@article {pmid40375333,
year = {2025},
author = {Cicherski, A and Lisiecka, A and Dojer, N},
title = {AlfaPang: alignment free algorithm for pangenome graph construction.},
journal = {Algorithms for molecular biology : AMB},
volume = {20},
number = {1},
pages = {7},
pmid = {40375333},
issn = {1748-7188},
support = {2022/47/B/ST6/03154//National Science Centre, Poland/ ; },
abstract = {The success of pangenome-based approaches to genomics analysis depends largely on the existence of efficient methods for constructing pangenome graphs that are applicable to large genome collections. In the current paper we present AlfaPang, a new pangenome graph building algorithm. AlfaPang is based on a novel alignment-free approach that allows to construct pangenome graphs using significantly less computational resources than state-of-the-art tools. The code of AlfaPang is freely available at https://github.com/AdamCicherski/AlfaPang .},
}

@article {pmid40375127,
year = {2025},
author = {Youseif, SH and El-Megeed, FHA and Soliman, MS and Ageez, A and Mohamed, AH and Ali, SA and El-Kholy, AA},
title = {Nodules-associated Klebsiella oxytoca complex: genomic insights into plant growth promotion and health risk assessment.},
journal = {BMC microbiology},
volume = {25},
number = {1},
pages = {294},
pmid = {40375127},
issn = {1471-2180},
support = {Grant ID: 42693//The U.S.-Egypt Science and Technology Joint Fund, Cycle 19/ ; Grant ID: 42693//The U.S.-Egypt Science and Technology Joint Fund, Cycle 19/ ; Grant ID: 42693//The U.S.-Egypt Science and Technology Joint Fund, Cycle 19/ ; Grant ID: 42693//The U.S.-Egypt Science and Technology Joint Fund, Cycle 19/ ; Grant ID: 42693//The U.S.-Egypt Science and Technology Joint Fund, Cycle 19/ ; Grant ID: 42693//The U.S.-Egypt Science and Technology Joint Fund, Cycle 19/ ; Grant ID: 42693//The U.S.-Egypt Science and Technology Joint Fund, Cycle 19/ ; },
mesh = {*Klebsiella oxytoca/genetics/isolation & purification/classification/drug effects ; Phylogeny ; Genome, Bacterial ; Whole Genome Sequencing ; *Root Nodules, Plant/microbiology ; Risk Assessment ; Anti-Bacterial Agents/pharmacology ; Genomics ; Plant Development ; },
abstract = {The swift emergence of antibiotic resistance genes (ARGs) across interconnected One Health compartments poses a significant global threat. Although plant growth-promoting (PGP) bacteria possess numerous attributes beneficial to host plants, many of these bacteria also harbor ARGs, necessitating a focused assessment of their negative implications. In this context, here we performed whole genome sequencing of 14 PGP endophytic strains isolated from root nodules of faba beans, belonging to three Klebsiella oxytoca species complex (KoSC): K. grimontii (n = 5), K. michiganensis (n = 5), and K. pasteurii (n = 4). We performed comparative genomics, molecular typing, and pangenome analyses on these strains. We identified significant diversity within the KoSC population, classifying the strains into five sequence types (STs), three of which are novel to this study (ST-542, ST-569, and ST-629). Phylogenomic analysis revealed that the bacterial strains clustered more closely by ST than by their source of isolation. Annotation of gene clusters indicated that all assembled genomes are enriched with genes involved in PGP activities, alongside a robust array of genes conferring tolerance to abiotic stresses. Importantly, our findings disclosed that the 14 assembled genomes harbored multiple ARGs, conferring resistance to various antibiotic classes, with 71% of the population classified as multidrug-resistant based on the in vitro antibiotic susceptibility assay. Furthermore, all genomes contained an array of virulence factors critical for survival, pathogenesis, biofilm formation, and root colonization. In conclusion, this study substantiates the hypothesis that certain PGP bacteria may serve as potential reservoirs of multidrug resistance, posing significant public health risks. Thus, the future advancement of bacteria-based biofertilizers should integrate environmental considerations and monitor their impact on antibiotic resistance dissemination in soil ecosystems.},
}

*Klebsiella oxytoca/genetics/isolation & purification/classification/drug effects
Phylogeny
Genome, Bacterial
Whole Genome Sequencing
*Root Nodules, Plant/microbiology
Risk Assessment
Anti-Bacterial Agents/pharmacology
Genomics
Plant Development

@article {pmid40373741,
year = {2025},
author = {LoTempio, JE and Donohue, CR and Moreno, JD and Cook-Deegan, R},
title = {Ethics choices during the Human Genome Project reflected their policy world, not ours.},
journal = {Cell genomics},
volume = {5},
number = {5},
pages = {100841},
doi = {10.1016/j.xgen.2025.100841},
pmid = {40373741},
issn = {2666-979X},
mesh = {Humans ; *Human Genome Project/ethics/legislation & jurisprudence/history ; *Genome, Human ; Informed Consent/ethics ; Genomics/ethics ; },
abstract = {Since human genomic data produced in the 1990s are still a significant part of the reference genome, decades-old decisions pertinent to the creation of these data persist. Here, we discuss how historical documents illustrate the 1990s policy and legal environment and how they affected ethical choices in the Human Genome Project (HGP). These documents inform current controversies about informed consent and how IRBs review similar protocols today. Finally, we discuss how this informs active work in large reference pangenome efforts.},
}

Humans
*Human Genome Project/ethics/legislation & jurisprudence/history
*Genome, Human
Informed Consent/ethics
Genomics/ethics

@article {pmid40371178,
year = {2025},
author = {Lanclos, VC and Feng, X and Cheng, C and Yang, M and Hider, CJ and Coelho, JT and Kojima, CY and Barnes, SJ and Cleveland, CS and Xie, M and Zhao, Y and Luo, H and Thrash, JC},
title = {New isolates refine the ecophysiology of the Roseobacter CHAB-I-5 lineage.},
journal = {ISME communications},
volume = {5},
number = {1},
pages = {ycaf068},
pmid = {40371178},
issn = {2730-6151},
abstract = {The CHAB-I-5 cluster is a pelagic lineage that can comprise a significant proportion of all Roseobacters in surface oceans and has predicted roles in biogeochemical cycling via heterotrophy, aerobic anoxygenic photosynthesis (AAnP), CO oxidation, DMSP degradation, and other metabolisms. Though cultures of CHAB-I-5 have been reported, none have been explored and the best-known representative, strain SB2, was lost from culture after obtaining the genome sequence. We have isolated two new CHAB-I-5 representatives, strains US3C007 and FZCC0083, and assembled complete, circularized genomes with 98.7% and 92.5% average nucleotide identities with the SB2 genome. Comparison of these three with 49 other unique CHAB-I-5 metagenome-assembled and single-cell genomes indicated that the cluster represents a genus with two species, and we identified subtle differences in genomic content between the two species subclusters. Metagenomic recruitment from over fourteen hundred samples expanded their known global distribution and highlighted both isolated strains as representative members of the clade. FZCC0083 grew over twice as fast as US3C007 and over a wider range of temperatures. The axenic culture of US3C007 occurs as pleomorphic cells with most exhibiting a coccobacillus/vibrioid shape. We propose the name Candidatus Thalassovivens spotae, gen nov., sp. nov. for the type strain US3C007[T] (= ATCC TSD-433[T] = NCMA B160[T]).},
}

@article {pmid40345436,
year = {2025},
author = {Schmidt, RJ and Furtado, LV and Fussell, AM and Jordan, D and Lebo, M and Syed, A and Temple-Smolkin, RL and Venner, E and Worthey, E and Carter, AB},
title = {Clinical Bioinformatician Body of Knowledge-Clinical Laboratory Regulation and Data Security Core: A Report of the Association for Molecular Pathology.},
journal = {The Journal of molecular diagnostics : JMD},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.jmoldx.2025.04.003},
pmid = {40345436},
issn = {1943-7811},
abstract = {Clinical bioinformaticians have come to play an essential role in clinical molecular diagnostic laboratories. However, the core knowledge needed for the clinical practice and training of this emerging group of professionals has not been previously established. Clinical laboratories are subject to a complex set of legal and accreditation requirements from numerous governmental and nongovernmental bodies that cover the generation, processing, storage, and distribution of patient data in the form of test results and intermediate data files. Clinical bioinformaticians are intimately involved in the development and maintenance of systems that perform these activities. This third article in the Association for Molecular Pathology's Clinical Bioinformatician Body of Knowledge Core series presents a body of knowledge for the clinical bioinformatician describing relevant laboratory regulations and data security in the domains of hardware, software, networks, and interoperability. Although this article does not substitute for legal counsel, it provides a resource for clinical bioinformaticians to identify and familiarize themselves with regulations affecting their professional functions within the laboratory.},
}

@article {pmid40371111,
year = {2025},
author = {Chibani, S and Yacoub, E and Boujemaa, S and Mardassi, H and Guglielmini, J and Vaysse, A and Khadraoui, N and Mlik, B and Ben Abdelmoumen Mardassi, B},
title = {A genome-wide investigation of Mycoplasma hominis genes associated with gynecological infections or infertility.},
journal = {Frontiers in microbiology},
volume = {16},
number = {},
pages = {1561378},
pmid = {40371111},
issn = {1664-302X},
abstract = {BACKGROUND AND AIM: Mycoplasma hominis is a human pathogenic bacterium that causes a wide range of genital infections and reproductive issues. Previously, based on an extended multilocus sequence typing scheme, we provided evidence for the segregation of M. hominis clinical strains into two distinct pathotypes: gynecological infections or infertility. Here, based on whole genome sequencing (WGS) data, we sought to provide a more refined picture of the phylogenetic relationship between these two M. hominis pathotypes, with the aim to delineate the underlying genetic determinants.

METHODS: We carried out WGS of 62 Tunisian M. hominis clinical strains collected over a 17-year period. The majority of these clinical strains are associated with infertility (n = 53) and the remaining nine isolates are from gynecological infections cases. An alignment-free distance-based procedure (Jolytree) was used to infer phylogenetic relationships among M. hominis isolates, while the phylogenetic method treeWAS was used to determine the statistical association between pathotypes of interest and genotypes at all loci.

RESULTS: The total pangenome of M. hominis strains was found to contain 1,590 genes including 966 core genes and 592 accessory genes, representing 60 and 37% of the total genome, respectively. Collectively, phylogenetic analyses based on WGS confirmed the distinction between the two M. hominis pathotypes. Strikingly, genome wide association analyses identified 4 virulence genes associated with gynecological infections, mainly involved in nucleotide salvage pathways and tolerance to oxidative stress, while five genes have been associated with infertility cases, two of which are implicated in biofilm formation.

CONCLUSION: In sum, this study further established the categorization of M. hominis into two pathotypes, and led to the identification of the associated genetic loci, thus holding out promising prospects for a better understanding of the differential interaction of M. hominis with its host.},
}

@article {pmid40365603,
year = {2025},
author = {Kumar, A and Männistö, MK and Pätsi, M and Kerkhof, LJ and Häggblom, MM},
title = {Genome analysis reveals diverse novel psychrotolerant Mucilaginibacter species in Arctic tundra soils.},
journal = {ISME communications},
volume = {5},
number = {1},
pages = {ycaf071},
pmid = {40365603},
issn = {2730-6151},
abstract = {As Arctic soil ecosystems warm due to climate change, enhanced microbial activity is projected to increase the rate of soil organic matter degradation. Delineating the diversity and activity of Arctic tundra microbial communities active in decomposition is thus of keen interest. Here, we describe novel cold-adapted bacteria in the genus Mucilaginibacter (Bacteroidota) isolated from Artic tundra soils in Finland. These isolates are aerobic chemoorganotrophs and appear well adapted to the low-temperature environment, where they are also exposed to desiccation and a wide regime of annual temperature variation. Initial 16S ribosomal RNA (rRNA)-based phylogenetic analysis suggested that five isolated strains represent new species of the genus Mucilaginibacter, confirmed by whole genome-based phylogenomic and average nucleotide identity. Five novel species are described: Mucilaginibacter geliditolerans sp. nov., Mucilaginibacter tundrae sp. nov., Mucilaginibacter empetricola sp. nov., Mucilaginibacter saanensis sp. nov., and Mucilaginibacter cryoferens sp. nov. Genome and phenotype analysis showed their potential in complex carbon degradation, nitrogen assimilation, polyphenol degradation, and adaptation to their tundra heath habitat. A pangenome analysis of the newly identified species alongside known members of the Mucilaginibacter genus sourced from various environments revealed the distinctive characteristics of the tundra strains. These strains possess unique genes related to energy production, nitrogen uptake, adaptation, and the synthesis of secondary metabolites that aid in their growth, potentially accounting for their prevalence in tundra soil. By uncovering novel species and strains within the Mucilaginibacter, we enhance our understanding of this genus and elucidate how environmental fluctuations shape the microbial functionality and interactions in Arctic tundra ecosystems.},
}

@article {pmid40364522,
year = {2025},
author = {Li, B and Li, X and Wang, Y and Liu, X and Li, K and Li, R and Faiz, MU and Darlington, UT and Rao, Z and Wu, Q and Yue, Y and Wang, S and Fei, Z and Liu, Y and Zheng, Y and Yue, J},
title = {KPGD: A kiwifruit pangenome database for comprehensive mining of genetic diversity in the genus Actinidia.},
journal = {Plant communications},
volume = {},
number = {},
pages = {101373},
doi = {10.1016/j.xplc.2025.101373},
pmid = {40364522},
issn = {2590-3462},
}

@article {pmid40358235,
year = {2025},
author = {Ravi, K and Falkowski, NR and Huffnagle, GB},
title = {Genomic and transcriptomic insights into vertebrate host-specific Lactobacillus johnsonii adaptation in the gastrointestinal tract.},
journal = {mSphere},
volume = {},
number = {},
pages = {e0005225},
doi = {10.1128/msphere.00052-25},
pmid = {40358235},
issn = {2379-5042},
abstract = {We conducted a comparative genomic analysis of Lactobacillus johnsonii strains isolated from the gastrointestinal tract of diverse vertebrate hosts to explore the genetic basis of host specificity. We then utilized transcriptomics analysis to investigate the expression profile of identified rodent-specific genes in mouse isolate MR1 during in vitro and in vivo growth conditions. There was significant heterogeneity among strains, in both genome sequence and content, with phylogenetic clustering of strains into distinct clades associated with rodent or avian sources. There were not sufficient genomes to identify whether porcine isolates formed their own genetic clade. However, human isolates did not form a distinct clade. Functional enrichment analysis revealed significant enrichment of several genes, including surface proteins and accessory secretory pathway-related genes, as well as tyrosine decarboxylase genes in rodent isolates compared to avian isolates, including in mouse isolate MR1. A total of 40 genes were identified as rodent-associated, and all were transcriptionally active in L. johnsonii MR1. The global transcriptomic analysis of L. johnsonii MR1 was done using cells grown anaerobically, at 37˚C, under both the late-exponential phase and stationary phase, as well as during in vivo growth in the cecum of mono-colonized germ-free mice. Several of these genes were uniquely regulated during late exponential vs stationary phase growth and in vivo colonization in mice, highlighting their potential role in nutrient adaptation and host-microbe interactions.IMPORTANCELactobacillus johnsonii is a well-known probiotic species with health-beneficial properties, including host immunomodulation and pathogen inhibition. Its growing relevance in the medical industry highlights the need to understand its biology, particularly how it adapts to different host environments. In bacteria, niche adaptation is often accompanied by the loss or gain of coding sequences along with changes in the genome size. In this study, we explored the genetic diversity of L. johnsonii strains from the gastrointestinal tracts of various vertebrates such as rodents, birds, swine, and humans. We found associations between genome content and host species of origin and could conceptually demonstrate that these genes are being differentially transcribed under varying conditions. Several functions were associated with specific host groups, suggesting that L. johnsonii strains have adapted to their hosts over time.},
}

@article {pmid40357401,
year = {2025},
author = {Chen, C and Wang, M and Huang, T and Huang, DL and Yu, S and Zhao, HM and Fu, XX and Li, XX and Wu, H},
title = {Genomic epidemiology of a novel Pandoraea pneumonica group caused severe bloodstream infection in Hainan, China, 2021-2024.},
journal = {Frontiers in cellular and infection microbiology},
volume = {15},
number = {},
pages = {1560634},
pmid = {40357401},
issn = {2235-2988},
mesh = {Humans ; China/epidemiology ; Phylogeny ; Anti-Bacterial Agents/pharmacology ; Whole Genome Sequencing ; Genome, Bacterial ; Male ; Microbial Sensitivity Tests ; Female ; RNA, Ribosomal, 16S/genetics ; Adult ; Middle Aged ; *Burkholderiaceae/genetics/isolation & purification/drug effects/classification ; *Bacteremia/epidemiology/microbiology ; Molecular Epidemiology ; Young Adult ; Aged ; Adolescent ; *Gram-Negative Bacterial Infections/epidemiology/microbiology ; },
abstract = {INTRODUCTION: Rarely does Pandoraea occur in bloodstream infections (BSI), although it's typically found in cystic fibrosis. This study aims to decipher the genetic map and obtain insights of clinical symptoms into Pandoraea from BSI patients.

METHODS: 30 suspected BSI patients' diagnostic records and medical histories were recorded. Pandoraea spp. isolates were collected and subjected to antimicrobial susceptibility testing, Sanger sequencing and Whole-genome sequencing (WGS).

RESULTS: Of the 30 clinical cases, five (16.67%) ultimately died, whereas 25 (83.33%) are alive. 30 purified Pandoraea isolates showed high degree of MIC values to Meropenem, Amoxicillin and Potassium Clavulanate, Gentamicin, and Ceftazidime. Then, all isolates were identified as P. pneumonica based on the 16S rRNA-based phylogenetic analysis. Among 28 genomes of them, the average genome size and average GC contents were 5,397,568 bp, and 62.43%, respectively. However, WP1 displayed high similarity (90.6%) to reference Pandoraea sp. LMG 31114. Genetic differences between the tested isolates and LMG 31114 suggested that the outbreak's causative pathogen could be a novel cluster of P. pneumonica. The genomes accumulated mutations at an estimated rate of 1.3 × 10[-7] mutations/year/site. Moreover, 26 clinical isolates within the P. pneumonica cluster were formed in July 2014, revealing a tendency to develop regional endemic patterns.

CONCLUSION: BSI caused by this novel cluster of P. pneumonica is linked to significant morbidity and mortality. Such cluster remains a critical public health challenge due to their regional epidemiological patterns and antibiotic treatment risk. This study contributed to the basis on pathogen identification, disease diagnosis, and BSI treatment.},
}

Humans
China/epidemiology
Phylogeny
Anti-Bacterial Agents/pharmacology
Whole Genome Sequencing
Genome, Bacterial
Male
Microbial Sensitivity Tests
Female
RNA, Ribosomal, 16S/genetics
Adult
Middle Aged
*Burkholderiaceae/genetics/isolation & purification/drug effects/classification
*Bacteremia/epidemiology/microbiology
Molecular Epidemiology
Young Adult
Aged
Adolescent
*Gram-Negative Bacterial Infections/epidemiology/microbiology

@article {pmid40356651,
year = {2025},
author = {Zhang, B and Sun, W and Wang, X and Ren, H and Wang, Y and Hu, S and Li, C and Wang, Y and Hou, J and Hu, X and Shi, R and Li, Y and Lu, S and Lu, Q and Liu, Z and Hu, P},
title = {Exploration of the biodiversity and mining novel target genes of Listeria monocytogenes strains isolated from beef through comparative genomics analysis.},
journal = {Frontiers in microbiology},
volume = {16},
number = {},
pages = {1560974},
pmid = {40356651},
issn = {1664-302X},
abstract = {L. monocytogenes is a significant foodborne pathogen. This study aims to explore the biodiversity and evolutionary characteristics of L. monocytogenes isolated from beef through pan-genome analysis, and to provide important reference value for its specific molecular detection. This study conducted an in-depth analysis of the virulence genes, antimicrobial resistance genes, and environmental resistance genes of 344 L. monocytogenes strains isolated from beef. Pan-genomic analysis revealed that L. monocytogenes from beef have open genomes, providing a solid genetic basis for adaptation to different environments. MLST analysis revealed that the most prevalent types of L. monocytogenes isolated from beef were ST9 and CC9. A total of 50 virulence genes were detected in these strains, with 26 virulence genes such as inlA, inlB, plcA, plcB, and prfA, present in all L. monocytogenes strains. The four most prevalent antibiotic resistance genes in L. monocytogenes were norB, lin, mprF, and FosX, indicating high resistance to fluoroquinolones, lincosamides, peptides, and phosphonic acid antibiotics. A total of 416 potential target genes were identified through pan-genomic screening, which were then further filtered using a hub gene selection method to mining novel target genes. Ultimately, 10 highly connected hub genes were selected: bglF_2, tilS, group_2105, group_2431, oleD, ndk, flgG, purB, pbpB, and fni. These genes play a crucial role in the pathogenesis of L. monocytogenes. The PCR results demonstrated the excellent specificity of the bglF_2 gene for L. monocytogenes. Moreover, in the artificial contamination experiment, the bglF_2 gene was able to effectively detect L. monocytogenes in beef samples. Therefore, the bglF_2 gene holds potential as a specific molecular target for the detection of L. monocytogenes strains in beef samples.},
}

@article {pmid40353686,
year = {2025},
author = {Gluck-Thaler, E and Forsythe, A and Puerner, C and Gutierrez-Perez, C and Stajich, JE and Croll, D and Cramer, RA and Vogan, AA},
title = {Giant transposons promote strain heterogeneity in a major fungal pathogen.},
journal = {mBio},
volume = {},
number = {},
pages = {e0109225},
doi = {10.1128/mbio.01092-25},
pmid = {40353686},
issn = {2150-7511},
abstract = {Fungal infections are difficult to prevent and treat in large part due to strain heterogeneity, which confounds diagnostic predictability. Yet, the genetic mechanisms driving strain-to-strain variation remain poorly understood. Here, we determined the extent to which Starships-giant transposons capable of mobilizing numerous fungal genes-generate genetic and phenotypic variability in the opportunistic human pathogen Aspergillus fumigatus. We analyzed 519 diverse strains, including 11 newly sequenced with long-read technology and multiple isolates of the same reference strain, to reveal 20 distinct Starships that are generating genomic heterogeneity over timescales relevant for experimental reproducibility. Starship-mobilized genes encode diverse functions, including known biofilm-related virulence factors and biosynthetic gene clusters, and many are differentially expressed during infection and antifungal exposure in a strain-specific manner. These findings support a new model of fungal evolution wherein Starships help generate variation in genome structure, gene content, and expression among fungal strains. Together, our results demonstrate that Starships are a previously hidden mechanism generating genotypic and, in turn, phenotypic heterogeneity in a major human fungal pathogen.IMPORTANCENo "one size fits all" option exists for treating fungal infections in large part due to genetic and phenotypic variability among strains. Accounting for strain heterogeneity is thus fundamental for developing efficacious treatments and strategies for safeguarding human health. Here, we report significant progress toward achieving this goal by uncovering a previously hidden mechanism generating heterogeneity in the human fungal pathogen Aspergillus fumigatus: giant transposons, called Starships, that span dozens of kilobases and mobilize fungal genes as cargo. By conducting a systematic investigation of these unusual transposons in a single fungal species, we demonstrate their contributions to population-level variation at the genome, pangenome, and transcriptome levels. The Starship compendium we develop will not only help predict variation introduced by these elements in laboratory experiments but will serve as a foundational resource for determining how Starships impact clinically relevant phenotypes, such as antifungal resistance and pathogenicity.},
}

@article {pmid40343462,
year = {2025},
author = {Dubois, S and Zytnicki, M and Lemaitre, C and Faraut, T},
title = {Pairwise graph edit distance characterizes the impact of the construction method on pangenome graphs.},
journal = {Bioinformatics (Oxford, England)},
volume = {},
number = {},
pages = {},
doi = {10.1093/bioinformatics/btaf291},
pmid = {40343462},
issn = {1367-4811},
abstract = {MOTIVATION: Pangenome variation graphs are an increasingly used tool to perform genome analysis, aiming to replace a linear reference in a wide variety of genomic analyses. The construction of a variation graph from a collection of chromosome-size genome sequences is a difficult task that is generally addressed using a number of heuristics. The question that arises is to what extent the construction method influences the resulting graph, and the characterization of variability.

RESULTS: We aim to characterize the differences between variation graphs derived from the same set of genomes with a metric which expresses and pinpoint differences. We designed a pairwise variation graph comparison algorithm, which establishes an edit distance between variation graphs, threading the genomes through both graphs. We applied our method to pangenome graphs built from yeast and human chromosome collections, and demonstrate that our method effectively characterizes discordances between pangenome graph construction methods and scales to real datasets.

AVAILABILITY: pancat compare is published as free Rust software under the AGPL3.0 open source license. Source code and documentation are available at https://github.com/dubssieg/rs-pancat-compare. Snapshot available on Software Heritage at swh:1:dir:61acda8ba3dac1709ed60530147d3871831be629.

