@article {pmid40527417,
year = {2025},
author = {Yaikhan, T and Singkhamanan, K and Suwannasin, S and Dechathai, T and Yingkajorn, M and Chusri, S and Surachat, K},
title = {Genomic insights into Metapseudomonas otitidis PA-NS83: The first clinical isolate from Thailand and its comparative genomic analysis.},
journal = {Infection, genetics and evolution : journal of molecular epidemiology and evolutionary genetics in infectious diseases},
volume = {},
number = {},
pages = {105786},
doi = {10.1016/j.meegid.2025.105786},
pmid = {40527417},
issn = {1567-7257},
abstract = {Metapseudomonas otitidis was first isolated from human middle ear fluid and has since been detected in both environmental and clinical samples, emerging as an opportunistic pathogen linked to chronic otitis media and other infections. This study reports the first clinical isolate of M. otitidis from Thailand, PA-NS83, and presents a comprehensive genomic characterization. Whole-genome sequencing and comparative analysis with 37 publicly available M. otitidis genomes revealed a diverse antimicrobial resistance (AMR) profile, with PA-NS83 carrying AMR genes commonly found in environmental isolates. Virulence gene analysis identified key determinants associated with biofilm formation, motility, secretion systems, and iron acquisition, highlighting its potential pathogenicity. Pan-genome analysis demonstrated substantial genomic diversity, with PA-NS83 clustering closely with M. otitidis CSMC7, an environmental isolate from polystyrene waste. However, PA-NS83 harbored 419 unique genes, including virulence-associated genes and a CRISPR-Cas system, suggesting adaptation to clinical settings. These findings underscore the genetic plasticity of M. otitidis and its potential role in human infections. Continued genomic surveillance and functional studies are essential to further assess its clinical significance and antimicrobial resistance mechanisms.},
}

@article {pmid40526067,
year = {2025},
author = {Chan, DTC and Agarwal, V and Baltrus, DA and Dillon, MM},
title = {Unified Classification of the Type III Secreted Effectors of Bacterial Plant Pathogens to Advance Phytopathology Research.},
journal = {Phytopathology},
volume = {},
number = {},
pages = {},
doi = {10.1094/PHYTO-02-25-0055-FI},
pmid = {40526067},
issn = {0031-949X},
abstract = {Many diverse bacterial phytopathogens deploy type III secreted effectors (T3SEs) to promote virulence by interrupting host immunity and other critical plant processes. However, the virulence of T3SEs has been countered on the host side through the evolution of a multitude of resistance genes (R-genes) capable of recognizing the presence of T3SEs and eliciting a response termed effector triggered immunity (ETI). This dynamic sets up an evolutionary arms race that has led to enormous diversification of both bacterial T3SEs and plant R-genes. Over the past decade, efforts to document and characterize the pangenome T3SE profiles of individual pathogens have generated indispensable resources that have facilitated collaborative research progress on these focal pathogens. However, despite the deeply integrated evolutionary history of T3SEs, the lack of concerted effort to synthesize T3SE conventions across diverse pathosystems has resulted in a lack of connectivity across the literature. Here, we catalogue the distribution of T3SEs across six of the most globally significant genera of bacterial phytopathogens. We show that the number of T3SEs per genome varies dramatically within and between genera, and that many T3SE families are present in multiple genera despite their sparse distributions across closely related strains. We also document all inter-genera evolutionary relationships for each T3SE family and propose integrated nomenclature conventions for all phytopathogen T3SEs. Ultimately, our expanded T3SE collection includes thousands of newly classified alleles, catalogues several previously unestablished homologies between distinct genera, and will enable more comprehensive studies on the implications of T3SE diversification for virulence and immunity.},
}

@article {pmid40525812,
year = {2025},
author = {Gelgie, AE and Gelalcha, BD and Christensen, D and Freeman, T and Beever, JE and Dego, OK},
title = {Prevalence and Whole Genome Sequence Analysis of Mycoplasma bovis Isolates From Bulk Tank Milk of Dairy Farms in Tennessee, USA.},
journal = {Journal of veterinary internal medicine},
volume = {39},
number = {4},
pages = {e70164},
pmid = {40525812},
issn = {1939-1676},
support = {//The 10× Genomics Single Cell Grant Program/ ; //UTIA Genomics Center for the Advancement of Agriculture/ ; },
mesh = {Animals ; Cattle ; *Mycoplasma bovis/genetics/isolation & purification ; Tennessee/epidemiology ; *Milk/microbiology ; Female ; *Mycoplasma Infections/veterinary/epidemiology/microbiology ; Prevalence ; *Mastitis, Bovine/microbiology/epidemiology ; Dairying ; Whole Genome Sequencing/veterinary ; },
abstract = {BACKGROUND: Mycoplasma bovis mastitis is an important disease of dairy cows that causes substantial economic losses. However, its prevalence in different states in the United States (US), including Tennessee, is not well known. Furthermore, recent studies showed a high prevalence of bovine hemotropic mycoplasmas in US dairy farms.

OBJECTIVES: Determine the prevalence of M. bovis in bulk tank milk (BTM) of dairy farms in Tennessee and evaluate the genetic diversity, virulence factors, and antimicrobial resistance genes of the identified isolates. In addition, the prevalence of Mycoplasma wenyonii and Candidatus Mycoplasma haemobos in the bulk tank milk was determined.

METHODS: Seventy-five BTM samples were collected from 59 dairy farms. Of the 59 farms, 56 are in Tennessee and the remaining 3 farms are in the neighboring states, Georgia (n = 2) and Alabama (n = 1). Milk samples were tested using bacterial culture, PCR, and qPCR. M. bovis isolates were genetically characterized by pangenome analysis.

RESULTS: Of the 56 farms, 3 (5.3%) were positive for M. bovis by bacterial culture and 43 (76.7%) were positive by PCR. Pangenome analysis showed clustering of current isolates with mastitis isolates from the US, Israel, and Europe. Of 75 BTM samples tested by qPCR, 42 (56%) and 51 (68%) were positive for M. wenyonii and C. M. haemobos, respectively.

CONCLUSIONS: M. bovis intramammary infection is prevalent in Tennessee dairy farms.},
}

Animals
Cattle
*Mycoplasma bovis/genetics/isolation & purification
Tennessee/epidemiology
*Milk/microbiology
Female
*Mycoplasma Infections/veterinary/epidemiology/microbiology
Prevalence
*Mastitis, Bovine/microbiology/epidemiology
Dairying
Whole Genome Sequencing/veterinary

@article {pmid40523568,
year = {2025},
author = {Zhao, Y and Zhao, Y and Shen, Q and Hu, X and Zhou, S and Huang, J},
title = {Evolution and epidemiology of pks[+]Klebsiella pneumoniae: Global and local insights.},
journal = {Microbial pathogenesis},
volume = {206},
number = {},
pages = {107812},
doi = {10.1016/j.micpath.2025.107812},
pmid = {40523568},
issn = {1096-1208},
abstract = {OBJECTIVE: This study aimed to investigate the epidemiological characteristics and genomic evolutionary mechanisms of pks-positive Klebsiella pneumoniae (pks [+] KPN), providing theoretical insights for infection prevention and control strategies.

METHODS: A total of 873 non-duplicate K. pneumoniae isolates collected between 2016 and 2022 at the Fifth Affiliated Hospital of Wenzhou Medical University were screened for pks [+] strains via PCR targeting clbA, clbB, clbN, and clbQ. Clonal structures of pks[+] and pks[-] strains were determined by MLST and KL typing, and virulence gene profiles (peg344, iucA, rmpA, rmpA2, iroB) were analyzed to compare the two populations. Global distribution patterns of pks [+] KPN were analyzed using data from the Bacterial and Viral Bioinformatics Resource Center (BV-BRC). Pan-genomic analysis via the IPGA platform and a phylogenetic tree was constructed. Core-genome comparative analysis identified lineage-specific genes in dominant pks[+] strains, and KEGG enrichment revealed their putative biological functions. Statistical analyses were performed using SPSS 26.0, with p < 0.05 considered statistically significant.

RESULTS: Among 873 clinical isolates, 105 (12.03 %) were pks [+] KPN, predominantly isolated from infectious disease and surgical departments. The pks island prevalence was significantly higher in non-carbapenem-resistant strains (25.45 %) than in carbapenem-resistant strains (1.04 %) (χ[2] = 125.57, p < 0.001). pks [+] strains exhibited higher virulence gene carriage rates (p < 0.05) and infected younger patients (57.97 ± 14.90 vs. 64.18 ± 17.29 years, t = 3.46, p = 0.001). pks [+] isolates showed a conserved clonal structure dominated by ST23-KL1 (66.7 %), while pks[-] strains displayed greater heterogeneity with 37 distinct ST-KL types. Analysis of 706 global pks [+] KPN revealed that ST23 (45.18 %), ST11 (15.72 %), and ST258 (15.16 %) are the predominant clonal lineages. Phylogenetic construction delineated five evolutionarily distinct clades among pks[+] strains. Comparative core genome analysis identified 245 lineage-associated genes, of which 96 were shared among dominant strains. Functional enrichment (KEGG) demonstrated that these conserved genes are significantly enriched in the galactose metabolism.

