@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.},
}

@article {pmid40905373,
year = {2025},
author = {Li, H},
title = {Finding easy regions for short-read variant calling from pangenome data.},
journal = {GigaScience},
volume = {14},
number = {},
pages = {},
doi = {10.1093/gigascience/giaf103},
pmid = {40905373},
issn = {2047-217X},
support = {U41HG010972//National Genome Research Institute/ ; U01HG010971//National Genome Research Institute/ ; U01HG013760//National Genome Research Institute/ ; U01HG013755//National Genome Research Institute/ ; U01HG013748//National Genome Research Institute/ ; U01HG013744//National Genome Research Institute/ ; R01HG011274//National Genome Research Institute/ ; R01HG010040//National Genome Research Institute/ ; //Human Pangenome Reference Consortium/ ; },
mesh = {Humans ; *Genome, Human ; *Genomics/methods ; *Genetic Variation ; Sequence Analysis, DNA/methods ; *Computational Biology/methods ; High-Throughput Nucleotide Sequencing/methods ; Software ; },
abstract = {BACKGROUND: While benchmarks on short-read variant calling suggest a low error rate below 0.5%, they are only applicable to predefined confident regions. For a human sample without such regions, the error rate could be 10 times higher. Although multiple sets of easy regions have been identified to alleviate the issue, they fail to consider nonreference samples or are biased toward existing short-read data or aligners.

RESULTS: Here, using hundreds of high-quality human assemblies, we derived a set of sample-agnostic easy regions where short-read variant calling reaches high accuracy. These regions cover 88.2% of GRCh38, 92.2% of coding regions, and 96.3% of ClinVar pathogenic variants. They achieve a good balance between coverage and easiness and can be generated for other human assemblies or species with multiple well-assembled genomes.

CONCLUSIONS: This resource provides a convenient and powerful way to filter spurious variant calls for clinical or research human samples.},
}

Humans
*Genome, Human
*Genomics/methods
*Genetic Variation
Sequence Analysis, DNA/methods
*Computational Biology/methods
High-Throughput Nucleotide Sequencing/methods
Software

@article {pmid40904111,
year = {2025},
author = {Kupczok, A and Gavriilidou, A and Paulitz, E and Guerrero-García, L and Baumdicker, F},
title = {Gene co-occurrence and its association with phage infectivity in bacterial pangenomes.},
journal = {Philosophical transactions of the Royal Society of London. Series B, Biological sciences},
volume = {380},
number = {1934},
pages = {20240070},
pmid = {40904111},
issn = {1471-2970},
support = {//Deutsche Forschungsgemeinschaft/ ; },
mesh = {*Bacteriophages/physiology ; *Bacteria/genetics/virology ; *Genome, Bacterial ; Host Specificity ; *Genes, Bacterial ; Phylogeny ; },
abstract = {Phages infect bacteria and have recently re-emerged as a promising strategy to combat bacterial infections. However, there is a lack of methods to predict whether and why a particular phage can or cannot infect a bacterial strain based on their genome sequences. Understanding the complex interactions between phages and their bacterial hosts is thus of considerable interest. We recently developed Goldfinder, a phylogenetic method to discover gene co-occurrences across bacterial pangenomes. Here, we expand Goldfinder to infer which gene presences or absences influence bacterial sensitivity to phages. By integrating a bacterial pangenome with an experimentally determined host range matrix, we infer associations between phage infectivity and the presence of accessory genes in bacterial pangenomes. The presented approach can be applied to predict bacterial genes that potentially enable phage infection, bacterial genes that prevent phage infection, and potential interactions between particular bacterial and phage accessory genes. Finally, the predicted interactions are clustered and visualized with the software Cytoscape. Here, we present a method to identify candidate genes within the pool of mobile accessory genes that may contribute to phage-host interactions. This approach will help to set up follow-up experiments and to understand the complex interactions between phages and bacteria.This article is part of the discussion meeting issue 'The ecology and evolution of bacterial immune systems'.},
}

*Bacteriophages/physiology
*Bacteria/genetics/virology
*Genome, Bacterial
Host Specificity
*Genes, Bacterial
Phylogeny

@article {pmid40890628,
year = {2025},
author = {Steensma, MJ and Ducro, BJ and Dibbits, B and Doekes, HP and van Schipstal, JGC and Kalblfleisch, T and Groenen, MAM and Derks, MFL},
title = {High-quality, haplotype-resolved reference genomes of the Dutch warmblood horse and Friesian horse using trio binning.},
journal = {BMC genomics},
volume = {26},
number = {1},
pages = {790},
pmid = {40890628},
issn = {1471-2164},
support = {4164023400//Topconsortium voor Kennis en Innovatie/ ; 4164023400//Topconsortium voor Kennis en Innovatie/ ; },
abstract = {BACKGROUND: In horses, genetic diversity is predominantly observed between breeds, with little variation within breeds. The studbooks of the two largest horse populations in the Netherlands, the Dutch Warmblood horse and Friesian horse population, have ongoing conservation projects including collecting large-scale genotype and sequence data. The current reference genome, derived from a Thoroughbred horse can lead to bias in genetic analyses of other horse breeds. Therefore, the aim of this study was to create high-quality breed-specific reference genomes of Dutch Warmblood and Friesian horses.

RESULTS: We performed nanopore long-read sequencing (R10.4, Q20+) of an F1 cross between a Dutch Warmblood horse and a Friesian horse to create two breed-specific reference genomes by trio binning. This resulted in high-quality, haplotype-resolved reference genomes with contig N50 of 37 and 35 Mb and single copy gene completeness of 99.2 and 99.3% for the Friesian and Warmblood, respectively. The majority of the chromosomes contained telomeric and /or centromeric sequences. The Ensembl gene annotation resulted in 19,750 and 19,872 protein coding genes for the Friesian and Warmblood, respectively. No large chromosomal rearrangements were observed between the Friesian and Warmblood genomes. However, a total of 722 large structural variations (> 10 kb) were identified, of which 14 affect the coding sequence of protein-coding genes.

CONCLUSION: The novel breed-specific reference genomes provide a valuable resource for future genetic analysis and breed conservation efforts and will contribute to ongoing equine pangenome efforts.

SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1186/s12864-025-11985-0.},
}

@article {pmid40898043,
year = {2025},
author = {Kolesch, F and Sohn, M and Rempel, A and Hippel, P and Wittler, R},
title = {SANS ambages: phylogenomics with abundance-filter, multi-threading, and bootstrapping on amino-acid or genomic sequences.},
journal = {BMC bioinformatics},
volume = {26},
number = {1},
pages = {227},
pmid = {40898043},
issn = {1471-2105},
abstract = {BACKGROUND: The increasing amount of available genome sequence data enables large-scale comparative studies. A common task is the inference of phylogenies- a challenging task if close reference sequences are not available, genome sequences are incompletely assembled, or the high number of genomes precludes multiple sequence alignment in reasonable time. SANS is an alignment-free, whole-genome based approach for phylogeny estimation.

RESULTS: Here we present a new implementation SANS ambages with a significantly increased application spectrum. It offers additional types of input data, parallelized processing, and bootstrapping. The source code (C++), documentation, and example data are freely available for download at: https://github.com/gi-bielefeld/sans . SANS can also be launched via the web-interface of the CloWM platform- free of charge, with a standard Life Science account: https://clowm.bi.denbi.de/workflows/0194b78f-9696-7402-a2b8-858508733618/ .

CONCLUSIONS: The new version not only shortens processing time on large datasets immensely by parallelization. Being able to also process amino acid sequences and offering a filter for low-abundant DNA read segments also enables new application cases. Bootstrapping and integrated visualization ease and enrich the interpretation of the resulting phylogenies.},
}

@article {pmid40894897,
year = {2025},
author = {Du, M and Zhang, F and Wang, X and Zhang, T and Yang, X and Liu, Y and Zhang, Y and Hou, T and Hang, G and Fang, X and Li, J and Xue, H and Zhou, Y and Wang, J},
title = {Structural and deleterious burdens and their effects on yield traits in foxtail millet domestication.},
journal = {iScience},
volume = {28},
number = {9},
pages = {113295},
doi = {10.1016/j.isci.2025.113295},
pmid = {40894897},
issn = {2589-0042},
abstract = {Crop domestication typically accumulates structural and deleterious variants through genetic bottlenecks and selection hitchhiking. However, the structural and deleterious variant burden has not been investigated in the foxtail millet (Setaria italica). Integrating comparative genomics, pangenomics, population genetics, and quantitative genetics, we identified 6,713 gene gains and 2,802 losses during domestication, affecting flowering time and developmental processes. Population genetics of 333 wild and cultivated accessions revealed 25.76% and 40.40% reductions in structural and deleterious variant burdens in cultivars, potentially reflecting a dramatic loss of genetic diversity of the wild progenitor. Quantitative genetics detected genetic association of yield traits, and essential roles of deleterious and structural variants in the formation of yield traits. In general, this study highlights significant impacts of structural and deleterious variants on yield traits and provides valuable guidelines for molecular breeding of foxtail millet.},
}

@article {pmid40894736,
year = {2025},
author = {Samano, A and Musat, M and Junaghare, M and Ahmad, A and Ali, M and Alves, S and Pasupuleti, S and Perera, J and Saada, O and Sabido, B and Smith, T and Walz, S and Chakraborty, M},
title = {Structural variants are enriched in deleterious visible phenotypes in Drosophila.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.1101/2025.08.15.670616},
pmid = {40894736},
issn = {2692-8205},
abstract = {Genome structural variants (SVs) comprise a sizable portion of functionally important genetic variation in all organisms; yet, many SVs evade discovery using short reads. While long-read sequencing can find the hidden SVs, the role of SVs in variation in organismal traits remains largely unclear. To address this gap, we investigate the molecular basis of 50 classical phenotypes in 11 Drosophila melanogaster strains using highly contiguous de novo genome assemblies generated with Oxford Nanopore long reads. These assemblies enabled the creation of a pangenome graph containing comprehensive, nucleotide-resolution maps of SVs, including complex rearrangements such as the interchromosomal inverted duplication Dp(2;4)eyD and large tandem duplications at the Bar locus. We uncovered new candidate causal mutations for 15 phenotypes and new molecular alleles for 2 mutations comprising tandem duplications, transposable element (TE) insertions, and indels. For example, we mapped the tarsal joint defect Ablp [eyD] to an 8 kb Roo retrotransposon insertion into an intergenic enhancer, a finding validated via CRISPR-Cas9. The wing vein phenotype plexus (px [1]) was linked to a 1.5 kb partial tandem gene duplication, and the century-old Curved (c [1]) wing phenotype was linked to a 7.5 kb DM412 retrotransposon inserted into the coding sequence of the muscle protein gene Strn-Mlck . We also unveiled 8 SV alleles of previously identified causal genes, including previously uncharacterized SVs underlying the extensively studied white and yellow phenotypes. Overall, 67.4% of the genes causing phenotypic changes harbored candidate SVs over 100 bp, whereas only 28% is expected based on euchromatic SVs. Our data, based on the 50 Drosophila phenotypes, 44 of which are strongly deleterious, suggests a disproportionately larger contribution of SVs to deleterious changes in visible phenotypes in Drosophila .},
}