SUPPLEMENTARY INFORMATION: Supplementary data are available online at https://doi.org/10.5281/zenodo.10932489. Code to replicate figures and analysis is available online at https://github.com/dubssieg/pancat_paper.},
}

@article {pmid40343348,
year = {2025},
author = {Zhang, Y and Wang, L},
title = {Advances in basic biology of alfalfa (Medicago sativa L.): a comprehensive overview.},
journal = {Horticulture research},
volume = {12},
number = {7},
pages = {uhaf081},
pmid = {40343348},
issn = {2662-6810},
abstract = {Alfalfa (Medicago sativa L.), a perennial legume forage, has been broadly cultivated owing to a variety of favorable characteristics, including comprehensive ecological adaptability, superior nutritive value and palatability, and nitrogen fixation capacity. The productivity traits of alfalfa, specifically its biomass yield and forage quality, are significantly influenced by a series of determinants, including internal developmental factors and external environmental cues. However, the regulatory mechanisms underlying the fundamental biological problems of alfalfa remain elusive. Here, we conducted a comprehensive review focusing on the genomics of alfalfa, advancements in gene-editing technologies, and the identification of genes that control pivotal agronomic characteristics, including biomass formation, nutritional quality, flowering time, and resistance to various stresses. Moreover, a molecular design roadmap for the 'ideal alfalfa' has been proposed and the potential of pangenomes, self-incompatibility mechanisms, de novo domestication, and intelligent breeding strategies to enhance alfalfa's yield, quality, and resilience were further discussed. This review will provide comprehensive information on the basic biology of alfalfa and offer new insights for the cultivation of ideal alfalfa.},
}

@article {pmid40342602,
year = {2025},
author = {Wang, C and Ye, Q and Jiang, A and Zhang, J and Shang, Y and Li, F and Zhou, B and Xiang, X and Gu, Q and Pang, R and Ding, Y and Wu, S and Chen, M and Wu, Q and Wang, J},
title = {Corrigendum: Pseudomonas aeruginosa detection using conventional PCR and quantitative real-time PCR based on species-specific novel gene targets identified by pangenome analysis.},
journal = {Frontiers in microbiology},
volume = {16},
number = {},
pages = {1583946},
doi = {10.3389/fmicb.2025.1583946},
pmid = {40342602},
issn = {1664-302X},
abstract = {[This corrects the article DOI: 10.3389/fmicb.2022.820431.].},
}

@article {pmid40341387,
year = {2025},
author = {Marin, MG and Quinones-Olvera, N and Wippel, C and Behruznia, M and Jeffrey, BM and Harris, M and Mann, BC and Rosenthal, A and Jacobson, KR and Warren, RM and Li, H and Meehan, CJ and Farhat, MR},
title = {Pitfalls of bacterial pan-genome analysis approaches: a case study of M. tuberculosis and two less clonal bacterial species.},
journal = {Bioinformatics (Oxford, England)},
volume = {},
number = {},
pages = {},
doi = {10.1093/bioinformatics/btaf219},
pmid = {40341387},
issn = {1367-4811},
abstract = {UNLABELLED: Pan-genome analysis is a fundamental tool for studying bacterial genome evolution; however, the variety of methods used to define and measure the pan-genome poses challenges to the interpretation and reliability of results. Using Mycobacterium tuberculosis (Mtb)-characterized by clonal evolution, absence of horizontal gene transfer, and a small accessory genome-as a model system, we systematically evaluated sources of variability in pan-genome estimates. Our analysis revealed that differences in assembly type (short-read vs. hybrid), annotation pipeline, and pan-genome software, significantly impact predictions of core and accessory genome size. Extending our analysis to two additional bacterial species, Escherichia coli and Staphylococcus aureus, we observed consistent tool-dependent biases but species-specific patterns in pan-genome variability. Our findings highlight the need for robust quality control and careful methodological selection to accurately capture genome diversity and evolution. This work underscores the importance of integrating nucleotide- and protein-level analyses to improve the reliability and reproducibility of pan-genome studies across diverse bacterial populations.

AVAILABILITY: Panqc is freely available under an MIT license at https://github.com/maxgmarin/panqc.

CONTACT: maha_farhat@hms.harvard.edu.

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

@article {pmid40331911,
year = {2025},
author = {Pardeshi, LA and van Duivenbode, I and Pel, MJC and Jonkheer, EM and Kupczok, A and de Ridder, D and Smit, S and van der Lee, TAJ},
title = {Pangenomics to understand prophage dynamics in the Pectobacterium genus and the radiating lineages of Pectobacterium brasiliense.},
journal = {Microbial genomics},
volume = {11},
number = {5},
pages = {},
doi = {10.1099/mgen.0.001392},
pmid = {40331911},
issn = {2057-5858},
mesh = {*Pectobacterium/genetics/virology/classification ; *Prophages/genetics ; Phylogeny ; Genome, Bacterial ; Plant Diseases/microbiology ; Genomics/methods ; Evolution, Molecular ; Solanum tuberosum/microbiology ; Bacteriophages/genetics ; },
abstract = {Bacterial pathogens of the genus Pectobacterium are responsible for soft-rot and blackleg diseases in a wide range of crops and have a global impact on food production. The emergence of new lineages and their competitive succession is frequently observed in Pectobacterium species, in particular in Pectobacterium brasiliense. With a focus on one such recently emerged P. brasiliense lineage in the Netherlands that causes blackleg in potatoes, we studied genome evolution in this genus using a reference-free graph-based pangenome approach. We clustered 1,977,865 proteins from 454 Pectobacterium spp. genomes into 30,156 homology groups. The Pectobacterium genus pangenome is open, and its growth is mainly contributed by the accessory genome. Bacteriophage genes were enriched in the accessory genome and contributed 16% of the pangenome. Blackleg-causing P. brasiliense isolates had increased genome size with high levels of prophage integration. To study the diversity and dynamics of these prophages across the pangenome, we developed an approach to trace prophages across genomes using pangenome homology group signatures. We identified lineage-specific as well as generalist bacteriophages infecting Pectobacterium species. Our results capture the ongoing dynamics of mobile genetic elements, even in the clonal lineages. The observed lineage-specific prophage dynamics provide mechanistic insights into Pectobacterium pangenome growth and contribution to the radiating lineages of P. brasiliense.},
}

*Pectobacterium/genetics/virology/classification
*Prophages/genetics
Phylogeny
Genome, Bacterial
Plant Diseases/microbiology
Genomics/methods
Evolution, Molecular
Solanum tuberosum/microbiology
Bacteriophages/genetics

@article {pmid40331826,
year = {2025},
author = {Socarras, KM and Marino, MC and Earl, JP and Ehrlich, RL and Cramer, NA and Mell, JC and Sen, B and Ahmed, A and Marconi, RT and Ehrlich, GD},
title = {Characterization of the family-level Borreliaceae pan-genome and development of an episomal typing protocol.},
journal = {mBio},
volume = {},
number = {},
pages = {e0094325},
doi = {10.1128/mbio.00943-25},
pmid = {40331826},
issn = {2150-7511},
abstract = {UNLABELLED: The Borreliaceae family includes many obligate parasitic bacterial species etiologically associated with a myriad of zoonotic borrelioses, including Lyme disease and vector-borne relapsing fevers. Borreliaceae infections are difficult to detect by both direct and indirect methods, often leading to delayed and missed diagnoses. Efforts to improve diagnostics center around the development of molecular diagnostics (MDx), but due to deep tissue sequestration and the lack of persistent bacteremias, even MDx assays suffer from a lack of sensitivity. Additionally, the extensive genomic heterogeneity among isolates, even within the same species, contributes to the lack of assay sensitivity, as single target assays, whether nucleic acid-based or serologically based, cannot provide universal coverage. This within-species heterogeneity is partly due to differences in replicon repertoires and genomic structures that have likely arisen to support the complex Borreliaceae life cycle necessary for these parasites to survive in multiple hosts, each with unique immune responses. We constructed a Borreliaceae family-level pan-genome and characterized the phylogenetic relationships among the constituent taxa, which supports the recent, although contested, taxonomy of splitting the family into at least two genera. Gene content profiles were created for the majority of the Borreliaceae replicons, providing for the first time their unambiguous molecular typing. Our characterization of the Borreliaceae pan-genome supports the splitting of the former Borrelia genus into two genera and provides for the phylogenetic placement of several non-species designated isolates. Mining this family-level pan-genome will enable the development of precision diagnostics corresponding to gene content-driven clinical outcomes while also providing targets for interventions.

IMPORTANCE: Using whole genome sequencing, we demonstrated that the bacteria that are transmitted by ticks and other arthropod vectors that cause Lyme disease and relapsing fevers, while related, do not belong within the same genus classification. In addition, through characterization of their highly atypical genomic structure, we were able to develop a genetic typing system that will help with future studies of how they cause disease while also providing targets for medical interventions.},
}

@article {pmid40325156,
year = {2025},
author = {Sharar, NS and Iovine, A and De Castro, C and Hall, RM and Kenyon, JJ},
title = {Phage-encoded enzymes found in Acinetobacter baumannii convert pseudaminic acid to 8-epipseudaminic acid.},
journal = {Communications biology},
volume = {8},
number = {1},
pages = {700},
pmid = {40325156},
issn = {2399-3642},
support = {GNT1194978//Department of Health | National Health and Medical Research Council (NHMRC)/ ; FT230100400//Department of Education and Training | Australian Research Council (ARC)/ ; },
mesh = {*Acinetobacter baumannii/virology/genetics/metabolism/enzymology ; *Sugar Acids/metabolism ; Bacterial Capsules/metabolism ; *Prophages/genetics/enzymology ; *Bacteriophages/genetics/enzymology ; },
abstract = {The nonulosonic acid 8-epipseudaminic acid was discovered only recently in two Acinetobacter baumannii strains but the genes responsible for conversion of pseudaminic acid to its 8-epimer were not found at the K locus. Here, we use a pan-genome approach to identify a pair of carbohydrate biosynthesis genes, epaA and epaB, and demonstrate using NMR analysis of the capsular polysaccharide that they encode enzymes able to convert pseudaminic acid to its 8-epimer. Via an extensive survey of available A. baumannii genomes, we show that the epaA and epaB genes are present in 17 different Caudoviricetes class prophages. The prophages are in genomes that carry different capsule biosynthesis loci from isolates recovered in several different countries. The presence of epaA and epaB genes in A. baumannii isolates that are able to produce pseudaminic acid leads to modification of capsular polysaccharides that decorate their cell surface with potential implications for capsule typing and capsule-targeting therapies.},
}

*Acinetobacter baumannii/virology/genetics/metabolism/enzymology
*Sugar Acids/metabolism
Bacterial Capsules/metabolism
*Prophages/genetics/enzymology
*Bacteriophages/genetics/enzymology

@article {pmid40318771,
year = {2025},
author = {Ortega-Sanz, I and Rovira, J and Megías, G and Rivero-Pérez, MD and Melero, B},
title = {Genome-Wide association study to identify genetic markers associated with Campylobacter jejuni motility.},
journal = {Microbial pathogenesis},
volume = {205},
number = {},
pages = {107657},
doi = {10.1016/j.micpath.2025.107657},
pmid = {40318771},
issn = {1096-1208},
abstract = {The ability of Campylobacter jejuni to survive and persist under harsh conditions is linked to the presence of flagella. This structure promotes the motility of the bacteria towards their optimum environment. The aim of this study was to examine the genetic basis for motility within 136 C. jejuni isolates through two different Genome-Wide Association Studies, gene presence/absence and Single Nucleotide Polymorphisms (SNPs). The motility phenotype was widely distributed across the phylogeny with large intra-lineage swarming performance variabilities. Accessory genes significantly associated with motility were found in four key genomic regions. One of these regions affected the Cj0727-Cj0733 operon, that encodes a putative ABC transporter system for phosphate uptake, while other influenced the capsule biosynthesis locus. Multiple SNPs mostly linked to increased motility were also discovered in clusters of genes, with special relevance to transport and membrane proteins. Therefore, the capsule and membrane composition might influence nutrient transfer, further impacting the protonmotive force that drives flagellar motor rotation in C. jejuni. The study provides novel genetic markers with a potential role in the motility phenotype of the pathogen.},
}

@article {pmid40316944,
year = {2025},
author = {Dong, T and Yi, W and Zhang, M and Zhu, N and Jie, J and Peng, Z and Jiang, L and Wang, C and Song, L and Hua, S and Guan, Q},
title = {Comprehensive analysis of the type VI secretion system in Neisseria: identification, distribution, and evolutionary insights.},
journal = {BMC genomics},
volume = {26},
number = {1},
pages = {439},
pmid = {40316944},
issn = {1471-2164},
support = {JLSWSRCZX2023-23//Jilin Provincial Department of Finance funds awarded to Prof. Chunyan Wang/ ; 23YQ10//Technology Development Project of Changchun City funds awarded to Prof. Lei Song/ ; 20240305027YY//Jilin Provincial Department of Science and Technology funds awarded to Prof. Shucheng Hua/ ; 04045970001//The research start-up funds of Prof. Qingtian Guan/ ; },
mesh = {*Type VI Secretion Systems/genetics/metabolism ; *Neisseria/genetics/metabolism/classification ; Bacterial Proteins/genetics/metabolism ; *Evolution, Molecular ; Genome, Bacterial ; Phylogeny ; Genomics ; Computational Biology ; },
abstract = {The genus Neisseria, a gram-negative diplococcus, includes commensal and pathogenic species that infect mucosal tissues, causing diseases such as gonorrhea and meningitis. The type VI secretion system (T6SS), a multifunctional molecular machine that facilitates the ability of gram-negative bacteria to deliver effectors for bacterial competition, virulence, and interaction with host cells, has been widely studied across various bacterial taxa. However, research on the T6SS in the genus Neisseria remains limited. In this study, we employed comparative genomics and pangenomics, among other bioinformatics approaches, to characterize the distribution of the T6SS and its related proteins, including effectors, immunity proteins and regulators, across different species within the genus. Through an analysis of 5,067 Neisseria genomes, we identified two complete T6SS loci. We found that more than half of the Neisseria species possess at least one complete T6SS locus. Further investigation revealed multiple T6SS-related loci. We also applied a statistics-based method for identifying T6SS-associated orthologous groups and revealed 64 new T6SS-associated proteins within the genus. Our research provides a comprehensive analysis of the T6SS in Neisseria, advancing the understanding of T6SS-related mechanisms.},
}

*Type VI Secretion Systems/genetics/metabolism
*Neisseria/genetics/metabolism/classification
Bacterial Proteins/genetics/metabolism
*Evolution, Molecular
Genome, Bacterial
Phylogeny
Genomics
Computational Biology

@article {pmid40316932,
year = {2025},
author = {He, S and Ding, Q and Wu, W and Zhang, Y and Kang, Y and Meng, Y and Zhu, S and Wu, J},
title = {Unraveling the genetic traits and functional diversity of the pan-genome in Pantoea dispersa.},
journal = {BMC genomics},
volume = {26},
number = {1},
pages = {435},
pmid = {40316932},
issn = {1471-2164},
support = {GJJ2200401//Jiangxi Provincial Department of Education/ ; },
mesh = {*Pantoea/genetics/classification/drug effects/pathogenicity ; *Genome, Bacterial ; Multigene Family ; *Genetic Variation ; Phylogeny ; *Genomics/methods ; Whole Genome Sequencing ; Virulence Factors/genetics ; },
abstract = {BACKGROUND: Medical devices are crucial in modern healthcare, but commonly used clinical tools such as cotton swabs can be easily contaminated by microorganisms (such as Pantoea), becoming vectors for pathogens and leading to patient infections or more severe outcomes. Despite the dual nature of the Pantoea that has garnered significant attention, research investigating Pantoea dispersa (P. dispersa) remains limited. This study conducted a pan-genome analysis of three isolates and 57 P. dispersa strains from NCBI to investigate their evolutionary relationships, population structure, and functional characteristics.

RESULTS: Whole-genome analysis revealed high genomic diversity among 60 strains of P. dispersa, identifying 6,791 orthologous gene clusters (OGs), with core genes accounting for 45.1% and accessory genes accounting for 54.9%. Additionally, 2,185 gene clusters were not annotated in the reference genome. Further analysis demonstrated that 782 gene clusters were annotated as 406 VFs that were unevenly distributed among different strains and primarily associated with nutritional or metabolic factors, motility, and immune modulation. This study also identified four VFs genes related to the type III secretion system (T3SS) and observed some VFs present only in specific genetic clusters. In the analysis of antibiotic resistance genes (ARGs), 12 ARGs were identified, with nine being highly conserved across all isolates, and resistance mechanisms primarily involved antibiotic efflux and antibiotic target alteration. Secondary metabolite analysis identified 289 gene clusters, with 23 matching known gene clusters, while the rest were new discoveries, including arylpolyene, NRPS, and terpene types. These results reveal the complex virulence factors (VFs) and secondary metabolite genes in P. dispersa, providing significant insights into its genetic diversity and biological significance.

CONCLUSION: This study provides the first pan-genome framework for P. dispersa, along with a map of its VFs, ARGs, and secondary metabolite gene clusters. This study provides a deep insight into the genetic diversity and potential biological significance of P. dispersa, offering valuable references for leveraging its unique strain characteristics and metabolic capabilities in industrial production and clinical therapy.},
}

*Pantoea/genetics/classification/drug effects/pathogenicity
*Genome, Bacterial
Multigene Family
*Genetic Variation
Phylogeny
*Genomics/methods
Whole Genome Sequencing
Virulence Factors/genetics

@article {pmid40315852,
year = {2025},
author = {Lin, MJ and Langmead, B and Safonova, Y},
title = {IGLoo enables comprehensive analysis and assembly of immunoglobulin heavy-chain loci in lymphoblastoid cell lines using PacBio high-fidelity reads.},
journal = {Cell reports methods},
volume = {},
number = {},
pages = {101033},
doi = {10.1016/j.crmeth.2025.101033},
pmid = {40315852},
issn = {2667-2375},
abstract = {High-quality human genome assemblies derived from lymphoblastoid cell lines (LCLs) provide reference genomes and pangenomes for genomics studies. However, LCLs pose technical challenges for profiling immunoglobulin (IG) genes, as their IG loci contain a mixture of germline and somatically recombined haplotypes, making genotyping and assembly difficult with widely used frameworks. To address this, we introduce IGLoo, a software tool that analyzes sequence data and assemblies derived from LCLs, characterizing somatic V(D)J recombination events and identifying breakpoints and missing IG genes in the assemblies. Furthermore, IGLoo implements a reassembly framework to improve germline assembly quality by integrating information on somatic events and population structural variations in IG loci. Applying IGLoo to the assemblies from the Human Pangenome Reference Consortium, we gained valuable insights into the mechanisms, gene usage, and patterns of V(D)J recombination and the causes of assembly artifacts in the IG heavy-chain (IGH) locus, and we improved the representation of IGH assemblies.},
}

@article {pmid40315479,
year = {2025},
author = {Kharey, G and Palace, V and Whyte, L and Greer, C},
title = {Pangenomic analysis of three putative hydrocarbon degrading genera Limnohabitans, Aquabacterium, and Novosphingobium collected from freshwater sources.},
journal = {Genome},
volume = {},
number = {},
pages = {},
doi = {10.1139/gen-2023-0099},
pmid = {40315479},
issn = {1480-3321},
abstract = {A pangenome analysis offers a unique exploration of the metabolic and genetic diversity, range of ecological niches, and evolution of a particular genus or species. However, such pangenomic analyses are uncommon among environmentally relevant genera. Here, we present freshwater pangenomes of 3 environmentally relevant genera, Limnohabitans, Aquabacterium, and Novosphingobium. These genera had been detected in hydrocarbon degrading cultures in previous research by our group. Using pangenomic tools we attempted to characterize the extent of hydrocarbon degradation potential within each pangenome and determine what ecological niche each genus occupies within hydrocarbon degradation. In total 46 Limnohabitans, 10 Aquabacterium, and 32 Novosphingobium freshwater genomes were collected from various databases and compiled into pangenomes. We found that each pangenome harbours downstream hydrocarbon degrading potential and unexpected genetic diversity within its core and accessory pangenomes possibly stemming from geographic and metagenomic data processing influences. This work was the first to explore pangenomes of these environmentally relevant genera.},
}

@article {pmid40312599,
year = {2025},
author = {T N, VV and Premnath, M and Stanley, JV and Paul, N and Mathew, J and Radhakrishnan, EK},
title = {Whole genome sequencing based prediction of antimicrobial resistance evolution among the predominant bacterial pathogens of diabetic foot ulcer.},
journal = {World journal of microbiology & biotechnology},
volume = {41},
number = {5},
pages = {161},
pmid = {40312599},
issn = {1573-0972},
support = {Award No. IF190734//Department of Science and Technology, Ministry of Science and Technology, India/ ; },
mesh = {*Diabetic Foot/microbiology ; Humans ; Anti-Bacterial Agents/pharmacology ; Whole Genome Sequencing ; Klebsiella pneumoniae/genetics/drug effects/isolation & purification ; Microbial Sensitivity Tests ; Biofilms/growth & development/drug effects ; *Bacteria/genetics/drug effects/isolation & purification/classification ; Genome, Bacterial ; *Drug Resistance, Multiple, Bacterial/genetics ; Evolution, Molecular ; Methicillin-Resistant Staphylococcus aureus/genetics/drug effects/isolation & purification ; Male ; beta-Lactamases/genetics ; Middle Aged ; Female ; },
abstract = {Emerging antibiotic resistance among bacterial pathogens of diabetic foot ulcers (DFUs) cause a significant threat to the human health. In the study, deep ulcer swabs were collected from 70 diabetic patients with foot ulcer. Among the 187 bacterial strains purified from the same, major representations were identified to be from Klebsiella pneumoniae and Staphylococcus spp. Here, polymicrobial infection (87.14%) was found to be more prevalent than monomicrobial (12.86%). From the antibiotic susceptibility test results, 34 bacterial isolates were identified as MDR pathogens with resistance to β-lactam and carbapenem classes of antibiotics. Furthermore, molecular screening has revealed the presence of antibiotic resistance gene such as blaSHV,blaCTX-M, blaTEM,blaOXA-48, NDM-1, mecA and blaZ genes among the isolates studied. Biofilm analysis has further revealed 31 strains to have strong and 3 with moderate biofilm production property. Among the MDR strains, K. pneumoniae (DFU2.2) and methicillin-resistant S. aureus (MRSA) (DFU24.3) were subjected to the whole-genome sequencing (WGS) based analysis due to their significant role in the chronicity of DFUs. The resistome prediction from the WGS data of DFU2.2 has revealed it to have the presence of a novel extended β-lactamase gene blaSHV-106 which has not been reported previously from India. Pan-genome analysis of DFU2.2 and DFU24.3 has also provided detailed insight into the genetic diversity, evolution, and pathogenic potential of the selected strains. The findings of this study hence suggest the emerging AMR to be one of the major risk factors challenging the therapeutic response of DFUs, the incidence of which is alarmingly high.},
}

*Diabetic Foot/microbiology
Humans
Anti-Bacterial Agents/pharmacology
Whole Genome Sequencing
Klebsiella pneumoniae/genetics/drug effects/isolation & purification
Microbial Sensitivity Tests
Biofilms/growth & development/drug effects
*Bacteria/genetics/drug effects/isolation & purification/classification
Genome, Bacterial
*Drug Resistance, Multiple, Bacterial/genetics
Evolution, Molecular
Methicillin-Resistant Staphylococcus aureus/genetics/drug effects/isolation & purification
Male
beta-Lactamases/genetics
Middle Aged
Female

@article {pmid40312324,
year = {2025},
author = {Bui, PH and Cao, TNM and Tran, TT and Matsumoto, T and Akada, J and Yamaoka, Y},
title = {Identification of genetic determinants of antibiotic resistance in Helicobacter pylori isolates in Vietnam by high-throughput sequencing.},
journal = {BMC microbiology},
volume = {25},
number = {1},
pages = {264},
pmid = {40312324},
issn = {1471-2180},
support = {2022B13//Research Center for Global and Local Infectious Diseases (RCGLID)/ ; 21K08010//Ministry of Education, Culture, Sports, Science and Technology/ ; 21K07898//Ministry of Education, Culture, Sports, Science and Technology/ ; 18KK0266, 19H03473, 21H00346 and 22H02871//Ministry of Education, Culture, Sports, Science and Technology/ ; DK62813/NH/NIH HHS/United States ; e-ASIA JRP, SATREPS, GACD//Japan Agency for Medical Research and Development/ ; },
mesh = {*Helicobacter pylori/genetics/drug effects/isolation & purification ; High-Throughput Nucleotide Sequencing ; *Anti-Bacterial Agents/pharmacology ; Humans ; *Helicobacter Infections/microbiology ; Microbial Sensitivity Tests ; Vietnam ; *Drug Resistance, Bacterial/genetics ; Genome-Wide Association Study ; Genotype ; Plasmids/genetics ; Bacterial Proteins/genetics ; Female ; Male ; Middle Aged ; *Drug Resistance, Multiple, Bacterial/genetics ; Adult ; Clarithromycin/pharmacology ; },
abstract = {The aim of this study was to identify genetic factors responsible for antibiotic resistance in Helicobacter pylori, a bacterium that can cause long-term gastroduodenal disease. The primary resistance of H. pylori to commonly used antibiotics was studied, and high-throughput next-generation sequencing (NGS) was employed to discover genetic determinants of resistance using a reference-based approach. A total of 123 H. pylori strains were cultured and tested for antibiotic susceptibility using an E test. Genotypic analysis was performed using NGS data with ARIBA v2.14.7 and PlasmidSeeker v1.3 for plasmid detection. Statistical correlations between resistant genotypes and phenotypes were evaluated. In addition, a genome-wide association study (GWAS) and linear mixed model were used to identify genetic variants associated with antimicrobial resistance phenotypes while adjusting for covariates such as population structure. Our results showed that 78.2% of the strains were resistant to metronidazole (MTZ), 22.5% to levofloxacin (LVX), 43.5% to clarithromycin (CLR) and 13.7% to amoxicillin (AMX). Resistance to tetracycline was not detected. Multi-drug resistance was detected in 48.8% of the strains. While plasmids were not detected, chromosomal genetic determinants of resistance to CLR, LVX, and AMX were identified, including mutations in 23S rRNA (A2142G and A2143G), gyrA (N87K/Y and D91Y/N/G), and pbp1 A (F366L, S414R, F473V, G595_V596insE, as well as the mutations T558S and T593A/G/P/S). Additionally, missense, frameshift, and nonsense mutations in rdxA were identified as genetic determinants of resistance to MTZ. No genetic determinants associated with tetracycline resistance were detected. A strong correlation was observed between resistance genotypes and phenotypes for CLR, LVX, AMX, and MTZ. In addition, we found that missense, frameshift and nonsense mutations in rdxA were genetic determinants of resistance to MTZ. We did not detect any genetic determinants associated with tetracycline resistance. There was a strong correlation between resistance genotypes and phenotypes for CLR, LVX, AMX, and MTZ. Furthermore, unitig-based GWAS revealed that AMX, LVX, and CLR resistance in H. pylori was mainly caused by chromosomal mutations that affected the targets of these antibiotics (pbp1 A, gyrA, and 23S rRNA, respectively). Our results highlight the need for regular evaluation and alternative therapies in Vietnam, given the high rates of H. pylori resistance to CLR, MTZ, and LVX. Our study also demonstrated the high capacity of NGS to detect genetic resistance determinants and its potential for implementation in local treatment policies.},
}

*Helicobacter pylori/genetics/drug effects/isolation & purification
High-Throughput Nucleotide Sequencing
*Anti-Bacterial Agents/pharmacology
Humans
*Helicobacter Infections/microbiology
Microbial Sensitivity Tests
Vietnam
*Drug Resistance, Bacterial/genetics
Genome-Wide Association Study
Genotype
Plasmids/genetics
Bacterial Proteins/genetics
Female
Male
Middle Aged
*Drug Resistance, Multiple, Bacterial/genetics
Adult
Clarithromycin/pharmacology

@article {pmid40311451,
year = {2025},
author = {Wang, L and Deng, X and Zhang, Y and Yang, Z and Wu, Z and Yao, W and Yao, P and He, H and Wu, B},
title = {Prevalence, genomic features, and antibiotic sensitivities of Neisseria meningitidis isolates from patients with invasive meningococcal disease and healthy carriers in Zhejiang Province, 2015-2023.},
journal = {Diagnostic microbiology and infectious disease},
volume = {113},
number = {1},
pages = {116843},
doi = {10.1016/j.diagmicrobio.2025.116843},
pmid = {40311451},
issn = {1879-0070},
abstract = {OBJECTIVE: A comprehensive understanding of invasive meningococcal disease (IMD) and healthy carriers is critical to monitor, control, and prevent the disease. This study investigated the epidemiology of IMD cases and carriage, and compared population-specific genetic variations and antimicrobial susceptibility of Neisseria meningitidis (N. meningitidis) strains isolated from patients with IMD and carriers.