CONCLUSION: This study systematically elucidates the clinical epidemiology, clonal dissemination patterns, and genomic evolution of pks [+] KPN, identifying ST23-KL1 as the dominant clone. The findings reveal that galactose metabolism may enhance the adaptability of dominant strains, thereby driving their global spread.},
}

@article {pmid40522106,
year = {2025},
author = {Garzon, A and Miramontes, C and Weimer, BC and Profeta, R and Hoyos-Jaramillo, A and Fritz, HM and Pereira, RV},
title = {Comparison of virulence and resistance genes in Mannheimia haemolytica and Pasteurella multocida from dairy cattle with and without bovine respiratory disease.},
journal = {Microbiology spectrum},
volume = {},
number = {},
pages = {e0120025},
doi = {10.1128/spectrum.01200-25},
pmid = {40522106},
issn = {2165-0497},
abstract = {UNLABELLED: Mannheimia haemolytica and Pasteurella multocida are two of the main bacterial pathogens associated with bovine respiratory disease (BRD). BRD represents one of the most significant health challenges in the cattle industry, causing substantial economic losses through animal morbidity and mortality while raising serious welfare concerns. The objectives of this project were to (i) characterize virulence factor (VF) and antimicrobial resistance (AMR) genes in M. haemolytica and P. multocida isolates from dairy cattle of different ages with and without BRD using whole-genome sequencing (WGS); (ii) evaluate associations between microbial genetic elements and animal disease status; and (iii) assess the accuracy of genome-based predictions for the antimicrobial resistance phenotype. Using a case-control study, AMR and VF genes were characterized from 149 P. multocida and 68 M. haemolytica isolates from preweaned calves, weaned heifers, and cows with and without BRD. The large genetic diversity observed in both bacterial species prevented the identification of unique genetic markers associated with disease status or age group. AMR genes (22 genes) from 12 antimicrobial classes were identified in P. multocida isolates, while 11 AMR genes for seven antimicrobial classes were identified in M. haemolytica isolates. Additionally, 28 and 15 virulence genes were identified in P. multocida and M. haemolytica, respectively. The ability of WGS-based predictions to predict phenotypic antimicrobial resistance showed variable accuracy across different antimicrobials, achieving moderate levels of agreement overall. Findings from this project demonstrate that identifying genomic markers based on gene presence/absence lacks discriminatory power within this population for identifying unique genotypes associated with disease status in these genomically diverse organisms.

IMPORTANCE: This case-control study provides key microbial ecological advances by elucidating the role of bacteria in the bovine respiratory disease complex in dairy cattle. Previous research has identified specific virulence factors in both bacterial genomes that resulted in disease. Our results challenge this perception and are of high impact, revealing that the pan-genome of both bacteria did not differentiate among the clinical cases or age groups, and a specific pathogenic pathotype was not evident in the isolates from this study, and it did not emerge when including additional public whole-genome sequences to increase the analytical power of the analysis (the first study to use this approach to evaluate bovine respiratory disease in cattle). In addition to these novel discoveries, this study describes the first population-scale genomic comparison of both Mannheimia haemolytica and Pasteurella multocida genomes collected from affected and healthy dairy cattle from different age groups and from multiple farms.},
}

@article {pmid40518659,
year = {2025},
author = {Gurung, S and Lee, CM and Weon, HY and Han, SR and Oh, TJ},
title = {Comparative Genome Analysis of Three Halobacillus Strains Isolated From Saline Environments Reveal Potential Salt Tolerance and Algicidal Mechanisms.},
journal = {Environmental microbiology reports},
volume = {17},
number = {3},
pages = {e70121},
pmid = {40518659},
issn = {1758-2229},
support = {RS-2024-00441423//The Bio & Medical Technology Development Program of the National Research Foundation (NRF) funded by the Korean government (MSIT)/ ; },
mesh = {*Salt Tolerance/genetics ; *Genome, Bacterial ; Harmful Algal Bloom ; Phylogeny ; *Bacillaceae/genetics/isolation & purification/physiology/classification ; Computational Biology ; Genomics ; },
abstract = {Harmful algal blooms (HABs) pose a significant global threat to water ecosystems, prompting extensive research into their inhibition and control strategies. This study presents genomic and bioinformatic analyses to investigate the algicidal potential and elucidate the survival mechanisms in harsh conditions of newly identified Halobacillus species three strains (SSTM10-2[T], SSBR10-3[T], and SSHM10-5[T]) isolated from saline environments. Moreover, genomic and bioinformatic analyses were conducted to elucidate their survival mechanisms in harsh conditions. Moreover, comparative genomic analysis revealed a diverse set of orthologous genes, with a core genome primarily associated with metabolism and information processing. Pangenome analysis highlighted accessory and unique genes potentially involved in environmental adaptation and stress response. Functional annotation using KEGG pathways identified genes linked to xenobiotic compound degradation, stress tolerance, and salt adaptation. Additionally, the study elucidated potential mechanisms underlying algicidal activity, implicating Carbohydrate-Active enZYmes (CAZymes), cytochrome P450 oxidases (CYP), and quorum sensing (QS) systems. Finally, analysis of KEGG pathways related to microcystin degradation suggested the strains' capacity to mitigate HABs. Thus, this research enhances understanding of the genomic diversity, phylogeny, and functional characteristics of Halobacillus species, offering insights into their ecological roles and potential applications in biotechnology and environmental management.},
}

*Salt Tolerance/genetics
*Genome, Bacterial
Harmful Algal Bloom
Phylogeny
*Bacillaceae/genetics/isolation & purification/physiology/classification
Computational Biology
Genomics

@article {pmid40517404,
year = {2025},
author = {Yu, J and Chen, Q and Yuan, L and Feng, S and Huang, M and Zheng, P and Chen, G and Tao, X and Edwards, D and Chen, ZH and Xu, S},
title = {Phylogenomic and super-pangenome analyses unveil the genetic landscape of tomato evolution and domestication.},
journal = {Plant biotechnology journal},
volume = {},
number = {},
pages = {},
doi = {10.1111/pbi.70199},
pmid = {40517404},
issn = {1467-7652},
support = {2023C1S01002//Project of Xianghu Laboratory/ ; 2024SSYS0099//Key Research and Development Program of Zhejiang Province/ ; },
abstract = {The tomato (Solanum lycopersicum L.), a principal fruit crop, exhibits significant genetic diversity shaped by domestication and breeding. Analysis of the gene-based super-pangenome, a catalogue of all genes across diverse genome-sequenced tomatoes, has not yet been fully explored. Here, we present a comprehensive analysis of the gene-based super-pangenome across 61 genetically diverse tomato varieties, revealing 59 066 orthologous groups, thereby providing a detailed genetic framework for understanding the evolution of tomatoes. Our phylogenetic analysis recalibrates the position of S. galapagense, challenging existing paradigms of tomato evolution. Identification of genes linked to key agronomic traits such as fruit size, ripening and stress tolerance, along with their presence/absence variation among accessions, offers a rich source of genetic markers for breeding programs. The study also highlights the impact of whole-genome triplication (WGT) and tandem gene duplication (TD) events on gene family expansion, particularly in distant wild relatives. The analysis of the LRR-RLK gene family, important for plant development and defence, reveals substantial sequence diversity and conservation. Rapidly evolving genes and those under positive selection, such as HAI3, CYP711A1/MAX1, WRKY9 and CNGC15, are implicated in stress tolerance and defence mechanisms. The identification of these genes, along with specific pathogenesis-related genes in distant wild relatives, suggests potential strategies to improve fruit shelf life, fruit set and stress tolerance in elite tomato cultivar breeding. Additionally, we have developed the tomatoPangenome platform, integrating genomic and pangenomic data, gene families and tools, to support sustainable production of high-quality, climate-resilient tomatoes and advance selective breeding for future food security.},
}

@article {pmid40517149,
year = {2025},
author = {Gonzalez-Garcia, LN and Rodriguez, MP and Parra-Muñoz, M and Clavijo, AM and Levy, L and Ovalle-Bracho, C and Colorado, C and Camargo, C and Quiceno, E and Moncada, MJ and Muskus, C and Urrea, DA and Baez-Aguirre, F and Restrepo, S and Echeverry, MC and Duitama, J},
title = {Genetic diversity and comparative genomics across Leishmania (Viannia) species.},
journal = {Communications biology},
volume = {8},
number = {1},
pages = {925},
pmid = {40517149},
issn = {2399-3642},
mesh = {*Leishmania/genetics/classification ; *Genetic Variation ; Phylogeny ; *Genomics/methods ; *Genome, Protozoan ; Humans ; Leishmaniasis/parasitology ; DNA Copy Number Variations ; },
abstract = {Leishmaniasis is an important public health problem worldwide, with a broad spectrum of clinical and epidemiological features partly associated with the diversity and complex life cycle of the Leishmania parasites. This study analyzes genomic data from 205 Leishmania (Viannia) samples, including 65 newly sequenced clinical isolates. It also provides chromosome-level genome assemblies for 10 isolates representing different species and populations. The observed distribution of Leishmania genomic diversity across the sampling locations suggests rapid adaptation to different ecosystems. The phylogenomic analysis provides new hypotheses challenging the current delimitation of species. Pangenomic analysis of high-quality assemblies shows consistent copy number variation between species for different gene families. Larger and more diverse amastin gene families were observed in the assembled genomes compared to previous reports based on the analysis of short-read data. This work provides genomic resources and helpful information regarding central problems in the biology of Leishmania spp, including species diversification, transmission dynamics, and the evolution of virulence mechanisms.},
}