@article {pmid40894719,
year = {2025},
author = {De Santiago, A and Barnes, S and Pereira, TJ and Marcellino-Barros, M and Durden, L and Han, MK and Thrash, JC and Bik, HM},
title = {Pseudoalteromonas is a novel symbiont of marine invertebrates that exhibits broad patterns of phylosymbiosis.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.1101/2025.08.22.671635},
pmid = {40894719},
issn = {2692-8205},
abstract = {Despite growing insights into the composition of marine invertebrate microbiomes, our understanding of their ecological and evolutionary patterns remains poor, owing to limited sampling depth and low-resolution datasets. Previous studies have provided mixed results when evaluating patterns of phylosymbiosis between marine invertebrates and marine bacteria. Here, we investigated potential animal-microbe symbioses in Pseudoalteromonas, an overlooked bacterial genus consistently identified as a core microbiome taxon in diverse invertebrates. Using a pangenomic analysis of 236 free-living and invertebrate-associated bacterial strains (including two new nematode-associated isolates generated in this study), we confirm that Pseudoalteromonas is a novel symbiont with substantial evidence of phylosymbiosis across at least three marine invertebrate phyla (e.g., Nematoda, Mollusca, and Cnidaria). Patterns of symbiosis were consistent irrespective of geography (including in Antarctica), with FISH images from nematodes indicating that bacterial symbionts form biofilms in the mouth and esophagus. The evolutionary history of Pseudoalteromonas is marked by substantial host-switching and lifestyle transitions, and host-associated genomes suggest that these bacteria are facultative symbionts involved in nutritional mutualisms. In marine environments, we hypothesize that horizontally-acquired symbionts may have co-evolved with invertebrates, using host mucus as a physical niche and food source, while providing their animal hosts with Vitamin B, amino acids, and bioavailable carbon compounds in return.},
}

@article {pmid40890415,
year = {2025},
author = {Laidoudi, Y and Davoust, B and Lepidi, H and Levasseur, A},
title = {Emergence of the zoonotic bacterium Necropsobacter rosorum in nutria Myocastor coypus with implications for wildlife and human health.},
journal = {Scientific reports},
volume = {15},
number = {1},
pages = {32252},
pmid = {40890415},
issn = {2045-2322},
mesh = {Animals ; Humans ; Phylogeny ; Genome, Bacterial ; France/epidemiology ; *Pasteurellaceae/genetics/isolation & purification/classification/pathogenicity ; Animals, Wild/microbiology ; *Zoonoses/microbiology ; Whole Genome Sequencing ; *Rodentia/microbiology ; *Bacterial Zoonoses/microbiology/epidemiology ; },
abstract = {The nutria (Myocastor coypus), a semi-aquatic rodent native to South America, poses significant ecological and agricultural threats as an invasive species in France, where it continues to proliferate despite sustained control efforts. A fatal case of pneumonia in a nutria from Marseille (France) prompted a microbiological investigation that led to the isolation, taxonomic classification, genomic characterization, and phylogenetic analysis of Necropsobacter rosorum. Whole-genome sequencing of the N. rosorum strain RG01 revealed a genome size of 2,505,657 base pairs and 2303 predicted open reading frames, showing high similarity to other publicly available N. rosorum genomes. Comparative pan-genomic analysis indicated a high level of genomic conservation among N. rosorum strains. The presence of putative virulence factors and a CRISPR-Cas system suggests both pathogenic potential and adaptive defense mechanisms against bacteriophage predation. This study also explored the genetic epidemiology of members of the Pasteurellaceae family, highlighting a considerable overlap between species infecting animals and humans. Among the 408,387 sequence records retrieved from GenBank, 62.1% were deemed suitable for genomic epidemiological analysis. Notably, N. rosorum was underrepresented, with only 13 entries spanning nine countries and three host types, revealing critical gaps in current surveillance and research. Collectively, these findings contribute to a better understanding of the microbiology and epidemiology of N. rosorum and Pasteurellaceae-associated infections, and underscore the importance of integrated, genomics-informed approaches for the monitoring, control, and prevention of zoonotic diseases.},
}

Animals
Humans
Phylogeny
Genome, Bacterial
France/epidemiology
*Pasteurellaceae/genetics/isolation & purification/classification/pathogenicity
Animals, Wild/microbiology
*Zoonoses/microbiology
Whole Genome Sequencing
*Rodentia/microbiology
*Bacterial Zoonoses/microbiology/epidemiology

@article {pmid40888908,
year = {2025},
author = {Vuong, TD and He, G and Hu, H and Valliyodan, B and Lee, D and Bayer, PE and Schapaugh, WT and Hessel, R and Edwards, D and Nguyen, HT},
title = {Identification of new genomic loci for seed protein and oil content in the soybean pangenome using genome-wide association and haplotype analyses.},
journal = {TAG. Theoretical and applied genetics. Theoretische und angewandte Genetik},
volume = {138},
number = {9},
pages = {237},
pmid = {40888908},
issn = {1432-2242},
support = {2120-152-0114//United Soybean Board/ ; DP200100762//Australian Research Council/ ; DP210100296//Australian Research Council/ ; },
mesh = {*Glycine max/genetics/metabolism ; *Haplotypes ; *Quantitative Trait Loci ; Polymorphism, Single Nucleotide ; Genome-Wide Association Study ; *Seeds/genetics/chemistry ; Chromosome Mapping ; Phenotype ; *Plant Proteins/genetics ; Genetic Markers ; *Genome, Plant ; *Plant Oils ; },
abstract = {The soybean [Glycine max (L.) Merr.] pangenome has been studied and shown to be an invaluable resource for investigating structural variations (SVs), from which different genomic markers were successfully developed and employed for genome-wide association studies (GWAS). Among the SVs markers, gene presence-and-absence variations (PAVs) have been developed in soybean, but have not been widely utilized for association analyses. Here, we reported GWAS and haplotype analysis of seed protein and oil content for two diverse panels, comprised over 500 soybean accessions evaluated in multiple field environments using three marker datasets, whole genome sequence (WGS)-single-nucleotide polymorphisms (SNPs), 50 K-SNPs, and PAVs. The analyses identified new quantitative trait loci (QTL) for protein and oil content, along with the validation of previously reported QTL for these traits. This includes a well-studied QTL on chromosome (Chr.) 20 and another one on Chr. 05 for protein and/or oil. Importantly, this study is the first to report a new genomic locus for both protein and oil mapped to Chr. 08. Gene ontology annotations and expression profiles suggested candidate genes. Further analyses using haplotype-based markers led to the identification of multiple haplotype blocks encompassing candidate genes. Among these, Glyma.05G243400 on Chr. 05 and Glyma.08G109900 and Glyma.08G110000 on Chr. 08 were identified as promising targets. These genes can be incorporated into soybean breeding programs to enhance the selection of desirable protein and oil phenotypes through a haplotype-based breeding approach.},
}

*Glycine max/genetics/metabolism
*Haplotypes
*Quantitative Trait Loci
Polymorphism, Single Nucleotide
Genome-Wide Association Study
*Seeds/genetics/chemistry
Chromosome Mapping
Phenotype
*Plant Proteins/genetics
Genetic Markers
*Genome, Plant
*Plant Oils

@article {pmid40885195,
year = {2025},
author = {Grujcic, V and Mehrshad, M and Vigil-Stenman, T and Lundin, D and Foster, RA},
title = {Stepwise genome evolution from a facultative symbiont to an endosymbiont in the N2-fixing diatom-Richelia symbioses.},
journal = {Current biology : CB},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.cub.2025.08.003},
pmid = {40885195},
issn = {1879-0445},
abstract = {A few genera of diatoms that form stable partnerships with N2-fixing filamentous cyanobacteria Richelia spp. are widespread in the open ocean. A unique feature of the diatom-Richelia symbioses is the symbiont cellular location spans a continuum of integration (epibiont, periplasmic, and endobiont) that is reflected in the symbiont genome size and content. In this study, we analyzed genomes derived from cultures and environmental metagenome-assembled genomes of Richelia symbionts, focusing on characters indicative of genome evolution. Our results show an enrichment of short-length transposases and pseudogenes in the periplasmic symbiont genomes, suggesting an active and transitionary period in genome evolution. By contrast, genomes of endobionts exhibited fewer transposases and pseudogenes, reflecting advanced stages of genome reduction. Pangenome analyses identified that endobionts streamline their genomes and retain most genes in the core genome, whereas periplasmic symbionts and epibionts maintain larger flexible genomes, indicating higher genomic plasticity compared with the genomes of endobionts. Functional gene comparisons with other N2-fixing cyanobacteria revealed that Richelia endobionts have similar patterns of metabolic loss but are distinguished by the absence of specific pathways (e.g., cytochrome bd ubiquinol oxidase and lipid A) that increase both dependency and direct interactions with their respective hosts. In conclusion, our findings underscore the dynamic nature of genome reduction in N2-fixing cyanobacterial symbionts and demonstrate the diatom-Richelia symbioses as a valuable and rare model to study genome evolution in the transitional stages from a free-living facultative symbiont to a host-dependent endobiont.},
}

@article {pmid40884803,
year = {2025},
author = {Arshad, F and Jayaraman, S and Talenti, A and Owen, R and Mohsin, M and Mansoor, S and Asif, M and Prendergast, J},
title = {A comprehensive water buffalo pangenome reveals extensive structural variation linked to population-specific signatures of selection.},
journal = {GigaScience},
volume = {14},
number = {},
pages = {},
doi = {10.1093/gigascience/giaf099},
pmid = {40884803},
issn = {2047-217X},
support = {//Commonwealth Scholarship Commission/ ; BB/T019468/1/BB_/Biotechnology and Biological Sciences Research Council/United Kingdom ; BBS/E/RL/230001A/BB_/Biotechnology and Biological Sciences Research Council/United Kingdom ; },
mesh = {Animals ; *Buffaloes/genetics ; *Genome ; *Genomics/methods ; *Selection, Genetic ; *Genetic Variation ; Genetics, Population ; },
abstract = {BACKGROUND: Water buffalo is a cornerstone livestock species in many low- and middle-income countries, yet major gaps persist in its genomic characterization-complicated by the divergent karyotypes of its two subspecies (swamp and river). Such genomic complexity makes water buffalo a particularly good candidate for the use of graph genomics, which can capture variation missed by linear reference approaches. However, the utility of this approach to improve water buffalo has been largely unexplored.

RESULTS: We present a comprehensive pangenome that integrates 4 newly generated, highly contiguous assemblies of Pakistani river buffalo with 8 publicly available assemblies from both subspecies. This doubles the number of accessible high-quality river buffalo genomes and provides the most contiguous assemblies for the subspecies to date. Using the pangenome to assay variation across 711 global samples, we uncovered extensive genomic diversity, including thousands of large structural variants absent from the reference genome, spanning over 140 Mb of additional sequence. We demonstrate the utility of these data by identifying putative functional indels and structural variants linked to selective sweeps in key genes involved in productivity and immune response across 26 populations.