METHODS: Surveillance data from 2015 to 2023 on patients with epidemic meningitis and healthy carriers in Zhejiang Province, China. We successfully collected 21 isolates from meningitis patients and 16 isolates from healthy individuals during this period. Serogroups of a total of 37 N. meningitidis isolates were determined by polymerase chain reaction (PCR) and slide agglutination, as well as whole genome sequencing to assess various genes, single nucleotide polymorphisms (SNPs), and core-pan genome differences. The antibiotic susceptibility of 37 isolates to 12 antibiotics was evaluated using the E-Test on Mueller-Hinton agar supplemented with 5 % sheep blood.

RESULTS: The annual incidence of IMD and carriage rates remained relatively low from 2015 to 2023. IMD cases were primarily observed in infants under 12 months-of-age. Healthy carriers were predominantly 5-9 and 30-59 years-of-age. Population gene analysis revealed no significant difference in genes between the two groups. Strains of patient and carrier groups were both highly resistant to quinolones and sulfonamides.

CONCLUSIONS: The findings enhance the understanding of N. meningitidis carriage in the context of prevalent invasive meningococcal strains. The findings will facilitate the development and updating of the immunization program of meningitis vaccine, and are critical in understanding the spread and drug use strategies of N. meningitidis.},
}

@article {pmid40310468,
year = {2025},
author = {Stritt, C and Reitsma, M and Marin, AMG and Goig, G and Dötsch, A and Borrell, S and Beisel, C and Comas, I and Brites, D and Gagneux, S},
title = {Gene conversion and duplication contribute to genetic variation in an outbreak of Mycobacterium tuberculosis.},
journal = {Microbial genomics},
volume = {11},
number = {5},
pages = {},
doi = {10.1099/mgen.0.001396},
pmid = {40310468},
issn = {2057-5858},
mesh = {*Mycobacterium tuberculosis/genetics/classification ; Humans ; *Gene Duplication ; *Gene Conversion ; *Genetic Variation ; Genome, Bacterial ; Disease Outbreaks ; *Tuberculosis/epidemiology/microbiology ; Phylogeny ; Sequence Analysis, DNA ; },
abstract = {Repeats are the most diverse and dynamic but also the least well-understood component of microbial genomes. For all we know, repeat-associated mutations such as duplications, deletions, inversions and gene conversion might be as common as point mutations, but because of short-read myopia and methodological bias, they have received much less attention. Long-read DNA sequencing opens the perspective of resolving repeats and systematically investigating the mutations they induce. For this study, we assembled the genomes of 16 closely related strains of the bacterial pathogen Mycobacterium tuberculosis from Pacific Biosciences HiFi reads, with the aim of characterizing the full spectrum of DNA polymorphisms. We found that complete and accurate genomes can be assembled from HiFi reads, with read size being the main limitation in the presence of duplications. By combining a reference-free pangenome graph with extensive repeat annotation, we identified 110 variants, 58 of which could be assigned to repeat-associated mutational mechanisms such as strand slippage and homologous recombination. Whilst recombination events were less frequent than point mutations, they affected large regions and introduced multiple variants at once, as shown by three gene conversion events and a duplication of 7.3 kb that involved ppe18 and ppe57, two genes possibly involved in immune subversion. The vast majority of variants were present in single isolates, such that phylogenetic resolution was only marginally increased when estimating a tree from complete genomes. Our study shows that the contribution of repeat-associated mechanisms of mutation can be similar to that of point mutations at the microevolutionary scale of an outbreak. A large reservoir of unstudied genetic variation in this 'monomorphic' bacterial pathogen awaits investigation.},
}

*Mycobacterium tuberculosis/genetics/classification
Humans
*Gene Duplication
*Gene Conversion
*Genetic Variation
Genome, Bacterial
Disease Outbreaks
*Tuberculosis/epidemiology/microbiology
Phylogeny
Sequence Analysis, DNA

@article {pmid40310270,
year = {2025},
author = {Newstead, L and Smith-Zaitlik, T and Kelly, C and Roberts, E and Street, S and Paterson, GK},
title = {Genomic characterization of Pseudomonas aeruginosa from canine otitis highlights the need for a One Health approach to this opportunistic pathogen.},
journal = {Microbial genomics},
volume = {11},
number = {5},
pages = {},
doi = {10.1099/mgen.0.001407},
pmid = {40310270},
issn = {2057-5858},
mesh = {Animals ; Dogs ; *Pseudomonas aeruginosa/genetics/isolation & purification/drug effects/classification ; *Pseudomonas Infections/veterinary/microbiology ; Phylogeny ; *Dog Diseases/microbiology ; Anti-Bacterial Agents/pharmacology ; *Otitis/microbiology/veterinary ; Genome, Bacterial ; One Health ; Genomics ; Drug Resistance, Multiple, Bacterial/genetics ; Whole Genome Sequencing ; Microbial Sensitivity Tests ; Drug Resistance, Bacterial/genetics ; Humans ; },
abstract = {In humans, Pseudomonas aeruginosa is well known as a prominent opportunistic pathogen associated with antimicrobial resistance (AMR), which presents a major challenge to successful treatment. This is also the case in animals, particularly in companion dogs where P. aeruginosa is a common cause of otitis. Despite its clinical significance, little data are available on the genomics and epidemiology of P. aeruginosa in dogs. To address this, we have genome-sequenced 34 canine otitis P. aeruginosa isolates from a veterinary referral hospital and analysed these along with a further 62 publicly available genomes from canine isolates. Phylogenetic analysis revealed that all three P. aeruginosa phylogroups, A-C, are represented amongst a diverse bacterial population isolated from dogs. We identify examples of persistent or recurrent infection by the same strain of up to 309 days between sampling, demonstrating the difficulty of successfully eradicating infection. Isolates encoded a variety of AMR genes with genomic and phenotypic AMR correlating poorly for β-lactams but showing complete concordance between fluoroquinolone resistance and quinolone resistance-determining regions (QRDRs) of DNA gyrase and topoisomerase IV. Pangenome-wide analysis between 80 canine otitis isolates (34 newly sequenced here and a further 46 publicly available) and a reference collection of 491 human isolates found no genes which were over-represented or specific to either host species, indicating similar strains infect both humans and dogs. This agrees with the sharing of multilocus sequence types between dogs and humans, including the isolation here of ST235 from three dogs, a lineage prominent among the multidrug resistant (MDR) and extensively drug-resistant (XDR) international high-risk clones of P. aeruginosa causing human infections. The presence of such 'high-risk' clones in companion dogs is concerning given their potential impact on animal health and the potential for zoonotic spread. These data provide new insight into this difficult-to-treat veterinary pathogen and promote the need for a One Health approach to tackling it.},
}

Animals
Dogs
*Pseudomonas aeruginosa/genetics/isolation & purification/drug effects/classification
*Pseudomonas Infections/veterinary/microbiology
Phylogeny
*Dog Diseases/microbiology
Anti-Bacterial Agents/pharmacology
*Otitis/microbiology/veterinary
Genome, Bacterial
One Health
Genomics
Drug Resistance, Multiple, Bacterial/genetics
Whole Genome Sequencing
Microbial Sensitivity Tests
Drug Resistance, Bacterial/genetics
Humans

@article {pmid40305331,
year = {2025},
author = {Oliva, A and Foare, R and Campbell, P and Twine, NA and Bauer, DC and Johar, AS},
title = {A Pangenomic Approach to Improve Population Genetics Analysis and Reference Bias in Underrepresented Middle Eastern and Horn of Africa Populations.},
journal = {Biomolecules},
volume = {15},
number = {4},
pages = {},
pmid = {40305331},
issn = {2218-273X},
mesh = {Humans ; *Genetics, Population/methods ; Genome-Wide Association Study ; Gene Frequency ; *Genomics/methods ; Genome, Human ; Middle East ; Population Density ; Polymorphism, Single Nucleotide ; },
abstract = {Genomics plays a crucial role in addressing health disparities, yet most studies rely on the hg38 linear reference genome, limiting the potential of pangenomic approaches, particularly for underrepresented populations. In this study, we focus on characterising East African populations, particularly Somalis, by constructing a variation graph using Mozabites from the Human Genome Diversity Project (HGDP) given their ancestral affinity with Somalis. We evaluated the effectiveness of this graph-based reference in estimating effective population sizes (Ne) in Bedouins compared to the hg38 reference and examined its impact on allele frequencies and genome-wide association studies (GWAS). Applying a coalescent model to the graph-based reference produced a Ne estimate of approximately 17 for the Bedouin population, which was significantly lower than the estimate from the hg38 reference (approximately 79,000). Only the graph-based estimate fell within the 95% confidence interval in simulations, indicating improved accuracy. Moreover, graph variants exhibited significantly lower allele frequencies (p-value < 2.2 × 10[-16]), suggesting potential effects on the interpretation and power of GWAS. Notably, GWAS variants specific to Bedouins derived from the graph showed lower frequencies (p = 0.023) than those obtained from the linear reference. These findings suggest that a pangenomic approach, informed by populations with ancestral affinities such as the Mozabites, provides more accurate estimates of Ne and allele frequencies. This highlights the importance of pangenomic strategies to better capture genetic diversity in underrepresented populations, a critical step towards improving population genetics studies, personalised medicine, and equitable healthcare.},
}

Humans
*Genetics, Population/methods
Genome-Wide Association Study
Gene Frequency
*Genomics/methods
Genome, Human
Middle East
Population Density
Polymorphism, Single Nucleotide

@article {pmid40303430,
year = {2025},
author = {Wu, H and Yang, W and Dong, G and Hu, Q and Li, D and Liu, J},
title = {Construction of the super pan-genome for the genus Actinidia reveals structural variations linked to phenotypic diversity.},
journal = {Horticulture research},
volume = {12},
number = {6},
pages = {uhaf067},
pmid = {40303430},
issn = {2662-6810},
abstract = {Kiwifruits, belonging to the genus Actinidia, are acknowledged as one of the most successfully domesticated fruits in the twentieth century. Despite the rich wild resources and diverse phenotypes within this genus, insights into the genomic changes are still limited. Here, we conducted whole-genome sequencing on seven representative materials from highly diversified sections of Actinidia, leading to the assembly and annotation of 14 haplotype genomes with sizes spanning from 602.0 to 699.6 Mb. By compiling these haplotype genomes, we constructed a super pan-genome for the genus. We identified numerous structural variations (SVs, including variations in gene copy number) and highly diverged regions in these genomes. Notably, significant SV variability was observed within the intronic regions of the MED25 and TTG1 genes across different materials, suggesting their potential roles in influencing fruit size and trichome formation. Intriguingly, our findings indicated a high genetic divergence between two haplotype genomes, with one individual, tentatively named Actinidia × leiocacarpae, from sect. Leiocacarpae. This likely hybrid with a heterozygous genome exhibited notable genetic adaptations related to resistance against bacterial canker, particularly through the upregulation of the RPM1 gene, which contains a specific SV, after infection by Pseudomonas syringae pv. actinidiae. In addition, we also discussed the interlineage hybridizations and taxonomic treatments of the genus Actinidia. Overall, the comprehensive pan-genome constructed here, along with our findings, lays a foundation for examining genetic compositions and markers, particularly those related to SVs, to facilitate hybrid breeding aimed at developing desired phenotypes in kiwifruits.},
}

@article {pmid40302206,
year = {2025},
author = {Drebes Dörr, NC and Lemopoulos, A and Blokesch, M},
title = {Exploring Mobile Genetic Elements in Vibrio cholerae.},
journal = {Genome biology and evolution},
volume = {},
number = {},
pages = {},
doi = {10.1093/gbe/evaf079},
pmid = {40302206},
issn = {1759-6653},
abstract = {Members of the bacterial species Vibrio cholerae are known both as prominent constituents of marine environments and as the causative agents of cholera, a severe diarrheal disease. While strains responsible for cholera have been extensively studied over the past century, less is known about their environmental counterparts, despite their contributions to the species' pangenome. This study analyzed the genome compositions of 46 V. cholerae strains, including pandemic and non-pandemic, toxigenic, and environmental variants, to investigate the diversity of mobile genetic elements (MGEs), embedded bacterial defense systems, and phage-associated signatures. Our findings include both conserved and novel MGEs across strains, pointing to shared evolutionary pathways and ecological niches. The defensome analysis revealed a wide array of antiphage/anti-plasmid mechanisms, extending well beyond the traditional CRISPR-Cas and restriction-modification systems. This underscores the dynamic arms race between V. cholerae and MGEs and suggests that non-pandemic strains may act as reservoirs for emerging defense strategies. Moreover, the study showed that MGEs are integrated into genomic hotspots, which may serve as critical platforms for the exchange of defense systems, thereby enhancing V. cholerae's adaptive capabilities against phage attacks and other invading MGEs. Overall, this research offers new insights into V. cholerae's genetic complexity and potential adaptive strategies, offering a better understanding of the differences between environmental strains and their pandemic counterparts, as well as the possible evolutionary pathways that led to the emergence of pandemic strains.},
}

@article {pmid40301681,
year = {2025},
author = {},
title = {Insights into the evolution and genetic diversity of the Malus genus from pan-genome analysis.},
journal = {Nature genetics},
volume = {},
number = {},
pages = {},
pmid = {40301681},
issn = {1546-1718},
}

@article {pmid40300094,
year = {2025},
author = {Wagner, N and Baumer, E and Lyubman, I and Shimony, Y and Bracha, N and Martins, L and Potnis, N and Chang, JH and Teper, D and Koebnik, R and Pupko, T},
title = {Effectidor II: A pan-genomic AI-based algorithm for the prediction of type III secretion system effectors.},
journal = {Bioinformatics (Oxford, England)},
volume = {},
number = {},
pages = {},
doi = {10.1093/bioinformatics/btaf272},
pmid = {40300094},
issn = {1367-4811},
abstract = {MOTIVATION: Type III secretion systems are used by many Gram-negative bacteria to inject type 3 effectors (T3Es) directly into eukaryotic cells, promoting disease or provoking immune response. Because of these opposing evolutionary forces, T3E repertoires often vary within taxonomic groups. Identifying the full effector gene repertoire in genomes of related individuals is crucial for determining core and specialized effectors, understanding the disease dynamics, and developing appropriate management strategies against pathogens. It can also help uncover novel T3Es that have recently emerged in a population. Our previously published Effectidor web server successfully addressed the challenge of identifying T3Es in a single bacterial genome. Here, we enriched the web server with various novel capabilities, including the identification of T3Es from multiple genome sequences simultaneously.

RESULTS: We present Effectidor II, a web server that relies on machine learning to predict T3E-encoding genes within bacterial pan-genomes. We demonstrate the benefit of learning based on features extracted from the entire sequences comprising the pan-genome and report a novel T3E discovered by it in Xanthomonas euroxanthea.

AVAILABILITY: Effectidor II is available at: https://effectidor.tau.ac.il and the source code is available at: https://github.com/naamawagner/Effectidor. A stand-alone version of Effectidor II is available at: https://github.com/naamawagner/Effectidor/tree/StandAlone. The source code for the standalone version and the data used in this work are also provided in https://doi.org/10.5281/zenodo.15081636.

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

@article {pmid40298491,
year = {2025},
author = {Karampatakis, T and Tsergouli, K and Behzadi, P},
title = {Carbapenem-Resistant Pseudomonas aeruginosa's Resistome: Pan-Genomic Plasticity, the Impact of Transposable Elements and Jumping Genes.},
journal = {Antibiotics (Basel, Switzerland)},
volume = {14},
number = {4},
pages = {},
pmid = {40298491},
issn = {2079-6382},
abstract = {Pseudomonas aeruginosa, a Gram-negative, motile bacterium, may cause significant infections in both community and hospital settings, leading to substantial morbidity and mortality. This opportunistic pathogen can thrive in various environments, making it a public health concern worldwide. P. aeruginosa's genomic pool is highly dynamic and diverse, with a pan-genome size ranging from 5.5 to 7.76 Mbp. This versatility arises from its ability to acquire genes through horizontal gene transfer (HGT) via different genetic elements (GEs), such as mobile genetic elements (MGEs). These MGEs, collectively known as the mobilome, facilitate the spread of genes encoding resistance to antimicrobials (ARGs), resistance to heavy metals (HMRGs), virulence (VGs), and metabolic functions (MGs). Of particular concern are the acquired carbapenemase genes (ACGs) and other β-lactamase genes, such as classes A, B [metallo-β-lactamases (MBLs)], and D carbapenemases, which can lead to increased antimicrobial resistance. This review emphasizes the importance of the mobilome in understanding antimicrobial resistance in P. aeruginosa.},
}

@article {pmid40298412,
year = {2025},
author = {Majernik, SN and Beaver, L and Bradley, PH},
title = {Small amounts of misassembly can have disproportionate effects on pangenome-based metagenomic analyses.},
journal = {mSphere},
volume = {},
number = {},
pages = {e0085724},
doi = {10.1128/msphere.00857-24},
pmid = {40298412},
issn = {2379-5042},
abstract = {Individual genes from microbiomes can drive host-level phenotypes. To help identify such candidate genes, several recent tools estimate microbial gene copy numbers directly from metagenomes. These tools rely on alignments to pangenomes, which, in turn, are derived from the set of all individual genomes from one species. While large-scale metagenomic assembly efforts have made pangenome estimates more complete, mixed communities can also introduce contamination into assemblies, and it is unknown how robust pangenome-based metagenomic analyses are to these errors. To gain insight into this problem, we re-analyzed a case-control study of the gut microbiome in cirrhosis, focusing on commensal Clostridia previously implicated in this disease. We tested for differentially prevalent genes in the Lachnospiraceae and then investigated which were likely to be contaminants using sequence similarity searches. Out of 86 differentially prevalent genes, we found that 33 (38%) were probably contaminants originating in taxa such as Veillonella and Haemophilus, unrelated genera that were independently correlated with disease status. Our results demonstrate that even small amounts of contamination in metagenome assemblies, below typical quality thresholds, can threaten to overwhelm gene-level metagenomic analyses. However, we also show that such contaminants can be accurately identified using a method based on gene-to-species correlation. After removing these contaminants, we observe that several flagellar motility gene clusters in the Lachnospira eligens pangenome are associated with cirrhosis status. We have integrated our analyses into an analysis and visualization pipeline, PanSweep, that can automatically identify cases where pangenome contamination may bias the results of gene-resolved analyses.IMPORTANCEMetagenome-assembled genomes, or MAGs, can be constructed without pure cultures of microbes. Large-scale efforts to build MAGs have yielded more complete pangenomes (i.e., sets of all genes found in one species). Pangenomes allow us to measure strain variation in gene content, which can strongly affect phenotype. However, because MAGs come from mixed communities, they can contaminate pangenomes with unrelated DNA; how much this impacts downstream analyses has not been studied. Using a metagenomic study of gut microbes in cirrhosis as our test case, we investigate how contamination affects analyses of microbial gene content. Surprisingly, even small, typical amounts of MAG contamination (<5%) result in disproportionately high levels of false positive associations (38%). Fortunately, we show that most contaminants can be automatically flagged and provide a simple method for doing so. Furthermore, applying this method reveals a new association between cirrhosis and gut microbial motility.},
}

@article {pmid40297728,
year = {2025},
author = {Li, X and Dai, X and He, H and Chen, W and Qian, Q and Shang, L and Guo, L and He, W},
title = {Uncovering the breeding contribution of transposable elements from landraces to improved varieties through pan-genome-wide analysis in rice.},
journal = {Frontiers in plant science},
volume = {16},
number = {},
pages = {1573546},
pmid = {40297728},
issn = {1664-462X},
abstract = {INTRODUCTION: The rice improvement process, driven by modern breeding techniques, represents the second revolutionary advancement in rice agronomic traits, following domestication. Advances in pan-genomes and enhanced capacity for analyzing structural variations have increasingly highlighted their role in rice genetic improvement. Transposable element (TE) variants have been previously reported to influence rice genomic diversity during the domestication, but their contribution to the improvement from landraces to improved varieties remains unclear.

METHODS: Here, we combined a high-quality pan-TE variation map, transcriptome profiles, and phenotypic data for 100 landraces and 92 improved varieties to investigate the contribution of TE variations to phenotypic improvement in rice.

RESULTS: The total number and length of TE variations in improved varieties were significantly greater than those in rice landraces, particularly for Ty3-retrotransposons, LTR Copia and Helitron elements. Comparing landraces and improved varieties, 4,334 selective TEs were detected within or near 3,070 genes that were enriched in basic metabolism and development and stress resistance. Among the 14,076 differentially expressed genes between the two groups, the expression level of 3,480 (24.7%) genes were significantly associated with TE variations. Combining with haplotype analysis, we demonstrated potential patterns of how TEs affect gene expression variation and thereby participate in the improvement of important agronomic traits in rice.

DISCUSSION: Collectively, our results highlight the contributions of TE variations to rice improvement in shaping the genetic basis of modern rice varieties and will facilitate the exploration of superior genes and advance molecular breeding efforts in rice.},
}

@article {pmid40297566,
year = {2024},
author = {Palomino Huarcaya, RA and Castillo-Vilcahuaman, C and Martel-Torres, SB and Merino Rafael, FA and Gutiérrez Moreno, SM},
title = {Comparative Genomics of Rhamnolipid Synthesis and Monoaromatic Hydrocarbon Tolerance Genes in Environmental Pseudomonas aeruginosa strains.},
journal = {F1000Research},
volume = {13},
number = {},
pages = {1519},
pmid = {40297566},
issn = {2046-1402},
mesh = {*Pseudomonas aeruginosa/genetics/metabolism/drug effects ; *Genomics ; *Glycolipids/biosynthesis/genetics ; Genome, Bacterial ; *Hydrocarbons/metabolism/toxicity ; Phylogeny ; Biodegradation, Environmental ; *Genes, Bacterial ; },
abstract = {BACKGROUND: Bioremediation faces several compounds to recover oil spilled ecosystem. The BTEX (benzene, toluene, ethylbenzene, and xylene) are toxic hydrocarbons requiring efficient microbial degradation for bioremediation. Pseudomonas aeruginosa can degrade hydrocarbons through emulsification (rhl genes) and tolerance (mla genes). However, genomic organization of these systems in environmental P. aeruginosa strains remains unclear. This study aimed to investigate the rhl and mla systems in six strains isolated from hydrocarbon-contaminated sites in Peru.

METHODS: Six Pseudomonas aeruginosa strains were evaluated in this study. Each strain were able to degrade hydrocarbon and tolerate heavy metals. DNA extraction, sequencing, and quality-controlled assembly, functional genome annotation was performed using BAKTA. Comparative analysis included high-quality Pseudomonas genomes from RefSeq, with ANI metrics. A phylogenetic tree was built from core gene alignment, revealed evolutionary connections and was visualized with iTOL.

RESULTS: The assembled genomes ranged from 5.6 to 6.0 Mbp with ~66% GC content. All the strains were confirmed as P. aeruginosa by ANI; placing them within Clade 1 alongside environmental and clinical strains. Pangenome analysis identified 3,544 core genes and a diverse accessory genome. All strains had rhlABRI genes in a conserved 3'-5' orientation. Most of them contained duplicated rhlB gene, except C1BHIC5 strain. However, rhlG varied in position and orientation, it was often near rhlC, with C1BHIC5 also displaying an exception in rhlG orientation.100% of strains presented mla system, associated with toluene tolerance, with two copies of mlaA, mlaFEDC, and mlaEFD genes arranged with high synteny but variable orientations. In comparison to Pseudomonas putida, where mla genes are positioned between murA and ppcD with an additional toluene tolerance gene (ttg2D).

