825007//National Natural Science Foundation of China/ ; 31825007//National Natural Science Foundation of China/ ; KJRC2023B20//Innovational Fund for Scientific and Technological Personnel of Hainan Province/ ; KJRC2023B20//Innovational Fund for Scientific and Technological Personnel of Hainan Province/ ; KJRC2023B20//Innovational Fund for Scientific and Technological Personnel of Hainan Province/ ; THAITS-3//The earmarked fund for Tropical High-efficiency Agricultural Industry Technology System of Hainan University/ ; THAITS-3//The earmarked fund for Tropical High-efficiency Agricultural Industry Technology System of Hainan University/ ; THAITS-3//The earmarked fund for Tropical High-efficiency Agricultural Industry Technology System of Hainan University/ ; 2022-2-023//Major (Key) Science and Technology Projects in Jinhua City/ ; },
abstract = {BACKGROUND: Super pangenomes, as complete genome sequencing at the genus level, have provided new insights into the speciation and evolution of functional genes. Genome size (GS) estimation is a critical first step. Although K-mer-based GS evaluators are applied extensively to guide genome assembly process and quality assessment, the results vary substantially with the tools and parameters used, presenting challenges for genus-level genome studies.

RESULTS: Here, we investigated K-mer spectra from datasets of species with and without whole genome duplication, revealing that the trade-off in K-mer length amplified the signal of genomic characteristics related to repeat content or heterozygosity. Moreover, GS predictions were influenced by genomic heterozygosity and sequencing accuracy when different K-mer lengths were employed. In contrast, consistent GS predictions were obtained across all HiFi-based evaluations, demonstrating high accuracy of the derived limiting values from the regions of GS evaluation convergence during continuous variation of K. Unlike traditional methods that rely on single predictions, we introduced a closed-loop GS-estimating framework, that incorporates steady-value calculations, leveraging the continuity and accuracy of HiFi reads. Finally, we developed a high-performance pipeline, LVgs (https://github.com/xingjianfeng100/LVgs), by integrating FastK and GenomeScope 2.0.

CONCLUSIONS: The robustness and applicability of LVgs for genus-level species was demonstrated through its application to various diploid and polyploidy species.

SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1186/s12864-025-12031-9.},
}

@article {pmid41028112,
year = {2025},
author = {Najar, IN and Sharma, P and Das, R and Mondal, K and Singh, AK and Radha, A and Sharma, V and Sharma, S and Thakur, N and Gandhi, SG and Kumar, V},
title = {Unveiling the probiotic potential of the genus Geobacillus through comparative genomics and in silico analysis.},
journal = {Scientific reports},
volume = {15},
number = {1},
pages = {33748},
pmid = {41028112},
issn = {2045-2322},
mesh = {*Probiotics ; *Geobacillus/genetics ; *Genome, Bacterial ; *Genomics/methods ; Computer Simulation ; CRISPR-Cas Systems ; Humans ; Prophages/genetics ; },
abstract = {Pursuing new probiotic targets has surged, driven by next-generation sequencing, facilitating a thorough exploration of bacterial traits. The genus Geobacillus stands out as a promising candidate for probiotics. The study explored the genetic attributes of the genus Geobacillus for their resilience to gastrointestinal conditions, nutrient production, and immunomodulatory compound creation, revealing potential probiotic traits. Predictive analyses of genomic elements like prophages, CRISPR-Cas systems, insertion sequences, genomic islands, antibiotic resistance genes, and CAZymes were conducted to assess safety. Comparative genomic analysis was performed using 18 published Geobacillus genomes and a few Lactobacillus and Bifidobacterium genomes as controls. Genes associated with probiotic traits, such as adhesion, stress tolerance (acid/bile, osmotic, oxidative), immune modulation, and molecular chaperones, were uniformly detected in Geobacillus. Mobile genetic elements (such as plasmids, prophages, and insertion sequences), virulence factors, toxins, and antibiotic resistance genes were absent, while CRISPR-Cas systems and CAZymes were present. The pan-genome comprised 25,284 protein-coding genes. Comparative genomic analysis revealed an open pan-genome for Geobacillus. Pan-genome exhibited variability, particularly in genes linked to environmental interaction and secondary metabolite synthesis. Geobacillus appears potentially safe and well-suited for the gut habitat. However, further in vitro studies are essential to confirm its probiotic potential.},
}

*Probiotics
*Geobacillus/genetics
*Genome, Bacterial
*Genomics/methods
Computer Simulation
CRISPR-Cas Systems
Humans
Prophages/genetics

@article {pmid41023782,
year = {2025},
author = {Chen, S and Wang, X and Zhang, L},
title = {Insights into the taxonomy and virulence-related genetic profiles in 97 Cupriavidus strains through comparative genomic analysis.},
journal = {BMC genomics},
volume = {26},
number = {1},
pages = {868},
pmid = {41023782},
issn = {1471-2164},
support = {52070037//National Natural Science Foundation of China/ ; 52070037//National Natural Science Foundation of China/ ; 52070037//National Natural Science Foundation of China/ ; JJKH20250338BS//Doctoral Students' Scientific Research and Innovation Capacity Improvement Project of Jilin Provincial Education Department of China/ ; JJKH20250338BS//Doctoral Students' Scientific Research and Innovation Capacity Improvement Project of Jilin Provincial Education Department of China/ ; },
mesh = {*Cupriavidus/genetics/classification/pathogenicity ; Phylogeny ; Virulence/genetics ; *Genome, Bacterial ; *Genomics/methods ; Virulence Factors/genetics ; },
abstract = {BACKGROUND: The taxonomic ambiguity caused by species complexes (closely related species with overlapping phenotypic traits but distinct genetic profiles) has increasingly garnered attention. Cupriavidus species hold environmental, industrial, and clinical relevance, yet unresolved species complexes within this genus may limit insights into their pathogenesis.

RESULTS: Six species (C. alkaliphilus, C. basilensis, C. gilardii, C. oxalaticus, C. necator, and C. taiwanensis) were identified as species complexes, comprising 36 correctly classified strains and 42 mislabeled strains. More importantly, C. alkaliphilus and a subset of C. taiwanensis are phylogenetically grouped together. We, therefore, propose a genome-based taxonomic framework to reclassify these species. For mislabeled strains, the 10 strains labeled as C. taiwanensis were reassigned to C. alkaliphilus; the remaining 32 strains were classified as 11 unnominated genomic groups. C. metallidurans and C. pauculus retained current classifications. The open pan-genome and prevalence of mobile genetic elements indicated high genetic variation in Cupriavidus. We identified 47 genes related to virulence factors. Virulence factors in almost all Cupriavidus strains were related to the antimicrobial activity (acrB), biofilm (adeG, algU), stress survival (clpP, katA, sodB, ureA, ureB, and ureG), adherence (htpB, kdsA), and others (icl); the opportunistic pathogens C. gilardii and C. metallidurans contained extra virulence genes (plc-2). Furthermore, six types of secretion systems (T1SS-T6SS) were identified in Cupriavidus. T2SS was conserved across all eight species; the other secretion systems presented diverse distribution. Interestingly, C. gilardii possesses two divergent T3SS clusters. Finally, emre, responsible for the efflux pump of aminoglycoside antibiotics, is a major antibiotic resistance gene of Cupriavidus strains. Other genes related to aminoglycosides, β-lactam, fosfomycin, and multidrug resistance are species-specific among opportunistic pathogens individually.

CONCLUSIONS: This study addresses the taxonomic ambiguities arising from species complexes within 97 strains of Cupriavidus and proposes a genome-based taxonomic framework based on phylogenomic analysis. Beyond classification, we advance insights into the genus's pathogenesis by delineating virulence-related genetic profiles, including conserved and species-specific virulence factors, secretion systems, and antibiotic resistance genes. Collectively, this work establishes a genomic foundation for understanding phylogenetic relationships and a comparative framework to explore pathogenicity across 97 strains of Cupriavidus.},
}

*Cupriavidus/genetics/classification/pathogenicity
Phylogeny
Virulence/genetics
*Genome, Bacterial
*Genomics/methods
Virulence Factors/genetics

@article {pmid41011836,
year = {2025},
author = {Harrison, L and Mukherjee, S and Li, C and Young, S and Zhang, Q and Zhao, S},
title = {Pangenomic Characterization of Campylobacter Plasmids for Enhanced Molecular Typing, Risk Assessment and Source Attribution.},
journal = {Pathogens (Basel, Switzerland)},
volume = {14},
number = {9},
pages = {},
doi = {10.3390/pathogens14090936},
pmid = {41011836},
issn = {2076-0817},
mesh = {*Plasmids/genetics/classification ; *Campylobacter/genetics/classification/drug effects ; Risk Assessment ; Humans ; *Campylobacter Infections/microbiology ; *Molecular Typing/methods ; Animals ; Drug Resistance, Bacterial/genetics ; },
abstract = {Plasmid-mediated dissemination of antimicrobial resistance (AMR) and virulence genes plays a critical role in enhancing the adaptive potential of Campylobacter spp. While Campylobacter plasmids of concern are commonly classified as pTet, pVir, pCC42 or a large plasmid encoding a T6SS (pT6SS), existing classification systems often lack the resolution to capture intra-group diversity. Here we demonstrate a plasmid typing approach with enhanced discriminatory power that categorizes these major plasmid groups into discrete subgroups and strengthens risk-assessment investigations. Pangenomic analysis of 424 Campylobacter plasmid sequences revealed 30 distinct plasmid groups. The four major groups above accounted for 74.3% of the dataset. Within these major groups, 177 plasmid type-specific loci were used to define 16 subgroups. pTet plasmids were subdivided into 5 subgroups, with subgroup 3 enriched in C. coli. pVir plasmids formed 3 subgroups, with only subgroup 3 harboring the tet(O) genes. The 5 pCC42 subgroups displayed Campylobacter species specificity while the 3 pT6SS subgroups encoded distinct AMR profiles. This high-resolution typing approach provides a unified and scalable method to characterize Campylobacter plasmid diversity and identifies genetic markers critical for pathogen surveillance, source attribution and mitigation strategies employed to safeguard human and animal health.},
}

*Plasmids/genetics/classification
*Campylobacter/genetics/classification/drug effects
Risk Assessment
Humans
*Campylobacter Infections/microbiology
*Molecular Typing/methods
Animals
Drug Resistance, Bacterial/genetics

@article {pmid41011762,
year = {2025},
author = {Elrefaey, A and Bentum, KE and Kuufire, E and James, T and Nyarku, R and Osei, V and Woube, Y and Samuel, T and Abebe, W},
title = {Genomic Markers Distinguishing Shiga Toxin-Producing Escherichia coli: Insights from Pangenome and Phylogenomic Analyses.},
journal = {Pathogens (Basel, Switzerland)},
volume = {14},
number = {9},
pages = {},
doi = {10.3390/pathogens14090862},
pmid = {41011762},
issn = {2076-0817},
support = {2021-38821-34710; 2022-67017-36982//National Institute of Food and Agriculture, United States Department of Agriculture (NIFA-USDA)/ ; },
mesh = {*Shiga-Toxigenic Escherichia coli/genetics/classification ; *Genome, Bacterial ; *Phylogeny ; Serogroup ; Genomics/methods ; Genetic Markers ; Escherichia coli Infections/microbiology ; Humans ; },
abstract = {Shiga toxin-producing Escherichia coli (STEC) are genetically diverse foodborne pathogens of major global public health concerns. Serogroup-level identification is critical for effective surveillance and outbreak control; however, it is often challenged by STEC's genome plasticity and frequent recombination. In this study, we employed a standardized pangenomic pipeline integrating Roary ILP Bacterial Core Annotation Pipeline (RIBAP) and Panaroo to analyze 160 complete, high-quality STEC genomes representing eight major serogroups at a 95% sequence identity threshold. Candidate serogroup-specific markers were identified using gene presence/absence profiles from RIBAP and Panaroo. Our analysis revealed several high-confidence markers, including metabolic genes (dgcE, fcl_2, dmsA, hisC) and surface polysaccharide-related genes (capD, rfbX, wzzB). Comparative pangenomic evaluation showed that RIBAP predicted a larger pangenome size than Panaroo. Additionally, some genomes from the O104:H1, O145:H28, and O45:H2 serotypes clustered outside their expected clades, indicating sporadic serotype misplacements in phylogenetic reconstructions. Functional annotation suggested that most candidate markers are involved in critical processes such as glucose metabolism, lipopolysaccharide biosynthesis, and cell surface assembly. Notably, approximately 22.9% of the identified proteins were annotated as hypothetical. Overall, this study highlights the utility of pangenomic analysis for potential identification of clinically relevant STEC serogroups markers and phylogenetic interpretation. We also note that pangenome analysis could guide the development of more accurate diagnostic and surveillance tools.},
}