*Leishmania/genetics/classification
*Genetic Variation
Phylogeny
*Genomics/methods
*Genome, Protozoan
Humans
Leishmaniasis/parasitology
DNA Copy Number Variations

@article {pmid40516885,
year = {2025},
author = {Cunha da Silva, G and Rossi, CC},
title = {Defense systems and mobile elements in Staphylococcus haemolyticus: a genomic view of resistance dissemination.},
journal = {Microbial pathogenesis},
volume = {206},
number = {},
pages = {107808},
doi = {10.1016/j.micpath.2025.107808},
pmid = {40516885},
issn = {1096-1208},
abstract = {Staphylococcus haemolyticus is a multidrug-resistant opportunistic pathogen and a major reservoir of antimicrobial resistance (AMR) genes within the Staphylococcaceae family. Its high genomic plasticity, frequent association with mobile genetic elements (MGEs), and prevalence in clinical settings underscore its relevance as both a threat and a conduit for resistance dissemination. In this study, we performed a comprehensive pan-genomic analysis of the S. haemolyticus defensome - including restriction-modification (RM), abortive infection (Abi), and CRISPR-Cas systems - across 692 high-quality genomes. Our results reveal a highly diverse and modular repertoire of immune systems, often organized in physical clusters and frequently associated with MGEs. We identified evidence of antagonistic interactions, with both defense and anti-defense elements encoded on plasmids and prophages. CRISPR spacer analysis showed a predominant targeting of phages, and genomes encoding CRISPR-Cas systems exhibited a lower abundance of MGEs and AMR genes, suggesting a trade-off between defense and gene acquisition. RNA-seq data from one reference strain indicate that only a fraction of the defensome is actively transcribed under standard conditions, hinting at environment-responsive regulation. Together, these findings provide new insights into the genomic strategies sustaining the persistence and adaptability of S. haemolyticus in clinical environments. The interplay between its immune systems and mobilome likely contributes not only to its evolutionary trajectory, but also to its role in the horizontal transfer of resistance determinants among pathogenic staphylococci. A deeper understanding of this immune-mobilome interface may help inform future strategies to limit the spread of resistance.},
}

@article {pmid40513520,
year = {2025},
author = {Wu, K and Yang, J and Zhang, T and Zuo, J and Lin, H and Wang, J and Zhang, A and Lei, C and Wang, H},
title = {Emergence and traceability of Salmonella enterica serotype Mbandaka harboring blaOXA-10 from chickens in China.},
journal = {Veterinary microbiology},
volume = {307},
number = {},
pages = {110593},
doi = {10.1016/j.vetmic.2025.110593},
pmid = {40513520},
issn = {1873-2542},
abstract = {Salmonella enterica serotype Mbandaka (S. Mbandaka), a multi-host adapted non-typhoidal Salmonella, has emerged as a significant public health concern in recent years. In this study, we isolated S. Mbandaka strains carrying a multidrug-resistant IncHI2A/IncHI2 plasmid from deceased chickens in China and performed whole-genome sequencing and comparative genomic analyses to investigate their global dissemination and evolutionary adaptation. The multidrug-resistant IncHI2A/IncHI2 plasmid in isolate YK35 harbored multiple antibiotic resistance genes (ARGs) including blaOXA-10, which was firstly observed in S. Mbandaka in China. It exhibited high sequence identity with IncHI2A/IncHI2 plasmids identified in other bacterial species, including S. Typhimurium, Klebsiella aerogenes, and E. coli, which suggested the cross-species dissemination of IncHI2A/IncHI2 plasmids and ARGs. Global genomic epidemiology classified S. Mbandaka strains into seven distinct clades, with the majority originating from the USA and the UK. The pan-genomic analysis indicated an open pan-genome structure, with continuous expansion of accessory genes, particularly those associated with replication, recombination, repair, and defense mechanisms, underscoring the evolutionary adaptation of S. Mbandaka to external environments. Evolutionary analysis further traced the international transmission routes of S. Mbandaka, revealing potential cross-regional spread, particularly from the USA and the UK to other countries, including China. The findings emphasize the global spread and evolutionary adaptation of S. Mbandaka, likely driven by international trade and horizontal gene transfer, including the acquisition of ARGs, which have contributed to its increasing public health risks. This study underscores the urgent need for enhanced surveillance and control measures to mitigate the spread of S. Mbandaka and its antibiotic resistance, particularly in the context of global food supply chains and international trade.},
}

@article {pmid40512587,
year = {2025},
author = {He, Y and Zhou, X and Zhang, L and Cui, Y and He, Y and Gehring, A and Deng, X and Shi, X},
title = {Prediction of Antibiotic Resistance Phenotypes and Minimum Inhibitory Concentrations in Salmonella Using Machine Learning Analysis of Its Pan-Genome and Pan-Resistome Features.},
journal = {Foodborne pathogens and disease},
volume = {},
number = {},
pages = {},
doi = {10.1089/fpd.2024.0170},
pmid = {40512587},
issn = {1556-7125},
abstract = {Traditional experimental methods for determining antibiotic resistance phenotypes (ARPs) and minimum inhibitory concentrations (MICs) in bacteria are laborious and time consuming. This study aims to explore the potential of whole-genome sequencing data combined with machine learning models for robustly predicting ARPs and MICs in Salmonella. Using a training set of 6394 Salmonella genomes alongside antimicrobial susceptibility testing results, we built two machine learning (ML) predictive models based on the pan-genome and pan-resistome. Each model was implemented using three algorithms: random forest, extreme gradient boosting (XGB), and convolutional neural network. Among them, XGB achieved the highest overall accuracy, with the pan-genome and pan-resistome models accurately predicting ARPs (98.51% and 97.77%) and MICs (81.42% and 78.99%) for 15 commonly used antibiotics. Feature extraction from pan-genome and pan-resistome data effectively reduced computational complexity and significantly decreased computation time. Notably, fewer than 10 key genomic features, often linked to known resistance or mobile genes, were sufficient for robust predictions for each antibiotic. This study also identified challenges, including imbalanced resistance classes and imprecise MIC measurements, which impacted prediction accuracy. These findings highlight the importance of using multiple evaluation metrics to assess model performance comprehensively. Overall, our findings demonstrated that ML, utilizing pan-genome or pan-resistome features, was highly effective in predicting antibiotic resistance and identifying correlated genetic features in Salmonella. This approach holds great potential to supplement conventional culture-based methods for routine surveillance of antibiotic-resistant bacteria.},
}

@article {pmid40512264,
year = {2025},
author = {Admas, T and Jiao, S and Pan, R and Zhang, W},
title = {Pan-omics insights into abiotic stress responses: bridging functional genomics and precision crop breeding.},
journal = {Functional & integrative genomics},
volume = {25},
number = {1},
pages = {128},
pmid = {40512264},
issn = {1438-7948},
support = {32372052//National Natural Science Foundation of China/ ; 32372052//National Natural Science Foundation of China/ ; 32372052//National Natural Science Foundation of China/ ; 32372052//National Natural Science Foundation of China/ ; },
mesh = {*Crops, Agricultural/genetics/growth & development/metabolism ; *Stress, Physiological/genetics ; *Plant Breeding ; *Genomics/methods ; Metabolomics/methods ; Proteomics/methods ; Multiomics ; },
abstract = {Crop production has been regarded as the major goal of agricultural activities, but the rapidly growing population and climate change have become more complex in the agricultural systems. Abiotic stress greatly affects crop productivity globally; developing more resilient crop varieties has become imperative. However, we can understand how plants tolerate abiotic stress better by using new methods that combine different scientific approaches like pan-genomics, pan-transcriptomics, pan-proteomics, pan-metabolomics, and pan-phenomics. Investigations using a pan-omics approach are necessary to consider the variation resulting from complex interactions among genes, proteins, metabolites, and regulatory networks within a species. A comparative study of core, dispensable, and unique components across different accessions assists in identifying novel genes, proteins, and metabolites responsible for stress tolerance. Moreover, databases and online repositories now enable the storage, analysis, and retrieval of data generated by high-throughput technologies. The combination provides guidelines for researchers to harness the potential of pan-omics in promoting sustainable agricultural practices. Therefore, the review focuses on recent trends in pan-omics for studying abiotic stress responses and their applications in crop improvement. It also highlights the application of artificial intelligence (AI) in data integration and monitoring crop environments.},
}