CONCLUSIONS: This study represents one of the first successful applications of graph genomics in water buffalo and offers valuable insights into how integrating assemblies can transform analyses of water buffalo and other species with complex evolutionary histories. We anticipate that these assemblies, as well as the pangenome and putative functional structural variants we have released, will accelerate efforts to unlock water buffalo's genetic potential, improving productivity and resilience in this economically important species.},
}

Animals
*Buffaloes/genetics
*Genome
*Genomics/methods
*Selection, Genetic
*Genetic Variation
Genetics, Population

@article {pmid40884642,
year = {2025},
author = {Lindstrand, A and Eisfeldt, J},
title = {Hybrid Sequencing Characterization of Complex Chromosomal Rearrangements.},
journal = {Methods in molecular biology (Clifton, N.J.)},
volume = {2968},
number = {},
pages = {151-159},
pmid = {40884642},
issn = {1940-6029},
mesh = {Humans ; *High-Throughput Nucleotide Sequencing/methods ; *Chromosome Aberrations ; *Gene Rearrangement ; *Whole Genome Sequencing/methods ; *Sequence Analysis, DNA/methods ; Genome, Human ; Chromosome Breakpoints ; },
abstract = {Complex chromosomal rearrangements (CCRs), defined as structural variants involving more than two chromosomes or multiple breakpoint junctions, are challenging to resolve, and causal mutations often go unnoticed in genome studies. Short-read whole-genome sequencing enables the characterization of rearrangement junctions in unique sequences. However, issues persist within repetitive regions of the genome, which are prone to rearrangements. Therefore, complementary genome sequencing technologies may be required to solve the structures of CCRs.Hybrid sequencing, which combines multiple genome sequencing datasets from the same individual, results in a more complete representation of the genome. This approach enhances the ability to resolve rearrangement structures and map breakpoint junctions more accurately.},
}

Humans
*High-Throughput Nucleotide Sequencing/methods
*Chromosome Aberrations
*Gene Rearrangement
*Whole Genome Sequencing/methods
*Sequence Analysis, DNA/methods
Genome, Human
Chromosome Breakpoints

@article {pmid40883985,
year = {2025},
author = {Lian, Q and Jiao, WB and Wang, Y},
title = {Designing Better Crops with Phased Pangenomes.},
journal = {Molecular plant},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.molp.2025.08.014},
pmid = {40883985},
issn = {1752-9867},
}

@article {pmid40878745,
year = {2025},
author = {Li, W and Liang, H and Sun, J and Zhang, X and He, Q and Zhou, P and Huo, D},
title = {A Near Telomere-To-Telomere Genome Assembly and Graph-Based Pangenome of Tartary Buckwheat (Fagopyrum tataricum).},
journal = {Plant biotechnology journal},
volume = {},
number = {},
pages = {},
doi = {10.1111/pbi.70333},
pmid = {40878745},
issn = {1467-7652},
support = {2023ZD04076//Biological Breeding-National Science and Technology Major Project/ ; TYSGJ202201//Critical Talent Workstation Project/ ; 202203021222244//Basic Research Program of Shanxi Province/ ; },
}

@article {pmid40877448,
year = {2025},
author = {Cheng, L and Bao, Z and Kong, Q and Lassois, L and Stein, N and Huang, S and Zhou, Q},
title = {Genome analyses and breeding of polyploid crops.},
journal = {Nature plants},
volume = {},
number = {},
pages = {},
pmid = {40877448},
issn = {2055-0278},
abstract = {Polyploidization is a common and important evolutionary process in the plant kingdom. Compared with diploid plant species, the intricate genome architecture of polyploid plant species presents substantial challenges in applying multi-omics approaches for crop breeding improvement. In this Review, we summarize the current techniques for analysing polyploid genomes, including constructing reference genomes and pan-genomes, and detecting variants. We also assess findings related to polyploid genome architecture, population genetics and breeding programmes, highlighting advanced techniques in the breeding of polyploid crops. Finally, we explore the challenges and demands posed by polyploid genome complexity during analysis with available biotechnological tools. This Review emphasizes the importance of a comprehensive understanding of polyploid genomic features for the further genetic improvement of polyploid crops.},
}

@article {pmid40875526,
year = {2025},
author = {Guo, L and He, Z and Huo, H},
title = {Panaln: Indexing pangenome for read alignment.},
journal = {Bioinformatics (Oxford, England)},
volume = {},
number = {},
pages = {},
doi = {10.1093/bioinformatics/btaf476},
pmid = {40875526},
issn = {1367-4811},
abstract = {MOTIVATION: Pangenome indexing is a critical supporting technology in biological sequence analysis such as read alignment applications. The need to accurately identify billions of small sequencing fragments carrying sequencing errors and genomic variants drives the development of scalable and efficient pangenome indexing approach.

RESULTS: We propose a new wavelet tree-based approach, called Panaln, for indexing pangenome and introduce a batch computation approach for fast count query over Panaln. We present a simple and effective seeding strategy and develop a pangenome program that uses the seed-and-extend paradigm for read alignment. Experimental results on simulated and real data demonstrate that Panaln uses significantly less space for the compared pangenome methods with generally higher accuracy. We provide a scalable index construction by representing pangenome with a linear model. Additionally, Panaln brings enhanced accuracy compared to the popular single reference methods.

Package: https://anaconda.org/bioconda/panaln and source code: https://github.com/Lilu-guo/Panaln.

SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.},
}

@article {pmid40872695,
year = {2025},
author = {Skarlatoudi, T and Anagnostou, GM and Theodorakis, V and Bosnea, L and Mataragas, M},
title = {Escherichia coli Strains Originating from Raw Sheep Milk, with Special Reference to Their Genomic Characterization, Such as Virulence Factors (VFs) and Antimicrobial Resistance (AMR) Genes, Using Whole-Genome Sequencing (WGS).},
journal = {Veterinary sciences},
volume = {12},
number = {8},
pages = {},
doi = {10.3390/vetsci12080744},
pmid = {40872695},
issn = {2306-7381},
support = {M16SYN2-00164//European Regional Development Fund, Ministry of Rural Development and Food, ESPA 2014-2020, RDP 2014-2022/ ; },
abstract = {The objective of this work was to deliver a comprehensive genetic characterization of a collection of E. coli strains isolated from raw sheep milk. To complete our purpose, the technique of whole-genome sequencing, coupled with bioinformatics and phenotypic characterization of antimicrobial resistance, was performed. These Gram-negative, facultative anaerobic bacteria belong to the family Enterobacteriaceae, together with other intestinal pathogens, such as Shigella spp. and Salmonella spp. Genetic analysis was carried out on all strains (phylogram, sequence types, VFs, AMR genes, and pangenome). The results showed the presence of various genetic traits that are related to virulence factors contributing to their pathogenic potential. In addition, genes conferring resistance to antibiotics were also detected and confirmed using phenotypic tests. Finally, the genome of the E. coli strains was characterized by the presence of several mobile genetic elements, thus facilitating the exchange of various genetic elements, associated with virulence and antimicrobial resistance, within and beyond the species, through horizontal gene transfer. Contaminated raw sheep milk with pathogenic E. coli strains is particularly alarming for cheese production in artisan dairies.},
}

@article {pmid40872298,
year = {2025},
author = {Campos-Godínez, JF and Villegas-Campos, M and Molina-Mora, JA},
title = {Core Perturbomes of Escherichia coli and Staphylococcus aureus Using a Machine Learning Approach.},
journal = {Pathogens (Basel, Switzerland)},
volume = {14},
number = {8},
pages = {},
doi = {10.3390/pathogens14080788},
pmid = {40872298},
issn = {2076-0817},
support = {C1163, C4604 and C5027//Universidad de Costa Rica/ ; },
mesh = {*Staphylococcus aureus/genetics/metabolism ; *Escherichia coli/genetics/metabolism ; *Machine Learning ; Gene Expression Regulation, Bacterial ; Gene Expression Profiling ; Gene Regulatory Networks ; },
abstract = {The core perturbome is defined as a central response to multiple disturbances, functioning as a complex molecular network to overcome the disruption of homeostasis under stress conditions, thereby promoting tolerance and survival under stress conditions. Based on the biological and clinical relevance of Escherichia coli and Staphylococcus aureus, we characterized their molecular responses to multiple perturbations. Gene expression data from E. coli (8815 target genes-based on a pangenome-across 132 samples) and S. aureus (3312 target genes across 156 samples) were used. Accordingly, this study aimed to identify and describe the functionality of the core perturbome of these two prokaryotic models using a machine learning approach. For this purpose, feature selection and classification algorithms (KNN, RF and SVM) were implemented to identify a subset of genes as core molecular signatures, distinguishing control and perturbation conditions. After verifying effective dimensional reduction (with median accuracies of 82.6% and 85.1% for E. coli and S. aureus, respectively), a model of molecular interactions and functional enrichment analyses was performed to characterize the selected genes. The core perturbome was composed of 55 genes (including nine hubs) for E. coli and 46 (eight hubs) for S. aureus. Well-defined interactomes were predicted for each model, which are jointly associated with enriched pathways, including energy and macromolecule metabolism, DNA/RNA and protein synthesis and degradation, transcription regulation, virulence factors, and other signaling processes. Taken together, these results may support the identification of potential therapeutic targets and biomarkers of stress responses in future studies.},
}

*Staphylococcus aureus/genetics/metabolism
*Escherichia coli/genetics/metabolism
*Machine Learning
Gene Expression Regulation, Bacterial
Gene Expression Profiling
Gene Regulatory Networks

@article {pmid40872164,
year = {2025},
author = {Han, X and Qiu, C and Gai, Z and Zhai, J and Song, J and Sun, J and Li, Z},
title = {Pan-Genome-Based Characterization of the PYL Transcription Factor Family in Populus.},
journal = {Plants (Basel, Switzerland)},
volume = {14},
number = {16},
pages = {},
doi = {10.3390/plants14162541},
pmid = {40872164},
issn = {2223-7747},
abstract = {Abscisic acid (ABA) is a key phytohormone involved in regulating plant growth and responses to environmental stress. As receptors of ABA, pyrabactin resistance 1 (PYR)/PYR1-like (PYL) proteins play a central role in initiating ABA signal transduction. In this study, a total of 30 PopPYL genes were identified and classified into three sub-families (PYL I-III) in the pan-genome of 17 Populus species, through phylogenetic analysis. Among these subfamilies, the PYL I subfamily was the largest, comprising 21 members, whereas PYL III was the smallest, with only four members. To elucidate the evolutionary dynamics of these genes, we conducted synteny and Ka/Ks analyses. Results indicated that most PopPYL genes had undergone purifying selection (Ka/Ks < 1), while a few were subject to positive selection (Ka/Ks > 1). Promoter analysis revealed 258 cis-regulatory elements in the PYL genes of Populus euphratica (EUP) and Populus pruinosa (PRU), including 127 elements responsive to abiotic stress and 33 ABA-related elements. Furthermore, six structural variations (SVs) were detected in PYL_EUP genes and significantly influenced gene expression levels (p < 0.05). To further explore the functional roles of PYL genes, we analyzed tissue-specific expression profiles of 17 PYL_EUP genes under drought stress conditions. PYL6_EUP was predominantly expressed in roots, PYL17_EUP exhibited leaf-specific expression, and PYL1_EUP showed elevated expression in stems. These findings suggest that the drought response of PYL_EUP genes is tissue-specific. Overall, this study highlights the utility of pan-genomics in elucidating gene family evolution and suggests that PYL_EUP genes contribute to the regulation of drought stress responses in EUP, offering valuable genetic resources for functional characterization of PYL genes.},
}

@article {pmid40872081,
year = {2025},
author = {Goche, T and Mavindidze, P and Zenda, T},
title = {Advances in Functional Genomics for Exploring Abiotic Stress Tolerance Mechanisms in Cereals.},
journal = {Plants (Basel, Switzerland)},
volume = {14},
number = {16},
pages = {},
doi = {10.3390/plants14162459},
pmid = {40872081},
issn = {2223-7747},
abstract = {Climate change, population growth and the increasing demand for food and nutritional security necessitate the development of climate-resilient cereal crops. This requires first gaining mechanistic insights into the molecular mechanisms underpinning plant abiotic and biotic stress tolerance. Although this is challenging, recent conceptual and technological advances in functional genomics, coupled with computational biology, high-throughput plant phenotyping and artificial intelligence, are now aiding our uncovering of the molecular mechanisms underlying plant stress tolerance. Integrating other innovative approaches such as genome editing, modern plant breeding and synthetic biology facilitates the development of climate-smart cereal crops. Here, we discuss major recent advances in plant functional genomic approaches and techniques such as third-generation sequencing, transcriptomics, pangenomes, genome-wide association studies and epigenomics, which have advanced our understanding of the molecular basis of stress tolerance and development of stress-resilient cereals. Further, we highlight how these genomics approaches are successfully integrated into new plant breeding methods for effective development of stress-tolerant crops. Overall, harnessing these advances and improved knowledge of crop stress tolerance could accelerate development of climate-resilient cereals for global food and nutrition security.},
}

@article {pmid40869928,
year = {2025},
author = {Nunes, NB and Castro, VS and da Cunha-Neto, A and Carvalho, FT and Carvalho, RCT and Figueiredo, EES},
title = {Integrated Whole-Genome Sequencing and In Silico Characterization of Salmonella Cerro and Schwarzengrund from Brazil.},
journal = {Genes},
volume = {16},
number = {8},
pages = {},
doi = {10.3390/genes16080880},
pmid = {40869928},
issn = {2073-4425},
support = {88887.828908/2023-00 and 88887.692875/2022-00//Fundação Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)/ ; 310181/2021-6//Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)/Brazil/ ; },
mesh = {Brazil ; Whole Genome Sequencing/methods ; *Salmonella/genetics/pathogenicity/isolation & purification/classification/drug effects ; Phylogeny ; *Genome, Bacterial ; Virulence Factors/genetics ; Animals ; Plasmids/genetics ; Cheese/microbiology ; Cattle ; Computer Simulation ; Drug Resistance, Bacterial/genetics ; Anti-Bacterial Agents/pharmacology ; },
abstract = {BACKGROUND: Salmonella is a bacterium that causes foodborne infections. This study characterized two strains isolated from cheese and beef in Brazil using whole-genome sequencing (WGS).