*Shiga-Toxigenic Escherichia coli/genetics/classification
*Genome, Bacterial
*Phylogeny
Serogroup
Genomics/methods
Genetic Markers
Escherichia coli Infections/microbiology
Humans

@article {pmid41011469,
year = {2025},
author = {Ficca, AG and Luziatelli, F and Abou Jaoudé, R and Ruzzi, M},
title = {Integrative Genomics and Metabolomics Analyses Provide New Insights into the Molecular Basis of Plant Growth Promotion by Pantoea agglomerans.},
journal = {Microorganisms},
volume = {13},
number = {9},
pages = {},
doi = {10.3390/microorganisms13092138},
pmid = {41011469},
issn = {2076-2607},
support = {This research was carried out within the Agritech National Research Center and received funding from the European Union Next-GenerationEU (PIANO NAZIONALE DI RIPRESA E RESILI-ENZA (PNRR) - MISSIONE 4 COMPONENTE 2, INVESTIMENTO 1.4 - D.D. 1032 17/06/2022,//This research was carried out within the Agritech National Research Center and received funding from the European Union Next-GenerationEU (PIANO NAZIONALE DI RIPRESA E RESILI-ENZA (PNRR) - MISSIONE 4 COMPONENTE 2, INVESTIMENTO 1.4 - D.D. 1032 17/06/2022,/ ; },
abstract = {Plant Growth-Promoting Rhizobacteria (PGPR) are emerging as a sustainable alternative in agriculture due to their environmentally friendly properties and their ability to enhance crop productivity. Among these, Pantoea agglomerans has gained attention for its versatility as both a biofertilizer and a biocontrol agent. In this study, we use comparative genomics to gain insight into the genetic diversity and functional specialization of members of this species. The pan-genome analysis of 20 representative P. agglomerans strains revealed that 32% of the genes constitute the core genome (2856 out of 8899), while the remaining 68% are classified as accessory or singleton genes, indicating a high level of genomic diversity within the species. Functional annotation showed that core genes are predominantly involved in central metabolic processes, whereas genes associated with specialized metabolic functions are found within the accessory and singleton categories. The comparative analysis demonstrated a mosaic distribution of genes related to nitrogen and sulfur metabolism, heavy metal resistance, defense mechanisms, and oligopeptide uptake, suggesting niche-specific adaptations and metabolic capabilities within this species. Exometabolome profiling of strains associated with different hosts, specifically plant (C1) or human (DSM3493[T]), demonstrated that omics-centered approaches can be utilized to select P. agglomerans strains tailored to specific agronomic requirements.},
}

@article {pmid41009900,
year = {2025},
author = {Ngan, WY and Rao, S and Fung, AHY and Habimana, O},
title = {Genomic Profiling Reveals Clinically Relevant Antimicrobial Resistance and Virulence Genes in Klebsiella pneumoniae from Hong Kong Wet Markets.},
journal = {Antibiotics (Basel, Switzerland)},
volume = {14},
number = {9},
pages = {},
doi = {10.3390/antibiotics14090922},
pmid = {41009900},
issn = {2079-6382},
support = {104006142.095798.26000.301.01//The University of Hong Kong's University Research Committee Seed Fund for Basic Research/ ; GCII-Seed-202409//GTIIT-Changzhou Innovation Institute/ ; },
abstract = {Background:Klebsiella pneumoniae is a highly dangerous microorganism that presents significant challenges to effectively eliminate in food production facilities, making it a serious and urgent public health concern. The wet markets of Hong Kong represent a considerable yet insufficiently explored source for the spread of microorganisms. Methods: This investigation employed whole-genome sequencing and comparative genomics to assess the genomic variation and adaptive traits of K. pneumoniae extracted from wooden cutting boards in these marketplaces. We examined four wet market isolates in conjunction with 39 publicly accessible genomes from diverse origins. Results: Pan-genome analysis revealed a diverse and open genetic structure significantly shaped by horizontal gene transfer. Phylogenetic reconstruction did not categorize the wet market isolates into a singular clade, indicating varied contamination sources; nonetheless, certain market isolates exhibited close phylogenetic affiliations with high-risk clinical clones, implying possible spillover events. These isolates exhibited a concerning variety of antimicrobial resistance genes (ARGs), chiefly encoding efflux pumps (acrAB, oqxAB), which confer resistance to numerous drug categories. Moreover, the evaluation for pathogenicity attributes uncovered genes associated with robust biofilm development (fim and mrk operons) and efficient iron procurement strategies. Conclusions: The existence of these genetically adaptable isolates, possessing multidrug resistance and virulence factors, renders wet markets potential amplifiers and reservoirs for the spread of resistant pathogens. These findings present the initial genomic evidence of such risks in Hong Kong's wet markets and emphasize the immediate necessity for improved hygiene protocols and comprehensive One Health surveillance to reduce transmission at the human-animal-environment interface.},
}

@article {pmid41007343,
year = {2025},
author = {Decker, S and Craine, W and Paulitz, T and Chen, C and Lu, C},
title = {Genomic Analysis of the Natural Variation of Fatty Acid Composition in Seed Oils of Camelina sativa.},
journal = {Biology},
volume = {14},
number = {9},
pages = {},
doi = {10.3390/biology14091199},
pmid = {41007343},
issn = {2079-7737},
support = {DE_SC0021369//US DOE/ ; },
abstract = {Camelina sativa is an oilseed crop that has shown strong promise as a biofuel feedstock. The profile of fatty acids greatly influences the oil quality; however, genetic mechanisms that determine the natural variation of fatty acid composition in camelina are not fully understood. A genome wide association study (GWAS) was performed to uncover genetic loci that may contribute to the contents of major fatty acids such as oleic and linolenic acids in camelina seed. Two approaches were taken to improve the GWAS efficiency. First, growing a diversity panel of 212 accessions in four locations and two nitrogen fertilization conditions revealed great variation in fatty acid contents in seeds. Second, using an improved reference genome, abundant markers, including 203,320 single nucleotide polymorphisms (SNPs) and 99,067 insertions/deletions (indels), were developed, which refined the population structure of the diversity panel. GWAS resulted in 118 genetic markers across 31 trait/treatment conditions. Closely linked markers were determined based on linkage decay and by comparing secondarily associated markers when highly associated ones were removed. Candidate genes were examined by comparing the pangenomes of 12 high-quality reference genomes. This study provides new resources to understand seed lipid metabolism and improve camelina oils through molecular breeding.},
}

@article {pmid41003669,
year = {2025},
author = {Krishnan, KJ and Hefner, Y and Szubin, R and Monk, J and Pride, DT and Palsson, B},
title = {PMkbase (version 1.0): an interactive web-based tool for tracking bacterial metabolic traits using phenotype microarrays made interoperable with sequence information and visualizing/processing PM data.},
journal = {Microbiology spectrum},
volume = {},
number = {},
pages = {e0327924},
doi = {10.1128/spectrum.03279-24},
pmid = {41003669},
issn = {2165-0497},
abstract = {Bacteria showcase remarkable metabolic diversity and traits, even among strains of the same species. In recent years, a large number of bacterial genomes have been sequenced, leading to the elucidation and documentation of genomic differences and commonalities across and within species. Genome-scale metabolic reconstructions, which are often defined and curated using data from phenotype microarrays, elucidate the differences in metabolic traits resulting from genomic diversity. These microarrays measure cellular respiration on a variety of carbon, nitrogen, phosphorus, and sulfur sources and various stressors and inhibitors over a period of time to determine the metabolic activity of a given strain. Despite their popularity in measuring bacterial metabolic activity and traits, no public databases that allow researchers to warehouse, access, and analyze this information currently exist. Additionally, there are no publicly available tools that allow researchers to view the variance of these metabolic traits across bacterial strains. To address this need, we present Phenotype Microarray Knowledgebase (PMkbase [version 1.0], https://pmkbase.com/), an interactive database that acts as a repository of phenotype microarray (PM) data with integrated sequence information. Binarized activity calls, along with associated kinetic parameters, are made for all metabolic substrates and inhibitors. Users can upload their own data for analysis and visualization and to perform quality checks on their experiments. PMkbase will address an unmet need to track and view bacterial metabolic traits and provide researchers with valuable information to develop metabolic models, enrich pangenomic analyses, and design new experiments.IMPORTANCEBacterial species can be differentiated by their metabolic profiles or the type of nutrients they consume. Interestingly, strains within the same species also display differences in nutrient consumption. Phenotype microarrays are a high-throughput, widely used technology to measure which substrates can be metabolized by various microbial strains and the extent to which inhibitors can affect it. Despite their widespread use, public databases to parse and access this data type at scale do not exist. PMkbase, which contains 9,024 data points for nitrogen substrate utilization, 41,664 data points for carbon substrate utilization, 8,448 data points for phosphorus/sulfur substrate utilization, and 27,264 data points on various antibiotics across three species (Escherichia coli, Pseudomonas putida, and Staphylococcus aureus), has been developed to allow researchers to freely access PM data, along with enriching the data with sequence information.},
}

@article {pmid41000933,
year = {2025},
author = {Kumar, L and Whang, SN and Potter, RF and Gilbert, NM},
title = {Strain-level differences in Gardnerella urinary tract persistence and pathogenesis are consistent with comparative phylogenomic analyses.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.1101/2025.09.19.677092},
pmid = {41000933},
issn = {2692-8205},
abstract = {BACKGROUND: Gardnerella is a genus of gram variable anaerobic bacteria that is commonly present in the female urogenital tract, especially during bacterial vaginosis (BV). BV is linked with increased risk of urinary tract infections (UTI) and Gardnerella has been frequently detected in urine collected directly from the bladder. Understanding the contribution of Gardnerella to urogenital pathogenesis has been complicated by its genetic heterogeneity and a shortage of data from in vivo models. Recently, a clinical isolate of Gardnerella displayed covert pathogenesis in a mouse urinary tract inoculation model, triggering urothelial exfoliation and promoting UTI by uropathogenic E. coli . Data from clinical studies suggests differential association of Gardnerella phylogenetic clades with BV or urogenital infections. In vitro data has demonstrated heterogeneity in the presence and expression of putative virulence determinants between Gardnerella strains. This study was designed to compare diverse Gardnerella strains in vivo to identify genomic variation associated with urinary tract persistence and pathogenesis.

METHODS: Eighteen Gardnerella clinical isolates from each of the four main phylogenetic clades were individually inoculated transurethrally into female C57BL/6 mice. Bacteriuria was monitored by quantitative culturing of Gardnerella in urine. Pathologic features were assessed by immunofluorescent and histological staining of bladder tissues. Pan-genome phylogenetic analyses were performed on the 18 Gardnerella isolates used for mouse infections to identify accessory genes that were associated with observable in vivo phenotypes, including long and short-term persistence, urothelial exfoliation and bladder edema. Genes that were significantly associated to phenotype were then matched against a pangenome analysis of 291 publicly available Gardnerella genomes to determine the conservation of these putative colonization and virulence factors across the genus.

RESULTS: Gardnerella strains displayed clear differences in persistence and pathogenesis in the mouse bladder that were congruent with phylogeny. Clade 2 strains were more persistent in the urinary tract whereas strains from the other three clades either caused transient bacteriuria or were undetectable. Strains from clade 2 and 4 induced urothelial exfoliation while edema was triggered by strains from clades 2, 3 and 4. Pangenome analyses revealed 45 genes that were associated with in vivo persistence and pathogenicity. Among the wider 291 publicly available genomes, clade 2 strains encoded more of the genes associated with bacteriuria phenotypes compared to strains in the other three clades. Exfoliation-associated genes were present in most clade 4 strains. Clade 3 strains lack most of the in vivo -associated genes, whereas clade 1 strains were more heterogenous.