*Crops, Agricultural/genetics/growth & development/metabolism
*Stress, Physiological/genetics
*Plant Breeding
*Genomics/methods
Metabolomics/methods
Proteomics/methods
Multiomics

@article {pmid40511850,
year = {2025},
author = {Coelho, JT and Teubner, L and Henson, MW and Lanclos, VC and Kojima, CY and Thrash, JC},
title = {Culture-supported ecophysiology of the SAR116 clade demonstrates metabolic and spatial niche partitioning.},
journal = {The ISME journal},
volume = {},
number = {},
pages = {},
doi = {10.1093/ismejo/wraf124},
pmid = {40511850},
issn = {1751-7370},
abstract = {Marine SAR116 bacterioplankton are ubiquitous in surface waters across global oceans and form their own order, Puniceispirillales, within the Alphaproteobacteria. To date no comparative physiology among diverse SAR116 isolates has been performed to capture the functional diversity within the clade, and further, diversity through the lens of metabolic potential and environmental preferences via clade-wide pangenomics continues to evolve with the addition of new genomes. Using high-throughput dilution-to-extinction cultivation, we isolated and genome sequenced five new and diverse SAR116 isolates from the northern Gulf of Mexico. Here we present a comparative physiological analysis of these SAR116 isolates, along with a pangenomic investigation of the SAR116 clade using a combination of metagenome-assembled genomes (MAGs, n = 258), single-amplified genomes (SAGs, n = 84), previously existing (n = 2), and new isolate genomes (n = 5), totaling 349 SAR116 genomes. Phylogenomic investigation supported the division of SAR116 into three distinct subclades, each with additional structure totaling 15 monophyletic groups. Our SAR116 isolates belonged to three groups within subclade I representing distinct genera with different morphologies and varied phenotypic responses to salinity and temperature. Overall, SAR116 genomes encoded differences in vitamin and amino acid synthesis, trace metal transport, and osmolyte synthesis and transport. They also had genetic potential for diverse sulfur oxidation metabolisms, placing SAR116 at the confluence of the organic and inorganic sulfur pools. SAR116 subclades showed distinct patterns in habitat preferences across open ocean, coastal, and estuarine environments, and three of our isolates represented the most abundant coastal and estuarine subclade. This investigation provides the most comprehensive exploration of SAR116 to date anchored by new culture genomes and physiology.},
}

@article {pmid40511294,
year = {2025},
author = {Wang, H and Zhang, C and Chen, Y and Guo, Y and Ding, L and Zhang, S and Du, G and Zhang, W and He, S},
title = {Gracilimonas qinghaiensis sp. nov., a halophilic bacterium from a high-altitude saline lake exhibiting diverse metabolic potential and ecological adaptation.},
journal = {Current research in microbial sciences},
volume = {9},
number = {},
pages = {100413},
pmid = {40511294},
issn = {2666-5174},
abstract = {Saline lakes are extreme habitats that host unique microbial communities with high biotechnological potential. In this study, a novel strain, designated Q87[T], was isolated from Gaxiukule Lake, a high-altitude magnesium sulfate-type saline lake in the Qaidam Basin, China. A polyphasic taxonomic approach, including morphological, physiological, chemotaxonomic, phylogenetic, and genomic analyses, was applied to characterize the isolate. Strain Q87[T] is a Gram-stain-negative, non-motile, rod-shaped bacterium showing high tolerance to salinity (0-15.0 %, w/v; optimum 5.0 %) and alkalinity (pH 6.0-10.5; optimum pH 7.0), with a temperature range for growth of 10-40 °C (optimum 32 °C). Phylogenetic and genomic analyses confirmed its affiliation with the genus Gracilimonas and revealed it as a distinct species. The genome of strain Q87[T] (3.3 Mb, G + C 41.5 %) encodes diverse functional genes associated with nitrogen and sulfur metabolism, stress adaptation, and biosynthesis of secondary metabolites, including terpenoids and polyketides. Comparative analyses with reference Gracilimonas strains demonstrated its unique genomic features and ecological adaptability. Structural modeling confirmed functional conservation of key enzymes involved in nitrogen detoxification and sulfide oxidation. Pangenome analysis highlighted the genetic diversity and open nature of the species of the genus Gracilimonas. Biogeographic assessments suggest a wide distribution of the genus in saline environments, especially in sediments. This study expands our understanding of the genus Gracilimonas taxonomy, physiology, and ecological potential, and underscores the importance of extremophilic bacteria as promising resources for environmental and industrial biotechnology.},
}

@article {pmid40508367,
year = {2025},
author = {Zhao, F and Li, X and Chen, Z and Guo, C},
title = {Pan-Genome-Wide Investigation and Expression Analysis of GATA Gene Family in Maize.},
journal = {Plants (Basel, Switzerland)},
volume = {14},
number = {11},
pages = {},
pmid = {40508367},
issn = {2223-7747},
support = {20220101330JC;CXGC2024ZD001//Ziqi Chen/ ; },
abstract = {GATA is a crucial transcription factor involved in plant growth, development, and responses to abiotic stress. Therefore, identifying and exploring GATA transcription factors in maize is of significant importance. In this study, we identified 75 ZmGATA genes based on the pan-genome of maize, which includes 26 high-quality maize genomes. These consist of 58 core genes (present in all 26 lines), 12 non-essential genes (present in 2 to 23 lines), 2 near-core genes (present in 24 to 25 lines), and 3 private genes (present in only 1 line). By evaluating the Ka/Ks ratio of the ZmGATA genes in 26 maize varieties, we found that the Ka/Ks ratios of ZmGATA31, ZmGATA32, ZmGATA36, and ZmGATA9 were greater than 1, which may indicate that these four genes are under positive selection. In contrast, the Ka/Ks ratios of other ZmGATA genes were less than 1, suggesting that these genes may be under purifying selection. In the 26 maize genomes, we observed a significant difference in the expression of ZmGATA8 between varieties affected by structural variations (SVs) and those not affected. In certain varieties, SVs altered conserved structures. Additionally, we analyzed the expression levels of ZmGATA genes in different maize tissues and under abiotic stress. ZmGATA38 and ZmGATA39 were highly expressed in the endosperm, thereby influencing starch synthesis, while ZmGATA7, ZmGATA10, ZmGATA19, ZmGATA28, and ZmGATA40 were found to be associated with abiotic stress responses. These findings provide valuable new resources for functional research on ZmGATA.},
}

@article {pmid40506254,
year = {2025},
author = {Varki, R and Rossi, M and Ferro, E and Oliva, M and Garrison, E and Langmead, B and Boucher, C},
title = {Accurate short-read alignment through r-index-based pangenome indexing.},
journal = {Genome research},
volume = {},
number = {},
pages = {},
doi = {10.1101/gr.279858.124},
pmid = {40506254},
issn = {1549-5469},
abstract = {Aligning to a linear reference genome can result in a higher percentage of reads going unmapped or being incorrectly mapped owing to variations not captured by the reference, otherwise known as reference bias. Recently, in efforts to mitigate reference bias, there has been a movement to switch to using pangenomes, a collection of genomes, as the reference. In this paper, we introduce Moni-align, the first short-read pangenome aligner built on the r-index, a variation of the classical FM-index that can index collections of genomes in O(r)-space, where r is the number of runs in the Burrows-Wheeler transform. Moni-align uses a seed-and-extend strategy for aligning reads, utilizing maximal exact matches as seeds, which can be efficiently obtained with the r-index. Using both simulated and real short-read data sets, we demonstrate that Moni-align achieves alignment accuracy comparable to vg map and vg giraffe, the leading pangenome aligners. Although currently best suited for aligning to localized pangenomes owing to computational constraints, Moni-align offers a robust foundation for future optimizations that could further broaden its applicability.},
}