OBJECTIVES: We evaluated their antimicrobial resistance profiles, virulence factors, plasmid content, serotypes and phylogenetic relationships.

METHODS: DNA was extracted and sequenced on the NovaSeq 6000 platform; the pangenome was assembled using the Roary tool; and the phylogenetic tree was constructed via IQ-TREE.

RESULTS AND DISCUSSION: For contextualization and comparison, 3493 Salmonella genomes of Brazilian origin from NCBI were analyzed. In our isolates, both strains carried the aac(6')-Iaa_1 gene, while only Schwarzengrund harbored the qnrB19_1 gene and the Col440I_1 plasmid. Cerro presented the islands SPI-1, SPI-2, SPI-3, SPI-4, SPI-5 and SPI-9, while Schwarzengrund also possessed SPI-13 and SPI-14. Upon comparison with other Brazilian genomes, we observed that Cerro and Schwarzengrund represented only 0.40% and 2.03% of the national database, respectively. Furthermore, they revealed that Schwarzengrund presented higher levels of antimicrobial resistance, a finding supported by the higher frequency of plasmids in this serovar. Furthermore, national data corroborated our findings that SPI-13 and SPI-14 were absent in Cerro. A virulence analysis revealed distinct profiles: the cdtB and pltABC genes were present in the Schwarzengrund isolates, while the sseK and tldE1 family genes were exclusive to Cerro. The results indicated that the sequenced strains have pathogenic potential but exhibit low levels of antimicrobial resistance compared to national data. The greater diversity of SPIs in Schwarzengrund explains their prevalence and higher virulence potential.

CONCLUSIONS: Finally, the serovars exhibit distinct virulence profiles, which results in different clinical outcomes.},
}

Brazil
Whole Genome Sequencing/methods
*Salmonella/genetics/pathogenicity/isolation & purification/classification/drug effects
Phylogeny
*Genome, Bacterial
Virulence Factors/genetics
Animals
Plasmids/genetics
Cheese/microbiology
Cattle
Computer Simulation
Drug Resistance, Bacterial/genetics
Anti-Bacterial Agents/pharmacology

@article {pmid40867941,
year = {2025},
author = {Yinsai, O and Yuantrakul, S and Srisithan, P and Zhou, W and Chittaprapan, S and Intajak, N and Kruayoo, T and Khamnoi, P and Tongjai, S and Daungsonk, K},
title = {Genomic Insights into Emerging Multidrug-Resistant Chryseobacterium indologenes Strains: First Report from Thailand.},
journal = {Antibiotics (Basel, Switzerland)},
volume = {14},
number = {8},
pages = {},
doi = {10.3390/antibiotics14080746},
pmid = {40867941},
issn = {2079-6382},
support = {HSRI 64-145 and HSRI 66-147//Health Systems Research Institute (HSRI), Thailand/ ; },
abstract = {Background: Chryseobacterium indologenes, an environmental bacterium, is increasingly recognized as an emerging nosocomial pathogen, particularly in Asia, and is often characterized by multidrug resistance. Objectives: This study aimed to investigate the genomic features of clinical C. indologenes isolates from Maharaj Nakorn Chiang Mai Hospital, Thailand, to understand their mechanisms of multidrug resistance, virulence factors, and mobile genetic elements (MGEs). Methods: Twelve C. indologenes isolates were identified, and their antibiotic susceptibility profiles were determined. Whole genome sequencing (WGS) was performed using a hybrid approach combining Illumina short-reads and Oxford Nanopore long-reads to generate complete bacterial genomes. The hybrid assembled genomes were subsequently analyzed to detect antimicrobial resistance (AMR) genes, virulence factors, and MGEs. Results: C. indologenes isolates were primarily recovered from urine samples of hospitalized elderly male patients with underlying conditions. These isolates generally exhibited extensive drug resistance, which was subsequently explored and correlated with genomic determinants. With one exception, CMCI13 showed a lower resistance profile (Multidrug resistance, MDR). Genomic analysis revealed isolates with genome sizes of 4.83-5.00 Mb and GC content of 37.15-37.35%. Genomic characterization identified conserved resistance genes (blaIND-2, blaCIA-4, adeF, vanT, and qacG) and various virulence factors. Phylogenetic and pangenome analysis showed 11 isolates clustering closely with Chinese strain 3125, while one isolate (CMCI13) formed a distinct branch. Importantly, each isolate, except CMCI13, harbored a large genomic island (approximately 94-100 kb) carrying significant resistance genes (blaOXA-347, tetX, aadS, and ermF). The absence of this genomic island in CMCI13 correlated with its less resistant phenotype. No plasmids, integrons, or CRISPR-Cas systems were detected in any isolate. Conclusions: This study highlights the alarming emergence of multidrug-resistant C. indologenes in a hospital setting in Thailand. The genomic insights into specific resistance mechanisms, virulence factors, and potential horizontal gene transfer (HGT) events, particularly the association of a large genomic island with the XDR phenotype, underscore the critical need for continuous genomic surveillance to monitor transmission patterns and develop effective treatment strategies for this emerging pathogen.},
}

@article {pmid40864264,
year = {2025},
author = {Pozzi, CM and Gaiti, A and Spada, A},
title = {Climate change and plant genomic plasticity.},
journal = {TAG. Theoretical and applied genetics. Theoretische und angewandte Genetik},
volume = {138},
number = {9},
pages = {231},
pmid = {40864264},
issn = {1432-2242},
mesh = {*Climate Change ; *Genome, Plant ; *Plants/genetics ; Quantitative Trait Loci ; DNA Transposable Elements ; *Adaptation, Physiological/genetics ; Genetic Variation ; Genomic Instability ; Evolution, Molecular ; },
abstract = {Genome adaptation, driven by mutations, transposable elements, and structural variations, relies on plasticity and instability. This allows populations to evolve, enhance fitness, and adapt to challenges like climate change. Genomes adapt via mutations, transposable elements, DNA structural changes, and epigenetics. Genome plasticity enhances fitness by providing the genetic variation necessary for organisms to adapt their traits and survive, which is especially critical during rapid climate shifts. This plasticity often stems from genome instability, which facilitates significant genomic alterations like duplications or deletions. While potentially harmful initially, these changes increase genetic diversity, aiding adaptation. Major genome reorganizations arise from polyploidization and horizontal gene transfer, both linked to instability. Plasticity and restructuring can modify Quantitative Trait Loci (QTLs), contributing to adaptation. Tools like landscape genomics identify climate-selected regions, resurrection ecology reveals past adaptive responses, and pangenome analysis examines a species' complete gene set. Signatures of past selection include reduced diversity and allele frequency shifts. Gene expression plasticity allows environmental adaptation without genetic change through mechanisms like alternative splicing, tailoring protein function. Co-opted transposable elements also generate genetic and regulatory diversity, contributing to genome evolution. This review consolidates these findings, repositioning genome instability not as a mere source of random error but as a fundamental evolutionary engine that provides the rapid adaptive potential required for plant survival in the face of accelerating climate change.},
}

*Climate Change
*Genome, Plant
*Plants/genetics
Quantitative Trait Loci
DNA Transposable Elements
*Adaptation, Physiological/genetics
Genetic Variation
Genomic Instability
Evolution, Molecular

@article {pmid40863502,
year = {2025},
author = {Popov, IV and Todorov, SD and Chikindas, ML and Venema, K and Ermakov, AM and Popov, IV},
title = {Beyond White-Nose Syndrome: Mitochondrial and Functional Genomics of Pseudogymnoascus destructans.},
journal = {Journal of fungi (Basel, Switzerland)},
volume = {11},
number = {8},
pages = {},
pmid = {40863502},
issn = {2309-608X},
support = {25-24-00351//Russian Science Foundation/ ; },
abstract = {White-Nose Syndrome (WNS) has devastated insectivorous bat populations, particularly in North America, leading to severe ecological and economic consequences. Despite extensive research, many aspects of the evolutionary history, mitochondrial genome organization, and metabolic adaptations of its etiological agent, Pseudogymnoascus destructans, remain unexplored. Here, we present a multi-scale genomic analysis integrating pangenome reconstruction, phylogenetic inference, Bayesian divergence dating, comparative mitochondrial genomics, and refined functional annotation. Our divergence dating analysis reveals that P. destructans separated from its Antarctic relatives approximately 141 million years ago, before adapting to bat hibernacula in the Northern Hemisphere. Additionally, our refined functional annotation significantly expands the known functional landscape of P. destructans, revealing an extensive repertoire of previously uncharacterized proteins involved in carbohydrate metabolism and secondary metabolite biosynthesis-key processes that likely contribute to its pathogenic success. By providing new insights into the genomic basis of P. destructans adaptation and pathogenicity, our study refines the evolutionary framework of this fungal pathogen and creates the foundation for future research on WNS mitigation strategies.},
}

@article {pmid40859707,
year = {2025},
author = {Zhu, Z and Stein, N},
title = {Pangenome insights into structural variation and functional diversification of barley CCT motif genes.},
journal = {The plant genome},
volume = {18},
number = {3},
pages = {e70098},
doi = {10.1002/tpg2.70098},
pmid = {40859707},
issn = {1940-3372},
support = {FKZ 031B1224//German Ministry of Education and Research (BMBF)/ ; },
mesh = {*Hordeum/genetics ; *Plant Proteins/genetics/metabolism ; Phylogeny ; *Genome, Plant ; Gene Expression Regulation, Plant ; Genetic Variation ; Genes, Plant ; },
abstract = {CONSTANS, CONSTANS-LIKE, TIMING OF CAB EXPRESSION1 (CCT) motif genes play a key role in barley (Hordeum vulgare L.) development and flowering, yet their genetic diversity remains underexplored. Leveraging a barley pangenome (76 genotypes) and pan-transcriptome (subset of 20 genotypes), we examined CCT gene variation and evolutionary dynamics. Motif-based searches, combined with genome assembly validation, revealed annotation limitations and novel frameshift variants (e.g., HvCO10, where Hv is Hordeum vulgare L.), indicating active diversification. Pangenome-wide phylogenetic analysis identified clade-specific domain expansions, including B-box domain additions in HvCO clades. Tissue-specific expression patterns further supported functional divergence among paralogs. Notably, VRN2, a canonical floral repressor associated with winter growth, was retained in spring genotypes, challenging its presumed exclusive role in vernalization. Discrepancies between VRN1 expression, VRN2 deletion, and growth habit implicated additional regulatory mechanisms. These findings highlight the power of pangenomes in resolving gene family complexity, refining annotations, and advancing the understanding of CCT genes to enhance barley resilience and adaptability.},
}

*Hordeum/genetics
*Plant Proteins/genetics/metabolism
Phylogeny
*Genome, Plant
Gene Expression Regulation, Plant
Genetic Variation
Genes, Plant

@article {pmid40859252,
year = {2025},
author = {Kileeg, Z and Mott, GA},
title = {A species-wide inventory of receptor-like kinases in Arabidopsis thaliana.},
journal = {BMC biology},
volume = {23},
number = {1},
pages = {266},
doi = {10.1186/s12915-025-02364-y},
pmid = {40859252},
issn = {1741-7007},
support = {RGPIN-2019-06395//Natural Sciences and Engineering Research Council of Canada/ ; },
abstract = {BACKGROUND: The receptor-like kinases (RLKs) are the largest family of proteins in plants. Characterized members play critical roles in diverse processes from growth to immunity, and yet the majority do not have a known function. Assigning function to RLKs poses a significant challenge due to the specificity of ligand recognition and because of the often pleiotropic or redundant functions RLKs possess. These problems inhibit the important work of identifying stress-related receptors that may be targets for crop improvement. Identification of stress-related evolutionary signatures can provide a way to expedite the discovery of candidate receptors. Pan-genome analysis can be used to compare naturally occurring variants within a species to identify evolutionary signatures that may otherwise be hidden by using only a single ecotype.