CONCLUSIONS: This study provides in vivo evidence for differential urinary tract colonization and pathogenesis by strains from different clades/species within the genus Gardnerella and identifies new putative persistence and virulence factors. Utilizing the in vivo data from tested strains, pangenome analyses predicts that clade 2 Gardnerella are the most likely to persist in the urinary tract and that clades 2 and 4 have the highest uropathogenic potential. These findings inform future targeted screening and treatment approaches aimed at limiting harmful Gardnerella urinary tract exposures.},
}

@article {pmid40996989,
year = {2025},
author = {Zhang, X and Yang, M and Yin, X and Qian, Y and Sun, F},
title = {DeepGene: An Efficient Foundation Model for Genomics based on Pan-genome Graph Transformer.},
journal = {IEEE transactions on computational biology and bioinformatics},
volume = {PP},
number = {},
pages = {},
doi = {10.1109/TCBBIO.2025.3614354},
pmid = {40996989},
issn = {2998-4165},
abstract = {Decoding the language of DNA sequences is a fundamental problem in genome research. Mainstream pre-trained models like DNABERT-2 and Nucleotide Transformer have demonstrated remarkable achievements across a spectrum of DNA analysis tasks. Yet, these models still face the pivotal challenge of (1) genetic language diversity, or the capability to capture genetic variations across individuals or populations in the foundation models; (2) model efficiency, specifically how to enhance performance at scalable costs for large-scale genetic foundational models; (3) length extrapolation, or the ability to accurately interpret sequences ranging from short to long within a unified model framework. In response, we introduce DeepGene, a model leveraging Pan-genome and Minigraph representations to encompass the broad diversity of genetic language. DeepGene employs the rotary position embedding to improve the length extrapolation in various genetic analysis tasks. On the 28 tasks in Genome Understanding Evaluation, DeepGene achieves the overall best score. DeepGene outperforms other cutting-edge models for its compact model size and superior efficiency in processing sequences of varying lengths. The datasets and source code of DeepGene are available at GitHub (https://github.com/wds-seu/DeepGene).},
}

@article {pmid40996036,
year = {2025},
author = {Herman, R and Meaden, S and Rudden, M and Cornmell, R and Wilkinson, HN and Hardman, MJ and Wilkinson, AJ and Murphy, B and Thomas, GH},
title = {Revealing the diversity of commensal corynebacteria from a single human skin site.},
journal = {mSystems},
volume = {},
number = {},
pages = {e0045925},
doi = {10.1128/msystems.00459-25},
pmid = {40996036},
issn = {2379-5077},
abstract = {UNLABELLED: Our understanding of the skin microbiome has significantly advanced with the rise of sequencing technologies. While Corynebacterium species are a major component of the human skin microbiome, research has largely centered on other prevalent genera like Staphylococcus and Cutibacterium. Prior to this study, complete genomes for skin-associated Corynebacterium were limited. For instance, only nine were available for the commonly identified species Corynebacterium tuberculostearicum. In this study, we explored Corynebacterium diversity from a single skin site, the axilla, using selective media to enrich for these bacteria. Long-read whole-genome sequencing and bioinformatic analysis of the enriched isolates provided unprecedented insight into the diversity of this genus at a single body site. The study yielded 215 closed genomes, comprising 30 distinct representative genomes following dereplication. These genomes span seven distinct species, including two new species provisionally named Corynebacterium axilliensis and Corynebacterium jamesii, as well as species not previously linked to the skin. Pangenome analysis of these isolates uncovered potential metabolic differences, antimicrobial resistance genes, novel biosynthetic gene clusters, prophages, and phage defense systems. This study represents the most detailed analysis to date of Corynebacterium from a single skin niche and highlights extensive variation even within a single host. Our culture-based Nanopore sequencing approach has expanded the number of publicly available skin Corynebacterium genomes, providing a valuable resource for future studies investigating the diversity and function of this important skin genus.

IMPORTANCE: This study uncovers the hidden diversity of Corynebacterium, an important yet often overlooked group of bacteria inhabiting human skin. Focusing on the underarm and using advanced sequencing techniques, we identified over 200 complete bacterial genomes. This collection includes species not previously known to reside on the skin, as well as two entirely new species, highlighting how little is currently known about this cutaneous genus. Most of these bacteria were isolated from a single individual, underscoring the vast microbial diversity that can exist within one person. By closely examining the corynebacterial community at a single site, we begin to uncover the complex relationships within a true microbial ecosystem. These findings deepen our understanding of the skin microbiome and provide a valuable resource for future research into how these microbes affect skin health, hygiene, and disease.},
}

@article {pmid40989616,
year = {2025},
author = {Lee, GY and Cho, HY and Sayem, SAJ and Kim, SJ and Ali, MS and Park, SC},
title = {Complete genome sequence and genomic characterization of the probiotic Limosilactobacillus reuteri PSC102.},
journal = {Open veterinary journal},
volume = {15},
number = {6},
pages = {2427-2438},
pmid = {40989616},
issn = {2218-6050},
mesh = {*Limosilactobacillus reuteri/genetics ; *Probiotics ; *Genome, Bacterial ; Whole Genome Sequencing/veterinary ; Animals ; Swine ; },
abstract = {BACKGROUND: Gut microbiota are potential sources of probiotics and play an essential role in maintaining intestinal health. Limosilactobacillus reuteri PSC102 (L. reuteri PSC102), which was isolated from the feces of healthy pigs, exhibited health-beneficial properties.

AIM: We aimed to conduct a whole-genome sequencing analysis of L. reuteri PSC102 to determine its molecular characteristics as a probiotic strain.

METHODS: Limosilactobacillus reuteri PSC102 cells were cultured in De Man-Rogosa-Sharpe medium, followed by DNA extraction for genomic analysis using the PacBio-Illumina sequencing platform. The EzBioCloud software was used to perform gene assembly, and the genes were interpreted by the National Center for Biotechnology Information (NCBI) and the Glimmer program. Core and pan-genomic analyses were performed to assess the extent of functional conservation in the genomic sequence. Moreover, the NCBI database and the Basic Local Alignment Search Tool software were used to identify antimicrobial resistance genes and virulence factors.

RESULTS: Limosilactobacillus reuteri PSC102 consists of a single circular chromosome with 2,048,626 bp, a guanine- cytosine of 38.9%, 18 rRNA genes, and 69 tRNA genes. Among the 1,846 protein-coding sequences, genes associated with probiotic characteristics were identified, including genes involved in host-microbe interactions, stress tolerance, biogenesis, and defense mechanisms. Furthermore, the genome of L. reuteri PSC102 comprises 2,446 pan-genome and 1,222 core-genome orthologous gene clusters. A total of 74 unique genes were identified in L. reuteri PSC102 genome. These genes mostly encode proteins potentially involved in the transport and metabolism of amino acids and carbohydrates. Moreover, antibacterial resistance genes and virulence factors were absent in L. reuteri PSC102.

CONCLUSION: The results of the molecular insight into L. reuteri PSC102 corroborates its use as a probiotic in humans and other animals.},
}

*Limosilactobacillus reuteri/genetics
*Probiotics
*Genome, Bacterial
Whole Genome Sequencing/veterinary
Animals
Swine

@article {pmid40987990,
year = {2025},
author = {Basu, U and Parida, SK},
title = {Next-generation translational genomics for developing future crops.},
journal = {Functional & integrative genomics},
volume = {25},
number = {1},
pages = {196},
pmid = {40987990},
issn = {1438-7948},
support = {OLP2503A//CSIR-North East Institute of Science and Technology/ ; },
mesh = {*Crops, Agricultural/genetics/growth & development ; *Genomics/methods ; *Plant Breeding/methods ; *Genome, Plant ; },
abstract = {Advancements in translational genomics have revolutionized crop breeding, driving us from traditional breeding methods towards next-generation strategies that integrate genomic, transcriptomic, and phenotypic data to expedite crop improvement. There has been a shift from single genomes to pan-genomes, which better capture intraspecific diversity, and from bulk transcriptome analyses to single-cell transcriptomics, enabling cell-specific insights into gene regulation and functional genomics. Both high throughput genopyting and phenotyping approaches are now possible due to rapid technological advancement in the field of translational genomics. Large-scale phenotyping data from multi-environment field trials is now possible due to AI-enabled digital and drone-based scanning. In the era of artificial intelligence and machine learning we have developed flexible models to handle complex genetic architecture of trait regulation using various tools and approaches. These genetic and genomic resources are the foundation for generating novel, adaptable, and high-yielding varieties, accelerating trait discovery and mapping. This review explores the comprehensive landscape of modern translational genomics, highlighting key shifts and innovations that enhance our capacity to address agricultural challenges. Integrative pipelines that unify these next-generation approaches could facilitate faster, more precise, and sustainable crop improvement, ultimately meeting the growing demands for future-ready crops.},
}

*Crops, Agricultural/genetics/growth & development
*Genomics/methods
*Plant Breeding/methods
*Genome, Plant

@article {pmid40986107,
year = {2025},
author = {Nguyen, CTK and Lam, PGH and Dang, NTT and Le, SN and Pham, TV and Vo, N and Dinh, HT and Nguyen, OVK and Nguyen, HD},
title = {Phenotypic, secondary metabolite, and genomic characterization of Bacillus siamensis B03 from brackish water with Anti‑Vibrio potential.},
journal = {Archives of microbiology},
volume = {207},
number = {11},
pages = {277},
pmid = {40986107},
issn = {1432-072X},
mesh = {*Bacillus/genetics/metabolism/isolation & purification/classification ; *Vibrio/drug effects ; *Anti-Bacterial Agents/pharmacology/metabolism ; Genome, Bacterial ; Secondary Metabolism ; Vietnam ; Bacterial Proteins/genetics/metabolism ; Genomics ; Phenotype ; Phylogeny ; Multigene Family ; Microbial Sensitivity Tests ; },
abstract = {This study aimed to provide the first genomic, functional, and metabolic characterization of Bacillus siamensis B03 from Lang Co Bay, Vietnam, and to evaluate the hypothesis that it harbors unique metabolic traits and antimicrobial potential against Vibrio spp.. B03 showed no hemolytic activity, moderate biofilm formation, tolerance to 10% NaCl, and broad extracellular enzyme secretion. Ethyl acetate extracts from the cell-free supernatant exhibited in vitro antibacterial activity against five Vibrio species, with inhibition zones of 14.7-22.3 mm. Metabolomic analysis tentatively identified 20 compounds, mainly cyclic dipeptides, some previously reported to possess antimicrobial properties. Draft, plasmid-free genome (3,745,205 bp; 46.4% GC) encodes 3,561 proteins and 72 tRNAs, with genes mainly for amino acid and carbohydrate metabolism, and contains gene clusters for bacillaene, fengycin, difficidin, bacillibactin (100% similarity), and surfactin (78%). Pan-genome analysis of 24 B. siamensis genomes revealed 2,254 core genes, with B03 contributing 31 unique genes, including those encoding NAD-dependent malic enzyme and adenylation domain proteins. These findings suggest B. siamensis B03 as a potential control agent against Vibrio pathogens.},
}

*Bacillus/genetics/metabolism/isolation & purification/classification
*Vibrio/drug effects
*Anti-Bacterial Agents/pharmacology/metabolism
Genome, Bacterial
Secondary Metabolism
Vietnam
Bacterial Proteins/genetics/metabolism
Genomics
Phenotype
Phylogeny
Multigene Family
Microbial Sensitivity Tests

@article {pmid40985593,
year = {2025},
author = {Recuerda, M and Kraemer, S and Rosoni, JRR and Repenning, M and Browne, M and Cataudela, JF and Di Giacomo, AS and Kopuchian, C and Campagna, L},
title = {A pangenomic approach reveals the sources of genetic variation fueling the rapid radiation of Capuchino Seedeaters.},
journal = {Evolution; international journal of organic evolution},
volume = {},
number = {},
pages = {},
doi = {10.1093/evolut/qpaf188},
pmid = {40985593},
issn = {1558-5646},
abstract = {The search for the genetic basis of phenotypes has primarily focused on single nucleotide polymorphisms, often overlooking structural variants (SVs). SVs can significantly affect gene function, but detecting and characterizing them is challenging, even with long-read sequencing. Moreover, traditional single-reference methods can fail to capture many genetic variants. Using long-reads, we generated a Capuchino Seedeater (Sporophila) pangenome, including 16 individuals from seven species, to investigate how SVs contribute to species and coloration differences. Leveraging this pangenome, we mapped short-read data from 127 individuals, genotyped variants identified in the pangenome graph and subsequently perform FST scans and genome-wide association studies. Species divergence primarily arises from SNPs and indels (< 50 bp) in non-coding regions of melanin-related genes, as larger SVs rarely overlap with divergence peaks. One exception was a 55 bp deletion near the OCA2 and HERC2 genes, associated with feather pheomelanin content. These findings support the hypothesis that the reshuffling of small regulatory alleles, rather than larger species-specific mutations, accelerated plumage evolution leading to prezygotic isolation in Capuchinos.},
}

@article {pmid40985147,
year = {2025},
author = {Eladawy, M and Heslop, N and Negus, D and Thomas, JC and Hoyles, L},
title = {Phenotype-genotype discordance in antimicrobial resistance profiles of Gram-negative uropathogens recovered from catheter-associated urinary tract infections in Egypt.},
journal = {The Journal of antimicrobial chemotherapy},
volume = {},
number = {},
pages = {},
doi = {10.1093/jac/dkaf352},
pmid = {40985147},
issn = {1460-2091},
support = {//Egyptian Ministry of Higher Education & Scientific Research/ ; //Egyptian Bureau for Cultural & Educational Affairs/ ; //Nottingham Trent University/ ; },
abstract = {OBJECTIVES: Catheter-associated urinary tract infections (CAUTIs) are among the most common healthcare-associated infections in low- and middle-income countries (LMICs), but there are few resistome data available for relevant uropathogens. The goal of this study was to characterize the antimicrobial resistance (AMR) phenotypes and genotypes of a large collection of Gram-negative bacteria recovered from CAUTIs in a hospital in Mansoura, Egypt.