CONCLUSIONS: In conclusion, the presence of the rhlABC genes and the BTEX tolerance genes in all of the analyzed strains allowed us to understand the great ability of P. aeruginosa to survive in polluted environments.},
}

*Pseudomonas aeruginosa/genetics/metabolism/drug effects
*Genomics
*Glycolipids/biosynthesis/genetics
Genome, Bacterial
*Hydrocarbons/metabolism/toxicity
Phylogeny
Biodegradation, Environmental
*Genes, Bacterial

@article {pmid40295880,
year = {2025},
author = {Zhao, K and Xue, H and Li, G and Chitikineni, A and Fan, Y and Cao, Z and Dong, X and Lu, H and Zhao, K and Zhang, L and Qiu, D and Ren, R and Gong, F and Li, Z and Ma, X and Wan, S and Varshney, RK and Wei, C and Yin, D},
title = {Pangenome analysis reveals structural variation associated with seed size and weight traits in peanut.},
journal = {Nature genetics},
volume = {},
number = {},
pages = {},
pmid = {40295880},
issn = {1546-1718},
abstract = {Peanut (Arachis hypogaea L.) is an important oilseed and food legume crop, with seed size and weight being critical traits for domestication and breeding. However, genomic rearrangements like structural variations (SVs) underlying seed size and weight remain unclear. Here we present a comprehensive pangenome analysis utilizing eight high-quality genomes (two diploid wild, two tetraploid wild and four tetraploid cultivated peanuts) and resequencing data of 269 accessions with diverse seed sizes. We identified 22,222 core or soft-core, 22,232 distributed and 5,643 private gene families. The frequency of SVs in subgenome A is higher than in subgenome B. We identified 1,335 domestication-related SVs and 190 SVs associated with seed size or weight. Notably, a 275-bp deletion in gene AhARF2-2 results in loss of interaction with AhIAA13 and TOPLESS, reducing the inhibitory effect on AhGRF5 and promoting seed expansion. This high-quality pangenome serves as a fundamental resource for the genetic enhancement of peanuts and other legume crops.},
}

@article {pmid40295838,
year = {2025},
author = {Henriques, LR and Botelho, BBF and Carlson, RM and Carvalho, JVRP and Oliveira, EG and Agarkova, IV and Van Etten, JL and Dunigan, DD and Rodrigues, RAL},
title = {Revealing the hidden diversity of Chlorella heliozoae-infecting giant viruses.},
journal = {Npj viruses},
volume = {3},
number = {1},
pages = {12},
pmid = {40295838},
issn = {2948-1767},
support = {Finance Code 001//Coordenação de Aperfeiçoamento de Pessoal de Nível Superior/ ; Finance Code 001//Coordenação de Aperfeiçoamento de Pessoal de Nível Superior/ ; Finance Code 001//Coordenação de Aperfeiçoamento de Pessoal de Nível Superior/ ; 1736030//National Science Foundation/ ; 1736030//National Science Foundation/ ; 402038/2023-1//Conselho Nacional de Desenvolvimento Científico e Tecnológico/ ; APQ-01057-23//Fundação de Amparo à Pesquisa do Estado de Minas Gerais/ ; },
abstract = {A new level of viral complexity has emerged from the isolation of green algae-infecting chloroviruses from diverse aquatic environments around the world over the past few decades. This study focuses on describing and comparing the genomic features of gammachloroviruses, previously referred to as SAG-viruses. We present 24 novel isolates capable of forming plaques on lawns of Chlorella heliozoae SAG 3.83, including the first giant virus isolated from Greenland. Together with 13 previous isolates, these new viruses form a robust dataset that we used to investigate the genomic landscape and to test whether environmental conditions influence the species diversity of gammachloroviruses. Genome sizes range from 283 kbp to 385 kbp, with one new isolate having the smallest genome found in the genus Chlorovirus. Based on phylogenomics and global genome identity analysis, we defined 10 species of "Gammachlorovirus", half of which are represented by a single isolate. We observed a high level of genome synteny, and the tRNA islets maintain a distinct interspecific pattern, although some notable variations are evident. Our analysis reveals an open pan-genome composed of 681 COGs, more than 30% of which consist of uncharacterized genes, highlighting significant innovative genetic potential for these viruses. Our results suggest that the subgenus "Gammachlorovirus" exhibits the greatest genetic diversity among chloroviruses, with variability that is independent of geographic location. Overall, these findings underscore the considerable diversity within these ten newly defined species and the importance of isolating and characterizing chloroviruses from new locations worldwide to enhance our understanding of the ecology and evolution of this group of giant algal viruses.},
}

@article {pmid40295467,
year = {2025},
author = {Hasnat, S and Rahman, MM and Yeasmin, F and Jubair, M and Helmy, YA and Islam, T and Hoque, MN},
title = {Genomic and Computational Analysis Unveils Bacteriocin Based Therapeutics against Clinical Mastitis Pathogens in Dairy Cows.},
journal = {Probiotics and antimicrobial proteins},
volume = {},
number = {},
pages = {},
pmid = {40295467},
issn = {1867-1314},
abstract = {Clinical mastitis (CM) remains a critical challenge in dairy production, exacerbated by the global rise of antibiotic-resistant pathogens, which threatens herd health and productivity. This study pioneers a dual genomic-computational strategy to develop bacteriocin-based therapeutics-a promising alternative to conventional antibiotics-by targeting conserved virulence mechanisms in CM-causing pathogens. We aimed to (i) identify essential core proteins in CM-causing pathogens of dairy cows using the genomic approach; and (ii) assess the efficacy of bacteriocin peptides (BPs) as novel therapeutic agents targeting the selected core proteins for sustainable management of mastitis. Through pan-genomic analysis of 16 clinically relevant pathogens, including Staphylococcus aureus, S. warneri, Streptococcus agalactiae, S. uberis, Escherichia coli, Klebsiella pneumoniae, Pseudomonas aeruginosa, P. putida, and P. asiatica, we identified 65 evolutionarily conserved core proteins. Prioritization based on essentiality, virulence, and resistance potential revealed Rho (transcription termination factor) and HupB (nucleoid-associated protein) as high-value therapeutic targets due to their critical roles in bacterial survival and pathogenicity. A computational screen of 70 BPs identified 14 candidates with high binding affinity for both Rho and HupB proteins. Molecular dynamics simulations demonstrated that BP8, a novel dual-action bacteriocin, competitively inhibits Rho-mediated transcription termination and disrupts HupB-DNA interactions, effectively crippling bacterial replication and virulence. BP8 exhibited superior structural stability and binding efficacy compared to other candidates, positioning it as a potent broad-spectrum agent against diverse CM pathogens, including multidrug-resistant strains. Our study underscores the untapped potential of bacteriocins in veterinary medicine, offering a sustainable solution to mitigate antibiotic overuse and resistance. The computational validation of BP8 provides a foundational framework for developing targeted therapies, with implications for reducing dairy industry losses and improving animal welfare. Further in vitro and in vivo studies are warranted to translate these insights into practical therapeutics.},
}

@article {pmid40289080,
year = {2025},
author = {Derbyshire, MC and Newman, TE and Khentry, Y and Michael, PJ and Bennett, SJ and Rijal Lamichhane, A and Graham-Taylor, C and Chander, S and Camplone, C and Vicini, S and Esquivel-Garcia, L and Coutu, C and Hegedus, D and Clarkson, J and Lindbeck, K and Kamphuis, LG},
title = {Recombination and transposition drive genomic structural variation potentially impacting life history traits in a host-generalist fungal plant pathogen.},
journal = {BMC biology},
volume = {23},
number = {1},
pages = {110},
pmid = {40289080},
issn = {1741-7007},
support = {CUR00023//Grains Research and Development Corporation/ ; CUR00023//Grains Research and Development Corporation/ ; CUR00023//Grains Research and Development Corporation/ ; CUR00023//Grains Research and Development Corporation/ ; CUR00023//Grains Research and Development Corporation/ ; CUR00023//Grains Research and Development Corporation/ ; CUR00023//Grains Research and Development Corporation/ ; CUR00023//Grains Research and Development Corporation/ ; CUR00023//Grains Research and Development Corporation/ ; CUR00023//Grains Research and Development Corporation/ ; 2021-1-IT02-KA131-HED-000007409//Erasmus+ Extra EU Mobility, University of Perugia/ ; 2021-1-IT02-KA131-HED-000007409//Erasmus+ Extra EU Mobility, University of Perugia/ ; },
mesh = {*Recombination, Genetic ; *Ascomycota/genetics/physiology ; *Genomic Structural Variation ; *Genome, Fungal ; *DNA Transposable Elements ; *Life History Traits ; *Plant Diseases/microbiology ; },
abstract = {BACKGROUND: An understanding of plant pathogen evolution is important for sustainable management of crop diseases. Plant pathogen populations must maintain adequate heritable phenotypic variability to survive. Polymorphisms ≥ 50 bp, known as structural variants (SVs), could contribute strongly to this variability by disrupting gene activities. SV acquisition is largely driven by mobile genetic elements called transposons, though a less appreciated source of SVs is erroneous meiotic double-strand break repair. The relative impacts of transposons and recombination on SV diversity and the overall contribution of SVs to phenotypic variability is elusive, especially in host generalists.

RESULTS: We use 25 high-quality genomes to create a graphical pan-genome of the globally distributed host-generalist crop pathogen Sclerotinia sclerotiorum. Outcrossing and recombination rates in this self-fertile species have been debated. Using bisulfite sequencing and short-read data from 190 strains, we show that S. sclerotiorum has many hallmarks of eukaryotic meiosis, including recombination hot and cold spots, centromeric and genic recombination suppression, and rapid linkage disequilibrium decay. Using a new statistic that captures average pairwise structural variation, we show that recombination and transposons make distinct contributions to SV diversity. Furthermore, despite only 5% of genes being dispensable, SVs often had a stronger impact than other variants across 14 life history traits measured in 103 distinct strains.

CONCLUSIONS: Transposons and recombination make distinct contributions to SV diversity in S. sclerotiorum. Despite limited gene content diversity, SVs may strongly impact phenotypic variability. This sheds light on the genomic forces shaping adaptive flexibility in host generalists.},
}

*Recombination, Genetic
*Ascomycota/genetics/physiology
*Genomic Structural Variation
*Genome, Fungal
*DNA Transposable Elements
*Life History Traits
*Plant Diseases/microbiology

@article {pmid40287657,
year = {2025},
author = {De Maayer, P and Green, T and Jordan, S and Smits, THM and Coutinho, TA},
title = {Pan-genome analysis of the Enterobacter hormaechei complex highlights its genomic flexibility and pertinence as a multidrug resistant pathogen.},
journal = {BMC genomics},
volume = {26},
number = {1},
pages = {408},
pmid = {40287657},
issn = {1471-2164},
support = {310030L_204333//Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung/ ; 310030L_204333//Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung/ ; 310030L_204333//Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung/ ; 310030L_204333//Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung/ ; 310030L_204333//Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung/ ; },
mesh = {*Enterobacter/genetics/classification/drug effects/pathogenicity ; *Genome, Bacterial ; Phylogeny ; *Drug Resistance, Multiple, Bacterial/genetics ; *Genomics/methods ; Anti-Bacterial Agents/pharmacology ; DNA Transposable Elements ; Plasmids/genetics ; },
abstract = {BACKGROUND: Enterobacter hormaechei is of increasing concern as both an opportunistic and nosocomial pathogen, exacerbated by its evolving multidrug resistance. However, its taxonomy remains contentious, and little is known about its pathogenesis and the broader context of its resistome. In this study, a comprehensive comparative genomic analysis was undertaken to address these issues.

RESULTS: Phylogenomic analysis revealed that E. hormaechei represents a complex, comprising three predicted species, E. hormaechei, E. hoffmannii and E. xiangfangensis, with the latter putatively comprising three distinct subspecies, namely oharae, steigerwaltii and xiangfangensis. The species and subspecies all display open and distinct pan-genomes, with diversification driven by an array of mobile genetic elements including numerous plasmid replicons and prophages, integrative conjugative elements (ICE) and transposable elements. These elements have given rise to a broad, relatively conserved set of pathogenicity determinants, but also a variable set of secretion systems. The E. hormaechei complex displays a highly mutable resistome, with most taxa being multidrug resistant.

CONCLUSIONS: This study addressed key issues pertaining to the taxonomy of the E. hormaechei complex, which may contribute towards more accurate identification of strains belonging to this species complex in the clinical setting. The pathogenicity determinants identified in this study could serve as a basis for a deeper understanding of E. hormaechei complex pathogenesis and virulence. The extensive nature of multidrug resistance among E. hormaechei complex strains highlights the need for responsible antibiotic stewardship to ensure effective treatment of these emerging pathogens.},
}

*Enterobacter/genetics/classification/drug effects/pathogenicity
*Genome, Bacterial
Phylogeny
*Drug Resistance, Multiple, Bacterial/genetics
*Genomics/methods
Anti-Bacterial Agents/pharmacology
DNA Transposable Elements
Plasmids/genetics

@article {pmid40287647,
year = {2025},
author = {Abdullah, M and Kadivella, M and Sharma, R and Baig, MS and Faisal, SM and Azam, S},
title = {Identification of virulence genes and clade-specific markers through pan-genomic analysis of Leptospira.},
journal = {BMC microbiology},
volume = {25},
number = {1},
pages = {248},
pmid = {40287647},
issn = {1471-2180},
support = {BT/PR21430/ADV/90/246/2016//Department of Biotechnology, Ministry of Science and Technology, India/ ; },
mesh = {*Leptospira/genetics/pathogenicity/classification ; Phylogeny ; *Genome, Bacterial ; *Virulence Factors/genetics ; Virulence/genetics ; Leptospirosis/microbiology ; Genomics ; Whole Genome Sequencing ; Humans ; Animals ; },
abstract = {Leptospirosis is an emerging zoonotic and neglected disease across the world causing huge loss of life and economy. In this study, we did whole genome sequencing of one Leptospira isolate and a comparative genomic analysis with 69 other species of Leptospira available in RefSeq database provided insight into taxonomic and evolutionary relationship between species. AAI and whole genome based phylogenomic analysis established 3 clusters of Leptospira i.e. pathogenic, intermediate and saprophytic correlating with level of virulence of species. Leptospira has large closed core genome of 1038 genes and an open pan genome with 20,822 genes. The mobilome related genes were found mainly in pan-genome of pathogenic clade. A total of 498 genes have been identified as virulomes, with 329 virulent genes exhibiting presence/absence in various Leptospira species contributing to each species specific virulence profile. The hierarchical clustering of the congregated pathogenic genes yielded five groups, each with a distinct pattern of predominant genes that were either unique or common among clades, indicating lineage uniqueness. Most of the virulent gene pool identified were significantly enriched in COG functional categories of Nucleotide transport and metabolism, Intracellular trafficking, secretion and vesicular transport, cell motility and amino acid transport & metabolism. Pathogenic leptospires exhibit fewer clade-specific genes than non-pathogenic and intermediate leptospires, indicating gene loss and gain events in the evolution of pathogenic leptospires from non-pathogenic. The study's clade-specific and virulent genes can be utilised as markers for defining clade and associated virulence levels in any new Leptospira isolates. Wet-lab validation of virulent genes will help in accurately targeting pathogenic pathways of Leptospira and controlling leptospirosis.},
}

*Leptospira/genetics/pathogenicity/classification
Phylogeny
*Genome, Bacterial
*Virulence Factors/genetics
Virulence/genetics
Leptospirosis/microbiology
Genomics
Whole Genome Sequencing
Humans
Animals

@article {pmid40284743,
year = {2025},
author = {Zaidi, SE and Zaheer, R and Zovoilis, A and Fossen, J and Van Domselaar, G and Waldner, C and McAllister, TA},
title = {Genomic Characterization of Enterococcus casseliflavus Isolated from Beef Cows and Calves.},
journal = {Microorganisms},
volume = {13},
number = {4},
pages = {},
pmid = {40284743},
issn = {2076-2607},
support = {001//Genomic Research and Development Initiative AMR (GRDI-AMR)/ ; 001//Beef Cattle Research Council/ ; 001//National Science and Engineering Research Council/ ; },
abstract = {Enterococcus species are used as One Health indicators of antimicrobial resistance (AMR) in humans, animals, and the environment. A surveillance study in beef cows and calves isolated Enterococcus casseliflavus along with E. faecium, E. faecalis, and E. hirae. Given the high prevalence of E. casseliflavus, we elected to characterize this species to better understand its role in the antimicrobial resistance of enterococci in cows and calves. Almost 12% of E. casseliflavus isolates exhibited multidrug resistance with the majority being resistant to lincomycin (99%), followed by quinupristin-dalfopristin (34%), ciprofloxacin (9.6%), tylosin (4.5%), erythromycin (2.7%), tetracycline (1.8%), tigecycline (1.5%), daptomycin (0.6%), streptomycin (0.3%), and kanamycin (0.3%). All E. casseliflavus were susceptible to chloramphenicol, penicillin, streptomycin, nitrofurantoin, gentamicin, and linezolid. Whole genome antimicrobial resistance gene profiling identified vanC-type intrinsic vancomycin resistance genes in all E. casseliflavus, with the vanC4XYT gene cluster being dominant (67%) followed by vanC2XYT (31%) and vanC3XYT (1.5%). Resistance genes for erythromycin (ermB) and tetracycline (tetM) were rarely identified (2.1% and 1.2%, respectively) within E. casseliflavus genomes. No resistance genes were identified to explain either the quinupristin-dalfopristin or ciprofloxacin resistance in these isolates. A core genome phylogenetic tree revealed two clades that exhibited no distinct association with the age of the host, time of sample collection, or the farm sampled. The open nature of the E. casseliflavus pan-genome highlighted its intraspecies diversity. These findings suggest that E. casseliflavus is likely a low-risk species in terms of contributing to antimicrobial resistance in the cow-calf sector.},
}

@article {pmid40284693,
year = {2025},
author = {Olivos-Caicedo, KY and Fernandez-Materan, FV and Daniel, SL and Anantharaman, K and Ridlon, JM and Alves, JMP},
title = {Pangenome Analysis of Clostridium scindens: A Collection of Diverse Bile Acid- and Steroid-Metabolizing Commensal Gut Bacterial Strains.},
journal = {Microorganisms},
volume = {13},
number = {4},
pages = {},
pmid = {40284693},
issn = {2076-2607},
support = {1R03AI147127-20A1/NH/NIH HHS/United States ; },
abstract = {Clostridium scindens is a commensal gut bacterium capable of forming the secondary bile acids as well as converting glucocorticoids to androgens. Historically, only two strains, C. scindens ATCC 35704 and C. scindens VPI 12708, have been characterized to any significant extent. The formation of secondary bile acids is important in the etiology of cancers of the GI tract and in the prevention of Clostridioides difficile infection. We determined the presence and absence of bile acid inducible (bai) and steroid-17,20-desmolase (des) genes among C. scindens strains and the features of the pangenome of 34 cultured strains of C. scindens and a set of 200 metagenome-assembled genomes (MAGs) to understand the variability among strains. The results indicate that the C. scindens cultivars have an open pangenome with 12,720 orthologous gene groups and a core genome with 1630 gene families, in addition to 7051 and 4039 gene families in the accessory and unique (i.e., strain-exclusive) genomes, respectively. The pangenome profile including the MAGs also proved to be open. Our analyses reveal that C. scindens strains are distributed into two clades, indicating the possible onset of C. scindens separation into two species, as suggested by gene content, phylogenomic, and average nucleotide identity (ANI) analyses. This study provides insight into the structure and function of the C. scindens pangenome, offering a genetic foundation of significance for many aspects of research on the intestinal microbiota and bile acid metabolism.},
}

@article {pmid40284145,
year = {2025},
author = {Li, R and Lei, C and Zhang, Q and Guo, X and Cui, X and Wang, X and Li, X and Gao, J},
title = {Pan-Genome-Based Characterization of the SRS Transcription Factor Family in Foxtail Millet.},
journal = {Plants (Basel, Switzerland)},
volume = {14},
number = {8},
pages = {},
pmid = {40284145},
issn = {2223-7747},
support = {Grant No. 2023YFD1200700/2023YFD1200701, 2023YFD1202705/2023YFD120270502//the National Key R&D Program of China/ ; Grant No. YDZJSX20231B007//the Central Government's Guidance Fund for Local Science and Technology Development/ ; Grant No. U22A20445//the National Natural Science Foundation of China/ ; Grant No. 20210302123383, 202303021221097//the Basic Research Program of Shanxi Province/ ; },
abstract = {The Short Internodes-Related Sequence (SRS) family, a class of plant-specific transcription factors crucial for diverse biological processes, was systematically investigated in foxtail millet using pan-genome data from 110 core germplasm resources as well as two high-quality genomes (xm and Yu1). We identified SRS members and analyzed their intra-species distribution patterns, including copy number variation (CNV) and interchromosomal translocations. A novel standardized nomenclature (Accession_SiSRSN[.n]_xDy or xTy) was proposed to unify gene family nomenclature, enabling the direct visualization of member number variation across germplasms and the identification of core/variable members while highlighting chromosomal translocations. Focusing on the two high-quality genomes, both harboring six core SRS members, we performed whole-genome collinearity analysis with Arabidopsis, rice, maize, soybean, and green foxtail. Ka/Ks analysis of collinear gene pairs revealed purifying selection acting on SiSRS genes. Promoter analysis identified abundant stress-responsive cis-elements. Among core members, the xm_SiSRS5 gene exhibited the highest expression during vegetative growth but showed significant downregulation under drought and salt stress, suggesting its role as a key negative regulator in abiotic stress responses. This study demonstrates the utility of pan-genomics in resolving gene family dynamics and establishes SiSRS5 as a critical target for stress tolerance engineering in foxtail millet.},
}

@article {pmid40282422,
year = {2025},
author = {Wang, J and Liu, S and Pu, J and Li, J and He, C and Zhang, L and Zhou, X and Xu, D and Zhou, L and Guo, Y and Zhang, Y and Wang, Y and Yang, B and Wang, P and Deng, X and Sun, C},
title = {Comprehensive Analysis of Ghd7 Variations Using Pan-Genomics and Prime Editing in Rice.},
journal = {Genes},
volume = {16},
number = {4},
pages = {},
doi = {10.3390/genes16040462},
pmid = {40282422},
issn = {2073-4425},
support = {32172022, 31371602, 31401358, 32260502//National Natural Science Foundation of China/ ; 2023NSFSC0213, 2024NSFTD0022, 2022NSFSC1748//Natural Science Foundation of Sichuan Province/ ; },
mesh = {*Oryza/genetics/growth & development ; Polymorphism, Single Nucleotide ; *Genome, Plant ; *Plant Proteins/genetics ; Gene Editing/methods ; Genomics/methods ; Haplotypes ; High-Throughput Nucleotide Sequencing ; INDEL Mutation ; },
abstract = {The Ghd7 gene in rice plays a crucial role in determining heading date, plant height, and grain yield. However, the variations in Ghd7 and their functional implications across different rice accessions are not fully understood. Based on the release of a large amount of rice genome data in recent years, we investigated Ghd7 through pan-genome analysis of 372 diverse rice varieties and figured out the structural variations (SVs) in the Ghd7 locus. However, due to the high cost of pan-genomes, most genomes are based on next-generation sequencing (NGS) data now. Therefore, we developed a method for identifying SVs using NGS data and Polymerase Chain Reaction (PCR) based on the results of pan-genome analysis and identified 977 accessions carrying such SVs of Ghd7. Furthermore, we identified 46 single-nucleotide polymorphisms (SNPs) and one insertion-deletion (InDel) in the coding region of Ghd7. They are classified into 49 haplotypes. Notably, a splice-site mutation in haplotype H6 causes aberrant mRNA splicing. Using prime editing (PE) technology, we successfully restored the functional of Ghd7 in Yixiang 1B (YX1B), delaying the heading date by approximately 16 days. This modification synchronized the heading date between YX1B and the restorer line Yahui 2115 (YH2115R), enhancing the hybrid rice seed production efficiency. In conclusion, our findings highlight the potential of integrating pan-genomics and precision gene editing to accelerate crop improvement and enhance agronomic traits.},
}

*Oryza/genetics/growth & development
Polymorphism, Single Nucleotide
*Genome, Plant
*Plant Proteins/genetics
Gene Editing/methods
Genomics/methods
Haplotypes
High-Throughput Nucleotide Sequencing
INDEL Mutation

@article {pmid40282010,
year = {2025},
author = {Islam, SI and Shahed, K and Ahamed, MI and Khang, LTP and Jung, WK and Sangsawad, P and Dinh-Hung, N and Permpoonpattana, P and Linh, NV},
title = {Pathogenomic Insights into Piscirickettsia salmonis with a Focus on Virulence Factors, Single-Nucleotide Polymorphism Identification, and Resistance Dynamics.},
journal = {Animals : an open access journal from MDPI},
volume = {15},
number = {8},
pages = {},
doi = {10.3390/ani15081176},
pmid = {40282010},
issn = {2076-2615},
abstract = {Effective control of bacterial infections remains a significant challenge in aquaculture. The marine bacterium Piscirickettsia salmonis (P. salmonis), responsible for piscirickettsiosis, causes widespread infections in various salmon species, leading to substantial mortality and economic losses. Despite efforts to genetically characterize P. salmonis, critical gaps persist in understanding its virulence factors, antimicrobial resistance genes, and single-nucleotide polymorphisms (SNPs). This study addresses these gaps through a comparative analysis of the pan-genome and core genomes of 80 P. salmonis strains from different geographical regions and genogroups. P. salmonis had an open pan-genome consisting of 14,564 genes, with a core genome of 1257 conserved genes. Eleven virulence-related genes were identified in the pan-genome, categorized into five functional groups, providing new insights into the pathogenicity of P. salmonis. Unique SNPs were detected in four key genes (gyrA, dnaK, rpoB, and ftsZ), serving as robust molecular markers for distinguishing the LF and EM genogroups. Notably, AMR genes identified in four LF strains suggest evolutionary adaptations under selective pressure. Functional annotation of the core genomes using the gene ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) databases demonstrated conserved gene clusters linked to essential intracellular survival mechanisms and bacterial pathogenicity. These findings suggest a direct association between core genome features and variations in pathogenesis and host-pathogen interactions across genogroups. Phylogenetic reconstruction further highlighted the influence of AMR genes on strain divergence. Collectively, this study enhances the genomic understanding of P. salmonis and lays the groundwork for improved diagnostic tools and targeted therapeutics to manage piscirickettsiosis in aquaculture.},
}

@article {pmid40276381,
year = {2025},
author = {Zhang, P and Wu, X and Ji, L and Yan, W and Chen, L and Dong, F},
title = {Comparative pan-genomic analysis reveals pathogenic mechanisms and genomic plasticity in Vibrio parahaemolyticus clinical and environmental isolates.},
journal = {Frontiers in cellular and infection microbiology},
volume = {15},
number = {},
pages = {1574627},
pmid = {40276381},
issn = {2235-2988},
mesh = {*Vibrio parahaemolyticus/genetics/pathogenicity/isolation & purification/classification ; *Vibrio Infections/microbiology/epidemiology ; Humans ; Virulence Factors/genetics ; Virulence/genetics ; *Genome, Bacterial ; Genomics ; *Environmental Microbiology ; Genetic Variation ; Type III Secretion Systems/genetics ; Interspersed Repetitive Sequences ; },
abstract = {INTRODUCTION: Vibrio parahaemolyticus is a human pathogen capable of inducing bacterial gastroenteritis. Clinical strains of V. parahaemolyticus are considered pathogenic due to their possession of hemolysin and a type III secretion system (T3SS). Some environmental isolates are also acquiring corresponding virulence genes.