@article {pmid40502105,
year = {2025},
author = {Tan, S and Majidian, S and Langmead, B and Zakeri, M},
title = {Movi Color: fast and accurate long-read classification with the move structure.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.1101/2025.05.22.655637},
pmid = {40502105},
issn = {2692-8205},
abstract = {The number of reference genomes is rapidly increasing, thanks to advances in long-read sequencing and assembly. While these collections can improve the sensitivity and specificity of classification methods, this requires highly efficient compressed indexes. K-mer-based approaches like Kraken 2 are efficient but limit the analysis to a fixed k-mer length. This is hard for the user to set ahead of time, and suboptimal settings can harm sensitivity and specificity. Methods that use compressed full-text indexes like SPUMONI2 and Cliffy lift this constraint, but are less efficient than k-mer-based tools. Further, these methods either cannot report a full listing of genomes where a match occurs, or cannot scale to large reference databases. We propose new methods and algorithms that use compressed full-text indexes to enable multi-class and taxonomic classification. Unlike past compressed-indexing methods for classification, ours uses the move structure, which is extremely fast thanks to its locality of reference. Our method, called Movi Color, augments the main table of the Movi index. Specifically, Movi Color assigns a "color" to each run of the Burrows-Wheeler Transform according to the subset of genomes from which the run suffixes originated. When the reference is highly repetitive - as is typical when indexing pangenomes or reference databases - only certain colors occur, creating opportunities to compress the index. For species-level classification, Movi Color achieves over 1.6 × higher precision and 2 × higher recall than Kraken 2 and Metabuli. At the genus level, it achieves 70% higher precision and 80% higher recall. Movi Color's read processing time is 7-20× faster than Metabuli and is a comparable to Kraken 2. Although Movi Color uses more memory than both Kraken 2 and Metabuli, its speed-accuracy trade-off makes it well-suited for real-time or high-throughput scenarios.},
}

@article {pmid40501862,
year = {2025},
author = {Asri, M and Chang, PC and Mier, JC and Sirén, J and Eskandar, P and Kolesnikov, A and Cook, DE and Brambrink, L and Hickey, G and Novak, AM and Dorfman, L and Webster, DR and Carroll, A and Paten, B and Shafin, K},
title = {Pangenome-aware DeepVariant.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.1101/2025.06.05.657102},
pmid = {40501862},
issn = {2692-8205},
abstract = {Population-scale genomics information provides valuable prior knowledge for various genomic analyses, especially variant calling. A notable example of such application is the human pangenome reference released by the Human Pangenome Reference Consortium, which has been shown to improve read mapping and structural variant genotyping. In this work, we introduce pangenome-aware DeepVariant, a variant caller that uses a pangenome reference alongside sample-specific read alignments. It generates pileup images of both reads and pangenome haplotypes near potential variants and uses a Convolutional Neural Network to infer genotypes. This approach allows directly using a pangenome for distinguishing true variant signals from sequencing or alignment noise. We assessed its performance on various short-read sequencing platforms and read mappers. Across all settings, pangenome-aware DeepVariant outperformed the linear-reference-based DeepVariant, reducing errors by up to 25.5%. We also show that Element reads with pangenome-aware DeepVariant can achieve 23.6% more accurate variant calling performance compared to existing methods.},
}

@article {pmid40498527,
year = {2025},
author = {Onetto, CA and Ward, C and Varela, C and Hale, L and Schmidt, SA and Borneman, A},
title = {Genetic and phenotypic diversity of wine-associated Hanseniaspora species.},
journal = {FEMS yeast research},
volume = {},
number = {},
pages = {},
doi = {10.1093/femsyr/foaf031},
pmid = {40498527},
issn = {1567-1364},
abstract = {The genus Hanseniaspora includes apiculate yeasts commonly found in fruit- and fermentation-associated environments. Their genetic diversity and evolutionary adaptations remain largely unexplored despite their ecological and oenological significance. This study investigated the phylogenetic relationships, genome structure, selection patterns, and phenotypic diversity of Hanseniaspora species isolated primarily from Australian wine environments, focusing on Hanseniaspora uvarum, the most abundant non-Saccharomyces yeast in wine fermentation. A total of 151 isolates were sequenced, including long-read genomes for representatives of the main phylogenetic clades. Comparative genomics revealed ancestral chromosomal rearrangements between the slow- (SEL) and fast-evolving lineages (FEL) that could have contributed to their evolutionary split, as well as significant loss of genes associated with mRNA splicing, chromatid segregation and signal recognition particle protein targeting in the FEL. Pangenome analysis within H. uvarum identified extensive copy number variation, particularly in genes related to xenobiotic tolerance and nutrient transport. Investigation into the selective landscape following the FEL/SEL divergence identified diversifying selection in 229 genes in the FEL, with significant enrichment in genes within the lysine biosynthetic pathway. Furthermore, phenotypic screening of 113 isolates revealed substantial intraspecific diversity, with specific species exhibiting enhanced ethanol, osmotic, copper, SO2, and cold tolerance.},
}

@article {pmid40495924,
year = {2025},
author = {Kamath B, V and Mallya, S and Mallikarjuna, SV and Kolathur, KK},
title = {The complete genome sequences of Bacillus velezensis B26: a promising biocontrol agent and biofertilizer.},
journal = {F1000Research},
volume = {14},
number = {},
pages = {170},
pmid = {40495924},
issn = {2046-1402},
mesh = {*Bacillus/genetics ; *Genome, Bacterial ; *Biological Control Agents ; *Whole Genome Sequencing ; *Fertilizers/microbiology ; Soil Microbiology ; Base Composition ; Animals ; },
abstract = {Bacillus velezensis is a bacterium widely recognized for its biocontrol properties and ability to promote plant growth. This study presents the whole-genome sequence of B. velezensis B26, a newly identified strain isolated from chicken carcass soil in Udupi, India. The bacterium showed strong activity against fungal pathogens and exhibited diverse enzymatic activities. The whole-genome sequencing was executed using Illumina technologies. Assembly revealed that strain B26 possesses a genome of 3,946,698-bp with a G+C content of 46.3%. Genome annotation identified 3776 protein-coding genes, 1 rRNA gene, 50 tRNA genes, 5 ncRNA genes, and 59 pseudogenes. Functional analysis of the B. velezensis B26 genome revealed 216 genes involved in carbohydrate metabolism, 3 genes in potassium metabolism, 148 genes linked for cofactors, vitamins, prosthetic groups and pigments, 10 genes involved in phosphorus metabolism, 24 genes associated with iron acquisition and metabolism, 20 genes for nitrogen metabolism, 6 genes involved in sulfur metabolism, 6 genes in secondary metabolism, 12 genes associated with metabolism of aromatic compounds, 43 genes involved in stress response and 36 genes associated with virulence, disease and defence. The raw sequence data generated in this work have been deposited in the NCBI database and the genome sequence is available under the accession number JAYKOV000000000. These genomic data provide insight into the biocontrol ability and plant-growth promoting capabilities of B. velezensis B26.},
}

*Bacillus/genetics
*Genome, Bacterial
*Biological Control Agents
*Whole Genome Sequencing
*Fertilizers/microbiology
Soil Microbiology
Base Composition
Animals

@article {pmid40487211,
year = {2025},
author = {Fan, H and Li, J and Huang, W and Liang, A and Jing, L and Li, J and Yang, QY and Liu, K and Yang, Z},
title = {Pan-genome analysis of the R2R3-MYB genes family in Brassica napus unveils phylogenetic divergence and expression profiles under hormone and abiotic stress treatments.},
journal = {Frontiers in plant science},
volume = {16},
number = {},
pages = {1588362},
pmid = {40487211},
issn = {1664-462X},
abstract = {INTRODUCTION: The R2R3-MYB transcription factors (TFs) are pivotal regulators of plant growth, development, and stress responses. However, their genetic diversity and functional roles in Brassica napus remain underexplored at a pan-genome scale.

METHODS: We identified R2R3-MYB genes in 18 published rapeseed genomes and analyzed their genomic distribution patterns, gene duplication, selective pressure, gene structure, conserved motifs, and phylogenetic relationships using a pan-genome approach. Additionally, transcriptomic datasets from hormone treatments and drought/heat stress experiments were analyzed to identify hormone-responsive and stress-responsive genes.

RESULTS: We systematically identified 7,552 R2R3-MYB genes from 18 B. napus genomes, which were grouped into 353 gene clusters based on the pan-genome approach, including 139 core, 121 softcore, 68 dispensable, and 25 private gene clusters. Similar to Arabidopsis, the B. napus R2R3-MYB genes can be clustered into 29 subgroups based on the phylogenetic tree, suggesting conserved functional roles in B. napus and A. thaliana. Cis-element profiling highlighted enrichment in hormone-responsive and stress-related elements in the promoter regions of the R2R3-MYB genes. Transcriptomic analyses identified 283 hormone-responsive and 266 stress-responsive R2R3-MYB genes, and 30 co-regulated genes under drought and heat stress implicate their roles in combined stress adaptation.