METHODS: Phenotypic AMR profiles and whole-genome sequence data were generated for 132 isolates. Resistomes were predicted using ResFinder, CARD and AMRFinder. Similarity of uropathogen genomic data was determined using sourmash (kmer signatures). Escherichia coli genomic data were subject to a pangenome analysis using Panaroo.

RESULTS: Sixty-seven E. coli (Phylogroup B2; 53.7%, 36/67), 14 Pseudomonas aeruginosa, 11 Klebsiella pneumoniae, 9 Proteus mirabilis, 8 Providencia spp., 5 Enterobacter hormaechei and 18 rare CAUTI-associated isolates were identified. Several (22/132) isolates were multidrug-resistant, while almost half (62/132) were extensively drug-resistant. Phenotype-genotype discordance was found to be an important consideration in resistome studies in Egypt, with a total concordance of 91% (1115/1225), 85.7% (1273/1485) and 80.5% (1196/1485) for ResFinder, CARD and AMRFinder, respectively. Pseudomonas, at the species level, exhibited the greatest discordance. At the antimicrobial level, meropenem was subject to greatest discordance. New AMR variants were found for Egypt for Pseudomonas (blaOXA-486, blaOXA-488, blaOXA-905, blaIMP-43, blaPDC-35, blaPDC-45, blaPDC-201) and E. coli (blaTEM-176, blaTEM-190).

CONCLUSIONS: This study shows that there is phenotype-genotype discordance in AMR profiling among CAUTI isolates, highlighting the need for comprehensive approaches in resistome studies. We also show the genomic diversity of Gram-negative uropathogens contributing to disease burden in a little-studied LMIC setting.},
}

@article {pmid40983756,
year = {2025},
author = {Dong, S and Wang, S and Li, L and Yu, J and Zhang, Y and Xue, JY and Chen, H and Ma, J and Zeng, Y and Cai, Y and Huang, W and Zhou, X and Wu, J and Li, J and Yao, Y and Hu, R and Zhao, T and Villarreal A, JC and Dirick, L and Liu, L and Ignatov, M and Jin, M and Ruan, J and He, Y and Wang, H and Xu, B and Rozzi, R and Wegrzyn, J and Stevenson, DW and Renzaglia, KS and Chen, H and Zhang, L and Zhang, S and Mackenzie, R and Moreno, JE and Melkonian, M and Wei, T and Gu, Y and Xu, X and Rensing, SA and Huang, J and Long, M and Goffinet, B and Bowman, JL and Van de Peer, Y and Liu, H and Liu, Y},
title = {Bryophytes hold a larger gene family space than vascular plants.},
journal = {Nature genetics},
volume = {},
number = {},
pages = {},
pmid = {40983756},
issn = {1546-1718},
abstract = {After 500 million years of evolution, extant land plants compose the following two sister groups: the bryophytes and the vascular plants. Despite their small size and simple structure, bryophytes thrive in a wide variety of habitats, including extreme conditions. However, the genetic basis for their ecological adaptability and long-term survival is not well understood. A comprehensive super-pangenome analysis, incorporating 123 newly sequenced bryophyte genomes, reveals that bryophytes possess a substantially greater diversity of gene families than vascular plants. This includes a higher number of unique and lineage-specific gene families, originating from extensive new gene formation and continuous horizontal transfer of microbial genes over their long evolutionary history. The evolution of bryophytes' rich and diverse genetic toolkit, which includes new physiological innovations like unique immune receptors, likely facilitated their spread across different biomes. These newly sequenced bryophyte genomes offer a valuable resource for exploring alternative evolutionary strategies for terrestrial success.},
}

@article {pmid40981977,
year = {2025},
author = {Suresh, R and Jayachandiran, S and Balu, P and Ranganadin, P and Dhamodharan, R},
title = {Comparative genome analysis of human pathogen Parvimonas micra revealed strain JM503A as potential novel species in the genus Parvimonas and high intra-species functional diversity.},
journal = {Microbial genomics},
volume = {11},
number = {9},
pages = {},
doi = {10.1099/mgen.0.001511},
pmid = {40981977},
issn = {2057-5858},
mesh = {Phylogeny ; Humans ; *Genome, Bacterial ; *Firmicutes/genetics/classification ; RNA, Ribosomal, 16S/genetics ; Virulence Factors/genetics ; Gram-Positive Bacterial Infections/microbiology ; },
abstract = {Parvimonas micra is a Gram-positive, anaerobic bacterium commonly found in the oral cavity, skin and gastrointestinal tract. While typically a harmless organism, it can cause infections in individuals with weakened immune systems, leading to conditions like periodontitis and deep-tissue abscesses. This study focuses on the comparative genomic analysis of P. micra to explore its evolutionary relationships, antimicrobial resistance profiles and functional diversity by assessing phylogenetic analyses, resistance genes, virulence factors, mobile genetic elements, carbohydrate-active enzymes and pan-genome analysis. Comparative genomic analysis of 11 P. micra strains reveals significant functional variations among the strains, indicating notable interspecies diversity. Phylogenetic and comparative genome analysis revealed that strain JM503A is taxonomically distinct from the P. micra species, with genome similarity ranging from 54% to 61%. The 16S rRNA sequence similarity of strain JM503A is 98.28%, indicating a distinct phylogenetic position. The average nucleotide identity value ranging from 91.32% to 91.7% and digital DNA-DNA hybridization values ranging from 43.00% to 44.00% of JM503A with other strains are below the cutoff values <95% and <70%, respectively, which confirms JM503A as a novel species. Based on its evolutionary relationships, strain JM503A is identified as a potential new species of Parvimonas, providing important evidence for its reclassification as a new species within the genus Parvimonas.},
}

Phylogeny
Humans
*Genome, Bacterial
*Firmicutes/genetics/classification
RNA, Ribosomal, 16S/genetics
Virulence Factors/genetics
Gram-Positive Bacterial Infections/microbiology

@article {pmid40981419,
year = {2025},
author = {Fouts, DE and Clarke, TH and Severin, GB and Brown, AN and Ottosen, EN and Holmes, CL and Moricz, BS and Mason, S and Sinha, R and Anderson, MT and DiRita, V and Bachman, MA and Mobley, HLT},
title = {Integrating genomic and Tn-Seq data to identify common in vivo fitness mechanisms across multiple bacterial species.},
journal = {mBio},
volume = {},
number = {},
pages = {e0198825},
doi = {10.1128/mbio.01988-25},
pmid = {40981419},
issn = {2150-7511},
abstract = {UNLABELLED: Sepsis, a life-threatening organ dysfunction, is due to an unregulated immune response to infection. Bacteremia is a leading cause of sepsis, and members of the Enterobacterales cause nearly half of bacteremia cases annually. Although previous Tn-Seq studies identified novel bacteremia-fitness genes, evidence for common pathways across species is lacking. To identify common fitness pathways in five bacteremia-causing Enterobacterales species, we utilized our pan-genome pipeline to integrate Tn-Seq fitness data with multiple available functional data types. Core genes from species pan-genomes were used to construct a multi-species core pan-genome, producing 2,850 core gene clusters found in four of five species. Integration of Tn-Seq fitness data identified 373 protein clusters conserved in all five species and a fitness gene in at least one of them. A scoring rubric was applied to these clusters, which incorporated Tn-Seq fitness defects, operon localization, and antibiotic susceptibility data, which reduced the number of bacteremia-fitness genes and identified seven common fitness mechanisms. Independent mutational validation of one prioritized fitness gene, tatC, showed reduced fitness in vivo across all species tested and increased susceptibility to β-lactams that was restored following tatC complementation in trans. By integrating known operon structures and antibiotic susceptibility with Tn-Seq fitness data, common genes within the core pan-genome emerged and revealed mechanisms essential for survival in the mammalian bloodstream. Our prediction and validation of tatC as a common bacteremia fitness factor supports the utility of this bioinformatic approach. This study represents a major step forward in prioritizing novel targets for therapy against sepsis infections.

IMPORTANCE: Bacteremia is a leading cause of sepsis, a life-threatening condition where an unregulated immune response to infection causes systemic organ failure. Nearly half of bacteremia cases are caused by members of the Gram-negative bacterial taxonomic order Enterobacterales. Given the public health impact of bacteremia and the reduction of existing antibiotic treatment options, novel strategies are needed to combat these infections. In this study, pan-genome software was used to predict seven shared fitness pathways in these bacteria that may serve as novel targets for the treatment of bacteremia. Briefly, a scoring rubric was applied to shared pan-genome clusters, which incorporated multiple data types, including Tn-Seq fitness defects, operon localization, and antibiotic susceptibility data to rank and prioritize fitness genes. To validate one of our predictions, mutations were constructed in tatC, which showed both reduced fitness in mice in all species tested and increased susceptibility to β-lactam antibiotics; complementation restored fitness and antibiotic susceptibility to wild-type levels. This study takes a novel bioinformatics approach to build a core pan-genome across multiple distantly related bacteria to integrate computational and experimental data to predict important shared fitness genes and represents a major step forward toward identifying novel targets of therapy against these deadly, widespread, life-threatening infections.},
}

@article {pmid40980711,
year = {2025},
author = {Roberts, MD and Josephs, EB},
title = {k-mer-based diversity scales with population size proxies more than nucleotide diversity in a meta-analysis of 98 plant species.},
journal = {Evolution letters},
volume = {9},
number = {4},
pages = {434-445},
pmid = {40980711},
issn = {2056-3744},
abstract = {A key prediction of neutral theory is that the level of genetic diversity in a population should scale with population size. However, as was noted by Richard Lewontin in 1974 and reaffirmed by later studies, the slope of the population size-diversity relationship in nature is much weaker than expected under neutral theory. We hypothesize that one contributor to this paradox is that current methods relying on single nucleotide polymorphisms (SNPs) called from aligning short reads to a reference genome underestimate levels of genetic diversity in many species. As a first step to testing this idea, we calculated nucleotide diversity (π) and k -mer-based metrics of genetic diversity across 112 plant species, amounting to over 205 terabases of DNA sequencing data from 27,488 individuals. After excluding 14 species with low coverage or no variant sites called, we compared how different diversity metrics correlated with proxies of population size that account for both range size and population density variation across species. We found that our population size proxies scaled anywhere from about 3 to over 20 times faster with k -mer diversity than nucleotide diversity after adjusting for evolutionary history, mating system, life cycle habit, cultivation status, and invasiveness. The relationship between k -mer diversity and population size proxies also remains significant after correcting for genome size, whereas the analogous relationship for nucleotide diversity does not. These results are consistent with the possibility that variation not captured by common SNP-based analyses explains part of Lewontin's paradox in plants, but larger scale pangenomic studies are needed to definitively address this question.},
}