RESULTS: Using 146 ecotypes of Arabidopsis, we generated a pan-RLKome to investigate species-wide natural diversity and identify structural variation and other patterns indicative of stress adaptation. We discovered significant presence/absence variation across a subset of RLKs, most of which occurred in specific subclades nested within receptor subfamilies. These same subclades tended to have arisen through proximal or tandem duplication, both of which are common mechanisms during the expansion of stress-related genes. We also identified strong positive selection across many gene subfamilies and a bias of positive selection in the extracellular domains of receptors. This suggests escape from adaptive conflict within the extracellular domain may have played a large role in the evolution and adaptation of the RLKs.

CONCLUSION: Taken together, this work represents an excellent tool for the comparative study of RLKs and has identified lineages and subclades within RLK subfamilies with the hallmarks of involvement in stress adaptation.},
}

@article {pmid40855470,
year = {2025},
author = {Maurizi, L and Musleh, L and Brunetti, F and Conte, AL and Riccioli, A and Sideri, S and Ammendolia, MG and Uccelletti, D and Schifano, E and De Angelis, M and Ianiro, G and Niro, A and Cutone, A and Conte, MP and Longhi, C},
title = {Uropathogenic Escherichia coli (UPEC) that hides its identity: features of LC2 and EC73 strains from recurrent urinary tract infections.},
journal = {BMC microbiology},
volume = {25},
number = {1},
pages = {547},
pmid = {40855470},
issn = {1471-2180},
support = {RM123188E89E940B//Ricerca Scientifica 2023 "Sapienza" University of Rome/ ; },
mesh = {*Uropathogenic Escherichia coli/genetics/isolation & purification/pathogenicity/classification ; *Urinary Tract Infections/microbiology ; Humans ; Animals ; *Escherichia coli Infections/microbiology ; Caenorhabditis elegans/microbiology ; Virulence ; Escherichia coli Proteins/genetics ; Virulence Factors/genetics ; Host-Pathogen Interactions ; Urinary Bladder/microbiology ; Recurrence ; Genome, Bacterial ; Cell Line ; },
abstract = {BACKGROUND: Uropathogenic Escherichia coli (UPEC) strains are the major causative agents of human urinary tract infections (UTIs). Many patients who develop UTIs will experience a recurrent UTI (RUTI) within 6 months despite antibiotic-mediated clearance of the initial infection. A significant proportion of RUTIs are caused by E. coli identical to the original strain. UPEC employs several strategies to adhere, colonize, and persist within the bladder niche. Knowledge about the mechanisms regulating specific host-pathogen interactions that promote bacterial persistence is necessary to develop new approaches to RUTI diagnosis and treatment.

RESULTS: LC2 and EC73 UPEC strains were collected from patients with RUTIs. E. coli CFT073 and K-12 MG1655 were used as reference strains. UPEC displayed phenotypic profiles like those of the general E. coli population. The pan-genome analysis revealed that LC2 harbored many unique genes encoding several different functions such as intracellular trafficking and secretion, and vesicular transport. Contrarily, EC73 was the strain with the lowest number of unique genes involved in replication, recombination, repair and cell wall/membrane/envelope biogenesis. LC2 and EC73 exhibited the capacity to invade bladder monolayers efficiently and to colonize the gut of Caenorhabditis elegans, with LC2 being significantly more virulent than EC73. T24 cells infected with EC73 and LC2 strains exhibited significantly increased mRNA levels of IL-6, IL-8, IL-1β and TNF-α. EC73 elicited the strongest cytokine response. Differently, no significant cytokine mRNA induction was detected in T24 cells infected with E. coli CFT073. LC2 and EC73 modulated the expression of proteins involved in reactive oxygen species (ROS) balance in infected cells, but to different extents.

CONCLUSION: The acquisition of virulence factors by horizontal transfer of accessory DNA, other than being the cause of transformation to pathogenic strains, is responsible for the genomic plasticity. Our findings suggest that a key role in RUTIs could be played by certain bacterial strains that may benefit from peculiar abilities to adapt and potentially develop reservoirs of persistence across different host environments.},
}

*Uropathogenic Escherichia coli/genetics/isolation & purification/pathogenicity/classification
*Urinary Tract Infections/microbiology
Humans
Animals
*Escherichia coli Infections/microbiology
Caenorhabditis elegans/microbiology
Virulence
Escherichia coli Proteins/genetics
Virulence Factors/genetics
Host-Pathogen Interactions
Urinary Bladder/microbiology
Recurrence
Genome, Bacterial
Cell Line

@article {pmid40854671,
year = {2025},
author = {Chaity, SC and Hosen, MA and Rahman, SR and Khan, MAS},
title = {Genomic characterization and comparative analysis of antibiotic resistance and virulence in Bangladeshi and global Klebsiella pneumoniae ST48 strains.},
journal = {Journal, genetic engineering & biotechnology},
volume = {23},
number = {3},
pages = {100557},
doi = {10.1016/j.jgeb.2025.100557},
pmid = {40854671},
issn = {2090-5920},
abstract = {Klebsiella pneumoniae is an opportunistic pathogen associated with nosocomial infections, known for its multidrug resistance (MDR) and biofilm-forming abilities. ST48 is a particularly concerning sequence type and an emerging international clone linked to global spread and MDR infections. This study examines the comprehensive genomic epidemiology of the local and global populations of K. pneumoniae ST48 strains using whole genomes sequence data. We performed phenotypic and genotypic characterization of a K. pneumoniae strain S3C and conducted molecular epidemiological analyses of local ST48 isolates in Bangladesh, followed by pan-genome and phylogenetic analyses of 397 global ST48 strains. The S3C strain was resistant to 17 out of 19 tested antibiotics and was a moderate biofilm former. Whole genome sequencing identified it as ST48 clonal type, with 13 acquired antibiotic resistance genes, 76 virulence-associated genes, and multiple mobile genetic elements. Comparative analysis of Bangladeshi ST48 strains indicated a high prevalence of MDR genes, particularly blaCTX-M-15, and a diverse array of virulence factors associated with biofilm formation, siderophore production, capsular biosynthesis and others. Pan-genome analysis of Bangladeshi ST48 strains revealed 8,030 genes, with 56.26% classified as core genes. In contrast, global ST48 strains had 16,307 genes, with 75.3% as accessory genes, highlighting extensive genomic plasticity. The phylogenetic analysis revealed that isolates from different regions clustered within the major clade, indicating the global dissemination of this sequence type. Our findings underscore the substantial genomic diversity and high resistance levels of K. pneumoniae ST48, emphasizing the need for targeted infection control measures and continuous surveillance.},
}

@article {pmid40854641,
year = {2025},
author = {Shahed, K and Chakma, A and Manjur, OHB and Islam, SI},
title = {Multiscale comparative pathogenomic analysis of Vibrio anguillarum linking serotype diversity, genomic plasticity and pathogenicity.},
journal = {Journal, genetic engineering & biotechnology},
volume = {23},
number = {3},
pages = {100522},
doi = {10.1016/j.jgeb.2025.100522},
pmid = {40854641},
issn = {2090-5920},
abstract = {Vibrio anguillarum is a major marine fish pathogen causing high mortality and potential zoonotic risks. Understanding its genomic diversity, virulence factors, and antibiotic resistance is crucial for aquaculture disease management. In this study, a comparative pan-genomic analysis of 16 V. anguillarum strains was conducted to examine core and accessory genome diversity, virulence factors, and antibiotic resistance mechanisms. The phylogenetic analysis was conducted using six core genes and SNPs to evaluate evolutionary relationships and pathogenic traits. The core genome contained 2,038 unique ORFs, while the accessory genome had 5,197 cloud genes, confirming an open pangenome. This study identified 118 pathogenic genomic islands, antibiotic resistance genes (tetracycline, quinolone, and carbapenem), and virulence factors, including type VI secretion system (T6SS) components and RTX toxins (hcp-2, vipB/mglB, rtxC). Core genes such as ftsI uncovered substantial evolutionary divergence among species, identifying more than 150 distinct SNPs. Phylogenetic analysis showed serotype-specific clustering, with O1 strains displaying genetic homogeneity, whereas O2 and O3 exhibited divergence, suggesting distinct evolutionary adaptations influencing pathogenicity and ecological interactions. These findings provide primary insights for developing molecular markers and targeted treatments for aquaculture pathogens.},
}

@article {pmid40852993,
year = {2025},
author = {Ryan, AP and Bergin, S and Scully, J and Zuniga-Soto, E and Hession, C and Barber, AE and Gómez-Molero, E and Bader, O and Morio, F and Zhai, B and Wolfe, KH and Butler, G},
title = {Small pangenome of Candida parapsilosis reflects overall low intraspecific diversity.},
journal = {mBio},
volume = {},
number = {},
pages = {e0132025},
doi = {10.1128/mbio.01320-25},
pmid = {40852993},
issn = {2150-7511},
abstract = {Candida parapsilosis is an opportunistic yeast pathogen that can cause life-threatening infections in immunocompromised humans. Whole-genome sequencing studies of the species have demonstrated remarkably low diversity, with strains typically differing by about 1.5 single nucleotide polymorphisms (SNPs) per 10 kb. However, SNP calling alone does not capture the full extent of genetic variation. Here, we define the pangenome of 372 C. parapsilosis isolates to determine variation in gene content. The pangenome consists of 5,859 genes, of which 48 are not found in the genome of the reference strain. This includes 5,791 core genes (present in ≥99.5% of isolates). Four genes, including the allantoin permease gene DAL4, were present in all isolates but were truncated in some strains. The truncated DAL4 was classified as a pseudogene in the reference strain CDC317. CRISPR-Cas9 gene editing showed that removing the early stop codon (producing the full-length Dal4 protein) is associated with improved use of allantoin as a sole nitrogen source. We find that the accessory genome of C. parapsilosis consists of 68 homologous clusters. This includes 38 previously annotated genes, 27 novel paralogs of previously annotated genes, and 3 uncharacterized open reading frames. Approximately one-third of the accessory genome (24/68 genes) is associated with gene fusions between tandem genes in the major facilitator superfamily. Additionally, we identified two highly divergent C. parapsilosis strains and found that, despite their increased phylogenetic distance (~30 SNPs per 10 kb), both strains have similar gene content to the other 372.IMPORTANCECandida parapsilosis is a human fungal pathogen listed in the high-priority group by the World Health Organization. It is an increasing cause of hospital-acquired and drug-resistant infections. Here, we studied the genetic diversity of 372 C. parapsilosis isolates, the largest genomic surveillance of this species to date. We show that there is relatively little genetic variation. However, we identified two more distantly related isolates from Germany, suggesting that even more sampling may yield more diversity. We find that the pangenome (the cumulative gene content of all isolates) is surprisingly small, compared to other fungal species. Many of the non-core genes are involved in transport. We also find that variations in gene content are associated with nitrogen metabolism, which may contribute to the virulence characteristics of this species.},
}