DISCUSSION: These findings provide the first pan-genome resource for R2R3-MYB genes in B. napus, which can serve as pivotal targets for enhancing stress resilience in rapeseed breeding programs.},
}

@article {pmid40484528,
year = {2025},
author = {Jeong, E and Seo, JA},
title = {Comparative genome analyses of Aspergillus oryzae and Aspergillus flavus originated from a Korean fermentation starter, nuruk.},
journal = {Food microbiology},
volume = {131},
number = {},
pages = {104807},
doi = {10.1016/j.fm.2025.104807},
pmid = {40484528},
issn = {1095-9998},
mesh = {*Aspergillus oryzae/genetics/isolation & purification/classification/metabolism ; *Aspergillus flavus/genetics/isolation & purification/classification/metabolism ; Phylogeny ; *Genome, Fungal ; Fermentation ; *Fermented Foods/microbiology ; Republic of Korea ; Food Microbiology ; Whole Genome Sequencing ; Polymorphism, Single Nucleotide ; Fungal Proteins/genetics ; },
abstract = {Aspergillus oryzae is an industrially important fungus used to produce traditional fermented foods and beverages in Korea and other East Asian countries. Conversely, A. flavus, which exhibits approximately 99.5 % of genomic similarity to A. oryzae, is a species that endangers food safety due to aflatoxin production. This study involved the genome sequences of A. oryzae KBP3 and KSS2 isolated from nuruk, a traditional Korean fermentation starter, assembled at the chromosomal level. To investigate differences among closely related species concerning food safety, compartive genome analysis was conducted on 30 strains of Aspergillus section Flavi, including nuruk strains and 28 genome sequences sourced from additional sequencing and the GenBank database. A detailed interspecific diversity was compared by examining the composition and chromosomal locations of annotated genes across 30 strains. A phylogenetic tree based on whole genome sequences, orthologous genes, and single nucleotide polymorphisms of core genes across 30 strains divided A. oryzae and A. flavus into two separate clades with some exceptions. This study presents two high-quality whole genome sequences of A. oryzae, providing significant genetic insights for this species and its closely related species. Our study confirmed the wide range of enzyme-related genes in A. oryzae isolated from nuruk, and its intraspecific genomic diversity. Our findings also systematically organize the pangenome analysis data of closely related species within Aspergillus section Flavi at the chromosomal level, enhancing the understanding of the genetic information relevant to food safety-related species.},
}

*Aspergillus oryzae/genetics/isolation & purification/classification/metabolism
*Aspergillus flavus/genetics/isolation & purification/classification/metabolism
Phylogeny
*Genome, Fungal
Fermentation
*Fermented Foods/microbiology
Republic of Korea
Food Microbiology
Whole Genome Sequencing
Polymorphism, Single Nucleotide
Fungal Proteins/genetics

@article {pmid40479512,
year = {2025},
author = {Strader, LC and Chen, T and Dong, X and Edwards, D and Sureshkumar, S and Balasubramanian, S and Antunes, MS and Zebluim, L and Chaisupa, P and Wright, RC},
title = {Core biological principles and tools stemming from basic Arabidopsis research.},
journal = {The Plant cell},
volume = {},
number = {},
pages = {},
doi = {10.1093/plcell/koaf141},
pmid = {40479512},
issn = {1532-298X},
abstract = {The model plant Arabidopsis thaliana has been a cornerstone of research in plant biology, contributing transformative insights into fundamental biological processes across eukaryotes. In this vignette, we explore the role of Arabidopsis in elucidating immune mechanisms, where plant studies have informed mammalian immunity and translational regulation. We discuss how Arabidopsis-driven advancements in pangenomics and repeat expansions have reshaped our understanding of genomic variability and its implications for diseases like Friedreich's ataxia. Breakthroughs in synthetic biology and bioproduction underscore Arabidopsis' role as a testbed for engineering specialized metabolites and advancing biotechnological applications. Finally, we examine how the development of tools like Auxin-Inducible Degradation (AID) has extended beyond plant research, providing critical methodologies to study protein function and develop novel therapeutics.},
}

@article {pmid40478766,
year = {2025},
author = {Ross, TA and Janice, J and Arredondo-Alonso, S and Löhr, IH and Holsbø, E and Corander, J and Pöntinen, AK and Kampffmeyer, M and Hegstad, K},
title = {Enterococcus lactis is ecologically and genetically distinct from the major opportunistic pathogen Enterococcus faecium.},
journal = {Microbial genomics},
volume = {11},
number = {6},
pages = {},
pmid = {40478766},
issn = {2057-5858},
mesh = {*Enterococcus faecium/genetics/classification/pathogenicity ; Genome, Bacterial ; Humans ; Phylogeny ; Animals ; Whole Genome Sequencing ; *Enterococcus/genetics/classification ; Evolution, Molecular ; Genetic Variation ; },
abstract = {Enterococcus faecium is a major human opportunistic bacterial pathogen and a close relative of the recently established species Enterococcus lactis. As a species, commensal E. lactis remains relatively understudied, and its genetic connectivity with E. faecium is not thoroughly understood. Here, we introduce a large collection of whole-genome sequenced isolates comprising 894 E. faecium and 392 E. lactis genomes. Using these genomes to complement publicly available data, we studied the genome content and the evolutionary relationship between these species. A wider range of host species was observed in E. faecium; in particular, there is a radiation of E. faecium clades specialized to domesticated and pet animals among which E. lactis is uncommon. Of note, pangenome analyses reveal that E. lactis has significantly more allelic variation and lower recombination rates in core genes compared with E. faecium. These observations suggest that E. lactis represents a population that has occupied its ecological niche longer than E. faecium has. This study enhances understanding of the evolutionary histories of these species and highlights the importance of sampling and studying closely related commensal bacteria in addition to clinically relevant opportunistic pathogens.},
}

*Enterococcus faecium/genetics/classification/pathogenicity
Genome, Bacterial
Humans
Phylogeny
Animals
Whole Genome Sequencing
*Enterococcus/genetics/classification
Evolution, Molecular
Genetic Variation

@article {pmid40475428,
year = {2025},
author = {Shivakumar, VS and Langmead, B},
title = {Partitioned Multi-MUM finding for scalable pangenomics.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.1101/2025.05.20.654611},
pmid = {40475428},
issn = {2692-8205},
abstract = {Pangenome collections are growing to hundreds of high-quality genomes. This necessitates scalable methods for constructing pangenome alignments that can incorporate newly-sequenced assemblies. We previously developed Mumemto, which computes maximal unique matches (multi-MUMs) across pangenomes using compressed indexing. In this work, we extend Mumemto by introducing two new partitioning and merging strategies. Both strategies enable highly parallel, memory efficient, and updateable computation of multi-MUMs. One of the strategies, called string-based merging, is also capable of conducting the merges in a way that follows the shape of a phylogenetic tree, naturally yielding the multi-MUM for the tree's internal nodes as well as the root. With these strategies, Mumemto now scales to 474 human haplo-types, the only multi-MUM method able to do so. It also introduces a time-memory tradeoff that allows Mumemto to be tailored to more scenarios, including in resource-limited settings.},
}

@article {pmid40472804,
year = {2025},
author = {Stanley, S and Silva-Costa, C and Gomes-Silva, J and Melo-Cristino, J and Malley, R and Ramirez, M},
title = {CC180 clade dynamics do not universally explain Streptococcus pneumoniae serotype 3 persistence post-vaccine: a global comparative population genomics study.},
journal = {EBioMedicine},
volume = {117},
number = {},
pages = {105781},
doi = {10.1016/j.ebiom.2025.105781},
pmid = {40472804},
issn = {2352-3964},
abstract = {BACKGROUND: Clonal complex 180 (CC180) is currently the major clone of serotype 3 Streptococcus pneumoniae (Spn) causing disease among children and adults worldwide. The 13-valent pneumococcal conjugate vaccine (PCV13) does not have significant efficacy against serotype 3 despite polysaccharide inclusion in the vaccine. It was hypothesized that PCV13 may effectively control Clade I of CC180 but that Clades III and IV are resistant, provoking a population shift that enables serotype 3 persistence. This has been observed in the United States, England, and Wales but not Spain. We tested this hypothesis further utilizing a dataset from Portugal to conduct our population genomics and molecular epidemiology comparative study.

METHODS: We performed whole-genome sequencing (WGS) of 501 serotype 3 strains from Portugal isolated from patients with pneumococcal infections between 1999 and 2020. The draft genomes underwent phylogenetic analyses, pangenome profiling, and a genome-wide association study (GWAS). We also completed antibiotic susceptibility testing and compiled over 2600 serotype 3 multilocus sequence type 180 (MLST180) WGSs to perform global comparative genomics.

FINDINGS: Relative to strains from all other lineages, CC180 Clades I, II, III, IV, and VI strains trend towards a decreased association with invasive disease cases compared to non-invasive pneumonia cases (binomial logistic regression, odds ratio or OR = 0.59, 95% confidence interval or CI = [0.34, 0.98], P = 0.046) and adult patients compared to paediatric patients (binomial logistic regression, OR = 0.34, 95% CI = [0.098, 0.92], P = 0.054). The serotype 3 CCs shifted post-PCV13 such that Clades I-VI comprise the majority of post-PCV13 lineages (binomial logistic regression, OR = 7.33, 95% CI = 4.36, 12.80, P < 0.0001), with Clade I representing 54% (220/404) of all post-PCV13 strains. As observed elsewhere, Clade I strains from Portugal are largely antibiotic-sensitive and carry the ΦOXC141 prophage. However, strains from Portugal and Spain, where Clade I remains dominant post-PCV13, have larger pangenomes and are associated with the presence of two genes encoding hypothetical proteins.