METHODS: This study initially examines the infection characteristics of V. parahaemolyticus, and subsequently employs pan-genomic analysis to identify genes that exhibit significant differences in distribution between environmental and clinical isolates, thereby revealing their potential impact on virulence.

RESULTS AND DISCUSSION: The epidemiological analysis of clinical isolates suggests that infections of V. parahaemolyticus are more prevalent in warm seasons, with O4:KUT serotype presenting more severe symptoms. OrthoFinder analysis revealed that environmental isolates possess a higher number of core genes. PEPPAN and KEGG analysis revealed that the 10 genes exclusively found in clinical isolates were predominantly associated with virulence. Additionally, the functions of genes differentially distributed in the environment were significantly more diverse compared to those in clinical settings. Analysis of mobile genetic elements suggested that environmental isolates harbor more mobile genetic elements, implying a potential for an increased number of resistance genes. The pathogenic characteristics of the strains examined in this study, genomic diversity and variation in mobile genetic elements are highly significant for deepening our understanding of the pathogenic mechanisms of V. parahaemolyticus and for the development of strategies to prevent its infections.},
}

*Vibrio parahaemolyticus/genetics/pathogenicity/isolation & purification/classification
*Vibrio Infections/microbiology/epidemiology
Humans
Virulence Factors/genetics
Virulence/genetics
*Genome, Bacterial
Genomics
*Environmental Microbiology
Genetic Variation
Type III Secretion Systems/genetics
Interspersed Repetitive Sequences

@article {pmid40275130,
year = {2025},
author = {Medina-Chávez, NO and Rodriguez-Cruz, UE and Souza, V and De la Torre-Zavala, S and Travisano, M},
title = {Salty secrets of Halobacterium salinarum AD88: a new archaeal ecotype isolated from Cuatro Cienegas Basin.},
journal = {BMC genomics},
volume = {26},
number = {1},
pages = {399},
pmid = {40275130},
issn = {1471-2164},
support = {IG200319,IN204822//PAPIIT-DGAPA, UNAM/ ; NASA IDEAS16002//NASA IDEAS/ ; },
mesh = {*Halobacterium salinarum/genetics/isolation & purification/classification/metabolism ; Phylogeny ; Genome, Archaeal ; Mexico ; Genomics ; },
abstract = {The Cuatro Cienegas Basin (CCB) in Mexico, represents a unique ecological habitat, characterized by extreme and fluctuating conditions, providing a window into ancient evolutionary processes. This basin, characterized by hypersalinity and phosphorus scarcity, harbors diverse microbial communities that exhibit remarkable adaptations to oligotrophic conditions. Among these, Halobacterium salinarum, a halophilic archaeon known for its polyploid genome and metabolic versatility, has been extensively studied as a model for extremophile survival. However, only a limited number of H. salinarum strains have been successfully cultured and characterized to date. Here, we report the isolation and genomic analysis of a novel Halobacterium salinarum strain, AD88, from microbial mats at the Archaean Domes site in the CCB. This strain displays unique genomic features, including smaller plasmid sizes and distinctive metabolic pathways for phosphorus and sulfur utilization. Comparative analyses with other Halobacterium strains revealed genetic innovations, such as genes involved in sulfolipid biosynthesis, enabling membrane stability in phosphorus-depleted environments, and adaptations for horizontal gene transfer, which facilitate genomic flexibility in response to environmental pressures. This study reveals that H. salinarum AD88 is the first recorded diploid strain of Halobacterium, a feature previously undocumented in this genus. Phylogenomic reconstruction positioned AD88 tightly within the Halobacterium clade, reflecting its evolutionary history within the genus. Pangenome analysis further highlighted the open nature of the Halobacterium genus, with AD88 contributing novel accessory genes linked to ecological specialization. These findings emphasize the evolutionary significance of the CCB as a natural laboratory for studying microbial adaptation and expand our understanding of archaeal genomic diversity and functional innovation under extreme conditions.},
}

*Halobacterium salinarum/genetics/isolation & purification/classification/metabolism
Phylogeny
Genome, Archaeal
Mexico
Genomics

@article {pmid40274494,
year = {2025},
author = {Good, BH and Bhatt, AS and McDonald, MJ},
title = {Unraveling the tempo and mode of horizontal gene transfer in bacteria.},
journal = {Trends in microbiology},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.tim.2025.03.009},
pmid = {40274494},
issn = {1878-4380},
abstract = {Research on horizontal gene transfer (HGT) has surged over the past two decades, revealing its critical role in accelerating evolutionary rates, facilitating adaptive innovations, and shaping pangenomes. Recent experimental and theoretical results have shown how HGT shapes the flow of genetic information within and between populations, expanding the range of possibilities for microbial evolution. These advances set the stage for a new wave of research seeking to predict how HGT shapes microbial evolution within natural communities, especially during rapid ecological shifts. In this article, we highlight these developments and outline promising research directions, emphasizing the necessity of quantifying the rates of HGT within diverse ecological contexts.},
}

@article {pmid40272172,
year = {2025},
author = {Hakimi, M and Ye, F and Saxena, A and Hu, X and Shen, H and Elankumaran, P and Stinman, CC and Macedo, N and Sahin, O and Burrough, ER and Li, G},
title = {Genomic insights into the population structure, antimicrobial resistance, and virulence of Brachyspira hyodysenteriae from diverse geographical regions.},
journal = {Microbiology spectrum},
volume = {},
number = {},
pages = {e0338624},
doi = {10.1128/spectrum.03386-24},
pmid = {40272172},
issn = {2165-0497},
abstract = {UNLABELLED: Swine dysentery, caused by the anaerobic spirochete Brachyspira hyodysenteriae, leads to mucohemorrhagic diarrhea in grower-finisher pigs, impacting swine production. Knowledge regarding its genomic epidemiology is limited. We performed a whole-genome sequence analysis for 251 B. hyodysenteriae genomes from 10 countries, including 117 isolates sequenced in this study. Phylogenomic analysis based on core-genome single nucleotide polymorphisms (SNPs) revealed nine lineages, with L7 (72 isolates, 28.69%), L9 (67 isolates, 26.69%), and L2 (53 isolates, 21.12%) predominating. Geographical clustering was observed with distinct lineage distributions. Multilocus sequence typing identified 69 sequence types (STs), including 20 novel STs across 251 genomes. Association between specific lineages, STs, and geographical regions was evident, highlighting evolutionary and regional patterns. The pan-genome analysis identified 5,231 genes, categorized into core (1,648), accessory (2,619), and unique (964) components. Functional annotation linked core genes to essential cellular processes, while accessory and unique genes were enriched in genetic variability, defense mechanisms, and secondary metabolism. The pan-genome exhibited a high proportion of hypothetical genes, necessitating further functional characterization. Antimicrobial resistance (AMR) screening detected the tva(A) and lnu(C) genes associated with tiamulin and lincomycin resistance, respectively, in specific lineages and STs. Virulence factor analysis identified genes linked to hemolysin production, iron uptake, and survival in host environments in most isolates, with a subset of genes demonstrating lineage-specific associations that are further linked to pathogenic potential. This comprehensive genomic epidemiological analysis elucidates the genetic diversity, antimicrobial resistance, and virulence of B. hyodysenteriae globally, enhancing understanding of its epidemiology and guiding interventions to mitigate swine dysentery.

IMPORTANCE: Brachyspira hyodysenteriae, the primary causative agent of swine dysentery, remains a less-studied pathogen than other bacterial species that impact animal health. This study uses whole-genome sequencing and advanced phylogenomic approaches to reveal the genetic diversity and geographical distribution of B. hyodysenteriae isolates, focusing on U.S. populations. The identification of nine distinct phylogenetic lineages and associated sublineages highlights the pathogen's complex population structure and regional variation. Importantly, the study detects AMR genes, including tva(A) and lnu(C), linked to tiamulin and lincomycin resistance, that may pose significant challenges to disease management. The analysis also identifies virulence-associated genes, shedding light on molecular mechanisms underlying pathogenicity. By combining core-genome SNP phylogenies with multilocus sequence typing and accessory genome insights, this work provides a robust framework for a better understanding of B. hyodysenteriae evolution. Overall, these findings underscore the importance of genomic surveillance in informing control strategies and improving swine health worldwide.},
}

@article {pmid40272150,
year = {2025},
author = {Ayoub, H and Kumar, MS and Mehta, R and Sethuraj, SE and Thomas, P and Dhanze, H and Dubey, M and Salih, HM and Chandrashekaraiah, GB and Cull, CA and Veeranna, RP and Amachawadi, RG},
title = {Genomic insights into Brucella melitensis in India: stability of ST8 and the role of virulence genes in regional adaptations.},
journal = {Microbiology spectrum},
volume = {},
number = {},
pages = {e0264724},
doi = {10.1128/spectrum.02647-24},
pmid = {40272150},
issn = {2165-0497},
abstract = {Brucella melitensis is a highly infectious zoonotic pathogen responsible for brucellosis, which significantly affects both human and livestock health worldwide. This study employed whole-genome sequencing (WGS) to analyze the genetic diversity of 24 B. melitensis isolates from India. Pangenome analysis revealed a highly conserved nature with the involved strains having very limited accessory genes. Multilocus Sequence Typing (MLST) identified sequence type ST8 as predominant among Indian strains. Analysis of virulence genes revealed a total of 43 virulence-related genes in all strains, emphasizing their critical role in the pathogenicity of B. melitensis. Unique gene profiles and distinct phylogenetic clusters suggest regional adaptations and evolutionary pressures. The comprehensive genomic insights from this study help to elucidate the geographic distribution and interspecies transmission of Indian strains, highlighting the importance of targeted brucellosis control measures in India. Additionally, the identification of conserved virulence genes involved in immune evasion and intracellular survival highlights their importance in the bacterium's pathogenicity. This research contributes to the global understanding of B. melitensis genomic diversity, providing valuable insights for broader epidemiological studies and brucellosis management strategies worldwide.IMPORTANCEB. melitensis is a significant cause of illness in both humans and animals, particularly in India, where the disease remains a major concern. This study highlights that only a few genetic types of the bacteria are circulating in the region, which means control efforts can be better focused on these specific types. By understanding the unique characteristics of Indian strains, and how these strains spread and adapt, this research offers valuable guidance for improving brucellosis prevention strategies. These insights can help in developing more effective diagnostic tools, enhancing vaccination efforts, and strengthening disease control programs to reduce the impact of brucellosis on public health and livestock industries.},
}

@article {pmid40272117,
year = {2025},
author = {Zehr, JD and Sun, Q and Ceres, K and Merrill, A and Tyson, GH and Ceric, O and Guag, J and Pauley, S and McQueary, HC and Sams, K and Reboul, G and Mitchell, PK and Anderson, R and Franklin-Guild, R and Guarino, C and Cronk, BD and Burbick, CR and Wolking, R and Peak, L and Zhang, Y and McDowall, R and Krishnamurthy, A and Slavic, D and Sekhon, PK and Needle, D and Gibson, R and Cazer, C and Rodriguez, J and Harris, B and Stanhope, MJ and Goodman, LB},
title = {Population and pan-genomic analyses of Staphylococcus pseudintermedius identify geographic distinctions in accessory gene content and novel loci associated with AMR.},
journal = {Applied and environmental microbiology},
volume = {},
number = {},
pages = {e0001025},
doi = {10.1128/aem.00010-25},
pmid = {40272117},
issn = {1098-5336},
abstract = {Staphylococcus pseudintermedius is a common representative of the normal skin microbiota of dogs and cats but is also a causative agent of a variety of infections. Although primarily a canine/feline bacterium, recent studies suggest an expanded host range including humans. This paper details population genomic analyses of the largest yet assembled and sequenced collection of S. pseudintermedius isolates from across the USA and Canada and assesses these isolates within a larger global population genetic context. We then employ a pan-genome-wide association study analysis of over 1,700 S. pseudintermedius isolates from sick dogs and cats, covering the period 2017-2020, correlating loci at a genome-wide level, with in vitro susceptibility data for 23 different antibiotics. We find no evidence from either core genome phylogenies or accessory genome content for separate lineages colonizing cats or dogs. Some core genome geographic clustering was evident on a global scale, and accessory gene content was noticeably different between various regions, some of which could be linked to known antimicrobial resistance (AMR) loci for certain classes of antibiotics (e.g., aminoglycosides). Analysis of genes correlated with AMR was divided into different categories, depending on whether they were known resistance mechanisms, on a plasmid, or a putatively novel resistance mechanism on the chromosome. We discuss several novel chromosomal candidates for follow-up laboratory experimentation, including, for example, a bacteriocin (subtilosin), for which the same protein from Bacillus subtilis has been shown to be active against Staphylococcus aureus infections, and for which the operon, present in closely related Staphylococcus species, is absent in S. aureus.IMPORTANCEStaphylococcus pseudintermedius is an important causative agent of a variety of canine and feline infections, with recent studies suggesting an expanded host range, including humans. This paper presents global population genomic data and analysis of the largest set yet sequenced for this organism, covering the USA and Canada as well as more globally. It also presents analysis of in vitro antibiotic susceptibility testing results for the North American (NA) isolates, as well as genetic analysis for the global set. We conduct a pan-genome-wide association study analysis of over 1,700 S. pseudintermedius isolates from sick dogs and cats from NA to correlate loci at a genome-wide level with the in vitro susceptibility data for 23 different antibiotics. We discuss several chromosomal loci arising from this analysis for follow-up laboratory experimentation. This study should provide insight regarding the development of novel molecular treatments for an organism of both veterinary and, increasingly, human medical concern.},
}

@article {pmid40270815,
year = {2025},
author = {Esteves, MAC and Carvalho, MF and Viana, AS and Martini, CL and Longo, LGA and Silva, DNS and Ferreira, ALP and Ferreira-Carvalho, BT and Planet, PJ and Figueiredo, AMS},
title = {Decoding the evolutionary history of ST30 Staphylococcus aureus: insights into a potentially silent MSSA bloodstream pathogen.},
journal = {Frontiers in microbiology},
volume = {16},
number = {},
pages = {1522747},
doi = {10.3389/fmicb.2025.1522747},
pmid = {40270815},
issn = {1664-302X},
abstract = {BACKGROUND: Staphylococcus aureus clonal complex 30 (CC30) is a historically significant pathogen affecting both hospital and community settings. The notable pandemic clones, phage-type 80/81 (PT80/81) and the Southwest Pacific clone (SWP) have spread internationally, contributing to significant morbidity and mortality. Despite their importance, research on the evolution of sequence type (ST) 30 has been limited, often focusing on a small number of strains or specific regions.

METHODS: In this study, we analyzed over 500 ST30 genomes from diverse sources, including Brazilian strains sequenced by our team, using genomic, pangenomic, phylogenetic, and time-calibrated phylogenetic analyses.

RESULTS: We traced key evolutionary events, estimating that the specialization of PT80/81 and SWP occurred after a divergence around 1868, forming a group of PT80/81-related strains and another group formed by SWP-related strains. Our findings highlight major events involving gene acquisition and loss, as well as mobile genetic elements (MGE). Notably, PT80/81 lost most lpl genes during diversification, which may have restricted the circulation of related strains. Contemporary strains-defined as those that emerged in the 21st century-predominantly cluster within a group divided into three subgroups, including Brazilian strains that acquired a novel pathogenicity island. Also clustering within the contemporary group, most toxic shock syndrome toxin-1 (TSST-1)-producing strains are methicillin-susceptible S. aureus (MSSA) that have gained additional virulence traits, including sea, which enhance their adaptability and virulence.

CONCLUSION: Our study revises the evolutionary history of ST30 S. aureus uncovering critical pathoadaptive events that may explain its success. Additionally, our findings emphasize a neglected issue: the high prevalence of MSSA in hospital infections, particularly the silent circulation of TSST-1 producing strains, capable of causing severe infections. Robust surveillance studies to monitor these strains are crucial.},
}

@article {pmid40269327,
year = {2025},
author = {He, F and Chen, S and Zhang, Y and Chai, K and Zhang, Q and Kong, W and Qu, S and Chen, L and Zhang, F and Li, M and Wang, X and Lv, H and Zhang, T and He, X and Li, X and Li, Y and Li, X and Jiang, X and Xu, M and Sod, B and Kang, J and Zhang, X and Long, R and Yang, Q},
title = {Pan-genomic analysis highlights genes associated with agronomic traits and enhances genomics-assisted breeding in alfalfa.},
journal = {Nature genetics},
volume = {},
number = {},
pages = {},
pmid = {40269327},
issn = {1546-1718},
abstract = {Alfalfa (Medicago sativa L.), a globally important forage crop, is valued for its high nutritional quality and nitrogen-fixing capacity. Here, we present a high-quality pan-genome constructed from 24 diverse alfalfa accessions, encompassing a wide range of genetic backgrounds. This comprehensive analysis identified 433,765 structural variations and characterized 54,002 pan-gene families, highlighting the pivotal role of genomic diversity in alfalfa domestication and adaptation. Key structural variations associated with salt tolerance and quality traits were discovered, with functional analysis implicating genes such as MsMAP65 and MsGA3ox1. Notably, overexpression of MsGA3ox1 led to a reduced stem-leaf ratio and enhanced forage quality. The integration of genomic selection and marker-assisted breeding strategies improved genomic estimated breeding values across multiple traits, offering valuable genomic resources for advancing alfalfa breeding. These findings provide insights into the genetic basis of important agronomic traits and establish a solid foundation for future crop improvement.},
}

@article {pmid40269305,
year = {2025},
author = {Graham, F},
title = {Daily briefing: Potato pangenome reveals the complex genetics of the humble spud.},
journal = {Nature},
volume = {},
number = {},
pages = {},
doi = {10.1038/d41586-025-01282-x},
pmid = {40269305},
issn = {1476-4687},
}

@article {pmid40268598,
year = {2025},
author = {Tai, HH and Shannon, LM and Strömvik, MV},
title = {Polyploidy in potatoes: challenges and possibilities for climate resilience.},
journal = {Trends in genetics : TIG},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.tig.2025.03.006},
pmid = {40268598},
issn = {0168-9525},
abstract = {Solanum section Petota Dumort. consists of tuber-bearing species (i.e., the cultivated potatoes and their wild relatives) that have both asexual and sexual propagation, variation in ploidy, and reproductive isolation. These species have undergone adaptation to a diversity of climates, altitudes, photoperiods, and geographical range. The section defies characterization with the biological species concept due to interspecies hybridization, allo- and auto-polyploidy, and phenotypic plasticity. Genetic studies, and more recently genome sequencing and pangenome analyses, are fostering a greater understanding of genetic processes that shape genome evolution and speciation in the section, shedding light on the phylogeny and providing insights on utilization of potato crop wild relatives in breeding for climate-resilient potato varieties.},
}

@article {pmid40268564,
year = {2025},
author = {Barros, JAS and Nunes-Nesi, A and Fernie, AR and Araújo, WL},
title = {Transcriptional crosstalk linking color, acidity, and aroma in peach.},
journal = {Trends in plant science},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.tplants.2025.04.003},
pmid = {40268564},
issn = {1878-4372},
abstract = {Color and flavor are key quality traits in fruits. Using a newly constructed peach pangenome, Chen et al. demonstrated that the PbBL gene, a known regulator of peach fruit color, also contributes to malate accumulation. This finding, along with previous studies, unveils a transcriptional mechanism that co-regulates multiple traits in peaches.},
}

@article {pmid40266657,
year = {2025},
author = {Naing, SY and Zomer, A and der Graaf-van Bloois, LV and Houben, M and Junker, K and Schreurs, O and Heuvelink, A and Wagenaar, JA and van Hout, J},
title = {Molecular epidemiology and emergence of sequence type 25 hypervirulent Klebsiella pneumoniae in pigs in the Netherlands (2013-2020): a global comparative analysis with human and pig isolates.},
journal = {Microbial genomics},
volume = {11},
number = {4},
pages = {},
doi = {10.1099/mgen.0.001388},
pmid = {40266657},
issn = {2057-5858},
mesh = {Animals ; *Klebsiella pneumoniae/genetics/pathogenicity/isolation & purification/classification/drug effects ; Swine ; Humans ; Netherlands/epidemiology ; *Klebsiella Infections/epidemiology/microbiology/veterinary ; Virulence/genetics ; Plasmids/genetics ; Phylogeny ; Molecular Epidemiology ; *Swine Diseases/microbiology/epidemiology ; Drug Resistance, Multiple, Bacterial/genetics ; Virulence Factors/genetics ; },
abstract = {Klebsiella pneumoniae (Kp), a ubiquitous pathogen found in diverse ecological niches, poses a threat to human and animal health. Hypervirulent Kp (hvKp) is concerning for its acquisition of virulence and antimicrobial resistance genes through plasmids. This study investigates hvKp as a cause of septicaemia in piglets in the Netherlands and examines the role of plasmids in virulence and host association. We collected 41 Kp isolates cultured from necropsies submitted from 15 different farms (2013-2020) and sequenced them using long-read sequencing. We identified sequence type (ST) 25 as the dominant Kp (67%, 10/15 farms) associated with septicaemia in pigs in the Netherlands. ST25 isolates displayed a hypervirulent profile, including the K2 hyper-capsule type and carried an iuc3 virulence plasmid. Further analysis revealed two ST25 clonal groups: CG25 and CG3804, a novel porcine clone. Multidrug resistance was identified in CG25 isolates from five pig farms. There was one colistin-resistant isolate carrying mcr-1 on a plasmid. Comparative genomic analysis was performed by including a large dataset of related publicly available Kp genomes from ST25 humans (n=230) and pigs (n=12) of all STs for phylogenetic and plasmid analysis. Pangenomic analysis revealed significantly higher iuc3 prevalence in global CG25 pig isolates (98%, 40/41) compared to humans (10%, 24/234) correlating with their enhanced virulence (scores 3-4 vs 0-1). The study highlights ST25 hvKp causing septicaemia in piglets in the Netherlands for the first time. Aerobactin lineage iuc3 on a plasmid is associated with infections in pigs and is responsible for an increased virulence score.},
}

Animals
*Klebsiella pneumoniae/genetics/pathogenicity/isolation & purification/classification/drug effects
Swine
Humans
Netherlands/epidemiology
*Klebsiella Infections/epidemiology/microbiology/veterinary
Virulence/genetics
Plasmids/genetics
Phylogeny
Molecular Epidemiology
*Swine Diseases/microbiology/epidemiology
Drug Resistance, Multiple, Bacterial/genetics
Virulence Factors/genetics

@article {pmid40265878,
year = {2025},
author = {Tosoroni, A and Di Vittori, V and Nanni, L and Musari, E and Papalini, S and Bitocchi, E and Bellucci, E and Pieri, A and Ghitarrini, S and Susek, K and Papa, R},
title = {Recent Advances in Molecular Tools and Pre-Breeding Activities in White Lupin (Lupinus albus).},
journal = {Plants (Basel, Switzerland)},
volume = {14},
number = {6},
pages = {},
doi = {10.3390/plants14060914},
pmid = {40265878},
issn = {2223-7747},
support = {862862//Horizon2020/ ; 101081329//Horizon2020/ ; },
abstract = {The higher adaptation of landraces to local agroclimatic conditions resulting from natural and moderate artificial selection by farmers within specific environments makes them a crucial source of alleles and genotypes for cultivation and breeding programs. Unlike modern cultivars, which have been developed under more intense artificial selective pressures, landraces exhibit a broader genetic base that has been documented in landrace collections for many crops. This review provides an overview of the importance of genetic resource valorisation in legume species, focusing on cultivated species of the Lupinus genus, particularly white lupin (Lupinus albus). On the one hand, legumes, including Lupins, are considered a crucial alternative source of protein within the framework of more sustainable agriculture. On the other hand, they are often neglected species in terms of breeding efforts, despite receiving increasing attention in recent years. Here, we also report on the latest advances in the development of genomic tools, such as the novel pangenome of white lupin and the identification of markers and loci for target adaptation traits, such as tolerance to alkaline soils, which can effectively support the breeding of Lupinus albus, especially for the introgression of desirable alleles from locally adapted varieties.},
}