@article {pmid40976223,
year = {2025},
author = {Lu, HB and Kong, LY and Chen, L and Chen, GJ and Wang, JJ},
title = {Isolation of diverse Undibacterium-related strains from alpine lakes and re-examining the taxonomic status of this genus.},
journal = {Systematic and applied microbiology},
volume = {48},
number = {6},
pages = {126661},
doi = {10.1016/j.syapm.2025.126661},
pmid = {40976223},
issn = {1618-0984},
abstract = {The genus Undibacterium is an important member of Oxalobacteraceae and most species of this genus were isolated from freshwater environments. The recent study based on the genomic analyses revised the taxonomic status of 23 Undibacterium species and proposed that these species should be assigned into four genera (Undibacterium, Neoundibacterium, Affinundibacterium and Paraundibacterium), respectively. During the investigation of microbial resources inhabited in alpine lakes from the southwestern China in 2023, 25 strains show the highest 16S rRNA gene sequence similarities with Undibacterium species were isolated. Utilizing the genomes of these 25 strains and 26 Undibacterium species, the phylogenies among these strains are reconstructed based on the core and pan-genome, respectively. The phylogenomic trees show that the 26 Undibacterium species should be divided into six clades and each clade should represent an independent genus. As the clades 2, 3, 4 and 5 proposed in this study have been revised in other study, the genera Cognatundibacterium and Pseudundibacterium are proposed in this study to accommodate the clades 1 and 6, respectively. The detailed genomic annotations reveal that all the 25 isolated Undibacterium-related strains harbor complete amino acids metabolisms and genes encoding DNA replication and repair, homologous recombination proteins, two-component and phosphate transport systems in response to the oligotrophic, high UV radiation and phosphorus-limited environments of alpine lakes. This study clarifies the role of Undibacterium-related strains in alpine lakes and demonstrates that isolating more strains is of great benefit to the bacterial taxonomy.},
}

@article {pmid40970632,
year = {2025},
author = {Wang, C and Wang, T and Zhang, T and Song, H and Shan, D and Bai, Y and Hu, Z and Li, J and Man, J and Xiao, P and Dai, C and Liu, X and Shen, F and Kong, J and Hu, J and Zheng, X},
title = {Domestication-Selected Promoter Insertion in WRKY17 Increases Cadmium Sensitivity in Apple.},
journal = {Plant biotechnology journal},
volume = {},
number = {},
pages = {},
doi = {10.1111/pbi.70376},
pmid = {40970632},
issn = {1467-7652},
support = {32172540//National Natural Science Fund/ ; 32372674//National Natural Science Fund/ ; SYND-2021-08//Sanya Yazhou Bay Science and Technology City/ ; CEFF-PXM2019_014207_000032//The Construction of Beijing Science and Technology Innovation and Service Capacity in Top Subjects/ ; SDAIT-06-06//Funds for Modern Agricultural Industry Technology System in Shandong Province, China/ ; //Taishan Scholar Foundation of the People's Government of Shandong Province/ ; B17043//The 2115 Talent Development Program of China Agricultural University and 111 Project/ ; 2022YFF1003100//National Key Research and Development Program of China/ ; ZDYF2021XDNY161//Hainan Province Science and Technology Special Fund/ ; },
abstract = {With increasing industrialisation and human activities, heavy metal pollution has become a serious environmental concern, particularly cadmium (Cd) contamination. This study reveals significant differences in Cd tolerance between wild apple (Malus spp.) and cultivated apple (Malus domestica). Through pan-genome analysis, we identified the transcription factor WRKY17 as a key regulator of Cd stress response, with a 3355-bp insertion (P-INS) in its promoter region being the primary genetic basis for this differential tolerance. In cultivated apples, P-INS suppresses WRKY17 expression, leading to reduced Cd tolerance. In contrast, wild apples lacking P-INS exhibit activated WRKY17 expression. Further investigation demonstrated that WRKY17 enhances Cd tolerance by inducing the expression of long non-coding RNA lncRNA400. Mechanistically, lncRNA400 forms an R-loop structure that recruits the histone demethylase JMJD5 to remove H3K27me3 marks from the promoter of the Plant Cadmium Resistance gene PCR2, thereby activating PCR2 expression. Notably, WRKY17 activation also accelerates leaf senescence, explaining why P-INS was retained during apple domestication-its suppression of WRKY17 maintains better agronomic traits despite reduced Cd tolerance. In apple cultivation, grafting wild apple rootstocks with cultivated scions effectively combines the Cd-tolerant traits of wild varieties with the delayed leaf senescence characteristics of cultivated cultivars, providing a practical solution for the apple industry to address Cd contamination.},
}

@article {pmid40964672,
year = {2025},
author = {Sun, X and Xu, P and Shi, Y and Wang, N and Li, Y},
title = {Drug selection based on pan-genomics genetic features of Mycobacterium tuberculosis.},
journal = {Frontiers in microbiology},
volume = {16},
number = {},
pages = {1663069},
pmid = {40964672},
issn = {1664-302X},
abstract = {Tuberculosis, caused by Mycobacterium tuberculosis, is a severe and persistent global public health issue, particularly exacerbated by the emergence of multidrug-resistant and extensively drug-resistant strains. This study employed pan-genomic approaches to analyze different strains with various resistance profiles, examining the diversity of bacterial genetic evolution in relation to mutations in resistance-related genes. The findings indicate that resistance-related genes are mostly core genes (94%), with a preference for base mutations closely associated with nonsynonymous mutations at resistance sites. Interestingly, while the majority of drugs induce positive selection in target genes, the tlyA gene under the influence of amikacin (AMI) undergoes passive selection. Cluster analysis of target genes suggests consistency between SNP clusters and drug-resistant clusters, revealing a strong correlation between bacterial evolutionary branches and resistance profiles. Consequently, based on pan-genome evolutionary characteristics, we identified the drug-resistant mutation pattern (DRMP) that can serve as a molecular fingerprint and indicator for drug sensitivity, aiding in the assessment and guidance of drug selection for treating different strains and the formulation of individualized treatment plans. This research not only enhances our understanding of the mechanisms of drug resistance in M. tuberculosis but also offers new perspectives for the development of new drugs, which is crucial for global tuberculosis control.},
}

@article {pmid40960612,
year = {2025},
author = {Nguyen, CTK and Nguyen, HD},
title = {Genomic and Functional Characterization of Bacillus siamensis B01 with Antimicrobial Activity Against Vibrio spp.},
journal = {Current microbiology},
volume = {82},
number = {11},
pages = {509},
pmid = {40960612},
issn = {1432-0991},
support = {VINIF. 2023.TS.2017//Quỹ Đổi mới sáng tạo Vingroup/ ; },
mesh = {*Bacillus/genetics/isolation & purification/classification/metabolism/physiology ; *Vibrio/drug effects/growth & development ; *Genome, Bacterial ; *Anti-Bacterial Agents/pharmacology/metabolism ; Base Composition ; Phylogeny ; Genomics ; Vietnam ; Microbial Sensitivity Tests ; },
abstract = {This study reports the first investigation of the biological, genomic, and anti-Vibrio properties of Bacillus siamensis B01 (= VTCC 910229) isolated from a mangrove forest in Vietnam. Comparative genomic analysis revealed a significant similarity between the genomes of strain B01 and B. siamensis KCTC 13613[T], as indicated by average nucleotide identity and digital DNA-DNA hybridization values of 98.8% and 97.5%, respectively. The draft genome comprised 3,823,156 bp, showed a GC composition of 46.2%, and encompassed 112 tRNAs and 3,738 coding sequences (CDSs), with key functional groups related to biological processes, amino acid transport, and metabolism. Within the genome, an 80,406 bp plasmid with a GC content of 38.5% was identified, carrying 105 CDSs, one tRNA, and seven mobile genetic elements without virulence and antibiotic resistance genes. Gene clusters for antibacterial compounds, including bacillaene, fengycin, difficidin, and bacillibactin, showed 100% similarity to known biosynthetic pathways. Pan-genome analysis revealed that strain B01 shares 2,433 core genes with 23 other B. siamensis genomes, whereas this isolate possesses 160 unique genes, accounting for 4.28% of its genome. The isolate grew optimally in neutral environments, tolerated alkaline pH and 10% NaCl, formed biofilms, showed no hemolysis, and secreted proteases, lipases, cellulases, and amylases. The ethyl acetate extract demonstrated antibacterial activity against Vibrio azureus, Vibrio sinaloensis, Vibrio neocaledonicus, Vibrio alginolyticus, and Vibrio parahaemolyticus with inhibition zones measuring 15.7-24.3 mm in diameter. These results underscore the promise of this Bacillus strain as a probiotic against pathogenic Vibrio in aquaculture.},
}

*Bacillus/genetics/isolation & purification/classification/metabolism/physiology
*Vibrio/drug effects/growth & development
*Genome, Bacterial
*Anti-Bacterial Agents/pharmacology/metabolism
Base Composition
Phylogeny
Genomics
Vietnam
Microbial Sensitivity Tests

@article {pmid40959552,
year = {2025},
author = {Wang, T and Zheng, Y and Sun, L and Guan, M and Hu, Y and Yu, H and Wu, D and Du, J},
title = {Analysis of maize PAL pan gene family and expression pattern under lepidopteran insect stress.},
journal = {Frontiers in plant science},
volume = {16},
number = {},
pages = {1651563},
pmid = {40959552},
issn = {1664-462X},
abstract = {INTRODUCTION: Phenylalanine ammonia-lyase (PAL), as the rate-limiting enzyme in plant phenylpropanoid metabolism, catalyzes the conversion of L-phenylalanine to trans-cinnamic acid and plays a pivotal role in plant-insect resistance mechanisms.

METHODS: Utilizing a maize pangenome constructed from 26 high-quality genomes, we systematically identified the ZmPAL gene family members. Evolutionary pressure and structural variation (SV) analyses were conducted, alongside reanalysis of publicly available RNA-seq datasets under lepidopteran stress conditions. Temporal expression patterns were further validated via qRT-PCR.

RESULTS: This investigation identified 29 ZmPAL genes, comprising 7 core, 2 near-core, 12 dispensable, and 8 private genes, revealing substantial limitations of single-reference genome-based studies. Evolutionary analysis indicated positive selection of ZmPAL8 in specific germplasms, while SV-affected ZmPAL5 exhibited significantly divergent expression patterns. Conserved expression profiles were observed among ZmPAL members under diverse lepidopteran stresses. Temporal-specific regulation was established: ZmPAL7, ZmPAL10, and ZmPAL23 dominated early defense responses, whereas ZmPAL10 and ZmPAL23 maintained predominance during mid-late phases.

DISCUSSION: This pangenome-based study provides novel insights into PAL-mediated phytoprotective mechanisms against lepidopteran pests and establishes a theoretical framework for understanding maize's molecular adaptation to biotic stressors.},
}

@article {pmid40959094,
year = {2025},
author = {Mudipalli Elavarasu, S and K, S},
title = {Rational design of an epitope-centric vaccine against Pseudomonas aeruginosa using pangenomic insights and immunoinformatics approach.},
journal = {Frontiers in immunology},
volume = {16},
number = {},
pages = {1617251},
pmid = {40959094},
issn = {1664-3224},
mesh = {*Pseudomonas aeruginosa/immunology/genetics ; *Epitopes, T-Lymphocyte/immunology/genetics ; *Epitopes, B-Lymphocyte/immunology/genetics ; *Pseudomonas Vaccines/immunology/genetics ; Molecular Docking Simulation ; Vaccines, Subunit/immunology ; Humans ; Computational Biology/methods ; *Pseudomonas Infections/immunology/prevention & control ; Molecular Dynamics Simulation ; Genome, Bacterial ; Vaccine Development ; Immunogenicity, Vaccine ; Immunoinformatics ; },
abstract = {INTRODUCTION: As a highly adaptable opportunistic pathogen, Pseudomonas aeruginosa presents a significant threat to people with weakened immune systems. This is because it naturally resists antibiotics and can form biofilms. These factors complicate treatment and underscore the urgent need for innovative therapeutic strategies, such as vaccines, to combat this pathogen.

METHODS: A pangenome analysis of P. aeruginosa genomes was performed to identify conserved core genes critical for bacterial survival and virulence. LptF, an outer membrane protein, was prioritized as a target for vaccine development. B-cell and T-cell epitopes were predicted from LptF using immunoinformatics tools, and a multi-epitope peptide vaccine was designed. The interaction between the vaccine candidate and Toll-like receptors (TLRs) was investigated through molecular docking and molecular dynamics simulations. Codon optimization and in-silico cloning were carried out to validate the vaccine's expression potential in E. coli. Immune response simulations evaluated the vaccine's immunogenicity.