@article {pmid40851827,
year = {2025},
author = {Liu, X and Zhang, M and Su, J and Wu, L and Shen, M and Zhuang, Y and Wang, Q and Chen, G},
title = {The evolution, variation, and expression patterns under development and stress responses of the NAC gene family in the barley pan-genome.},
journal = {Frontiers in plant science},
volume = {16},
number = {},
pages = {1635416},
pmid = {40851827},
issn = {1664-462X},
abstract = {The NAC transcription factor family is pivotal in regulating plant development and stress responses, yet its diversity and evolutionary dynamics in barley (Hordeum vulgare) remain underexplored. In this study, we performed a comprehensive pan-genome analysis to identify and characterize the HvNACs across 20 barley accessions. A ranging from 127 to 149 HvNACs were identified in each genome, in which the Morex genome harbored the highest count. These HvNACs were classified into 201 orthogroups, further stratified into core (102), soft-core (18), shell (25), and lineage-specific (56) categories. Phylogenetic analysis delineated them into 12 subfamilies, of which the core genes have undergone strong purifying selection, by contrast, the shell and lineage-specific genes were under relaxed selection constraint, suggesting functional diversification in barley. Genomic variation, such as PAVs and CNVs, largely driven by TEs, highlighted the dynamic nature of NAC loci. Furthermore, transcriptome profiling of the HvNACs demonstrated diverse tissue expression patterns and different response characteristics under salt stress. These findings elucidate the evolutionary and functional dynamics of HvNACs, offering valuable insights for genetic improvement of breeding programs in barley as well as in other crops.},
}

@article {pmid40848949,
year = {2025},
author = {Jayachandiran, S and Suresh, R and Dhamodharan, R},
title = {Comparative and phylogenomic analysis of Chlamydia pneumoniae reveals unique carbohydrate active enzyme family (GT5) among respiratory isolates.},
journal = {Infection, genetics and evolution : journal of molecular epidemiology and evolutionary genetics in infectious diseases},
volume = {},
number = {},
pages = {105813},
doi = {10.1016/j.meegid.2025.105813},
pmid = {40848949},
issn = {1567-7257},
abstract = {Chlamydia pneumoniae is an obligatory intracellular pathogen found in human and animals. Understanding the genomic diversity is crucial for unravelling its pathogenic mechanisms and transmission dynamics. In this study, 14 complete genomes of C. pneumoniae strains were compared for functional diversity analysis. The koala isolate LPCoLN appears as a phylogenetically distinct showing the fewest accessory genes and the highest incorporation of unique or absent genes among the strains analyzed. Functional annotation indicates that certain metabolic pathways between the LPCoLN and the human respiratory strain AR39 were the same, which is most likely due to phage-associated elements present in AR39. The presence of the GT5 CAZyme family is significantly associated with strains of respiratory origin, suggesting a potential role in respiratory adaptation and pathogenic strategies including tissue colonization, immune evasion, and niche-specific persistence. The strong association between GT5 CAZymes and respiratory-origin strains highlights their potential as diagnostic markers and therapeutic targets.},
}

@article {pmid40848717,
year = {2025},
author = {Dishuck, PC and Munson, KM and Lewis, AP and Dougherty, ML and Underwood, JG and Harvey, WT and Hsieh, P and Pastinen, T and Eichler, EE},
title = {Structural variation, selection, and diversification of the NPIP gene family from the human pangenome.},
journal = {Cell genomics},
volume = {},
number = {},
pages = {100977},
doi = {10.1016/j.xgen.2025.100977},
pmid = {40848717},
issn = {2666-979X},
abstract = {The NPIP gene family is among the most positively selected gene families in humans/apes and drives independent duplication in primate lineages. These duplications promote genetic instability, leading to recurrent disease-associated microduplication and microdeletion syndromes. Despite its importance, little is known about its function or variation in humans, as short-read sequencing cannot distinguish high-identity duplications. Using long-read assemblies of 169 human haplotypes, we find extreme variation in the content and organization of NPIP loci. We identify fixed and polymorphic paralogs and observe ongoing positive selection. With long-read RNA sequencing (RNA-seq), we create paralog-specific gene models, the majority of which were not previously documented, and observe paralog-specific tissue specificity. This analysis of an exceptionally dynamic gene family provides candidates for future functional study.},
}

@article {pmid40847283,
year = {2025},
author = {Fouéré, C and Costes, V and Hozé, C and Raja Ravi Shankar, A and Besnard, F and Costa Monteiro Moreira, G and Sorin, V and Le Danvic, C and Chaulot-Talmon, A and Ali, F and Deloche, MC and Bonnet, A and Sellem, E and Jammes, H and Fritz, S and Boussaha, M and Boichard, D and Kiefer, H and Sanchez, MP},
title = {Genetic regulation of sperm DNA methylation in cattle through meQTL mapping.},
journal = {BMC genomics},
volume = {26},
number = {1},
pages = {771},
pmid = {40847283},
issn = {1471-2164},
support = {101000226//European Union's Horizon 2020/ ; 101000226//European Union's Horizon 2020/ ; 101000226//European Union's Horizon 2020/ ; 101000226//European Union's Horizon 2020/ ; 101000226//European Union's Horizon 2020/ ; 101000226//European Union's Horizon 2020/ ; 101000226//European Union's Horizon 2020/ ; 101000226//European Union's Horizon 2020/ ; 101000226//European Union's Horizon 2020/ ; 101000226//European Union's Horizon 2020/ ; 101000226//European Union's Horizon 2020/ ; 101000226//European Union's Horizon 2020/ ; 101000226//European Union's Horizon 2020/ ; 101000226//European Union's Horizon 2020/ ; 101000226//European Union's Horizon 2020/ ; 101000226//European Union's Horizon 2020/ ; 101000226//European Union's Horizon 2020/ ; 101000226//European Union's Horizon 2020/ ; 101000226//European Union's Horizon 2020/ ; ANR-21-CE20-0021//Agence Nationale de la Recherche/ ; ANR-21-CE20-0021//Agence Nationale de la Recherche/ ; ANR-21-CE20-0021//Agence Nationale de la Recherche/ ; ANR-21-CE20-0021//Agence Nationale de la Recherche/ ; ANR-21-CE20-0021//Agence Nationale de la Recherche/ ; ANR-21-CE20-0021//Agence Nationale de la Recherche/ ; ANR-21-CE20-0021//Agence Nationale de la Recherche/ ; ANR-21-CE20-0021//Agence Nationale de la Recherche/ ; ANR-21-CE20-0021//Agence Nationale de la Recherche/ ; ANR-21-CE20-0021//Agence Nationale de la Recherche/ ; ANR-21-CE20-0021//Agence Nationale de la Recherche/ ; ANR-21-CE20-0021//Agence Nationale de la Recherche/ ; ANR-21-CE20-0021//Agence Nationale de la Recherche/ ; ANR-21-CE20-0021//Agence Nationale de la Recherche/ ; ANR-21-CE20-0021//Agence Nationale de la Recherche/ ; ANR-21-CE20-0021//Agence Nationale de la Recherche/ ; ANR-21-CE20-0021//Agence Nationale de la Recherche/ ; ANR-21-CE20-0021//Agence Nationale de la Recherche/ ; ANR-21-CE20-0021//Agence Nationale de la Recherche/ ; },
mesh = {Animals ; Male ; *DNA Methylation ; Cattle ; *Spermatozoa/metabolism ; *Quantitative Trait Loci ; CpG Islands ; Genome-Wide Association Study ; Polymorphism, Single Nucleotide ; Chromosome Mapping ; Epigenesis, Genetic ; },
abstract = {BACKGROUND: DNA methylation (DNAm) plays an important functional role and is influenced by genetic variants known as methylation QTLs (meQTLs). The majority of meQTL studies have been conducted in human blood. Despite its unique landscape, the genetic regulation of sperm DNAm remains largely unexplored. In this study, we leveraged DNAm measured in sperm from 405 Holstein bulls using reduced representation bisulfite sequencing (RRBS) and performed sequence-level genome-wide association studies for 166,985 variable CpGs (s.d. >5%). We reported heritability estimates and have mapped both cis-meQTLs and trans-meQTLs.

RESULTS: Heritability estimates ranged from 0 to 1 and averaged 0.26 across all selected CpGs, with 76% of estimates above 0.1. The meQTL mapping revealed that 32.9% of the CpGs had a cis-meQTL, 3.6% had a trans-meQTL and 1.0% had both cis- and trans-meQTLs. The cis-CpGs were located on average 261 kb (absolute mean) from their cis-meQTL top SNPs (defined by the most significant association). MeQTLs were enriched in featured genomic annotations, including regions surrounding transcription start sites and ATAC-seq peaks. We also identified spurious trans-associations by analyzing data across multiple genome assemblies, including the construction of a partial pangenome. Additionally, eight trans-meQTL hotspots, defined as variants associated with at least 30 trans-CpGs, were identified and overlapped with genes involved in epigenetic regulation. Using peripheral blood mononuclear cell DNAm from 54 out of the 405 bulls, we did not observe a similar effect of the trans-meQTL hotspots to that one observed in sperm.

CONCLUSIONS: For the first time, meQTLs have been detected and characterized in bovine sperm, contributing to a better understanding of the transmission of paternally inherited DNAm marks. These findings provide useful information for further research aimed at integrating epigenetic information into the prediction of performance traits.},
}

Animals
Male
*DNA Methylation
Cattle
*Spermatozoa/metabolism
*Quantitative Trait Loci
CpG Islands
Genome-Wide Association Study
Polymorphism, Single Nucleotide
Chromosome Mapping
Epigenesis, Genetic

@article {pmid40845168,
year = {2025},
author = {Le, MH and Proctor, M and Huang, JP},
title = {Chromosome Level Genome Assembly of Dynastes reidi Reveals Structural Evolution of Autosomes and the Sex Chromosomes in Hercules Beetles.},
journal = {G3 (Bethesda, Md.)},
volume = {},
number = {},
pages = {},
doi = {10.1093/g3journal/jkaf198},
pmid = {40845168},
issn = {2160-1836},
abstract = {The Hercules beetles have long been iconic symbols of evolutionary diversification, sexual selection, and systematics. Despite their rapid phenotypic evolution and a rich history of inspiring evolutionary biologists, genomic resources for these charismatic beetles remain limited, especially for the Giant Hercules beetles. We present the first chromosome-level genome assembly of a Giant Hercules beetle from the Lesser Antilles. The assembled genome is approximately 837 Mb in size, with a scaffold N50 of 66.68 Mb, which can be anchored to 11 pseudochromosomes with a BUSCO completeness score of 95.9%. An estimate of 55.5% of the genome can be attributed to repetitive elements. Additionally, we detected candidate sex-linked chromosomes by comparing sequencing read depths between one male and two females using Illumina short reads. The chromosome-level genome assembly of Dynastes reidi not only provides critical insights into evolutionary and functional genomics, but also supports informed conservation and management efforts. In addition, this genomic resource will enable future pangenome analyses aimed at understanding the genetic basis of species divergence and morphological innovation in beetles. Our study also marks the emergence of a new model system to investigate the origin and diversification of phenotypic novelty by leveraging genomic resources across diverse domesticated beetle breeds.},
}