@article {pmid40263939,
year = {2025},
author = {Li, Y and Arús, P and Wu, J and Zhu, G and Fang, W and Chen, C and Wang, X and Cao, K and Wang, L},
title = {Panvariome and pangenome of 1,020 global peach accessions shed light on evolution patterns, hidden natural variations and efficient gene discovery.},
journal = {Molecular plant},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.molp.2025.04.009},
pmid = {40263939},
issn = {1752-9867},
abstract = {Natural variations are the basis of crop improvement. However, genomic variability remains largely understudied. We present the full-spectrum integrated panvariome and pangenome of 1,020 peach accessions, including 10.5 million SNPs, indels, DELs, INSs, DUPs, INVs, TRAs, CNVs, TIPs, and PAVs, uncovering 70.6% novel variants and 3,289 novel genes. Analysis of the panvariome reconstructs the globally evolutionary history of peach and identifies several novel trait-causally rare variants, improving the power of breeding markers. Landraces and improved accessions encode more genes than wild accessions, implying the gene gains during domestication and improvement. Global introgression patterns reveal its new utilizations in phenotype prediction and gene mining and firstly suggest that the most likely wild progenitor of domesticated peach is Prunus mira and almond was involved in the origin of Prunus davidiana. We develop a novel panvariome-based solution for association study, GWASPV, identifying several trait-conferring genes and more than 2,000 novel associations, that achieves rapid and precise identification of trait-conferring genes using only one-step GWAS. Our study provides a novel solution for gene mining, with important implications in accelerating plant breeding.},
}

@article {pmid40263846,
year = {2025},
author = {Gómez-Baltazar, A and Hernández-Pérez, CF and Franco-Frias, CU and Castañeda-Ruelas, GM and Cabrera-Diaz, E and Hernández-Iturriaga, M},
title = {Genomic diversity and distribution of Listeria monocytogenes strains isolated from imported and national fresh produce in Mexico from 2014 to 2018.},
journal = {Food research international (Ottawa, Ont.)},
volume = {208},
number = {},
pages = {116211},
doi = {10.1016/j.foodres.2025.116211},
pmid = {40263846},
issn = {1873-7145},
mesh = {*Listeria monocytogenes/genetics/isolation & purification/classification/pathogenicity ; Mexico ; *Food Microbiology ; *Genetic Variation ; Virulence Factors/genetics ; Whole Genome Sequencing ; *Genome, Bacterial ; Virulence/genetics ; Drug Resistance, Bacterial/genetics ; Polymorphism, Single Nucleotide ; *Vegetables/microbiology ; Prophages/genetics ; },
abstract = {Listeria monocytogenes is a major foodborne pathogen associated with fresh produce contamination, posing a significant public health risk due to its adaptability and virulence. This study investigates the genomic diversity and distribution of L. monocytogenes strains isolated from imported and domestic fresh produce in Mexico between 2014 and 2018. A total of 113 L. monocytogenes strains were isolated from produce commodities and subjected to whole-genome sequencing. The analysis focused on identifying lineages, serogroups, clonal complexes (CCs), antimicrobial resistance genes, virulence factors, prophage-associated regions, and SNP clusters, while the pangenome was characterized to assess both core and accessory gene diversity. Two main lineages (I and II) were identified, with lineage I predominantly associated with imported produce. Thirty-two CCs were detected, with CC4, CC11, and CC20 being the most prevalent. The pangenome analysis revealed 2188 core genes and 3739 accessory genes. Antimicrobial resistance genes, including fosX, lin, norB, and sul, were present in all strains. Virulence analysis identified 78 virulence genes, with notable differences among serogroups. Prophage analysis revealed 189 prophage-associated regions, with common phages such as A118 and LP-101 detected predominantly in serogroup IIa. The SNP cluster analysis grouped the strains into 33 clusters, with 48 % of the strains from imported produce concentrated in only three major clusters, indicating potential common sources or similar environmental exposures. The significant genomic diversity and SNP clustering of L. monocytogenes strains underscore the pathogen's adaptability and widespread dissemination potential in the global food supply chain. The presence of virulent CCs and antimicrobial resistance genes highlights an ongoing public health risk, emphasizing the need for enhanced surveillance and targeted interventions to prevent listeriosis outbreaks.},
}

*Listeria monocytogenes/genetics/isolation & purification/classification/pathogenicity
Mexico
*Food Microbiology
*Genetic Variation
Virulence Factors/genetics
Whole Genome Sequencing
*Genome, Bacterial
Virulence/genetics
Drug Resistance, Bacterial/genetics
Polymorphism, Single Nucleotide
*Vegetables/microbiology
Prophages/genetics

@article {pmid40261029,
year = {2025},
author = {Espinoza, ME and Swing, AM and Elghraoui, A and Modlin, SJ and Valafar, F},
title = {Interred mechanisms of resistance and host immune evasion revealed through network-connectivity analysis of M. tuberculosis complex graph pangenome.},
journal = {mSystems},
volume = {10},
number = {4},
pages = {e0049924},
doi = {10.1128/msystems.00499-24},
pmid = {40261029},
issn = {2379-5077},
support = {R01AI105185//HHS | NIH | National Institute of Allergy and Infectious Diseases (NIAID)/ ; R01AI163202//HHS | NIH | National Institute of Allergy and Infectious Diseases (NIAID)/ ; },
mesh = {*Mycobacterium tuberculosis/genetics/immunology/drug effects ; *Genome, Bacterial ; Humans ; *Immune Evasion/genetics ; *Tuberculosis/microbiology/immunology ; Drug Resistance, Bacterial/genetics ; Host-Pathogen Interactions/genetics/immunology ; Antitubercular Agents/pharmacology ; Bacterial Proteins/genetics ; },
abstract = {Mycobacterium tuberculosis complex successfully adapts to environmental pressures through mechanisms of rapid adaptation which remain poorly understood despite knowledge gained through decades of research. In this study, we used 110 reference-quality, complete de novo assembled, long-read sequenced clinical genomes to study patterns of structural adaptation through a graph-based pangenome analysis, elucidating rarely studied mechanisms that enable enhanced clinical phenotypes offering a novel perspective to the species' adaptation. Across isolates, we identified a pangenome of 4,325 genes (3,767 core and 558 accessory), revealing 290 novel genes, and a substantially more complete account of difficult-to-sequence esx/pe/pgrs/ppe genes. Seventy-four percent of core genes were deemed non-essential in vitro, 38% of which support the pathogen's survival in vivo, suggesting a need to broaden current perspectives on essentiality. Through information-theoretic analysis, we reveal the ppe genes that contribute most to the species' diversity-several with known consequences for antigenic variation and immune evasion. Construction of a graph pangenome revealed topological variations that implicate genes known to modulate host immunity (Rv0071-73, Rv2817c, cas2), defense against phages/viruses (cas2, csm6, and Rv2817c-2821c), and others associated with host tissue colonization. Here, the prominent trehalose transport pathway stands out for its involvement in caseous granuloma catabolism and the development of post-primary disease. We show paralogous duplications of genes implicated in bedaquiline (mmpL5 in all L1 isolates) and ethambutol (embC-A) resistance, with a paralogous duplication of its regulator (embR) in 96 isolates. We provide hypotheses for novel mechanisms of immune evasion and antibiotic resistance through gene dosing that can escape detection by molecular diagnostics.IMPORTANCEM. tuberculosis complex (MTBC) has killed over a billion people in the past 200 years alone and continues to kill nearly 1.5 million annually. The pathogen has a versatile ability to diversify under immune and drug pressure and survive, even becoming antibiotic persistent or resistant in the face of harsh chemotherapy. For proper diagnosis and design of an appropriate treatment regimen, a full understanding of this diversification and its clinical consequences is desperately needed. A mechanism of diversification that is rarely studied systematically is MTBC's ability to structurally change its genome. In this article, we have de novo assembled 110 clinical genomes (the largest de novo assembled set to date) and performed a pangenomic analysis. Our pangenome provides structural variation-based hypotheses for novel mechanisms of immune evasion and antibiotic resistance through gene dosing that can compromise molecular diagnostics and lead to further emergence of antibiotic resistance.},
}

*Mycobacterium tuberculosis/genetics/immunology/drug effects
*Genome, Bacterial
Humans
*Immune Evasion/genetics
*Tuberculosis/microbiology/immunology
Drug Resistance, Bacterial/genetics
Host-Pathogen Interactions/genetics/immunology
Antitubercular Agents/pharmacology
Bacterial Proteins/genetics

@article {pmid40261018,
year = {2025},
author = {Chi, W and Zhang, H and Li, X and Zhou, Y and Meng, Q and He, L and Yang, Y and Liu, S and Shi, K},
title = {Comparative genomic analysis of 255 Oenococcus oeni isolates from China: unveiling strain diversity and genotype-phenotype associations of acid resistance.},
journal = {Microbiology spectrum},
volume = {},
number = {},
pages = {e0326524},
doi = {10.1128/spectrum.03265-24},
pmid = {40261018},
issn = {2165-0497},
abstract = {Oenococcus oeni, the only species of lactic acid bacteria capable of fully completing malolactic fermentation under challenging wine conditions, continues to intrigue researchers owing to its remarkable adaptability, particularly in combating acid stress. However, the mechanism underlying its superior adaptation to wine stresses still remains elusive due to the lack of viable genetic manipulation tools for this species. In this study, we conducted genomic sequencing and acid resistance phenotype analysis of 255 O. oeni isolates derived from diverse wine regions across China, aiming to elucidate their strain diversity and genotype-phenotype associations of acid resistance through comparative genomics. A significant correlation between phenotypes and evolutionary relationships was observed. Notably, phylogroup B predominantly consisted of acid-resistant isolates, primarily originating from Shandong and Shaanxi wine regions. Furthermore, we uncovered a noteworthy linkage between prophage genomic islands and acid resistance phenotype. Using genome-wide association studies, we identified key genes correlated with acid resistance, primarily involved in carbohydrates and amino acid metabolism processes. This study offers profound insights into the genetic diversity and genetic basis underlying adaptation mechanisms to acid stress in O. oeni.IMPORTANCEThis study provides valuable insights into the genetic basis of acid resistance in Oenococcus oeni, a key lactic acid bacterium in winemaking. By analyzing 255 isolates from diverse wine regions in China, we identified significant correlations between strain diversity, genomic islands, and acid resistance phenotypes. Our findings reveal that certain prophage-related genomic islands and specific genes are closely linked to acid resistance, offering a deeper understanding of how O. oeni adapts to acidic environments. These discoveries not only advance our knowledge of microbial stress responses but also pave the way for selecting and engineering acid-resistant strains, enhancing malolactic fermentation efficiency and wine quality. This research underscores the importance of genomics in improving winemaking practices and addressing challenges posed by high-acidity wines.},
}

@article {pmid40259521,
year = {2025},
author = {Gatica-Soria, LM and Roulet, ME and Tulle, WD and Sato, HA and Barrandeguy, ME and Sanchez-Puerta, MV},
title = {Highly variable mitochondrial chromosome content in a holoparasitic plant due to recurrent gains of foreign circular DNA.},
journal = {Physiologia plantarum},
volume = {177},
number = {2},
pages = {e70231},
doi = {10.1111/ppl.70231},
pmid = {40259521},
issn = {1399-3054},
support = {06/A092-T1//Secretaría de Investigación, Internacionales y Posgrado, Universidad Nacional de Cuyo/ ; PICT2020-01018//Fondo para la Investigación Científica y Tecnológica/ ; PICT2021 -GTR_TI-00435//Fondo para la Investigación Científica y Tecnológica/ ; },
mesh = {Gene Transfer, Horizontal/genetics ; DNA, Mitochondrial/genetics ; *Chromosomes, Plant/genetics ; *DNA, Circular/genetics ; *Genome, Mitochondrial/genetics ; Evolution, Molecular ; Phylogeny ; },
abstract = {Multichromosomal mitochondrial genomes (mtDNAs) in eukaryotes exhibit remarkable structural diversity, yet intraspecific variability and the origin of the individual chromosomes remain poorly understood. We focus on a holoparasitic angiosperm with an mtDNA consisting of 65 chromosomes largely composed of foreign DNA acquired by horizontal gene transfer (HGT) from its mimosoid hosts. The frequency, timing and population dynamics of these HGT events have not been examined. Here, we sampled different individuals of the holoparasite Lophophytum mirabile, along with their host plants, to assess mtDNA intraspecific variability and capture recent events that may bring insights into the HGT process. We also gathered mitochondrial data from 43 mimosoids to identify older and recent HGT events and assess precisely the proportion of foreign DNA. Through comparative genomic and evolutionary analyses, we uncovered great intraspecific variability in chromosome content and defined the mitochondrial pangenome of L. mirabile with 105 distinct chromosomes. The estimated foreign content reaches 93.5% of the mtDNA, including 73 fully foreign chromosomes that support the circle-mediated HGT model as a key mechanism for their acquisition. We inferred recurrent DNA transfers from the host plants, leading to new mitochondrial chromosomes that replicate autonomously. Our results emphasize the importance of adopting a pangenomic approach to fully capture the genetic diversity and evolution of multichromosomal mitochondrial genomes. This study shows that HGT can strongly influence the mtDNA content and generate enormous intraspecific variability even in geographically close individuals.},
}

Gene Transfer, Horizontal/genetics
DNA, Mitochondrial/genetics
*Chromosomes, Plant/genetics
*DNA, Circular/genetics
*Genome, Mitochondrial/genetics
Evolution, Molecular
Phylogeny

@article {pmid40258473,
year = {2025},
author = {Gao, Y and Yang, L and Kuhn, K and Li, W and Zanton, G and Bowman, M and Zhao, P and Zhou, Y and Fang, L and Cole, JB and Rosen, BD and Ma, L and Li, C and Baldwin, RL and Van Tassell, CP and Zhang, Z and Smith, TPL and Liu, GE},
title = {Long read and preliminary pangenome analyses reveal breed-specific structural variations and novel sequences in Holstein and Jersey cattle.},
journal = {Journal of advanced research},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.jare.2025.04.014},
pmid = {40258473},
issn = {2090-1224},
abstract = {INTRODUCTION: Most SV studies in livestock rely on short-read sequencing, posing challenges in accurately characterizing large genomic variants due to their limited read length.

OBJECTIVES: Our goal is to reveal structural variation and novel sequences specific to Holstein and Jersey cattle breeds using long-read and pan-genome analyses.

METHODS: We sequenced 20 Holsteins and 8 Jersey cattle using PacBio HiFi to 20×, and integrated five read-based and one assembly-based SV caller to determine SVs.

RESULTS: We assembled the 28 genomes averaging 3.25 Gb with a contig N50 of 69.36 Mb and using the ARS-UCD1.2 reference, we acquired Holstein/Jersey SV catalogs with 74,068/54,689 events spanning 202/135 Mb (7.43 %/4.97 % of the genome). SVs were enriched in less conserved, non-coding, and non-regulatory regions. Comparing Holsteins with differing feed efficiency (FE), SVs unique to high FE were linked to energy metabolism and olfactory receptors, while those specific to low FE were associated with material transport. We constructed Holstein/Jersey pangenome graphs with 148,598/105,875 nodes and 208,891/147,990 edges, representing 47,028/37,137 biallelic and multi-allelic events, and 63.75/42.34 Mb of novel sequence. We observed SV count saturation with 20 Holsteins, while adding Jerseys significantly increased the SV count, highlighting breed-specific SV events.

CONCLUSION: Our long-read data and SV catalogs are valuable resources, revealing that the cattle genome is more complex than previously thought.},
}

@article {pmid40258447,
year = {2025},
author = {Liu, J and Mo, D and Luo, L and Shi, Y and Xu, S},
title = {Sheep pan-genome retrieves the lost sequences and genes during domestication and selection.},
journal = {Genomics},
volume = {},
number = {},
pages = {111047},
doi = {10.1016/j.ygeno.2025.111047},
pmid = {40258447},
issn = {1089-8646},
abstract = {The reference genome plays a crucial role in uncovering genomic variations, which increase our understanding of the molecular mechanisms influencing biological traits. However, most of the sheep reference genomes derive from a single sheep individual, which couldn't adequately represent the genetic diversity of sheep. The map-to-pan strategy was used to construct the sheep pan-genome based on 801 samples with short read whole genome sequencing data including 724 domestic individuals from 151 sheep populations/breeds and 77 wild individuals from seven genus Ovis species, and a total of 195 Mb of nonreference sequences were assembled that absent from the ARS-UI_Ramb_v2.0 reference. MAKER2 pipeline, integrating ab initio gene prediction, RNA-Seq, and protein homology was used to annotate the nonreference sequences. As a result, a total of additional 2678 genes were predicted in the nonreference sequences. We also identified 13,317 novel single nucleotide polymorphisms (SNPs) by mapping the sequences that could not be aligned to ARS1-UI_Ramb_v2.0 to the nonreference sequences. Population genetic analysis, including principal component analysis (PCA), phylogenetic tree, and ADMIXTURE based on the novel SNPs revealed a clear phylogenetic relationship of the world's domestic sheep, as well as their close wild relatives. Additionally, pangenome-wide presence and absence variations (PAVs) analysis exhibited a decreasing trend in gene number from wild populations to domestic populations. Several genes, GZMH, NFE2L3, GPR146 and CALHM6 with significant changes of presence frequencies during the evolutionary history of sheep were identified by PAV selection analysis. Functional annotation revealed that these genes were primarily associated with immune responses. Our results highlight the implications of the sheep pan-genome in identifying previously unknown genetic variations. PAVs can be used to track and reveal the changes in genomic architecture throughout the evolutionary history of sheep, such as, gene loss. The genes, GZMH, NFE2L3, GPR146 and CALHM6 related to immune regulation and inflammatory responses may play important roles during the domestication history of sheep. These findings broaden our knowledge about the genetic diversity in sheep genomes, and provide insight into the domestication and breeding history of sheep.},
}

@article {pmid40253154,
year = {2025},
author = {Yadav, S and Rahim, MS and Devi, A and Sharma, RK},
title = {Revolutionizing Speciality Teas: Multi-omics prospective to breed anthocyanin-rich tea.},
journal = {Food research international (Ottawa, Ont.)},
volume = {209},
number = {},
pages = {116312},
doi = {10.1016/j.foodres.2025.116312},
pmid = {40253154},
issn = {1873-7145},
mesh = {*Anthocyanins/biosynthesis ; *Camellia sinensis/genetics/metabolism ; *Tea/chemistry/genetics/metabolism ; *Plant Breeding/methods ; Gene Expression Regulation, Plant ; Metabolomics ; *Genomics/methods ; Transcriptome ; Multiomics ; },
abstract = {Variations in metabolite accumulation particularly anthocyanins have been of keen interest to the global tea industry due to their potential health benefits. Previous studies on tea genome, transcriptome, and metabolome provided an integrated spectrum of bioactive metabolites biosynthesis in tea plants. However, comprehending knowledge of anthocyanin biosynthesis and its accumulation in tea plants needed to be unified with multi-omics approaches that can build a complete depiction of the regulatory genomic machinery for improving quality characteristics in tea. Furthermore, true visualization, interpretation, and precise dissection of key traits required significant enrichment of multi-omics data for integration of machine learning. This review emphasizes the role of genetics, epigenetics, and transcriptional regulation of early (EBG) and late biosynthetic genes (LBG) involved in anthocyanin biosynthesis and accumulation in purple tea. Additionally, other factors including key transcription factors, transporters, photosynthesis, vacuole pH, and co-biosynthesis of other flavonoids were discussed. We envision an integration of pangenome and genome-wide strategies (GWAS, mGWAS, EWAS) which can offer new insights for the breeding of anthocyanin-rich tea cultivars to fetch better trade revenue and nutraceutical benefits.},
}

*Anthocyanins/biosynthesis
*Camellia sinensis/genetics/metabolism
*Tea/chemistry/genetics/metabolism
*Plant Breeding/methods
Gene Expression Regulation, Plant
Metabolomics
*Genomics/methods
Transcriptome
Multiomics

@article {pmid40248511,
year = {2025},
author = {Boby, F and Bhuiyan, DMNH and Khan, DMS and Parvez, MM},
title = {Draft genome sequence data on Bacillus safensis FB03 isolated from the rhizosphere soil of leguminous plant in Bangladesh.},
journal = {Data in brief},
volume = {60},
number = {},
pages = {111527},
pmid = {40248511},
issn = {2352-3409},
abstract = {With the aim of investigating the biotechnological potential of Bacillus safensis' FB03, isolated from the rhizosphere soil of Bahrind region of Bangladesh, the current work focused on its complete genomic analysis and phenotypic description. The size of the genome of the isolate was 3.6 Mb with 41.59 % GC content. Genome annotation revealed the presence of many genes related to siderophore production, enzyme degradation, UV and stress tolerance. Six biosynthesis gene clusters for bacillibacin, bacilysin, bottromycin, Schizokinen, fengycin, and lychensin were identified through genome mining. Significantly, FB03 was found to contain only two acquired antimicrobial resistance genes and was anticipated to be non-pathogenic to humans. The openness of the Bacillus safensis pan-genome was demonstrated by the pan-genome analysis. According to this research, Bacillus safensis FB03 may be a good fit for a variety of biotechnological applications.},
}

@article {pmid40247941,
year = {2025},
author = {Zhang, J and Chen, C and Yang, Q and Xu, J and Han, Z and Ma, W and Zhang, X and Xu, K and Zhao, J and Chen, X},
title = {Evolution of HD-ZIP transcription factors and their function in cabbage leafy head formation.},
journal = {Frontiers in plant science},
volume = {16},
number = {},
pages = {1583110},
pmid = {40247941},
issn = {1664-462X},
abstract = {INTRODUCTION: The HD-ZIP protein, a unique class of transcription factors in plants, plays a crucial role in plant growth and development. Although some HD-ZIP transcription factors have been associated with leafy head formation in Chinese cabbage, their regulatory mechanisms remain poorly understood.

METHODS: This study identified the HD-ZIP family using HMM and TBtools, constructed a phylogenetic tree with OrthoFinder, and analyzed gene family expansion and contraction using CAFE. Conserved features were analyzed with MAFFT, MEME, and TBtools; regulatory networks were predicted using ATRM and PlantTFDB; and gene expression was validated by qRT-PCR.

RESULTS AND DISCUSSION: In this study, HD-ZIP gene sequences from 87 species were analyzed to explore the evolutionary history of this gene family. Despite significant variation in gene family expansion and contraction across species, our findings indicated that HD-ZIP family proteins were conserved in both lower (Charophyta) and higher plants, where they were potentially involved in root, stem, and leaf differentiation. In our analysis of 22 Brassica species, HD-ZIP III protein sequences and domains were conserved. However, within the pan-genome A of 18 Brassica rapa species, differences were observed in auxin-related cis-elements within the HD-ZIP III promoter regions between heading and non-heading cabbage varieties. RNA-seq analysis of wild-type A03 (heading) and mutant fg-1 (non-heading) revealed that 131 genes formed a protein interaction network or clustered in the same branch as HD-ZIP family genes. Through GO enrichment and qRT-PCR, several key candidate genes of Brassica rapa ssp. pekinensis A03 associated with leafy head formation in cabbage were identified. These findings established a foundation for understanding the molecular mechanisms by which the HD-ZIP gene family regulated head growth in Chinese cabbage.},
}

@article {pmid40245288,
year = {2025},
author = {Wang, Z and Fan, Y and Sun, J and Ma, S and Wang, Z and Li, J and Liu, K and Xiong, Z and Li, C and Wang, D and Zhang, H and Hua, J and Bao, Y},
title = {Pan-analysis of intra- and inter-species diversity reveals a group of highly variable immune receptor genes in rice.},
journal = {The Plant journal : for cell and molecular biology},
volume = {122},
number = {1},
pages = {e70163},
doi = {10.1111/tpj.70163},
pmid = {40245288},
issn = {1365-313X},
support = {JSSCBS20230082//Shuangchuang Program of Jiangsu Province/ ; JBGS2021040//Seed Industry Revitalization Project of Jiangsu Province/ ; NAUSY-MS06//Guidance Foundation, the Sanya Institute of Nanjing Agricultural University/ ; 31871602//National Natural Science Foundation of China/ ; 32072033//National Natural Science Foundation of China/ ; 32301884//National Natural Science Foundation of China/ ; 32472216//National Natural Science Foundation of China/ ; 323MS070//Hainan Provincial Natural Science Foundation of China/ ; 325QN368//Hainan Provincial Natural Science Foundation of China/ ; },
mesh = {*Oryza/genetics/immunology ; *Plant Proteins/genetics/metabolism ; *Genetic Variation ; *Plant Immunity/genetics ; NLR Proteins/genetics ; Phylogeny ; Species Specificity ; Genome, Plant/genetics ; Genes, Plant/genetics ; Gene Expression Regulation, Plant ; Receptors, Pattern Recognition/genetics ; },
abstract = {Plant immune receptors and their natural variations play a central role in combating disease-causing pathogens. These immune receptors include intracellular nucleotide-binding leucine-rich repeat (LRR) receptors (NLRs) and cell-surface pattern recognition receptors (PRRs) that can be further classified as receptor-like proteins (RLPs) and receptor-like kinases (RLKs). Although the NLRome has been characterized, the repertoire and extent of diversity of PRRome remain undetermined in rice. In this study, we examined the diversity of immune receptor genes using high-quality genomes of 309 rice accessions from 8 species within the genus Oryza. A total of 376 310 immune receptor genes were identified, including 149 592 NLR-coding genes and 226 718 PRR coding genes. Shannon entropy analysis revealed a set of immune receptors that display significant intra-species and inter-species diversity in rice. In general, RLPs are more variable than RLKs, while NLRs and LRR-RLPs are more variable than LRR-RLKs. Additionally, NLR and PRR genes exhibit contrasting shoot/root expression patterns, with NLRs generally skewed towards root expression. Furthermore, we found that the size of the LRR-RLK gene families correlates with local annual precipitation, suggesting a stronger selection pressure on LRR-RLK genes in rice accessions grown under wet conditions than dry conditions. In sum, this pan-genomic analysis not only reveals the extensive diversity of the immune receptor repertoires in rice but also provides potential target genes for improving disease resistance in rice.},
}

*Oryza/genetics/immunology
*Plant Proteins/genetics/metabolism
*Genetic Variation
*Plant Immunity/genetics
NLR Proteins/genetics
Phylogeny
Species Specificity
Genome, Plant/genetics
Genes, Plant/genetics
Gene Expression Regulation, Plant
Receptors, Pattern Recognition/genetics