RESULTS: Our pangenome analysis identified highly conserved core genes, including LptF, which proved crucial for bacterial virulence. A multi-epitope peptide vaccine was designed using the most immunogenic B-cell and T-cell epitopes derived from LptF. Studies using molecular docking and dynamic simulation have shown stable interactions between the vaccine and TLRs, with the POA_V_RS09 construct exhibiting the highest stability. Codon optimization indicated high expression efficiency in E. coli. Immune simulations revealed robust adaptive immune responses, including sustained IgG production, the formation of memory B cells, and the activation of T-cell responses.

DISCUSSION: The POA_V_RS09 vaccine candidate exhibited excellent stability, immunogenic potential, and expression efficiency, making it a promising candidate for combating P. aeruginosa infections. This study provides a strong foundation for developing effective therapeutic strategies to address the growing issue of antimicrobial resistance in P. aeruginosa. More experimental validation is needed to verify its effectiveness in preclinical and clinical environments.},
}

*Pseudomonas aeruginosa/immunology/genetics
*Epitopes, T-Lymphocyte/immunology/genetics
*Epitopes, B-Lymphocyte/immunology/genetics
*Pseudomonas Vaccines/immunology/genetics
Molecular Docking Simulation
Vaccines, Subunit/immunology
Humans
Computational Biology/methods
*Pseudomonas Infections/immunology/prevention & control
Molecular Dynamics Simulation
Genome, Bacterial
Vaccine Development
Immunogenicity, Vaccine
Immunoinformatics

@article {pmid40949834,
year = {2025},
author = {Fu, X and Bi, X and Lv, T and Chen, Y},
title = {Characterization of High-Linezolid-MIC Clostridioides difficile Isolated from a Chinese Hospital: First Genomic Evidence of Cfr(B) Transmission and Tn6218 Association.},
journal = {Infection and drug resistance},
volume = {18},
number = {},
pages = {4789-4798},
pmid = {40949834},
issn = {1178-6973},
abstract = {BACKGROUND: Clostridioides difficile (C. difficile) exhibiting high linezolid minimum inhibitory concentration (>4 µg/mL) remains infrequently reported in clinical settings. Notably, the prevalence of linezolid-resistant C. difficile is exceptionally low (<3% in Chinese isolates), and the underlying genetic determinants are poorly characterized.

METHODS: We conducted a genomic study to investigate the genetic characteristics of C. difficile with high linezolid MIC. To determine the MIC of linezolid and delineate antimicrobial resistance profiles, these isolates were systematically subjected to antimicrobial susceptibility testing. Multilocus sequence typing, antimicrobial resistance genes, and the characteristics of the cfr gene in linezolid-resistant C. difficile strains were analyzed following whole-genome sequencing. Roary was used to construct a pangenome phylogenetic tree, and a Bayesian evolutionary analysis was performed using BEAST.4.

RESULTS: Among 421 screened C. difficile isolates, nine isolates (2.1%) exhibited high-linezolid MICs (≥16 μg/mL), including six ST37 (A-B+) and three ST3 strains (two A-B-). All harbored cfr(B) on Tn6218, sharing homology with E. faecium (NG_050395.1).

CONCLUSION: This study underscores the risk of cfr(B) dissemination via mobile genetic elements in clinical settings, urging surveillance of co-occurrence in Enterococcus and C. difficile to curb resistance spread.},
}

@article {pmid40946678,
year = {2025},
author = {Tariq, A and Ahmed, A and Khatoon, A and Karim, A},
title = {Identification of drug targets in pan-drug resistant Acinetobacter baumannii via whole genome sequencing and subtractive genomics.},
journal = {Computers in biology and medicine},
volume = {197},
number = {Pt B},
pages = {111058},
doi = {10.1016/j.compbiomed.2025.111058},
pmid = {40946678},
issn = {1879-0534},
abstract = {In this study, we report, to the best of our knowledge, the first complete genome sequence of a pan drug resistant (PDR) Acinetobacter baumannii strain (JRCGR-AK-AB-01) from Karachi, Pakistan. Strain JRCGR-AK-AB-01 exhibited a pan drug resistant phenotype, showing susceptibility only to polymyxin B and intermediate susceptibility to colistin. Hybrid genome sequencing using MinION long-reads and DNBSEQ short-reads revealed that the genome size of strain JRCGR-AK-AB-01 is 4.03 Mb. We identified that JRCGR-AK-AB-01 is closely related to other A. baumannii strains based on Average Amino Acid Identity (AAI), Genome-to-Genome Distance Calculator (GGDC), and Average Nucleotide Identity (ANI) analyses. Furthermore, pan-genome analysis revealed an open pan-genome, indicating frequent gene exchange. Subsequently, a subtractive genomics approach was employed to identify potential drug targets within the core genes that are essential, druggable, and non-homologous to both human proteins and gut microbiota. Finally, the selected genes were screened against the JRCGR-AK-AB-01 proteome to eliminate redundancies. Among these, NADP-dependent isocitrate dehydrogenase (IDH) was used for downstream analysis. Its structure was predicted via homology modeling and validated using different bioinformatics tools. Molecular docking and molecular dynamics (MD) simulations revealed that neomycin and paromomycin were the potent drugs against Acinetobacter spp. In vitro studies confirmed that neomycin (2.25 mg/mL) exhibited antimicrobial activity against the PDR strain of A. baumannii. Overall, this study defines genomic features and identifies potential therapeutic targets in PDR A. baumannii, thereby providing a foundation for future experimental validation and novel treatment strategies.},
}

@article {pmid40943284,
year = {2025},
author = {Wang, S and Zhong, X and Cheng, Y and Yu, Y and Wan, J and Liu, Q and Shu, Y and Wu, X and Li, Y},
title = {Pan-Genome Analysis of Cannabis sativa: Insights on Genomic Diversity, Evolution, and Environment Adaption.},
journal = {International journal of molecular sciences},
volume = {26},
number = {17},
pages = {},
doi = {10.3390/ijms26178354},
pmid = {40943284},
issn = {1422-0067},
abstract = {Cannabis sativa is a crop which has been cultivated since ancient times, with important cultural and industrial value. Due to its substantial economic impact, cannabis has attracted widespread scientific attention. A pan-genome is a significant tool for breeding, because it provides a comprehensive representation of genetic diversity. To provide a valuable tool for Cannabis breeding, we constructed a Cannabis pan-genome based on 113 accessions. A total of 24,679,380 bp of non-reference-genome sequences were assembled, identifying 1313 protein-coding genes. Using pan-genome analyses, a total of 32,428 gene presence/absence variations (PAVs) were obtained, and gene loss was recovered during the domestication of Cannabis. By partitioning the pan-genome using PAVs, a total of 23,309 core genes were identified, accounting for 71.88% of all genes in the pan-genome. In particular, there were 7148 flexible genes, making up 22.05% of the pan-genome. The flexible genes were associated with adaptive traits, including stress resistance and disease resistance in Cannabis. Population genetic analysis presented gene distribution, gene flow, and gene specificity on a pan-genome level. These results provide important genetic basis, functional genes, and guidance for Cannabis breeding.},
}

@article {pmid40943130,
year = {2025},
author = {Vega-Muñoz, MA and López-Hernández, F and Cortés, AJ and Roda, F and Castaño, E and Montoya, G and Henao-Rojas, JC},
title = {Pangenomic and Phenotypic Characterization of Colombian Capsicum Germplasm Reveals the Genetic Basis of Fruit Quality Traits.},
journal = {International journal of molecular sciences},
volume = {26},
number = {17},
pages = {},
doi = {10.3390/ijms26178205},
pmid = {40943130},
issn = {1422-0067},
support = {80740-451-2021//the Ministry of Science, Technology, and Innovation of Colombian Government/ ; 2022000100068//Proyecto Jóvenes Investigadores/ ; },
abstract = {Capsicum is one of the most economically significant vegetable crops worldwide, owing to its high content of bioactive compounds with nutritional, pharmacological, and industrial relevance. However, research has focused on C. annuum, often disregarding local diversity and secondary gene pools, which may contain hidden variation for quality traits. Therefore, this study evaluated the genetic and phenotypic diversity of 283 accessions from the Colombian germplasm collection in the agrobiodiversity hotspot of northwest South America, representing all five domesticated species of the genus. A total of 18 morphological, physicochemical, and biochemical fruit traits were assessed, including texture, color, capsaicinoid, and carotenoid content. The phenotypic data were integrated with genomic information obtained through genotyping-by-sequencing (GBS) using the C. annuum reference genome and a multispecies pangenome. Fixed-and-Random-Model-Circulating-Probability-Unification (FarmCPU) and Bayesian-information-and-Linkage-disequilibrium-Iteratively-Nested-Keyway (BLINK) genome-wide association studies (GWAS) were performed on both alignments, respectively, leading to the identification of complex polygenic architectures with 144 and 150 single nucleotide polymorphisms (SNPs) significantly associated with key fruit quality traits. Candidate genes involved in capsaicinoid biosynthesis were identified within associated genomic regions, terpenoid and sterol pathways, and cell wall modifiers. These findings highlight the potential of integrating pangenomic resources with multi-omics approaches to accelerate Capsicum improvement programs and facilitate the development of cultivars with enhanced quality traits and increased agro-industrial value.},
}

@article {pmid40930091,
year = {2025},
author = {Minich, JJ and Allsing, N and Din, MO and Tisza, MJ and Maleta, K and McDonald, D and Hartwick, N and Mamerto, A and Brennan, C and Hansen, L and Shaffer, J and Murray, ER and Duong, T and Knight, R and Stephenson, K and Manary, MJ and Michael, TP},
title = {Culture-independent meta-pangenomics enabled by long-read metagenomics reveals associations with pediatric undernutrition.},
journal = {Cell},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.cell.2025.08.020},
pmid = {40930091},
issn = {1097-4172},
abstract = {The human gut microbiome is linked to child malnutrition, yet traditional microbiome approaches lack resolution. We hypothesized that complete metagenome-assembled genomes (cMAGs), recovered through long-read (LR) DNA sequencing, would enable pangenome and microbial genome-wide association study (GWAS) analyses to identify microbial genetic associations with child linear growth. LR methods produced 44-64× more cMAGs per gigabase pair (Gbp) than short-read methods, with PacBio (PB) yielding the most accurate and cost-effective assemblies. In a Malawian longitudinal pediatric cohort, we generated 986 cMAGs (839 circular) from 47 samples and applied this database to an expanded set of 210 samples. Machine learning identified species predictive of linear growth. Pangenome analyses revealed microbial genetic associations with linear growth, while genome instability correlated with declining length-for-age Z score (LAZ). This resource demonstrates the power of comparing cMAGs with health trajectories and establishes a new standard for microbiome association studies.},
}

@article {pmid40926249,
year = {2025},
author = {Huang, Y and Liu, Y and Liu, C and Yi, C and Lai, J and Ling, H and Su, H and Han, F},
title = {Distinct evolutionary trajectories of subgenomic centromeres in polyploid wheat.},
journal = {Genome biology},
volume = {26},
number = {1},
pages = {271},
pmid = {40926249},
issn = {1474-760X},
support = {31991212//National Natural Science Foundation of China/ ; 2022YFF1003303//National Key Research and Development Program of China/ ; },
mesh = {*Centromere/genetics ; *Triticum/genetics ; *Polyploidy ; *Evolution, Molecular ; Retroelements ; Genome, Plant ; Chromosomes, Plant/genetics ; },
abstract = {BACKGROUND: Centromeres are crucial for precise chromosome segregation and maintaining genome stability during cell division. However, their evolutionary dynamics, particularly in polyploid organisms with complex genomic architectures, remain largely enigmatic. Allopolyploid wheat, with its well-defined hierarchical ploidy series and recent polyploidization history, serves as an excellent model to explore centromere evolution.