INTERPRETATION: Clade I became dominant in Portugal post-PCV13, despite the burden of the prophage and antibiotic sensitivity. The additional accessory genome content may mitigate these fitness costs. Regional differences in Clade I prevalence and pangenome heterogeneity suggest that clade dynamics is not a generalizable approach to understanding serotype 3 vaccine escape.

FUNDING: National Institute of Child Health and Human Development, Pfizer, and Merck Sharp & Dohme.},
}

@article {pmid40467258,
year = {2025},
author = {Li, Y and Liu, Y and Zheng, B and Zhang, C and Cai, Y and Cheng, Y and Wang, J},
title = {Multicellular behavior and genomic characterization of Salmonella Typhimurium in animal-derived food chains in Xinjiang, China: Phenotypic resistance, biofilm formation, and sequence types.},
journal = {Food research international (Ottawa, Ont.)},
volume = {214},
number = {},
pages = {116698},
doi = {10.1016/j.foodres.2025.116698},
pmid = {40467258},
issn = {1873-7145},
mesh = {*Biofilms/growth & development ; Animals ; China ; *Salmonella typhimurium/genetics/drug effects/isolation & purification/physiology/classification ; *Food Microbiology ; Drug Resistance, Multiple, Bacterial/genetics ; Phenotype ; Anti-Bacterial Agents/pharmacology ; Sheep ; Cattle ; Whole Genome Sequencing ; Genome, Bacterial ; },
abstract = {Salmonella Typhimurium Is a globally significant foodborne pathogen that causes diseases in livestock and poultry, which can lead to human infections and fatalities through contaminated food. In this study, we investigated the prevalence of Salmonella Typhimurium in the animal-derived food chain in Xinjiang, China. Among 5075 samples, the detection rate of Salmonella was 8.26 % (419/5075). Of these isolates, 27.21 % (114/419) were identified as Salmonella Typhimurium. Phenotypic analysis revealed significant antibiotic resistance: 82.46 % (94/114) of the strains exhibited multidrug resistance (MDR), with high resistance rates to amoxicillin / clavulanic acid, ampicillin, and tetracycline. Congo red plate assays demonstrated that 62.28 % (71/114) of the strains exhibited multicellular behavior (RDAR morphotype). Biofilm formation assays indicated that 96.49 % (110/114) of the strains possessed biofilm-forming capabilities, with 18.18 % (20/110) showing strong biofilm formation. Notably, strains displaying multicellular behavior exhibited enhanced biofilm formation, and biofilm capability was positively correlated with antibiotic resistance phenotypes. Whole-genome sequencing of 40 representative strains identified four sequence types (ST19, ST34, ST99, ST128), with ST34 being the most predominant. Distinct host preferences were observed: ST34 strains originated exclusively from cattle and sheep, while ST19, ST99, and ST128 strains were isolated from geese and pigeons. Resistance gene profiling revealed that strains harboring resistance genes exhibited stronger resistance phenotypes, while ST99 and ST128 strains lacked detectable resistance genes. Plasmids R64, R478, and pKPC_CAV1321 were identified in cattle- and sheep-derived strains, whereas pSLT-BT and pSPCV plasmids were predicted in strains from geese and pigeons. Pan-genome analysis and phylogenetic reconstruction demonstrated distinct genetic clustering among ST types, with ST19 and ST128 showing closer evolutionary relationships. This study provides comprehensive insights into the prevalence, phenotypic characteristics, and genomic diversity of Salmonella Typhimurium in the animal-derived food chain in Xinjiang. Our findings contribute to region-specific pathogen control strategies, enhancing public health safety and consumer protection.},
}

*Biofilms/growth & development
Animals
China
*Salmonella typhimurium/genetics/drug effects/isolation & purification/physiology/classification
*Food Microbiology
Drug Resistance, Multiple, Bacterial/genetics
Phenotype
Anti-Bacterial Agents/pharmacology
Sheep
Cattle
Whole Genome Sequencing
Genome, Bacterial

@article {pmid40463162,
year = {2025},
author = {Das, A and Biddanda, A and McCoy, RC and Schatz, MC},
title = {Assembling unmapped reads reveals hidden variation in South Asian genomes.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.1101/2025.05.14.653340},
pmid = {40463162},
issn = {2692-8205},
abstract = {Conventional genome mapping-based approaches systematically miss genetic variation, particularly in regions that substantially differ from the reference. To explore this hidden variation, we examined unmapped and poorly mapped reads from the genomes of 640 human individuals from South Asian (SAS) populations in the 1000 Genomes Project and the Simons Genome Diversity Project. We assembled tens of megabases of non-redundant sequence in tens of thousands of large contigs, much of which is present in both SAS and non-SAS populations. We demonstrated that much of this sequence is not discovered by traditional variant discovery approaches even when using complete genomes and pangenomes. Across 20,000 placed contigs, we found 8,215 intersections with 106 protein coding genes and >15,000 placements within 1 kbp of a known GWAS hit. We used long read data from a subset of samples to validate the majority of their assembled sequences, aligned RNA-seq data to identify hundreds of unplaced contigs with transcriptional potential, and queried existing nucleotide databases to evaluate the origins of the remaining unplaced sequences. Our results highlight the limitations of even the most complete reference genomes and provide a model for understanding the distribution of hidden variation in any human population.},
}

@article {pmid40463112,
year = {2025},
author = {Eskandar, P and Paten, B and Sirén, J},
title = {Lossless Pangenome Indexing Using Tag Arrays.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.1101/2025.05.12.653561},
pmid = {40463112},
issn = {2692-8205},
abstract = {Pangenome graphs represent the genomic variation by encoding multiple haplotypes within a unified graph structure. However, efficient and lossless indexing of such structures remains challenging due to the scale and complexity of pangenomic data. We present a practical and scalable indexing framework based on tag arrays, which annotate positions in the Burrows-Wheeler transform (BWT) with graph coordinates. Our method extends the FM-index with a run-length compressed tag structure that enables efficient retrieval of all unique graph locations where a query pattern appears. We introduce a novel construction algorithm that combines unique k -mers, graph-based extensions, and haplotype traversal to compute the tag array in a memory-efficient manner. To support large genomes, we process each chromosome independently and then merge the results into a unified index using properties of the multi-string BWT and r-index. Our evaluation on the HPRC graphs demonstrates that the tag array structure compresses effectively, scales well with added haplotypes, and preserves accurate mapping information across diverse regions of the genome. This indexing method enables lossless and haplotype-aware querying in complex pangenomes and offers a practical indexing layer to develop scalable aligners and downstream graph-based analysis tools.},
}

@article {pmid40463106,
year = {2025},
author = {Hamilton, W and Massey, J and Hardy, E and López-Madrigal, S and Phelps, M and Martin, M and Newton, I},
title = {Wolbachia uses ankyrin repeats to target specific fly proteins.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
pmid = {40463106},
issn = {2692-8205},
abstract = {UNLABELLED: Arthropods, the most diverse phylum on Earth, are hosts to a plethora of bacterial parasites that secrete various effectors of unknown function during infection. The most prevalent of these is the intracellular bacterium Wolbachia pipientis . The microbe infects between 40-60% of insect species, causes important reproductive manipulations, and limits virus replication in arthropod vectors, becoming a promising biocontrol agent. Understanding the molecular basis of Wolbachia infection and Wolbachia- induced phenotypes is critical to the use of Wolbachia in vector control. These Wolbachia ankyrin repeat proteins (WARPs) represent a highly dynamic and diverse part of the Wolbachia pangenome and remain thus far, largely uncharacterized. Here, we perform molecular and genetic screens to identify interactions between Wolbachia w Mel WARPs and their target host proteins in Drosophila melanogaster . Our results identify strong interactions of two Wolbachia proteins, WARP434 and WARP754, with two host targets (CG11327 and Ptp61F, respectively). Heterologous expression of these two WARPs is extremely toxic in Drosophila tissues and the toxicity is dependent on the ankyrin repeat domain of each WARP. Importantly, knockdown of the host targets alleviates toxicity, confirming WARP/target interactions. Finally, antibodies targeting both WARPs show expression by Wolbachia during infection of Drosophila cells. Understanding how Wolbachia manipulates its host biology and which host pathways it targets during infection will help us divine how the most prevalent intracellular bacterial parasite on Earth interacts with its insect hosts at the molecular level. Our screen is the first step towards that goal.