@article {pmid40245044,
year = {2025},
author = {Mendoza-Mujica, G and Calvay-Sanchez, KD and Zarate-Sulca, Y and Jimenez-Vasquez, V},
title = {New insights into the genomic information of an overlooked human pathogen: Bartonella rochalimae causative agent of Carrion's disease.},
journal = {PLoS neglected tropical diseases},
volume = {19},
number = {4},
pages = {e0013040},
doi = {10.1371/journal.pntd.0013040},
pmid = {40245044},
issn = {1935-2735},
abstract = {The Bartonella genus includes over twenty species, most transmitted by arthropods and possibly eleven related to human diseases, though some currently lack specific vectors or hosts. Bartonella rochalimae, a Gram-negative pleomorphic bacterium, was first isolated in 2007 from a woman who traveled to Peru and developed Carrion's disease-like symptoms. Hence, this study aims to report on bacterial isolates from patients diagnosed with Carrion's disease, which were found to be caused by B. rochalimae rather than B. bacilliformis, and to characterize the genomic aspects of B. rochalimae as a human pathogen. Five strains of B. rochalimae were identified using pangenomic and phylogenetic analysis. Additional analyses included core and clade-specific genes, gene ontology (GO), virulence factors (VF), and subcellular localization. This study identified five B. rochalimae strains from the regions of Ancash, Cajamarca, and Huánuco in Peru, suggesting regional circulation. The findings emphasize the importance of further research on B. rochalimae gene functions and its role in outbreak developments, highlighting the importance of improved diagnostics and enhanced surveillance.},
}

@article {pmid40243587,
year = {2025},
author = {Gutiérrez, AV and Matthews, M and Diaz, M and Le Viet, T and de Oliveira Martins, L and Jørgensen, F and Aird, H and Painset, A and Som, N and Omelchenko, O and Adriaenssens, EM and Kingsley, RA and Gilmour, MW},
title = {Population structure and gene flux of Listeria monocytogenes ST121 reveal prophages as a candidate driver of adaptation and persistence in food production environments.},
journal = {Microbial genomics},
volume = {11},
number = {4},
pages = {},
doi = {10.1099/mgen.0.001397},
pmid = {40243587},
issn = {2057-5858},
mesh = {*Listeria monocytogenes/genetics/virology/classification/isolation & purification ; *Prophages/genetics ; Phylogeny ; *Food Microbiology ; Humans ; Genome, Bacterial ; United Kingdom ; Listeriosis/microbiology ; Adaptation, Physiological/genetics ; Whole Genome Sequencing ; Evolution, Molecular ; },
abstract = {Listeria monocytogenes is a bacterial pathogen found in an increasing number of food categories, potentially reflecting an expanding niche and food safety risk profile. In the UK, Listeria monocytogenes sequence type (ST) 121 is more frequently isolated from foods and food environments than from cases of clinical listeriosis, consistent with a relatively low pathogenicity. In this study, we determined the evolution associated with the environmental persistence of a Listeria monocytogenes clone by investigating clone-specific genome features in the context of the ST121 population structure from international sources. To enable unambiguous comparative genomic analysis of ST121 strains, we constructed 16 new high-quality genome assemblies from Listeria monocytogenes isolated from foods, food environments and human clinical sources in the UK from 1987 to 2019. Our dataset was supplemented with additional UK and international genomes from databases held by the Institut Pasteur and the UK Health Security Agency. Time-scaled phylogenetic reconstruction revealed that clade-specific microevolution correlated with key characteristics that may confer adaptations important for success in the environmental niche. For example, a prophage designated LP-13-6 unique to a clade is associated with multi-year persistence in a food production setting. This prophage, observed in a strain that persisted for over a decade, may encode mechanisms facilitating environmental persistence, including the exclusion of other bacteriophages. Pangenome analysis provided insights into other candidate genetic elements associated with persistence and biocide tolerance. The comparative genomic dataset compiled in this study includes an international collection of 482 genome sequences that serve as a valuable resource for future studies to explore conserved genes, regulatory regions, mutations and variations associated with particular traits, such as environmental persistence, pathogenicity or biocide tolerance.},
}

*Listeria monocytogenes/genetics/virology/classification/isolation & purification
*Prophages/genetics
Phylogeny
*Food Microbiology
Humans
Genome, Bacterial
United Kingdom
Listeriosis/microbiology
Adaptation, Physiological/genetics
Whole Genome Sequencing
Evolution, Molecular

@article {pmid40241821,
year = {2025},
author = {Terra, LA and Klepa, MS and Nogueira, MA and Hungria, M},
title = {Pangenome analysis indicates evolutionary origins and genetic diversity: emphasis on the role of nodulation in symbiotic Bradyrhizobium.},
journal = {Frontiers in plant science},
volume = {16},
number = {},
pages = {1539151},
pmid = {40241821},
issn = {1664-462X},
abstract = {The Bradyrhizobium genus is widely known for encompassing many species capable of forming nodules and establishing the biological nitrogen fixation process with several legumes, significantly contributing to agriculture and environmental sustainability. Despite its importance, questions about the evolution, pangenome, and symbiotic genes of Bradyrhizobium are still poorly understood. In this study, we analyzed the pangenome of a set of Bradyrhizobium symbiotic species using the Roary and GET_HOMOLOGUES tools in strains originated from the Northern and Southern Hemispheres. We also investigated the presence and correlation of the fix, nif, nod, Type III secretion system (T3SS) and their effector proteins, and T4SS genes, trying to find differences between clades, hosts, and biogeographic origin. Pangenome analysis of Bradyrhizobium species from the Northern and Southern Hemispheres provided valuable insights into their diversity, biogeography, origin, and co-evolution with their legume host plants. The genus possesses a relatively small core genome compared to the expanded accessory genome, a key feature that facilitates genetic exchange and acquisition of new genes, allowing adaptation to a variety of environments. Notably, the presence or absence of T3SS effector proteins varied significantly according to the geographic location, suggesting specific environmental adaptations, as well as a direct relationship with nodulation genes. Comparative analysis indicated that symbiotic Bradyrhizobium species originated in the Northern Hemisphere and present a greater diversity of orthologous groups than those from the Southern Hemisphere. These results contribute to our understanding of the evolutionary history of these symbiotic bacteria.},
}

@article {pmid40240877,
year = {2025},
author = {Li, W and Chu, C and Zhang, T and Sun, H and Wang, S and Liu, Z and Wang, Z and Li, H and Li, Y and Zhang, X and Geng, Z and Wang, Y and Li, Y and Zhang, H and Fan, W and Wang, Y and Xu, X and Cheng, L and Zhang, D and Xiong, Y and Li, H and Zhou, B and Guan, Q and Deng, CH and Han, Y and Ma, H and Han, Z},
title = {Pan-genome analysis reveals the evolution and diversity of Malus.},
journal = {Nature genetics},
volume = {},
number = {},
pages = {},
pmid = {40240877},
issn = {1546-1718},
support = {CARS-27//Earmarked Fund for China Agriculture Research System/ ; 32172522//National Natural Science Foundation of China (National Science Foundation of China)/ ; 32422077//National Natural Science Foundation of China (National Science Foundation of China)/ ; 2019M661344//China Postdoctoral Science Foundation/ ; },
abstract = {Malus Mill., a genus of temperate perennial trees with great agricultural and ecological value, has diversified through hybridization, polyploidy and environmental adaptation. Limited genomic resources for wild Malus species have hindered the understanding of their evolutionary history and genetic diversity. We sequenced and assembled 30 high-quality Malus genomes, representing 20 diploids and 10 polyploids across major evolutionary lineages and geographical regions. Phylogenomic analyses revealed ancient gene duplications and conversions, while six newly defined genome types, including an ancestral type shared by polyploid species, facilitated the detection of strong signals for extensive introgressions. The graph-based pan-genome captured shared and species-specific structural variations, facilitating the development of a molecular marker for apple scab resistance. Our pipeline for analyzing selective sweep identified a mutation in MdMYB5 having reduced cold and disease resistance during domestication. This study advances Malus genomics, uncovering genetic diversity and evolutionary insights while enhancing breeding for desirable traits.},
}

@article {pmid40240605,
year = {2025},
author = {Guo, D and Li, Y and Lu, H and Zhao, Y and Kurata, N and Wei, X and Wang, A and Wang, Y and Zhan, Q and Fan, D and Zhou, C and Lu, Y and Tian, Q and Weng, Q and Feng, Q and Huang, T and Zhang, L and Gu, Z and Wang, C and Wang, Z and Wang, Z and Huang, X and Zhao, Q and Han, B},
title = {A pangenome reference of wild and cultivated rice.},
journal = {Nature},
volume = {},
number = {},
pages = {},
pmid = {40240605},
issn = {1476-4687},
abstract = {Oryza rufipogon, the wild progenitor of Asian cultivated rice Oryza sativa, is an important resource for rice breeding[1]. Here we present a wild-cultivated rice pangenome based on 145 chromosome-level assemblies, comprising 129 genetically diverse O. rufipogon accessions and 16 diverse varieties of O. sativa. This pangenome contains 3.87 Gb of sequences that are absent from the O. sativa ssp. japonica cv. Nipponbare reference genome. We captured alternate assemblies that include heterozygous information missing in the primary assemblies, and identified a total of 69,531 pan-genes, with 28,907 core genes and 13,728 wild-rice-specific genes. We observed a higher abundance and a significantly greater diversity of resistance-gene analogues in wild rice than in cultivars. Our analysis indicates that two cultivated subpopulations, intro-indica and basmati, were generated through gene flows among cultivars in South Asia. We also provide strong evidence to support the theory that the initial domestication of all Asian cultivated rice occurred only once. Furthermore, we captured 855,122 differentiated single-nucleotide polymorphisms and 13,853 differentiated presence-absence variations between indica and japonica, which could be traced to the divergence of their respective ancestors and the existence of a larger genetic bottleneck in japonica. This study provides reference resources for enhancing rice breeding, and enriches our understanding of the origins and domestication process of rice.},
}

@article {pmid40240601,
year = {2025},
author = {Sun, H and Tusso, S and Dent, CI and Goel, M and Wijfjes, RY and Baus, LC and Dong, X and Campoy, JA and Kurdadze, A and Walkemeier, B and Sänger, C and Huettel, B and Hutten, RCB and van Eck, HJ and Dehmer, KJ and Schneeberger, K},
title = {The phased pan-genome of tetraploid European potato.},
journal = {Nature},
volume = {},
number = {},
pages = {},
pmid = {40240601},
issn = {1476-4687},
abstract = {Potatoes were first brought to Europe in the sixteenth century[1,2]. Two hundred years later, one of the species had become one of the most important food sources across the entire continent and, later, even the entire world[3]. However, its highly heterozygous, autotetraploid genome has complicated its improvement since then[4-7]. Here we present the pan-genome of European potatoes generated from phased genome assemblies of ten historical potato cultivars, which includes approximately 85% of all haplotypes segregating in Europe. Sequence diversity between the haplotypes was extremely high (for example, 20× higher than in humans), owing to numerous introgressions from wild potato species. By contrast, haplotype diversity was very low, in agreement with the population bottlenecks caused by domestication and transition to Europe. To illustrate a practical application of the pan-genome, we converted it into a haplotype graph and used it to generate phased, megabase-scale pseudo-genome assemblies of commercial potatoes (including the famous French fries potato 'Russet Burbank') using cost-efficient short reads only. In summary, we present a nearly complete pan-genome of autotetraploid European potato, we describe extraordinarily high sequence diversity in a domesticated crop, and we outline how this resource might be used to accelerate genomics-assisted breeding and research.},
}

@article {pmid40239363,
year = {2025},
author = {Wang, M and Jin, L and Wang, R and Wang, Q and Wang, S and Wu, X and Yao, C and Corander, J and Wang, H},
title = {KpnK48 clone driving hypervirulent carbapenem-resistant Escherichia coli epidemics: Insights into its evolutionary trajectory similar to Klebsiella pneumoniae.},
journal = {Drug resistance updates : reviews and commentaries in antimicrobial and anticancer chemotherapy},
volume = {81},
number = {},
pages = {101243},
doi = {10.1016/j.drup.2025.101243},
pmid = {40239363},
issn = {1532-2084},
abstract = {AIMS: Hypervirulent and carbapenem-resistant pathogens posed a significant and growing threat to global public health. This study focused on the rapid spread of a hypervirulent carbapenem-resistant E. coli (hv-CREC) subclone and its genomic resembles with hypervirulent carbapenem-resistant K. pneumoniae (hv-CRKP), driven by recombination impacting both chromosomal and plasmid gene content.

METHODS: A multicenter molecular epidemiological study was conducted on 653 CREC clinical isolates collected across China (2013-2022), integrated with public genomic data. Pangenome-wide and phylogeographical analyses were performed to uncover recombination events, define the epidemic clone, and trace its evolutionary history. Growth advantage and virulence were evaluated through competition assays and Galleria mellonella infection models.

RESULTS: Sequence types (ST) 167, ST410, ST617, and ST361 collectively accounted for 53.8 % (351/653) of the CREC isolates, with ST167 showing a sharp increase in prevalence after 2017. Among these, subclone named KpnK48 emerged as the primary driver of the increase in ST167 CREC prevalence. Traced to a European origin, KpnK48 rapidly expanded globally, particularly in China. The remarkable success of KpnK48 could plausibly be attributed to enhanced survival and virulence, driven by the acquisition of a ∼492 kb recombinant genomic region which mirrored the genomic architecture underlying the hv-CRKP ST11-K64 clone, reflecting a Klebsiella-like evolutionary path. Additionally, plasmid shift in KpnK48 clone from the prevalent NDM-IncX3 plasmid to Klebsiella-common NDM-IncF plasmid expanded its resistance spectrum and virulence gene repertoire, likely further amplifying its pathogenicity and success.

CONCLUSIONS: The KpnK48 subclone combined the features of hypervirulence and carbapenem resistance, bridging genomic traits of E. coli and K. pneumoniae, signifying a broader evolutionary trend with profound global health implications.},
}

@article {pmid40236780,
year = {2025},
author = {Zong, W and Chen, L and Zhang, D and Zhang, Y and Wang, J and Hou, X and Chai, J and An, Y and Tian, M and He, X and Song, C and He, J and Liu, X and Wang, L and D'Alessandro, E and Wang, L and Yin, Y and Li, M and Liu, D and Wang, J and Zhang, L},
title = {Two telomere-to-telomere pig genome assemblies and pan-genome analyses provide insights into genomic structural landscape and genetic adaptations.},
journal = {iMeta},
volume = {4},
number = {2},
pages = {e70013},
pmid = {40236780},
issn = {2770-596X},
abstract = {This study presented two high-precision telomere-to-telomere genome assemblies for Min and Rongchang pigs, including a detailed exploration of the telomeric and centromeric regions. By integrating pan-genome and multi-omics analyses, structural variations linked to genetic adaptation were identified, providing a valuable resource for advancing pig breeding and genetic improvement.},
}

@article {pmid40236772,
year = {2025},
author = {Wang, X and Zhou, P and Hu, X and Bai, Y and Zhang, C and Fu, Y and Huang, R and Suzhen, N and Song, X},
title = {T2T genome, pan-genome analysis, and heat stress response genes in Rhododendron species.},
journal = {iMeta},
volume = {4},
number = {2},
pages = {e70010},
pmid = {40236772},
issn = {2770-596X},
abstract = {This study reports the first high-quality telomere-to-telomere (T2T) Rhododendron liliiflorum genome with 11 chromosomes that are gap free. The 24 telomeres and all 13 centromeres detected in this genome, which reached the highest quality gold level. In addition, other three Rhododendron species were sequenced and assembled to the chromosomal level. Based on 15 Rhododendron genomes, we conducted a pan-genome analysis of genus Rhododendron. Combining the genome and whole transcriptome sequencing, we identified several key genes and miRNAs related to the heat stress, which were further verified by transgenic experiments. Our findings provide rich resources for comparative and functional genomics studies of Rhododendron species.},
}

@article {pmid40236729,
year = {2025},
author = {Yang, M and Kong, X and Zhou, C and Kuang, R and Wu, X and Liu, C and He, H and Xu, Z and Wei, Y},
title = {Genomic insights into the domestication and genetic basis of yield in papaya.},
journal = {Horticulture research},
volume = {12},
number = {5},
pages = {uhaf045},
pmid = {40236729},
issn = {2662-6810},
abstract = {Papaya (Carica papaya L.) is an important tropical and subtropical fruit crop, and understanding its genome is essential for breeding. In this study, we assembled a high-quality genome of 344.17 Mb for the newly cultivated papaya 'Zihui', which contains 22 250 protein-coding genes. By integrating 201 resequenced papaya genomes, we identified four distinct papaya groups and a 34 Mb genomic region with strong domestication selection signals. Within these regions, two key genes associated with papaya yield were discovered: Cp_zihui06549, encoding a leucine-rich receptor-like protein kinase, and Cp_zihui06768, encoding the accumulation of photosystem one 1 (APO1) protein. Heterologous expression of Cp_zihui06549 in tomato confirmed that the total number of fruits in transgenic lines more than doubled compared to wild-type plants, resulting in a significant yield increase. Furthermore, we constructed a pan-genome of papaya and obtained a 77.41 Mb nonreference sequence containing 1543 genes. Within this pan-genome, 2483 variable genes, we detected, including four genes annotated as the 'terpene synthase activity' Gene Ontology term, which were lost in cultivars during domestication. Finally, gene retention analyses were performed using gene presence and absence variation data and differentially expressed genes across various tissues and organs. This study provides valuable insights into the genes and loci associated with phenotypes and domestication processes, laying a solid foundation for future papaya breeding efforts.},
}

@article {pmid40236485,
year = {2025},
author = {Dione, N and Mlaga, KD and Liang, S and Jospin, G and Marfori, Z and Alvarado, N and Scarsella, E and Uttarwar, R and Ganz, HH},
title = {Comparative genomic and phenotypic description of Escherichia ruysiae: a newly identified member of the gut microbiome of the domestic dog.},
journal = {Frontiers in microbiology},
volume = {16},
number = {},
pages = {1558802},
pmid = {40236485},
issn = {1664-302X},
abstract = {INTRODUCTION: Escherichia ruysiae is a newly identified species within the Escherichia genus, yet its presence in domestic animals remains largely unexamined. This study characterizes four isolates detected for the first time in the domestic dog (Canis lupus familiaris), focusing on their phenotypic and genomic features.

METHODS: We used culturomic methods to isolate four E. ruysiae isolates that were initially identified as Escherichia coli using MALDI-TOF mass spectrometry. Whole-genome sequencing confirmed that the isolates belonged to E. ruysiae, not E. coli. Phenotypic characterization included enzymatic activity assays and antimicrobial susceptibility testing. Comparative genomic analyses were performed on these four isolates, along with 14 additional E. ruysiae and representative genomes from the five other Escherichia species in order to assess genetic diversity and functional gene distribution.

RESULTS AND DISCUSSION: All strains exhibited similar enzymatic activities and resistance to clindamycin, erythromycin, and metronidazole. The pangenome analysis revealed that most missing gene orthologs are related to motility followed by metabolism, including synthetases, reductases, phosphatases, permeases, transferases, and epimerases, as well as structural genes like efflux pumps and transporters. Phylogroup typing using the ClermonTyping method identified two main groups within the E. ruysiae species, Clade III and IV. Typical virulence genes associated with E. coli are absent in these strains. The multiple approaches used in this study expand our understanding of the diverse aspects of the recently described species, E. ruysiae.},
}

@article {pmid40236475,
year = {2025},
author = {Zhu, X and Huang, Y and Shi, Y and Gao, X and Chen, D and Liu, C and Cao, S and Xue, X and Li, Y},
title = {Comparative genomic analysis of food-animal-derived and human-derived Clostridium perfringens isolates from markets in Shandong, China.},
journal = {Frontiers in microbiology},
volume = {16},
number = {},
pages = {1543511},
pmid = {40236475},
issn = {1664-302X},
abstract = {Clostridium perfringens (C. perfringens) is a foodborne pathogen that poses a significant threat to both animal husbandry and public health. In this study, 27 C. perfringens strains were isolated from animal samples and animal-derived food products. Antibiotics resistances among the isolates were phenotypically and genotypically analyzed and Whole genome sequencing (WGS). In combination with the genomes of 141 human-derived C. perfringens strains from public databases, this study conducted comprehensive analyses of antibiotic resistance genes, virulence genes, multilocus sequence typing (MLST), prophage detection, and pan-genome analysis for a total of 168 strains of C. perfringens. Antibiotics resistances among the isolates were phenotypically and genotypically analyzed and found 24 of them (88.9%, 24/27) were identified as multidrug-resistant (MDR). WGS analysis revealed that 13 strains belonged to known sequence types (ST), and the remaining strains represented 10 new STs. By analysis in combination with data of 141 C. perfringens isolates from the database, it was implied that ST221, ST72 and ST370 were present in both animal-derived and human-derived C. perfringens. It is worth noting that 108 out of 168 strains of C. perfringens (64.3%, 108/168) were found to carry prophages, which were found more prevalent in human-derived C. perfringens isolates. Pan-genome and phylogenetic analysis of 168 C. perfringens strains indicated that C. perfringens possesses an open pan-genome with genetic diversity. This study provides genomic insights into C. perfringens from food animals and humans, shedding light on the importance for monitoring the C. perfringens in livestock in China for better public health.},
}

@article {pmid40235155,
year = {2025},
author = {Liang, YY and Liu, H and Lin, QQ and Shi, Y and Zhou, BF and Wang, JS and Chen, XY and Shen, Z and Qiao, LJ and Niu, JW and Ling, SJ and Luo, WJ and Zhao, W and Liu, JF and Kuang, YW and Ingvarsson, PK and Guo, YL and Wang, B},
title = {Pan-genome analysis reveals local adaptation to climate driven by introgression in oak species.},
journal = {Molecular biology and evolution},
volume = {},
number = {},
pages = {},
doi = {10.1093/molbev/msaf088},
pmid = {40235155},
issn = {1537-1719},
abstract = {The genetic base of local adaptation has been extensively studied in natural populations. However, a comprehensive genome-wide perspective on the contribution of structural variants (SVs) and adaptive introgression to local adaptation remains limited. In this study, we performed de novo assembly and annotation of 22 representative accessions of Quercus variabilis, identifying a total of 543,372 SVs. These SVs play crucial roles in shaping genomic structure and influencing gene expression. By analysing range-wide genomic data, we identified both SNPs and SVs associated with local adaptation in Q. variabilis and Q. acutissima. Notably, SV-outliers exhibit selection signals that did not overlap with SNP-outliers, indicating that SNP-based analyses may not detect the same candidate genes associated with SV-outliers. Remarkably, 29-37% of candidate SNPs were located in a 250 kb region on chromosome 9, referred to as Chr9-ERF. This region contains eight duplicated ethylene-responsive factor (ERF) genes, which may have contributed to local adaptation of Q. variabilis and Q. acutissima. We also found that a considerable number of candidate SNPs were shared between Q. variabilis and Q. acutissima in the Chr9-ERF region, suggesting a pattern of repeated selection. We further demonstrated that advantageous variants in this region were introgressed from western populations of Q. acutissima into Q. variabilis, providing compelling evidence that introgression facilitates local adaptation. This study offers a valuable genomic resource for future studies on oak species and highlights the importance of pan-genome analysis in understating mechanism driving adaptation and evolution.},
}

@article {pmid40232949,
year = {2025},
author = {Iranzadeh, A and Alisoltani, A and Kiran, AM and Breiman, RF and Chaguza, C and Peno, C and Cornick, JE and Everett, DB and Mulder, N},
title = {Comparative pangenomics of Streptococcus pneumoniae from Malawi: uncovering genetic variability and pathogenicity.},
journal = {Microbial genomics},
volume = {11},
number = {4},
pages = {},
doi = {10.1099/mgen.0.001370},
pmid = {40232949},
issn = {2057-5858},
mesh = {*Streptococcus pneumoniae/genetics/pathogenicity/classification/isolation & purification ; Malawi/epidemiology ; Humans ; *Pneumococcal Infections/microbiology/epidemiology ; *Genetic Variation ; Serogroup ; Genome, Bacterial ; Phylogeny ; Genomics ; Virulence/genetics ; Child ; Bacterial Proteins/genetics ; Child, Preschool ; Female ; Bacteremia/microbiology ; },
abstract = {Streptococcus pneumoniae is a significant cause of bacterial infections, including pneumonia, meningitis and septicemia, primarily affecting children, the elderly and immunocompromised individuals. This study aimed to elucidate the serotype and lineage distribution and molecular mechanisms underlying pneumococcal invasiveness through a comprehensive pangenomic analysis of 1416 isolates from Malawi. Our analysis comprised 810 isolates from asymptomatic carriers and 606 isolates from patients with bacteraemia or meningitis. We identified 58 serotypes, with serotypes 1, 5 and 12F exhibiting significantly higher prevalence among patients. These serotypes likely exhibit reduced nasopharyngeal colonization and demonstrate rapid dissemination to sterile sites. Notably, these serotypes form a distinct lineage with distinct genomic characteristics, including the absence of V-type ATP synthase. The pangenome analysis revealed two highly conserved surface protein complexes, F-type ATP synthase and SecA1-SecY, which deserve further investigation as potential targets for novel therapeutic interventions.},
}

*Streptococcus pneumoniae/genetics/pathogenicity/classification/isolation & purification
Malawi/epidemiology
Humans
*Pneumococcal Infections/microbiology/epidemiology
*Genetic Variation
Serogroup
Genome, Bacterial
Phylogeny
Genomics
Virulence/genetics
Child
Bacterial Proteins/genetics
Child, Preschool
Female
Bacteremia/microbiology

@article {pmid40232097,
year = {2025},
author = {Kim, SS},
title = {Application of Comparative Genomics for the Development of PCR Primers for the Detection of Harmful or Beneficial Microorganisms in Food: Mini-Review.},
journal = {Foods (Basel, Switzerland)},
volume = {14},
number = {6},
pages = {},
pmid = {40232097},
issn = {2304-8158},
abstract = {Gene markers are widely utilized for detecting harmful and beneficial microorganisms in food products. Primer sequences targeting the 16S rRNA region, recognized as a conserved region, have been conventionally employed in PCR analyses. However, several studies have highlighted limitations and false-positive results associated with the use of these primer sequences. Consequently, pan-genome analysis, a comparative genomic approach, has been increasingly applied to design more selective gene markers. This mini-review explores the application of pan-genome analysis in developing PCR primers for the detection of harmful microorganisms, such as Salmonella, Cronobacter, Staphylococcus, and Listeria, as well as beneficial microorganisms like Lactobacillus. Additionally, the review discusses the applicability, advantages, limitations, and future directions of pan-genome analysis for primer design. A comparative overview of bioinformatics tools, recent trends, and verification methods is also provided, offering valuable insights for researchers interested in leveraging pan-genome analysis for advanced primer design.},
}

@article {pmid40228902,
year = {2025},
author = {Rausch, T and Marschall, T and Korbel, JO},
title = {The impact of long-read sequencing on human population-scale genomics.},
journal = {Genome research},
volume = {35},
number = {4},
pages = {593-598},
doi = {10.1101/gr.280120.124},
pmid = {40228902},
issn = {1549-5469},
mesh = {Humans ; *Genomics/methods ; *Genome, Human ; *High-Throughput Nucleotide Sequencing/methods ; *Sequence Analysis, DNA/methods ; Genomic Structural Variation ; DNA Methylation ; *Genetics, Population ; },
abstract = {Long-read sequencing technologies, particularly those from Pacific Biosciences and Oxford Nanopore Technologies, are revolutionizing genome research by providing high-resolution insights into complex and repetitive regions of the human genome that were previously inaccessible. These advances have been particularly enabling for the comprehensive detection of genomic structural variants (SVs), which is critical for linking genotype to phenotype in population-scale and rare disease studies, as well as in cancer. Recent developments in sequencing throughput and computational methods, such as pangenome graphs and haplotype-resolved assemblies, are paving the way for the future inclusion of long-read sequencing in clinical cohort studies and disease diagnostics. DNA methylation signals directly obtained from long reads enhance the utility of single-molecule long-read sequencing technologies by enabling molecular phenotypes to be interpreted, and by allowing the identification of the parent of origin of de novo mutations. Despite this recent progress, challenges remain in scaling long-read technologies to large populations due to cost, computational complexity, and the lack of tools to facilitate the efficient interpretation of SVs in graphs. This perspective provides a succinct review on the current state of long-read sequencing in genomics by highlighting its transformative potential and key hurdles, and emphasizing future opportunities for advancing the understanding of human genetic diversity and diseases through population-scale long-read analysis.},
}

Humans
*Genomics/methods
*Genome, Human
*High-Throughput Nucleotide Sequencing/methods
*Sequence Analysis, DNA/methods
Genomic Structural Variation
DNA Methylation
*Genetics, Population

@article {pmid40226526,
year = {2025},
author = {Ren, X and Liu, X and Che, Y and Yang, L and Mao, Y and Li, M and Sun, Z and Bai, X and Gao, H and Wang, Y and Wang, D},
title = {Serotype Distribution, Virulence, and Antibiotic Resistance Genomic Characterization of Group B Streptococcus - China, 1998-2024.},
journal = {China CDC weekly},
volume = {7},
number = {13},
pages = {413-421},
pmid = {40226526},
issn = {2096-7071},
abstract = {INTRODUCTION: Streptococcus agalactiae, or group B Streptococcus (GBS), can cause severe infections in humans, yet comprehensive genomic characterization from China remains limited. This study presents an extensive genomic analysis of GBS isolates collected in China from 1998 to 2024.