RESULTS: In this study, we perform a systematic comparative analysis of centromeres in common wheat and its corresponding ancestral species, utilizing the latest comprehensive reference genome assembly available. Our findings reveal that wheat centromeres predominantly consist of five types of centromeric-specific retrotransposon elements (CRWs), with CRW1 and CRW2 being the most prevalent. We identify distinct evolutionary trajectories in the functional centromeres of each subgenome, characterized by variations in copy number, insertion age, and CRW composition. By utilizing CENH3-ChIP data across various ploidy levels, we uncover a series of CRW invasion events that have shaped the evolution of AA subgenome centromeres. Conversely, the evolutionary process of the DD subgenome centromeres involves their expansion from diploid to hexaploid wheat, facilitating adaptation to a larger genomic context. Integration of complete einkorn centromere assemblies and Aegilops tauschii pan-genomes further revealed subgenome-specific centromere evolutionary trajectories. By inclusion of synthetic hexaploid from S2-S3 generations, alongside 2x/6 × natural accessions, we demonstrate that DD subgenome centromere expansion represents a gradual evolutionary process rather than an immediate response to polyploidization.

CONCLUSIONS: Our study provides a comprehensive landscape of centromere adaptation, evolution, and maturation, along with insights into how retrotransposon invasions drive centromere evolution in polyploid wheat.},
}

*Centromere/genetics
*Triticum/genetics
*Polyploidy
*Evolution, Molecular
Retroelements
Genome, Plant
Chromosomes, Plant/genetics

@article {pmid40924370,
year = {2025},
author = {Gaurav, A and Singh, H and Dige, M and Mukesh, M and Navani, NK},
title = {Comparative Genome Analysis and Characterization of Lacticaseibacillus Paracasei NKN344 Strain Isolated from Curd of Buffalo Milk Reared on Brackish Water Lagoons of the Eastern Indian Coast.},
journal = {Probiotics and antimicrobial proteins},
volume = {},
number = {},
pages = {},
pmid = {40924370},
issn = {1867-1314},
support = {BT/NER/95/SP47965/2022//DBT-Himalayan Bioresource Mission/ ; BT/PR41336/AAQ/1/808/2020//Department of Biotechnology, Ministry of Science and Technology, India/ ; },
abstract = {Ethnic fermented foods represent a significant repository for discovering novel probiotic entities. These fermented foods, entrenched in indigenous practices, have conserved a distinct microbiota through generations. Exploration of these fermented foods could yield microbial consortia capable of transforming human health. However, comprehensive research into the probiotic attributes and quality analysis is necessary before its usage as biotherapeutics. In the current study, Chilika curd - an ethnic fermented curd originating from Odisha was explored to isolate novel probiotic strains. A detailed phenotypic and genomic characterization of a novel Lacticaseibacillus paracasei strain was conducted. Host-probiotic interactions were assessed using the Caenorhabditis elegans model. Lacticaseibacillus paracasei NKN344 exhibited robust survival under various physiochemical stresses, such as in vitro simulated gut environment and in vivo Caenorhabditis elegans intestinal model. Additionally, an in-depth bioinformatic analysis revealed the metabolic prowess of Lacticaseibacillus paracasei NKN344, including a few bacteriocin-encoding operons. Lastly, the production of active bacteriocin by Lacticaseibacillus paracasei NKN344 was validated, showing inhibitory activity against Bacillus cereus, a major food spoilage bacterium. Results of the current study proved that Lacticaseibacillus paracasei NKN344 isolated from Chilika curd has promising probiotic properties and seems favorable for its use in functional fermented foods.},
}

@article {pmid40923439,
year = {2025},
author = {Thallman, RM and Borgert, JE and Engle, BN and Keele, JW and Snelling, WM and Gondro, C and Kuehn, LA},
title = {A Vision of How Low-Coverage Sequence Data Should Contribute to Genetic Evaluation in the Future.},
journal = {Journal of animal science},
volume = {},
number = {},
pages = {},
doi = {10.1093/jas/skaf294},
pmid = {40923439},
issn = {1525-3163},
abstract = {Low-coverage sequencing refers to sequencing DNA of individuals to a low depth of coverage (e.g., 0.5X) and imputing that sequence to genomic sequence based on reference haplotypes from individuals sequenced to high depth of coverage (e.g., ≥ 10X). It has been proposed as an alternative to genotyping by SNP arrays. At least one commercial product based on it is available for agricultural species. Concerns limiting adoption in its current form are: 1) the cost of storing the huge volume of data it generates and 2) whether that additional data will result in improved accuracy of genetic evaluation. This work envisions future implementation of low-coverage sequencing to reduce storage costs and enhance genetic evaluations by leveraging the additional information in the full sequence of the pangenome to account for more genetic variation. We propose addressing the storage issue by representing genomic sequence of an individual in a pair of haplotype arrays with each element pointing to an enumerated haplotype of the sequence within one of approximately 50,000 defined genome segments. Assuming 60 million genomic variants, the infrastructure required to translate the identifier of any enumerated haplotype into its genomic sequence would require less than 10 gigabytes of binary storage. Each haplotype array element would require 2 bytes, so the marginal binary storage required to represent the genomic sequence of an individual would be about 200 kilobytes (KB), similar to the genotypes from a SNP array with 200,000 markers. This assumes no pedigree and no ambiguity of the imputation, though the latter is unrealistic. Strategies to minimize, and when necessary, to manage and efficiently represent ambiguity are proposed. The genomic sequence of an individual could be stored in about 1 KB (binary) if both parents have unambiguous sequence stored as described above. The proposed system for representing the pangenome includes algorithms for read mapping and imputation intended to leverage all known genetic variation in the target population. It is also designed to use sequencing reads generated for imputing genomic sequence of new individuals to identify unrecognized mutations, crossovers, and structural variants, thus continuously improving the genome representation, especially if widespread use of low-coverage sequencing in livestock industries is realized. This could make improved genetic merit and management of livestock feasible without computational burden.},
}

@article {pmid40919784,
year = {2025},
author = {Leite, VLM and Faria, AR and Guerra, CF and Souza, SdSR and Freitas, AdAR and Morais, JM and Merquior, VLC and Planet, PJ and Teixeira, LM},
title = {Hidden diversity in Enterococcus faecalis revealed by CRISPR2 screening: eco-evolutionary insights into a novel subspecies.},
journal = {Microbiology spectrum},
volume = {},
number = {},
pages = {e0142825},
doi = {10.1128/spectrum.01428-25},
pmid = {40919784},
issn = {2165-0497},
abstract = {Enterococcus faecalis is a commensal bacterium that colonizes the gut of humans and animals and is a major opportunistic pathogen, known for causing multidrug-resistant healthcare-associated infections (HAIs). Its ability to thrive in diverse environments and disseminate antimicrobial resistance genes (ARGs) across ecological niches highlights the importance of understanding its ecological, evolutionary, and epidemiological dynamics. The CRISPR2 locus has been used as a valuable marker for assessing clonality and phylogenetic relationships in E. faecalis. In this study, we identified a group of E. faecalis strains lacking CRISPR2, forming a distinct, well-supported clade. We demonstrate that this clade meets the genomic criteria for classification as a novel subspecies, here referred to as "subspecies B." Through a comprehensive pangenome analysis and comparative genomics, we explored the adaptive ecological traits underlying this diversification process, identifying clade-specific features and their predicted functional roles. Our findings suggest that the frequent isolation of subspecies B from meat products and processing facilities may reflect dissemination routes involving environmental contamination (e.g., water, plants, soil) from avian species. The absence of key virulence traits required for pathogenicity in mammals, particularly humans, and the lack of clinically relevant resistance determinants indicate that subspecies B currently poses minimal threat to public health compared with the broadly disseminated "subspecies A." Nevertheless, the unclear potential for genetic exchange between these subspecies and the frequent association of subspecies B with food sources calls for continued genomic surveillance of E. faecalis from a One Health perspective to detect and mitigate the emergence of high-risk variants in advance.IMPORTANCEExploring intraspecific genetic variability in generalist bacteria with pathogenic potential, such as Enterococcus faecalis, is a key to uncovering stable evolutionary trends. By screening the CRISPR2 locus across a representative set of genomes from diverse sources, this study reveals a previously unrecognized lineage within the population structure of E. faecalis, associated with underexplored nonhuman and nonhospital reservoirs. These findings broaden our knowledge of the species' genetic landscape and shed light on its adaptive strategies and patterns of ecological dissemination. By bridging phylogenetic patterns with variation in genetic defense systems and accessory traits, the study generates testable hypotheses about the genomic determinants and corresponding selective pressures that shape the species' behavior and long-term dissemination. This work offers new perspectives on the eco-evolutionary dynamics of E. faecalis and highlights the value of genomic surveillance beyond clinical settings, in alignment with One Health principles.},
}

@article {pmid40918259,
year = {2025},
author = {Khasapane, NG and Nkhebenyane, SJ and Thekisoe, O and Ramatla, T and Lekota, KE},
title = {Population structure, resistome, and virulome of Staphylococcus chromogenes strains from milk of subclinical bovine mastitis in South Africa.},
journal = {Frontiers in cellular and infection microbiology},
volume = {15},
number = {},
pages = {1654546},
pmid = {40918259},
issn = {2235-2988},
mesh = {Animals ; Cattle ; *Mastitis, Bovine/microbiology ; South Africa/epidemiology ; Multilocus Sequence Typing ; *Staphylococcal Infections/veterinary/microbiology ; Female ; *Milk/microbiology ; *Staphylococcus/genetics/drug effects/isolation & purification/classification/pathogenicity ; Anti-Bacterial Agents/pharmacology ; Swine ; Phylogeny ; *Drug Resistance, Bacterial/genetics ; Genome, Bacterial ; Virulence Factors/genetics ; Plasmids/genetics ; Genetic Variation ; Polymorphism, Single Nucleotide ; },
abstract = {INTRODUCTION: Staphylococcus chromogenes are commonly found in intramammary infections associated with bovine subclinical mastitis in dairy cattle, yet their genomic diversity and antimicrobial resistance dynamics remain poorly characterized, particularly in African settings.

METHODS: This study presents a comparative genomic analysis of 17 S. chromogenes isolates from South Africa, including five newly sequenced bovine mastitis strains and twelve porcine-derived genomes retrieved from GenBank. In-silico analysis using multilocus sequence typing (MLST), virulence genes, antibiotic resistance genes and plasmids replicon types were used to characterise these isolates.

RESULTS AND DISCUSSION: Pairwise average nucleotide identity (ANI) analysis revealed that bovine isolates SC21, SC28, and SC33 are closely related and likely clonal members of the bovine-adapted ST138 lineage (ANI >99.7%), while SC12 and SC14 are more genetically distinct and show closer similarity (ANI >91%) to porcine-derived strains. This was supported by whole-genome SNP (wgSNP) analysis, whereby the ST138 bovine-derived isolates formed a clonal lineage and displayed a diverse population structure compared to porcine strains. Resistome profiling uncovered antimicrobial resistance gene (ARG) content, bovine isolates reflecting only four core ARGs i.e., dfrC, mgrA, norA, and tet(38), which confer resistance to trimethoprim, fluoroquinolones, and tetracyclines. In contrast, the compared porcine strains harboured a diverse set of resistance determinants, including blaZ, ermC, tet(K), and vgaALC that encode for beta-lactams, macrolides, tetracycline, and lincosamides, respectively. The five S. chromogenes isolates grouped into two 2 sequence types, namely ST138 and ST62. Pangenome reconstruction of 177 global genomes confirmed that S. chromogenes possesses an open pangenome, with only ~17.5% of genes conserved as core or soft-core elements. Notably, unique strain-specific genes of the ST138 were determined to be associated with trehalose metabolism identified in bovine isolates, potentially reflecting niche-specific adaptation to the mammary environment in the Free State Province of South Africa.