@article {pmid40844250,
year = {2025},
author = {Gonzalez-Reyes, M and Ramos-Tapia, I and Ugalde, JA},
title = {A global perspective on the genomics of Moraxella catarrhalis.},
journal = {Microbial genomics},
volume = {11},
number = {8},
pages = {},
doi = {10.1099/mgen.0.001488},
pmid = {40844250},
issn = {2057-5858},
mesh = {*Moraxella catarrhalis/genetics/classification/pathogenicity/drug effects ; Phylogeny ; Humans ; Virulence Factors/genetics ; Genomics ; Genome, Bacterial ; Moraxellaceae Infections/microbiology ; Whole Genome Sequencing ; Genetic Variation ; Drug Resistance, Bacterial/genetics ; Anti-Bacterial Agents/pharmacology ; },
abstract = {Moraxella catarrhalis is an opportunistic pathogen of the human respiratory tract, primarily associated with otitis media in children and exacerbations of chronic obstructive pulmonary disease in adults. Despite its clinical importance, the genomic diversity and functional specialization of M. catarrhalis remain insufficiently characterized. This study aimed to analyse the global genetic diversity of M. catarrhalis using whole-genome sequencing to identify phylogenetic lineages, antimicrobial resistance patterns and key virulence factors. Phylogenomic analysis of 345 publicly available genomes identified 3 phylogroups, of which 1 exhibited significant genomic divergence and was excluded from further analyses due to its potential classification as a separate species. The remaining two phylogroups corresponded to previously described seroresistant and serosensitive lineages. Phylogroup B exhibited a higher prevalence of antimicrobial resistance genes, particularly bro-1 and bro-2, while phylogroup A exhibited unique metabolic adaptation, including genes encoding for the DppB-DppC-DppD dipeptide transport system. Both phylogroups shared crucial virulence factors, including UspA1 and UspA2, which facilitate adhesion and immune evasion. Potential therapeutic targets were identified, including PilQ, essential for type IV pilus biogenesis, and CopB, which plays a key role in iron acquisition and immune evasion. Overall, these findings highlight the significance of phylogenomics approaches in elucidating the genetic mechanisms underlying pathogenicity and resistance in M. catarrhalis, providing insights for future therapeutic and preventive strategies.},
}

*Moraxella catarrhalis/genetics/classification/pathogenicity/drug effects
Phylogeny
Humans
Virulence Factors/genetics
Genomics
Genome, Bacterial
Moraxellaceae Infections/microbiology
Whole Genome Sequencing
Genetic Variation
Drug Resistance, Bacterial/genetics
Anti-Bacterial Agents/pharmacology

@article {pmid40841174,
year = {2025},
author = {Chandra, G and Hossen, MH and Scholz, S and Dilthey, AT and Gibney, D and Jain, C},
title = {Pangenome-based genome inference using integer programming.},
journal = {Genome research},
volume = {},
number = {},
pages = {},
doi = {10.1101/gr.280567.125},
pmid = {40841174},
issn = {1549-5469},
abstract = {Affordable genotyping methods are essential in genomics. Commonly used genotyping methods primarily support single nucleotide variants and short indels but neglect structural variants. Additionally, accuracy of read alignments to a reference genome is unreliable in highly polymorphic and repetitive regions, further impacting genotyping performance. Recent works highlight the advantage of haplotype-resolved pangenome graphs in addressing these challenges. Building on these developments, we propose a rigorous alignment-free genotyping method. Our optimization framework identifies a path through the pangenome graph that maximizes the matches between the path and substrings of sequencing reads (e.g., k-mers) while minimizing recombination events (haplotype switches) along the path. We prove that this problem is NP-Hard and develop efficient integer-programming solutions. We benchmarked the algorithm using downsampled short-read datasets from homozygous human cell lines with coverage ranging from 0.1× to 10×. Our algorithm accurately estimates complete major histocompatibility complex (MHC) haplotype sequences with small edit distances from the ground-truth sequences, providing a significant advantage over existing methods on low-coverage inputs. While this algorithm is designed for haploid genomes, we discuss directions for extending it to diploid genotyping.},
}

@article {pmid40835889,
year = {2025},
author = {Zhang, H and Liu, N and Wang, Y and Zheng, X and Li, W and Liu, Z and Liu, J and Wang, Y and Xing, L and Li, T and Yun, Y and Zhou, Q and Wang, M and Qin, Y and Yan, J and Gong, Z and He, Q and Du, H},
title = {Super-pangenome analyses across 35 accessions of 23 Avena species highlight their complex evolutionary history and extensive genomic diversity.},
journal = {Nature genetics},
volume = {},
number = {},
pages = {},
pmid = {40835889},
issn = {1546-1718},
abstract = {Common oat, belonging to the genus Avena with 30 recognized species, is a nutritionally important cereal crop and high-quality forage worldwide. Here, we construct a genus-level super-pangenome of Avena comprising 35 high-quality genomes from 14 cultivated oat accessions and 21 wild species. The fully resolved phylogenomic analysis unveils the origin and evolutionary scenario of Avena species, and the super-pangenome analysis identifies 26.62% and 59.93% specific genes and haplotypes in wild species. We delineate the landscape of structural variations (SVs) and the transcriptome profile based 1,401 RNA-sequencing (RNA-seq) samples from diverse abiotic stress treatments in oat. We highlight the crucial role of SVs in modulating gene expression and shaping adaptation to diverse stresses. Further combining SV-based genome-wide association studies (GWASs), we characterize 13 candidate genes associated with drought resistance such as AsARF7, validated by transgenic oat lines. Our study provides unprecedented genomic resources to facilitate genomic, evolution and molecular breeding research in oat.},
}

@article {pmid40835741,
year = {2025},
author = {Han, C and Lu, S and Hu, P and Chang, J and Zou, D and Li, F and Li, Y and Lu, Q and Ren, H},
title = {Machine learning based on pangenome-wide association studies reveals the impact of host source on the zoonotic potential of closely related bacterial pathogens.},
journal = {Communications biology},
volume = {8},
number = {1},
pages = {1253},
pmid = {40835741},
issn = {2399-3642},
support = {CSTB2023NSCQ-MSX0515//Natural Science Foundation of Chongqing (Natural Science Foundation of Chongqing Municipality)/ ; },
mesh = {Animals ; *Machine Learning ; Humans ; *Genome-Wide Association Study ; *Brucella/genetics/pathogenicity/classification ; *Genome, Bacterial ; *Zoonoses/microbiology ; *Brucellosis/microbiology/transmission ; Swine ; Cattle ; Whole Genome Sequencing ; Sheep ; },
abstract = {Variations in host species significantly impact bacterial growth traits and antibiotic resistance, making it essential to consider host origin when evaluating the zoonotic potential of pathogens. This study focuses on multiple Brucella species, which share highly similar genetic material, to explore the relationship between host origin and zoonotic potential by integrating pan-genome-wide association studies (pan-GWAS) with machine learning (ML). Our results present an open pangenome of Brucella spp. derived from the whole-genome sequencing (WGS) data of 991 strains and identify 268 genes potentially associated with the zoonotic potential of Brucella. Integrating these genes into an ML model based on the support vector machine (SVM) algorithm allows us to predict the zoonotic potential of various Brucella strains with high accuracy. Our findings reveal that zoonotic potential varies by host origin: Brucella melitensis strains isolated from humans exhibit higher zoonotic potential than those isolated from cattle, goats, and sheep, while Brucella suis biovar 2 strains isolated from domestic pigs display higher zoonotic potential than those isolated from wild boars. Our study proposes a method for predicting and quantifying the zoonotic potential of closely related bacterial pathogens from different host origins, providing valuable insights for risk assessment and public health strategy.},
}

Animals
*Machine Learning
Humans
*Genome-Wide Association Study
*Brucella/genetics/pathogenicity/classification
*Genome, Bacterial
*Zoonoses/microbiology
*Brucellosis/microbiology/transmission
Swine
Cattle
Whole Genome Sequencing
Sheep

@article {pmid40830656,
year = {2025},
author = {Igolkina, AA and Vorbrugg, S and Rabanal, FA and Liu, HJ and Ashkenazy, H and Kornienko, AE and Fitz, J and Collenberg, M and Kubica, C and Mollá Morales, A and Jaegle, B and Wrightsman, T and Voloshin, V and Bezlepsky, AD and Llaca, V and Nizhynska, V and Reichardt, I and Bezrukov, I and Lanz, C and Bemm, F and Flood, PJ and Nemomissa, S and Hancock, A and Guo, YL and Kersey, P and Weigel, D and Nordborg, M},
title = {A comparison of 27 Arabidopsis thaliana genomes and the path toward an unbiased characterization of genetic polymorphism.},
journal = {Nature genetics},
volume = {},
number = {},
pages = {},
pmid = {40830656},
issn = {1546-1718},
support = {EPICLINES//EC | EC Seventh Framework Programm | FP7 Ideas: European Research Council (FP7-IDEAS-ERC - Specific Programme: "Ideas" Implementing the Seventh Framework Programme of the European Community for Research, Technological Development and Demonstration Activities (2007 to 2013))/ ; 847548//EC | EU Framework Programme for Research and Innovation H2020 | H2020 Priority Excellent Science | H2020 European Research Council (H2020 Excellent Science - European Research Council)/ ; 1001GenomesPlus//Deutsche Forschungsgemeinschaft (German Research Foundation)/ ; BB/S004661/1//RCUK | Biotechnology and Biological Sciences Research Council (BBSRC)/ ; },
abstract = {Making sense of whole-genome polymorphism data is challenging, but it is essential for overcoming the biases in SNP data. Here we analyze 27 genomes of Arabidopsis thaliana to illustrate these issues. Genome size variation is mostly due to tandem repeat regions that are difficult to assemble. However, while the rest of the genome varies little in length, it is full of structural variants, mostly due to transposon insertions. Because of this, the pangenome coordinate system grows rapidly with sample size and ultimately becomes 70% larger than the size of any single genome, even for n = 27. Finally, we show how short-read data are biased by read mapping. SNP calling is biased by the choice of reference genome, and both transcriptome and methylome profiling results are affected by mapping reads to a reference genome rather than to the genome of the assayed individual.},
}

@article {pmid40829589,
year = {2025},
author = {Sibbald, SJ and Lawton, M and Maclean, C and Roger, AJ and Archibald, JM},
title = {Pangenome biology and evolution in harmful algal-bloom-forming pelagophytes.},
journal = {Current biology : CB},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.cub.2025.07.055},
pmid = {40829589},
issn = {1879-0445},
abstract = {In prokaryotes, lateral gene transfer (LGT) is a key mechanism leading to intraspecies variability in gene content and the phenomenon of pangenomes. In microbial eukaryotes, however, the extent to which LGT-driven pangenomes exist is unclear. Pelagophytes are ecologically important marine algae that include Aureococcus anophagefferens-a species notorious for causing harmful algal blooms. To investigate genome evolution across Pelagophyceae and within Ac. anophagefferens, we used long-read sequencing to produce high-quality genome assemblies for five strains of Ac. anophagefferens (52-54 megabase pairs [Mbp]), a telomere-to-telomere assembly for Pelagomonas calceolata (32 Mbp), and the first reference genome for Aureoumbra lagunensis (41 Mbp). Using comparative genomics and phylogenetics, we show remarkable strain-level genetic variation in Ac. anophagefferens, with a pangenome (23,356 orthogroups) that is 81.1% core and 18.9% accessory. Although gene content variation within Ac. anophagefferens does not appear to be largely driven by recent prokaryotic LGTs (2.6% of accessory orthogroups), 368 orthogroups were acquired from bacteria in a common ancestor of all analyzed strains and are not found in P. calceolata or Au. lagunensis. A total of 1,077 recent LGTs from prokaryotes and viruses were identified within Pelagophyceae overall, constituting 3.5%-4.0% of the orthogroups in each species. This includes genes likely contributing to the ecological success of pelagophytes globally and in long-lasting harmful blooms.},
}