METHODS: GBS genomes were obtained from public databases and through de novo sequencing. Serotype confirmation was conducted via pan-genomic analysis, phylogenetic relationships were established using maximum-likelihood methodology, and virulence and antibiotic resistance genes were identified through the Virulence Factor Database and Comprehensive Antibiotic Resistance Database. Statistical analyses were performed using SPSS 26.0, primarily employing Fisher's exact tests.

RESULTS: Analysis of 747 GBS genomes revealed eight serotypes (Ia, Ib, II, III, IV, V, VI, VII) and nontypeable strains. Serotypes III, Ib, Ia, V, and II constituted 96.65% of all isolates. GBS prevalence remained low from 1998-2011 but increased substantially after 2012. Geographic distribution demonstrated significant regional heterogeneity. Phylogenetic analysis categorized the 747 genomes into five distinct lineages, with lineage 5 being predominant. Six virulence factor categories encompassing 56 virulence-associated genes were identified, with 33 genes present in nearly all genomes. Twenty-seven antibiotic resistance genes spanning nine drug classes were detected, particularly those conferring resistance to peptides and macrolide antibiotics, indicating widespread antimicrobial resistance mechanisms in GBS.

CONCLUSIONS: GBS infections in China exhibit serotype distributions similar to global patterns but with notable regional variations. This comprehensive genomic characterization provides critical insights for developing targeted prevention strategies and treatment approaches for GBS infections in China.},
}

@article {pmid40224327,
year = {2025},
author = {Nakandala, U and Furtado, A and Henry, RJ},
title = {Citrus genomes: past, present and future.},
journal = {Horticulture research},
volume = {12},
number = {5},
pages = {uhaf033},
pmid = {40224327},
issn = {2662-6810},
abstract = {Over the past decade, genome sequencing and assembly approaches have been greatly improved, resulting in the assembly of many genomes for citrus, including wild, domesticated, and citrus-related genomes. Improvements in technologies have led to assembled genomes with higher completeness, contiguity, quality, and accuracy that have greatly facilitated annotation and analysis. This review summarizes the evolution of the sequencing, assembly, and annotation technologies leading to citrus genomes over the past 11 years, a comprehensive evaluation of their quality, contiguity, and completeness, and the major findings and applications. Of the 50 genomes now available, 35 have been assembled to chromosome level and 15 to draft level, and 14 were haplotype-resolved assemblies. To date there have been four pangenome-wide studies for citrus. The very recent genomes assembled with long-read sequencing have achieved >99% and >98% assembly and annotation completeness (BUSCO), respectively. However, some early genomes are not of the same high quality as more recently sequenced genomes and would benefit from re-sequencing. A more comprehensive pangenome based upon a larger set of species and genotypes assembled at the haplotype level would allow genomics to deliver the maximum benefits for citrus improvement and research.},
}

@article {pmid40223124,
year = {2025},
author = {Azam, S and Sahu, A and Pandey, NK and Neupane, M and Van Tassell, CP and Rosen, BD and Gandham, RK and Rath, SN and Majumdar, SS},
title = {Constructing a draft Indian cattle pangenome using short-read sequencing.},
journal = {Communications biology},
volume = {8},
number = {1},
pages = {605},
pmid = {40223124},
issn = {2399-3642},
mesh = {Animals ; Cattle/genetics ; *Genome ; Polymorphism, Single Nucleotide ; *Genomics/methods ; Quantitative Trait Loci ; India ; Genetic Variation ; Sequence Analysis, DNA ; High-Throughput Nucleotide Sequencing ; },
abstract = {Indian desi cattle, known for their adaptability and phenotypic diversity, represent a valuable genetic resource. However, a single reference genome often fails to capture the full extent of their genetic variation. To address this, we construct a pangenome for desi cattle by identifying and characterizing non-reference novel sequences (NRNS). We sequence 68 genomes from seven breeds, generating 48.35 billion short reads. Using the PanGenome Analysis (PanGA) pipeline, we identify 13,065 NRNS (~41 Mbp), with substantial variation across the population. Most NRNS were unique to desi cattle, with minimal overlap (4.1%) with the Chinese indicine pangenome. Approximately 40% of NRNS exhibited ancestral origins within the Bos genus and were enriched in genic regions, suggesting functional roles. These sequences are linked to quantitative trait loci for traits such as milk production. The pangenome approach enhances read mapping accuracy, reduces spurious single nucleotide polymorphism calls, and uncovers novel genetic variants, offering a deeper understanding of desi cattle genomics.},
}

Animals
Cattle/genetics
*Genome
Polymorphism, Single Nucleotide
*Genomics/methods
Quantitative Trait Loci
India
Genetic Variation
Sequence Analysis, DNA
High-Throughput Nucleotide Sequencing

@article {pmid40219973,
year = {2025},
author = {Jiang, M and Qian, Q and Lu, M and Chen, M and Fan, Z and Shang, Y and Bu, C and Du, Z and Song, S and Zeng, J and Xiao, J},
title = {PlantPan: A comprehensive multi-species plant pan-genome database.},
journal = {The Plant journal : for cell and molecular biology},
volume = {122},
number = {1},
pages = {e70144},
doi = {10.1111/tpj.70144},
pmid = {40219973},
issn = {1365-313X},
support = {32170669//the National Natural Science Foundation of China/ ; XDA0450000//the Strategic Priority Research Program of the Chinese Academy of Sciences/ ; 2022098//the Youth Innovation Promotion Association of the Chinese Academy of Science/ ; },
mesh = {*Genome, Plant/genetics ; *Databases, Genetic ; *Plants/genetics ; Genetic Variation ; Multigene Family ; },
abstract = {The pan-genome represents the complete genomic diversity of specific species, serving as a valuable resource for studying species evolution, crop domestication, and guiding crop breeding and improvement. While there are several single-species-specific plant pan-genome databases, the availability of multi-species pan-genome databases is limited. Additionally, variations in methods and data types used for plant pan-genome analysis across different databases hinder the comparison and integration of pan-genome information from various projects at multi-species or single-species levels. To tackle this challenge, we introduce PlantPan, a comprehensive database housing the results of pan-genome analysis for 195 genomes from 11 plant species. PlantPan aims to provide extensive information, including gene-centric and sequence-centric pan-genome information, graph-based pan-genome, pan-genome openness profiles, gene functions and its variation characteristics, homologous genes, and gene clusters across different species. Statistically, PlantPan incorporates 9 163 011 genes, 694 191 gene clusters, 526 973 370 genome variations, and 1 616 089 non-redundant genome variation groups at the species level, 33 455,098 genome synteny, and 177 827 non-redundant genome synteny groups at the species level. Regarding functional genes, PlantPan contains 5 222 720 genes related to transcription factors, 395 247 literature-reported resistance genes, 455 748 predicted microbial/disease resistance genes, and 1 612 112 genes related to molecular pathways. In summary, PlantPan is a vital platform for advancing the application of pan-genomes in molecular breeding for crops and evolutionary research for plants.},
}

*Genome, Plant/genetics
*Databases, Genetic
*Plants/genetics
Genetic Variation
Multigene Family

@article {pmid40212029,
year = {2025},
author = {Frias-De-Diego, A and Jara, M and Lanzas, C},
title = {Influence of Sequencing Technology on Pangenome-Level Analysis and Detection of Antimicrobial Resistance Genes in ESKAPE Pathogens.},
journal = {Open forum infectious diseases},
volume = {12},
number = {4},
pages = {ofaf183},
pmid = {40212029},
issn = {2328-8957},
support = {R35 GM134934/GM/NIGMS NIH HHS/United States ; },
abstract = {As sequencing costs decrease, short-read and long-read technologies are indispensable tools for uncovering the genetic drivers behind bacterial pathogen resistance. This study explores the differences between the use of short-read (Illumina) and long-read (Oxford Nanopore Technologies [ONT]) sequencing in detecting antimicrobial resistance (AMR) genes in ESKAPE pathogens (ie, Enterococcus faecium, Staphylococcus aureus, Klebsiella pneumoniae, Acinetobacter baumannii, Pseudomonas aeruginosa, and Enterobacter cloacae). Utilizing a dataset of 1385 whole genome sequences and applying commonly used bioinformatic methods in bacterial genomics, we assessed the differences in genomic completeness, pangenome structure, and AMR gene and point mutation identification. Illumina presented higher genome completeness, while ONT identified a broader pangenome. Hybrid assembly outperformed both Illumina and ONT at identifying key AMR genetic determinants, presented results closer to Illumina's completeness, and revealed ONT-like pangenomic content. Notably, Illumina consistently detected more AMR-related point mutations than its counterparts. This highlights the importance of method selection based on research goals, particularly when using publicly available data ranging a wide timespan. Differences were also observed for specific gene classes and bacterial species, underscoring the need for a nuanced understanding of technology limitations. Overall, this study reveals the strengths and limitations of each approach, advocating for the use of Illumina for common AMR analysis, ONT for studying complex genomes and novel species, and hybrid assembly for a more comprehensive characterization, leveraging the benefits of both technologies.},
}

@article {pmid40210717,
year = {2025},
author = {Li, W},
title = {Solanum pan-genome highlights paralog diversification.},
journal = {Nature genetics},
volume = {57},
number = {4},
pages = {774},
doi = {10.1038/s41588-025-02178-2},
pmid = {40210717},
issn = {1546-1718},
}

@article {pmid40210439,
year = {2025},
author = {Smith, BJ and Zhao, C and Dubinkina, V and Jin, X and Zahavi, L and Shoer, S and Moltzau-Anderson, J and Segal, E and Pollard, KS},
title = {Accurate estimation of intraspecific microbial gene content variation in metagenomic data with MIDAS v3 and StrainPGC.},
journal = {Genome research},
volume = {},
number = {},
pages = {},
doi = {10.1101/gr.279543.124},
pmid = {40210439},
issn = {1549-5469},
abstract = {Metagenomics has greatly expanded our understanding of the human gut microbiome by revealing a vast diversity of bacterial species within and across individuals. Even within a single species, different strains can have highly divergent gene content, affecting traits such as antibiotic resistance, metabolism, and virulence. Methods that harness metagenomic data to resolve strain-level differences in functional potential are crucial for understanding the causes and consequences of this intraspecific diversity. The enormous size of pangenome references, strain mixing within samples, and inconsistent sequencing depth present challenges for existing tools that analyze samples one at a time. To address this gap, we updated the MIDAS pangenome profiler, now released as version 3, and developed StrainPGC, an approach to strain-specific gene content estimation that combines strain tracking and correlations across multiple samples. We validate our integrated analysis using a complex synthetic community of strains from the human gut and find that StrainPGC outperforms existing approaches. Analyzing a large, publicly available metagenome collection from inflammatory bowel disease patients and healthy controls, we catalog the functional repertoires of thousands of strains across hundreds of species, capturing extensive diversity missing from reference databases. Finally, we apply StrainPGC to metagenomes from a clinical trial of fecal microbiota transplantation for the treatment of ulcerative colitis. We identify two Escherichia coli strains, from two different donors, that are both frequently transmitted to patients but have notable differences in functional potential. StrainPGC and MIDAS v3 together enable precise, intraspecific pangenomic investigations using large collections of metagenomic data without microbial isolation or de novo assembly.},
}

@article {pmid40210437,
year = {2025},
author = {Quah, FX and Almeida, MV and Blumer, M and Yuan, CU and Fischer, B and See, K and Jackson, B and Zatha, R and Rusuwa, B and Turner, GF and Santos, ME and Svardal, H and Hemberg, M and Durbin, R and Miska, E},
title = {Lake Malawi cichlid pangenome graph reveals extensive structural variation driven by transposable elements.},
journal = {Genome research},
volume = {},
number = {},
pages = {},
doi = {10.1101/gr.279674.124},
pmid = {40210437},
issn = {1549-5469},
abstract = {Pangenome methods have the potential to uncover hitherto undiscovered sequences missing from established reference genomes, making them useful to study evolutionary and speciation processes in diverse organisms. The cichlid fishes of the East African Rift Lakes represent one of nature's most phenotypically diverse vertebrate radiations, but single-nucleotide polymorphism (SNP)-based studies have revealed little sequence difference, with 0.1%-0.25% pairwise divergence between Lake Malawi species. These were based on aligning short reads to a single linear reference genome and ignored the contribution of larger-scale structural variants (SVs). We constructed a pangenome graph that integrates six new and two existing long-read genome assemblies of Lake Malawi haplochromine cichlids. This graph intuitively represents complex and nested variation between the genomes and reveals that the SV landscape is dominated by large insertions, many exclusive to individual assemblies. The graph incorporates a substantial amount of extra sequence across seven species, the total size of which is 33.1% longer than that of a single cichlid genome. Approximately 4.73% to 9.86% of the assembly lengths are estimated as interspecies structural variation between cichlids, suggesting substantial genomic diversity underappreciated in SNP studies. Although coding regions remain highly conserved, our analysis uncovers a significant proportion of SV sequences as transposable element (TE) insertions, especially DNA, LINE, and LTR TEs. These findings underscore that the cichlid genome is shaped both by small-nucleotide mutations and large, TE-derived sequence alterations, both of which merit study to understand their interplay in cichlid evolution.},
}

@article {pmid40203032,
year = {2025},
author = {Timilsina, S and Iruegas-Bocardo, F and Jibrin, MO and Sharma, A and Subedi, A and Kaur, A and Minsavage, GV and Huguet-Tapia, JC and Klein-Gordon, J and Adhikari, P and Adhikari, TB and Cirvilleri, G and de la Barrera, LBT and Bernal, E and Creswell, TC and Doan, TTK and Coutinho, TA and Egel, DS and Félix-Gastélum, R and Francis, DM and Kebede, M and Ivey, ML and Louws, FJ and Luo, L and Maynard, ET and Miller, SA and Nguyen, NTT and Osdaghi, E and Quezado-Duval, AM and Roach, R and Rotondo, F and Ruhl, GE and Shutt, VM and Thummabenjapone, P and Trueman, C and Roberts, PD and Jones, JB and Vallad, GE and Goss, EM},
title = {Diversification of an emerging bacterial plant pathogen; insights into the global spread of Xanthomonas euvesicatoria pv. perforans.},
journal = {PLoS pathogens},
volume = {21},
number = {4},
pages = {e1013036},
doi = {10.1371/journal.ppat.1013036},
pmid = {40203032},
issn = {1553-7374},
abstract = {Emerging and re-emerging plant diseases continue to present multifarious threats to global food security. Considerable recent efforts are therefore being channeled towards understanding the nature of pathogen emergence, their spread and evolution. Xanthomonas euvesicatoria pv. perforans (Xep), one of the causal agents of bacterial spot of tomato, rapidly emerged and displaced other bacterial spot xanthomonads in many tomato production regions around the world. In less than three decades, it has become a dominant xanthomonad pathogen in tomato production systems across the world and presents a compelling example for understanding diversification of recently emerged bacterial plant pathogens. Although Xep has been continuously monitored in Florida since its discovery, the global population structure and evolution at the genome-scale is yet to be fully explored. The objectives of this work were to determine genetic diversity globally to ascertain if different tomato production regions contain genetically distinct Xep populations, to examine genetic relatedness of strains collected in tomato seed production areas in East Asia and other production regions, and to evaluate variation in type III secretion effectors, which are critical pathogenicity and virulence factors, in relationship to population structure. We used genome data from 270 strains from 13 countries for phylogenetic analysis and characterization of type III effector gene diversity among strains. Our results showed notable genetic diversity in the pathogen. We found genetically similar strains in distant tomato production regions, including seed production regions, and diversification over the past 100 years, which is consistent with intercontinental dissemination of the pathogen in hybrid tomato production chains. Evolution of the Xep pangenome, including the acquisition and loss of type III secreted effectors, is apparent within and among phylogenetic lineages. The apparent long-distance movement of the pathogen, together with variants that may not yet be widely distributed, poses risks of emergence of new variants in tomato production.},
}

@article {pmid40202301,
year = {2025},
author = {Mahillon, M and Debonneville, C and Groux, R and Roquis, D and Brodard, J and Faoro, F and Foissac, X and Schumpp, O and Dittmer, J},
title = {From insect endosymbiont to phloem colonizer: comparative genomics unveils the lifestyle transition of phytopathogenic Arsenophonus strains.},
journal = {mSystems},
volume = {},
number = {},
pages = {e0149624},
doi = {10.1128/msystems.01496-24},
pmid = {40202301},
issn = {2379-5077},
abstract = {UNLABELLED: Bacteria infecting the plant phloem represent a growing threat worldwide. While these organisms often resist in vitro culture, they multiply both in plant sieve elements and hemipteran vectors. Such cross-kingdom parasitic lifestyle has emerged in diverse taxa via distinct ecological routes. In the genus Arsenophonus, the phloem pathogens "Candidatus Arsenophonus phytopathogenicus" (Ap) and "Ca. Phlomobacter fragariae" (Pf) have evolved from insect endosymbionts, but the genetic mechanisms underlying this transition have not been explored. To fill this gap, we obtained the genomes of both strains from insect host metagenomes. The resulting assemblies are highly similar in size and functional repertoire, rich in viral sequences, and closely resemble the genomes of several facultative endosymbiotic Arsenophonus strains of sap-sucking hemipterans. However, a phylogenomic analysis demonstrated distinct origins, as Ap belongs to the "Triatominarum" clade, whereas Pf represents a distant species. We identified a set of orthologs encoded only by Ap and Pf in the genus, including hydrolytic enzymes likely targeting plant substrates. In particular, both bacteria encode putative plant cell wall-degrading enzymes and cysteine peptidases related to xylellain, a papain-like peptidase from Xylella fastidiosa, for which close homologs are found in diverse Pseudomonadota infecting the plant vasculature. In silico predictions and gene expression analyses further support a role during phloem colonization for several of the shared orthologs. We conclude that the double emergence of phytopathogenicity in Arsenophonus may have been mediated by a few horizontal gene transfer events, involving genes acquired from other Pseudomonadota, including phytopathogens.

IMPORTANCE: We investigate the genetic mechanisms of a transition in bacterial lifestyle. We focus on two phloem pathogens belonging to the genus Arsenophonus: "Candidatus Arsenophonus phytopathogenicus" and "Ca. Phlomobacter fragariae." Both bacteria cause economically significant pathologies, and they have likely emerged among facultative insect endosymbionts. Our genomic analyses show that both strains are highly similar to other strains of the genus associated with sap-sucking hemipterans, suggesting a recent lifestyle shift. Importantly, although the phytopathogenic Arsenophonus strains belong to distant clades, they share a small set of orthologs unique in the genus pangenome. We provide evidence that several of these genes produce hydrolytic enzymes that are secreted and may target plant substrates. The acquisition and exchange of these genes may thus have played a pivotal role in the lifestyle transition of the phytopathogenic Arsenophonus strains.},
}

@article {pmid40198110,
year = {2025},
author = {Chowdhury, G and Hoshiko, Y and Okuno, M and Kitahara, K and Albert, MJ and Miyoshi, SI and Ogura, Y and Dutta, S and Ramamurthy, T and Mukhopadhyay, AK},
title = {Whole-genome-based characterization of Escherichia albertii strains isolated from paediatric diarrhoeal cases in Kolkata, India.},
journal = {Microbial genomics},
volume = {11},
number = {4},
pages = {},
pmid = {40198110},
issn = {2057-5858},
mesh = {Humans ; *Diarrhea/microbiology ; Phylogeny ; India ; Virulence Factors/genetics ; *Escherichia/genetics/isolation & purification/drug effects/classification/pathogenicity ; *Genome, Bacterial ; Whole Genome Sequencing ; Feces/microbiology ; Microbial Sensitivity Tests ; Child, Preschool ; Infant ; Child ; Anti-Bacterial Agents/pharmacology ; Male ; Female ; Drug Resistance, Bacterial/genetics ; Bacterial Toxins/genetics ; },
abstract = {Escherichia albertii is a Gram-negative facultative anaerobic bacterium that causes diarrhoea in humans. This study shows the isolation of E. albertii from hospitalized paediatric diarrhoeal cases and genome-based characteristics with putative virulence factors and antimicrobial resistance. E. albertii isolates were identified by species-specific PCR, targeting the gene encoding cytolethal distending toxin (Ea-cdt). The genome of E. albertii was sequenced to identify (i) genes encoding virulence factors (ii) antibiotic resistance-encoding genes, including the mobile genetic elements and (iii) core gene-based phylogenetic relationships and pan-genome features. A total of 10 (1.2%) E. albertii isolates were isolated from 854 faecal samples, of which 6 (60%) were found as the sole pathogen and the remaining 4 (40%) were identified along with other pathogens, such as enteroaggregative Escherichia coli, rotavirus and adenovirus. Patients from whom E. albertii was isolated presented cholera-like diarrhoea, i.e. with watery stool (60%) with moderate dehydration (100%), fever (20%) and abdominal pain (20%). The antimicrobial susceptibility testing of E. albertii showed that most of the isolates were susceptible or reduced susceptible to most of the antibiotics except resistance to erythromycin (80%), tetracycline (50%), nalidixic acid (40%), ampicillin (40%), doxycycline (30%) and ceftriaxone (20%). In the whole-genome sequence, E. albertii isolates revealed several virulence-encoding genes, namely the intimin (eae, E. coli attaching and effacing), the cytolethal distending toxin type II subunit A (cdt-IIA), adhesion (paa, porcine attaching- and effacing-associated), non-LEE (locus of enterocyte effacement) encoded effector A (nleA) and antimicrobial resistance genes (ARGs) conferring resistance to tetracycline (tetA, tetR), sulphonamides (sul2), fluoroquinolones (qnrS) and beta-lactamases (bla CTX-M, blaTEM). The SNP-based phylogenetic analysis of 647 whole genomes of E. albertii isolates from the National Center for Biotechnology Information databases did not reveal any comparable clustering pattern based on the biological source and place of isolation. The genome of some of the E. albertii was closely related to those of the isolates from China and the United Kingdom. The PFGE patterns revealed that most of the E. albertii isolates were distinct clones. This study reports on the extensive genome analysis of diarrhoea-associated E. albertii harbouring multiple virulence and ARGs.},
}

Humans
*Diarrhea/microbiology
Phylogeny
India
Virulence Factors/genetics
*Escherichia/genetics/isolation & purification/drug effects/classification/pathogenicity
*Genome, Bacterial
Whole Genome Sequencing
Feces/microbiology
Microbial Sensitivity Tests
Child, Preschool
Infant
Child
Anti-Bacterial Agents/pharmacology
Male
Female
Drug Resistance, Bacterial/genetics
Bacterial Toxins/genetics