CONCLUSION: These findings advance our understanding of S. chromogenes population structure and resistance ecology. They underscore the importance of continued genomic surveillance of livestock pathogens to inform targeted intervention strategies and improve animal health in diverse production settings, and further clarify the implications for future antibiotic therapy and prevention of infections associated with this species.},
}

Animals
Cattle
*Mastitis, Bovine/microbiology
South Africa/epidemiology
Multilocus Sequence Typing
*Staphylococcal Infections/veterinary/microbiology
Female
*Milk/microbiology
*Staphylococcus/genetics/drug effects/isolation & purification/classification/pathogenicity
Anti-Bacterial Agents/pharmacology
Swine
Phylogeny
*Drug Resistance, Bacterial/genetics
Genome, Bacterial
Virulence Factors/genetics
Plasmids/genetics
Genetic Variation
Polymorphism, Single Nucleotide

@article {pmid40918067,
year = {2025},
author = {Kamaraj, V and Gupta, A and Raman, K and Narayanan, M and Sinha, H},
title = {GViNC: an innovative framework for genome graph comparison reveals hidden patterns in the genetic diversity of human populations.},
journal = {NAR genomics and bioinformatics},
volume = {7},
number = {3},
pages = {lqaf121},
pmid = {40918067},
issn = {2631-9268},
mesh = {Humans ; *Genetic Variation ; *Genome, Human ; *Genomics/methods ; *Software ; *Genetics, Population ; },
abstract = {Genome graphs provide a powerful reference structure for representing genetic diversity. Their structure emphasizes the polymorphic regions in a collection of genomes, enabling network-based comparisons of population-level variation. However, current tools are limited in their ability to quantify and compare structural features across large genome graphs. We introduce GViNC, Genome graph Visualization, Navigation, and Comparison, a novel framework that enables partitioning genome graphs into interpretable subgraphs, mapping linear coordinates to graph nodes, and summarizing both local and global structural variation using new metrics for variability, hypervariability, and graph distances. We applied GViNC to multiple pan-genomic and population-specific genome graphs constructed with over 85M variants in 2504 individuals from the 1000 Genomes Project. We found that genomic complexity varied by ancestry and across chromosomes, with rare variants increasing variability by 10-fold and hypervariability by 50-fold. GViNC highlighted key regions of the human genome, such as Human Leukocyte Antigen and DEFB loci, and many previously unreported high-diversity regions, some with population-specific signatures in protein-coding and regulatory genes. By bridging sequence-level variation and graph-level topology, GViNC enables scalable, quantitative exploration of genome structure across populations. GViNC's versatility can aid researchers in extensively investigating the genetic diversity of different cohorts, populations, or species of interest.},
}

Humans
*Genetic Variation
*Genome, Human
*Genomics/methods
*Software
*Genetics, Population

@article {pmid40916704,
year = {2025},
author = {Ficoseco, CMA and Chieffi, D and Montemurro, M and Bavaro, A and Rizzello, CG and Nader-Macias, MEF and Fadda, S and Fanelli, F and Fusco, V and Vignolo, GM},
title = {Genomic Characterisation of Limosilactobacillus fermentum CRL2085 Unveiling Probiotic Traits for Application in Cattle Feed.},
journal = {Environmental microbiology reports},
volume = {17},
number = {5},
pages = {e70176},
doi = {10.1111/1758-2229.70176},
pmid = {40916704},
issn = {1758-2229},
support = {//This work was financially supported by the Joint Bilateral Agreement CNR/CONICET (ITALY-Argentina) "Lactic Acid Bacteria as bioprotective agents against zoonotic pathogens in the meat chain" Biennial Programme 2023-2024/ ; },
mesh = {Animals ; *Probiotics ; Cattle ; *Limosilactobacillus fermentum/genetics/isolation & purification/metabolism ; *Animal Feed/microbiology ; *Genome, Bacterial ; Genomics ; Genomic Islands ; Bacterial Adhesion ; },
abstract = {Limosilactobacillus fermentum CRL2085, isolated from feedlot cattle rations, displayed high efficiency as a probiotic when administered to animals. A comprehensive genomic analysis was performed to elucidate the genetic basis underlying its probiotic potential. Fifteen genomic islands and CRISPR-Cas elements were identified in its genome. Pan-genomic analysis highlighted the dynamic evolution of this species, and clustering based on the nucleotide genomic similarity only partially correlated with the source of isolation or the geographic origin of the strains. Several genes known to confer probiotic properties were identified, including those related to adhesion, resistance to acidic pH and bile salts, tolerance to oxidative stress, metabolism/transport of sugars and other compounds, and genes for exopolysaccharide biosynthesis. In silico analysis of antimicrobial resistance genes and virulence determinants confirmed the safety of this strain. Moreover, genes related to B-group vitamins biosynthesis and feruloyl esterase hydrolase were also found, showing the nutritional contribution of the strain, which also showed moderate adhesion capability, exopolysaccharide production when grown with sucrose, and the capacity to metabolise 42 out of 95 carbon substrates tested. This data provides the genetic basis for deciphering the mechanisms beyond the benefits demonstrated by its use during cattle intensive raising and confirms its promising role as a probiotic.},
}

Animals
*Probiotics
Cattle
*Limosilactobacillus fermentum/genetics/isolation & purification/metabolism
*Animal Feed/microbiology
*Genome, Bacterial
Genomics
Genomic Islands
Bacterial Adhesion

@article {pmid40913342,
year = {2025},
author = {Soleymani, F and Correa, SM and Arend, M and Forghanisardaghi, N and Treves, H and Razaghi-Moghadam, Z and Nikoloski, Z},
title = {Constraint-based metabolic modeling reveals metabolic properties underpinning the unprecedented growth of Chlorella ohadii.},
journal = {The New phytologist},
volume = {},
number = {},
pages = {},
doi = {10.1111/nph.70528},
pmid = {40913342},
issn = {1469-8137},
support = {NI 1472/16-1//Deutsche Forschungsgemeinschaft/ ; SCHR 617/13-1//Deutsche Forschungsgemeinschaft/ ; NNF23OC0085412//Novo Nordisk Foundation Center for Basic Metabolic Research/ ; },
abstract = {Comparative molecular and physiological analyses of organisms from one taxonomic group grown under similar conditions offer a strategy to identify gene targets for trait improvement. While this strategy can also be performed in silico using genome-scale metabolic models for the compared organisms, we continue to lack solutions for the de novo generation of such models, particularly for eukaryotes. To facilitate model-driven identification of gene targets for growth improvement in green algae, here we present a semiautomated platform for de novo generation of genome-scale algal metabolic models. We deployed this platform to reconstruct an enzyme-constrained, genome-scale metabolic model of Chlorella ohadii, the fastest growing green alga reported to date, and validated the growth predictions in experiments under three growth conditions. We also proposed a computational strategy to identify targets for growth improvement based on flux analyses. Extensive flux-based comparative analyses using all existing models of green algae resulted in the identification of potential targets for growth improvement not only in standard but also in extreme light conditions, where C. ohadii still exhibits exceptional growth. Our findings indicate that the developed platform provides the basis for the generation of pan-genome-scale metabolic models of algae.},
}

@article {pmid40913088,
year = {2025},
author = {Chandola, U and Manirakiza, E and Maillard, M and Lavier Aydat, LJ and Camuel, A and Trottier, C and Tanaka, A and Chaumier, T and Giraud, E and Tirichine, L},
title = {A Bradyrhizobium isolate from a marine diatom induces nitrogen-fixing nodules in a terrestrial legume.},
journal = {Nature microbiology},
volume = {},
number = {},
pages = {},
pmid = {40913088},
issn = {2058-5276},
abstract = {Biological nitrogen fixation converts atmospheric nitrogen into ammonia, essential to the global nitrogen cycle. While cyanobacterial diazotrophs are well characterized, recent studies have revealed a broad distribution of non-cyanobacterial diazotrophs (NCDs) in marine environments, although their study is limited by poor cultivability. Here we report a previously uncharacterized Bradyrhizobium isolated from the marine diatom Phaeodactylum tricornutum. Phylogenomic analysis places the strain within photosynthetic Bradyrhizobium, suggesting evolutionary adaptations to marine and terrestrial niches. Average nucleotide identity supports its classification as a previously undescribed species. Remarkably, inoculation experiments showed that the isolate induced nitrogen-fixing nodules in the Aeschynomene indica legume, pointing to symbiotic capabilities across ecological boundaries. Pangenome analysis and metabolic predictions indicate that this isolate shares more features with terrestrial photosynthetic Bradyrhizobium than with marine NCDs. Overall, these findings suggest that symbiotic interactions could evolve across different ecological niches, and raise questions about the evolution of nitrogen fixation and microbe-host interactions.},
}

@article {pmid40910469,
year = {2025},
author = {Behruznia, M and Marin, M and Whiley, DJ and Farhat, MR and Thomas, JC and Domingo-Sananes, MR and Meehan, CJ},
title = {The Mycobacterium tuberculosis complex pangenome is small and shaped by sub-lineage-specific regions of difference.},
journal = {eLife},
volume = {13},
number = {},
pages = {},
pmid = {40910469},
issn = {2050-084X},
support = {SBF006\1090/AMS_/Academy of Medical Sciences/United Kingdom ; },
mesh = {*Mycobacterium tuberculosis/genetics/classification ; *Genome, Bacterial ; *Genetic Variation ; Humans ; Tuberculosis/microbiology ; Phylogeny ; Evolution, Molecular ; Virulence ; },
abstract = {The Mycobacterium tuberculosis complex (MTBC) is a group of bacteria causing tuberculosis (TB) in humans and animals. Understanding MTBC genetic diversity is crucial for insights into its adaptation and traits related to survival, virulence, and antibiotic resistance. While it is known that within-MTBC diversity is characterised by large deletions found only in certain lineages (regions of difference [RDs]), a comprehensive pangenomic analysis incorporating both coding and non-coding regions remains unexplored. We utilised a curated dataset representing various MTBC genomes, including under-represented lineages, to quantify the full diversity of the MTBC pangenome. The MTBC was found to have a small, closed pangenome with distinct genomic features and RDs both between lineages (as previously known) and between sub-lineages. The accessory genome was identified to be a product of genome reduction, showing both divergent and convergent deletions. This variation has implications for traits like virulence, drug resistance, and metabolism. The study provides a comprehensive understanding of the MTBC pangenome, highlighting the importance of genome reduction in its evolution, and underlines the significance of genomic variations in determining the pathogenic traits of different MTBC lineages.},
}

*Mycobacterium tuberculosis/genetics/classification
*Genome, Bacterial
*Genetic Variation
Humans
Tuberculosis/microbiology
Phylogeny
Evolution, Molecular
Virulence

@article {pmid40910370,
year = {2025},
author = {Stepanauskas, R and Brown, JM and Arasti, S and Mai, U and Gavelis, G and Pachiadaki, M and Bezuidt, O and Munson-McGee, JH and Chang, T and Biller, SJ and Berube, PM and Mirarab, S},
title = {Net rate of lateral gene transfer in marine prokaryoplankton.},
journal = {The ISME journal},
volume = {},
number = {},
pages = {},
doi = {10.1093/ismejo/wraf159},
pmid = {40910370},
issn = {1751-7370},
abstract = {Lateral gene transfer is a major evolutionary process in Bacteria and Archaea. Despite its importance, lateral gene transfer quantification in nature using traditional phylogenetic methods has been hampered by the rarity of most genes within the enormous microbial pangenomes. Here, we estimated lateral gene transfer rates within the epipelagic tropical and subtropical ocean using a global, randomized collection of single amplified genomes and a non-phylogenetic computational approach. By comparing the fraction of shared genes between pairs of genomes against a lateral gene transfer-free model, we show that an average cell line laterally acquires and retains ~13% of its genes every 1 million years. This translates to a net lateral gene transfer rate of ~250 genes L-1 seawater day-1 and involves both "flexible" and "core" genes. Our study indicates that whereas most genes are exchanged among closely related cells, the range of lateral gene transfer exceeds the contemporary definition of bacterial species, thus providing prokaryoplankton with extensive genetic resources for lateral gene transfer-based adaptation to environmental stressors. This offers an important starting point for the quantitative analysis of lateral gene transfer in natural settings and its incorporation into evolutionary and ecosystem studies and modeling.},
}

@article {pmid40907038,
year = {2025},
author = {Long, GS and Singh, N and Patel, S and Braukmann, T and Tsang, RSW and Duvvuri, VR},
title = {Integrated genomic approaches improve Treponema pallidum phylogenetics and lineage classification.},
journal = {Canadian journal of microbiology},
volume = {},
number = {},
pages = {},
doi = {10.1139/cjm-2025-0021},
pmid = {40907038},
issn = {1480-3275},
abstract = {Syphilis cases have been consistently rising since its near elimination in the late 1990s. This resurgence, along with increasing rates of macrolide resistance and congenital syphilis, has triggered renewed efforts to better understand and control the disease. We analyzed 827 T. pallidum genomes and created a new genome-based hierarchical lineage framework, recapitulating the major T. pallidum lineages and characterizing sub-lineages. An updated pangenome was constructed, revealing that T. pallidum subsp. pallidum lineages are determined by a single hypothetical major outer sheath C-terminal domain-containing gene while no significant genetic difference was observed between T. pallidum subsp. pertenue and T. pallidum subsp. endemicum. This study introduces an integrated genomic approach to characterize T. pallidum and highlights the significance of pangenomes in supporting public health.},
}