@article {pmid40828965,
year = {2025},
author = {Dai, S and Zhao, P and Li, W and Peng, L and Jiang, E and Du, Y and Zhang, W and Dai, X and Yang, L and Li, Z and Xu, L and Lan, X and Lyu, W and Yang, L and Fang, L and Liu, GE and Zhou, Y},
title = {Global pangenome analysis highlights the critical role of structural variants in cattle improvement and identifies a unique event as a novel enhancer in IGFBP7[+] cells.},
journal = {Molecular biology and evolution},
volume = {},
number = {},
pages = {},
doi = {10.1093/molbev/msaf205},
pmid = {40828965},
issn = {1537-1719},
abstract = {Based on a pangenome graph platform, we simultaneously analyzed the impacts of SNPs and SVs in the population structure and phenotypic formation of global cattle using 2,409 individuals from 82 breeds. We demonstrated that SVs, like SNPs, effectively explain the population structure of global cattle. Genomic regions under strong selection, identified using both SNPs and SVs, consistently revealed footprints associated with human-mediated selection of economic traits in European improved cattle or natural selection of geographical adaptations. Notably, we detected that ∼40.14% of SVs were not tagged (LD, r2 < 0.6) by nearby SNPs. These "orphan" SVs may uncover new genetic signals and represent recent mutations associated with specific selection pressures or local environmental adaptation. Selected SVs tagged by SNPs also play causal or dominant roles in regions under selection. For example, our single-cell RNA sequencing has demonstrated that a notable SNP-tagged SV functions as an enhancer of the IGFBP7 gene, regulating fat deposition through IGFBP7+ cells. In conclusion, these SV-related mechanisms likely have caused some differences in economic traits and local adaptability across global cattle populations. Our integrated approaches highlight the unique and indispensable roles of SVs in shaping genetic diversity, offering novel insights into adaptation, selection, and strategies for improving cattle populations.},
}

@article {pmid40827877,
year = {2025},
author = {Kenney, SM and M'ikanatha, NM and Ganda, E},
title = {Genomic evolution of Salmonella Dublin in cattle and humans in the United States.},
journal = {Applied and environmental microbiology},
volume = {},
number = {},
pages = {e0068925},
doi = {10.1128/aem.00689-25},
pmid = {40827877},
issn = {1098-5336},
abstract = {Increasingly, antimicrobial-resistant (AMR) Salmonella Dublin is a threat to human and animal health, therefore requiring a One Health approach to comprehensively understand pathogen evolution. Moreover, S. Dublin dissemination throughout the United States and the food supply chain is a concern for food safety and security. Here, we leveraged multi-agency biosurveillance data and genomic sequencing of S. Dublin strains to provide a robust analysis of its evolution across human, animal, and environmental reservoirs. This study advances our understanding of AMR S. Dublin, elucidates factors driving AMR emergence, and informs interventions to protect public health. In total, 2,150 strains collected between 2002 and 2023 throughout the United States from clinical bovine (N = 581), clinical human (N = 664), and environmental (N = 905) sources were identified. After uniform quality control, raw reads were assembled de novo followed by genome annotation and characterization of plasmids, antimicrobial resistance genes, and virulence factors. Strain relatedness was evaluated using a core genome maximum-likelihood phylogeny and pairwise core genome single-nucleotide polymorphism (SNP) differences. We identified the highest prevalence of drug-specific antimicrobial resistance genes and multidrug resistance plasmid, IncA/C2 (P < 0.001), in bovine clinical strains, which also had the greatest genetic diversity. Despite source-dependent differences in antimicrobial resistance gene frequency and types, 72% of S. Dublin strains in our study differed with at least one other strain by 20 or fewer SNPs. This high degree of genomic similarity highlights the potential for cross-transmission between humans, animals, and the environment and underscores the importance of considering strain source when assessing and monitoring antimicrobial resistance.IMPORTANCESalmonella Dublin is a zoonotic, sometimes foodborne, pathogen that causes severe illness in cattle and humans. Our study takes a One Health approach to understanding genetic differences in strains within and between different reservoirs in the United States. We identified differences in antimicrobial resistance potential and genome content between clinical bovine, clinical human, and environmental strains. Nonetheless, the U.S. population of S. Dublin is highly related and diverges minimally over time and geography. These findings highlight the importance of the One Health framework when combating zoonotic antimicrobial-resistant pathogens like Salmonella Dublin.},
}

@article {pmid40811403,
year = {2025},
author = {Alanko, JN and Biagi, E and Puglisi, SJ},
title = {Finimizers: Variable-Length Bounded-Frequency Minimizers for $k$-mer Sets.},
journal = {IEEE transactions on computational biology and bioinformatics},
volume = {22},
number = {2},
pages = {899-910},
doi = {10.1109/TCBBIO.2025.3545285},
pmid = {40811403},
issn = {2998-4165},
abstract = {The minimizer of a $k$-mer is the smallest $m$-mer inside the $k$-mer according to some total order $< $ of the $m$-mers. Minimizers are often used as keys in hash tables in indexing tasks in metagenomics and pangenomics. The main weakness of minimizer-based indexing is the possibility of very frequently occurring minimizers, which can slow query times down significantly. Popular minimizer alignment tools employ various and often wild heuristics as workarounds, typically by ignoring frequent minimizers or blacklisting commonly occurring patterns, to the detriment of other metrics (e.g., alignment recall, space usage, or code complexity). In this paper, we introduce frequency-bounded minimizers, which we call finimizers, for indexing sets of $k$-mers. The idea is to use an order relation $< $ for minimizer comparison that depends on the frequency of the minimizers within the indexed $k$-mers. With finimizers, the length $m$ of the $m$-mers is not fixed, but is allowed to vary depending on the context, so that the length can increase to bring the frequency down below a user-specified threshold $t$. Setting a maximum frequency solves the issue of very frequent minimizers and gives us a worst-case guarantee for the query time. We show how to implement a particular finimizer scheme efficiently using the Spectral Burrows-Wheeler transform ($SBWT$) (Alanko et al. Proc. SIAM ACDA, 2023) augmented with longest common suffix information. In experiments, we explore in detail the special case in which we set $t = 1$. This choice simplifies the index structure and makes the scheme completely parameter-free apart from the choice of $k$. A prototype implementation of this scheme exhibits $k$-mer localization times close to, and often faster than, state-of-the-art minimizer-based schemes.},
}

@article {pmid40802147,
year = {2025},
author = {Pushkarna, S and Kumar, A and Arora, K and Malhotra, P and Suneja, P and Dang, AS},
title = {Exploring the potential of Lactobacillus rhamnosus as gluten-digesting bacteria.},
journal = {Irish journal of medical science},
volume = {},
number = {},
pages = {},
pmid = {40802147},
issn = {1863-4362},
support = {DST/INSPIRE Fellowship/2019/IF190883//INSPIRE ("Innovation in Science Pursuit for Inspired Research") Fellowship, Department of Science & Technology, under the Ministry of Science and Technology, Government of India, New Delhi/ ; },
abstract = {BACKGROUND: Celiac disease (CeD), a multifactorial disorder, develops when gluten, the toxic environmental inducer, interacts with CeD susceptibility genetic markers, resulting in a chronic enteropathy. Several extra-intestinal complications may also arise in cases of delayed management. There persists a growing demand to develop non-dietary adjuvant therapeutic options that can help relieve symptoms and improve patients' quality of life.

AIM: The present study conducted a bioinformatic approach to look into the potential of using Lactobacillus rhamnosus, a well-established probiotic, as gluten-digesting bacteria and provide the basis for future therapeutic developments.

METHODS: Complete genome assemblies of forty-nine L. rhamnosus strains were subjected to annotation using RAST and a pan genome analysis with BPGA. Genes for peptidases were identified using BlastKOALA and Prokka, followed by domain analysis using the NCBI-CD search tool to screen for gluten-digesting activity.

RESULTS: Genome annotation of all the strains under study highlighted the presence of sixty-one peptidases in L. rhamnosus. Domain analysis further revealed that nine of these peptidases, including aminopeptidase N, neutral endopeptidase, oligoendopeptidase F, dipeptidyl-peptidase 5, proline iminopeptidase, Xaa-Pro dipeptidyl-peptidase, aminopeptidase C, aminopeptidase E, and PII-type proteinase, shared domains with already established gluten-digesting enzymes, suggesting their potential role in degrading toxic gliadin peptides.

CONCLUSION: The current in silico analysis indicates that this well-known probiotic species, in addition to showcasing a plethora of beneficial properties, may also hold great potential in terms of reducing gluten toxicity. With further studies, L. rhamnosus can prove to be a promising candidate in CeD treatment and management.},
}

@article {pmid40753951,
year = {2025},
author = {Wei, CR and Basharat, Z and Adhikari, P},
title = {Implications of virtual screening for South African natural compounds against Plesiomonas shigelloides, a pathogen with zoonotic potential.},
journal = {Computers in biology and medicine},
volume = {196},
number = {Pt B},
pages = {110882},
doi = {10.1016/j.compbiomed.2025.110882},
pmid = {40753951},
issn = {1879-0534},
abstract = {Plesiomonas shigelloides is an emerging pathogen associated with gastroenteritis and poses a growing public health concern, especially in regions with limited access to advanced medical treatments. The purpose of this study was to explore the therapeutic potential of South African natural product compounds against P. shigelloides by targeting the essential enzyme Pyridoxine 5'-phosphate synthase or PPS (encoded by PdxJ). P. shigelloides proteomes (n = 26) were processed using the Bacterial Pan Genome Analysis (BPGA) pipeline to identify conserved targets. Targeting conserved protein ensures the potential for broad-spectrum efficacy. PPS was chosen as drug target and its structure was predicted using AlphaFold, enabling high-confidence modeling. Subsequently, docking was performed using AutoDock Vina, focusing on a library of South African compounds (n > 1000). The three inhibitors demonstrating strong binding affinities to the PPS were Scutiaquinone A, Mesquitol-(4α→5)-3,3',4',7,8-pentahydroxyflavonone, and Riccardin C. To further validate the stability and efficacy of these interactions, molecular dynamics (MD) simulations were carried out for 100 ns. The simulations revealed stable interactions between the inhibitors and PPS, suggesting potential inhibition of the PPS enzyme. Mesquitol derivative was found to be the safest and recommended for further experimental validation. This study highlights the promising potential of South African natural compounds in combating P. shigelloides infections, paving the way for the development of novel therapeutic strategies.},
}

@article {pmid38421269,
year = {2024},
author = {Deery, J and Carmody, M and Flavin, R and Tomanek, M and O'Keeffe, M and McGlacken, GP and Reen, FJ},
title = {Comparative genomics reveals distinct diversification patterns among LysR-type transcriptional regulators in the ESKAPE pathogen Pseudomonas aeruginosa.},
journal = {Microbial genomics},
volume = {10},
number = {2},
pages = {},
pmid = {38421269},
issn = {2057-5858},
mesh = {Humans ; Pseudomonas aeruginosa/genetics ; Genomics ; *Pseudomonas Infections ; Pseudomonas ; *Cystic Fibrosis/genetics ; },
abstract = {Pseudomonas aeruginosa, a harmful nosocomial pathogen associated with cystic fibrosis and burn wounds, encodes for a large number of LysR-type transcriptional regulator proteins. To understand how and why LTTR proteins evolved with such frequency and to establish whether any relationships exist within the distribution we set out to identify the patterns underpinning LTTR distribution in P. aeruginosa and to uncover cluster-based relationships within the pangenome. Comparative genomic studies revealed that in the JGI IMG database alone ~86 000 LTTRs are present across the sequenced genomes (n=699). They are widely distributed across the species, with core LTTRs present in >93 % of the genomes and accessory LTTRs present in <7 %. Analysis showed that subsets of core LTTRs can be classified as either variable (typically specific to P. aeruginosa) or conserved (and found to be distributed in other Pseudomonas species). Extending the analysis to the more extensive Pseudomonas database, PA14 rooted analysis confirmed the diversification patterns and revealed PqsR, the receptor for the Pseudomonas quinolone signal (PQS) and 2-heptyl-4-quinolone (HHQ) quorum-sensing signals, to be amongst the most variable in the dataset. Successful complementation of the PAO1 pqsR [-] mutant using representative variant pqsR sequences suggests a degree of structural promiscuity within the most variable of LTTRs, several of which play a prominent role in signalling and communication. These findings provide a new insight into the diversification of LTTR proteins within the P. aeruginosa species and suggests a functional significance to the cluster, conservation and distribution patterns identified.},
}

Humans
Pseudomonas aeruginosa/genetics
Genomics
*Pseudomonas Infections
Pseudomonas
*Cystic Fibrosis/genetics