IMPORTANCE: Molecular interactions drive co-evolutionary arms races between hosts and pathogens. These interactions shape the structure and function of both host and parasite proteins, enabling immunity or virulence during infection. Understanding the molecular details that unfold during these events illustrates not only how hosts and parasites co-evolve at the molecular level but also may help characterize the function of poorly understood proteins. The most prevalent intracellular infection on earth is Wolbachia pipientis, with between 40-60% of insects harboring the bacterial symbiont. Understanding how Wolbachia infects host cells and the molecular tools it uses to alter cell biology is critical to the use of the microbe in vector control. Here, we identify Wolbachia proteins used by the symbiont to interface with specific host proteins. Understanding the molecular mechanisms underlying this host-microbe interaction will shed light on how an important symbiont, used in the control of vector populations and disease transmission, uses WARPs to interact with host targets and how targeting this host protein contributes to infection.},
}

@article {pmid40462382,
year = {2025},
author = {Yacoub, MN and Stajich, JE},
title = {Comparative genomics reveals intra and inter species variation in the pathogenic fungus Batrachochytrium dendrobatidis.},
journal = {Genome biology and evolution},
volume = {},
number = {},
pages = {},
doi = {10.1093/gbe/evaf114},
pmid = {40462382},
issn = {1759-6653},
abstract = {The Global Panzootic Lineage (GPL) of Batrachochytrium dendrobatidis (Bd) has been described as a main driver of amphibian extinctions. Pathogen studies have benefited from three Bd-GPL strain genomes, but identifying the genetic and molecular features that distinguish the B. dendrobatidis lineages requires additional high quality genomes from diverse lineages. We sequenced and assembled genomes with Oxford Nanopore Technologies to produce assemblies of three Bd-BRAZIL isolates and one non-pathogen outgroup species Polyrhizophydium stewartii. The Bd-BRAZIL assembly sizes ranged between 22.0-26.1 Mb with 8,495 - 8,620 predicted protein-coding genes. We sought to categorize the pangenome of the species by identifying homologous genes across the sampled genomes as either being core and present in all strains, or accessory and shared among strains in a lineage, an analysis that has not yet been conducted on B. dendrobatidis and its lineages. We identified a core genome consisting of 6,278 gene families, and an accessory genome of 202 Bd-BRAZIL and 172 Bd-GPL specific gene families. We discovered copy number differences in pathogenicity gene families: M36 Peptidases, Crinkler Necrosis genes, Aspartyl Peptidases, Carbohydrate-Binding Module-18 genes, and S41 Proteases, between Bd-BRAZIL and Bd-GPL strains. Comparison of B. dendrobatidis and two closely related saprophytic species identified differences in protein sequence and domain counts for M36 and CBM18 families respectively. Our pangenome analysis of lineage-specific gene content led us to explore how the selection of the reference genome affects recovery of RNAseq transcripts when comparing different strains. We tested the hypothesis that genomic variation among Bd-GPL and Bd-BRAZIL lineages can impact transcript count data by comparing results with our new Bd-BRAZIL genomes as the reference genomes. Our analysis examines the genomic variation between strains in Bd-BRAZIL and Bd-GPL and offers insights into the application of these high quality reference genomes resources for future studies.},
}

@article {pmid40453788,
year = {2025},
author = {Golletz, P and Jensen, SD and Collignon, M and Hall, C and Khamas, AB and Møllebjerg, A and Schlafer, S and Meyer, RL and Tykwinska, K},
title = {Coaggregation of oral pathogens by postbiotic lactobacilli.},
journal = {Journal of oral microbiology},
volume = {17},
number = {1},
pages = {2508483},
pmid = {40453788},
issn = {2000-2297},
abstract = {INTRODUCTION: Coaggregation may reduce the abundance of bacteria in physiological fluids, such as saliva, as aggregated bacteria are cleared more easily than planktonic cells. This study aimed to identify Lactobacillus strains that coaggregate with oral pathogens with the perspective of using this approach to improve oral health.

MATERIAL AND METHODS: Coaggregation of 719 postbiotic Lactobacillus strains with target pathogens Fusobacterium nucleatum, Porphyromonas gingivalis, and Prevotella intermedia was quantified by absorbance. Coaggregation efficacy of selected strains with clinical isolates and in the presence of other salivary bacteria was determined by flow cytometry. Brightfield and confocal microscopy were applied to characterize the size and structure of coaggregates. Pangenome analysis was used to identify genomic regions potentially involved in the coaggregation activity.

RESULTS: Two strains, Lacticaseibacillus rhamnosus 1B06 and Lacticaseibacillus paracasei 8A12, coaggregated efficiently with all three target pathogens and clinical isolates of the same species even in the presence of other salivary bacteria. The coaggregation capability of the selected Lactobacillus strains was unique and could not be reproduced with other genetically similar lactic acid bacteria of the same species.

CONCLUSION: Lactobacillus strains capable of coaggregating oral pathogens were identified as promising candidates for the development of new postbiotic ingredients for oral hygiene products.},
}

@article {pmid40445831,
year = {2025},
author = {Dong, Z and Whitehead, J and Fu, M and MacIsaac, JL and Rehkopf, DH and Rosero-Bixby, L and Kobor, MS and Korthauer, K},
title = {Complete reference genome and pangenome improve genome-wide detection and interpretation of DNA methylation using sequencing and array data.},
journal = {Cell reports},
volume = {44},
number = {6},
pages = {115755},
doi = {10.1016/j.celrep.2025.115755},
pmid = {40445831},
issn = {2211-1247},
abstract = {The complete telomere-to-telomere human genome assembly (T2T-CHM13) and the draft human pangenome reference provide unique opportunities to refine DNA methylation (DNAm) studies. Here, we find that T2T-CHM13 calls 7.4% more CpGs genome wide compared to GRCh38 across four widely used short-read DNAm profiling methods and improves the evaluation of probe cross-reactivity and mismatch for Illumina DNAm arrays, yielding new and more reproducible sets of unambiguous probes. The pangenome reference further expands CpG calling by 4.5% in short-read sequencing data and identifies cross-population and population-specific unambiguous probes in DNAm arrays, owing to its improved representation of genetic diversity. These benefits facilitate the discovery of biologically relevant DNAm alterations in epigenome-wide association studies (EWASs). For instance, additional DNAm alterations enriched in cancer-related genes and pathways are identified in cancer EWASs. Together, this study highlights the practical applications of T2T-CHM13 and pangenome for genome biology and provides a basis for expansion of DNAm investigations.},
}

@article {pmid40444387,
year = {2025},
author = {Lötter, A and Bruna, T and Duong, TA and Barry, K and Lipzen, A and Daum, C and Yoshinaga, Y and Grimwood, J and Jenkins, JW and Talag, J and Borevitz, J and Lovell, JT and Schmutz, J and Wegrzyn, JL and Myburg, AA},
title = {A haplotype-resolved reference genome for Eucalyptus grandis.},
journal = {G3 (Bethesda, Md.)},
volume = {},
number = {},
pages = {},
doi = {10.1093/g3journal/jkaf112},
pmid = {40444387},
issn = {2160-1836},
abstract = {E. grandis is a hardwood tree used worldwide as pure species or hybrid partner to breed fast-growing plantation forestry crops that serve as feedstocks of timber and lignocellulosic biomass for pulp, paper, biomaterials and biorefinery products. The current v2.0 genome reference for the species (Bartholome et al. 2015; Myburg et al. 2014) served as the first reference for the genus and has helped drive the development of molecular breeding tools for eucalypts. Using PacBio HiFi long reads and Omni-C proximity ligation sequencing, we produced an improved, haplotype-phased assembly (v4.0) for TAG0014, an early-generation selection of E. grandis. The two haplotypes are 571 Mbp (HAP1) and 552 Mbp (HAP2) in size and consist of 37 and 46 contigs scaffolded onto 11 chromosomes (contig N50 of 28.9 and 16.7 Mbp), respectively. These haplotype assemblies are 70 to 90 Mbp smaller than the diploid v2.0 assembly but capture all except one of the 22 telomeres, suggesting that substantial redundant sequence was included in the previous assembly. A total of 35,929 (HAP1) and 35,583 (HAP2) gene models were annotated, of which 438 and 472 contain long introns (>10 kbp) in gene models previously (v2.0) identified as multiple smaller genes. These and other improvements have increased gene annotation completeness levels from 93.8% to 99.4% in the v4.0 assembly. We found that 6,493 and 6,346 genes are within tandem duplicate arrays (HAP1 and HAP2, respectively, 18.4% and 17.8% of the total) and >43.8% of the haplotype assemblies consists of repeat elements. Analysis of synteny between the haplotypes and the E. grandis v2.0 reference genome revealed extensive regions of collinearity, but also some major rearrangements, and provided a preview of population and pan-genome variation in the species.},
}

@article {pmid40442592,
year = {2025},
author = {Wang, H and Liu, J and Guo, Y and Chen, Y and Zhang, C and He, S and Zhang, W and Ding, L},
title = {Taxonomic, genomic, and ecological insights into a novel Flavobacteriaceae strain from coastal tidal flats.},
journal = {BMC microbiology},
volume = {25},
number = {1},
pages = {344},
pmid = {40442592},
issn = {1471-2180},
support = {42176101//National Natural Science Foundation of China/ ; 2021Z046//Ningbo Key Science and Technology Development Program/ ; IF2021087//Scientific Research Foundation of Graduate School of Ningbo University/ ; D16013//National 111 Project of China/ ; },
mesh = {Phylogeny ; *Flavobacteriaceae/classification/genetics/isolation & purification/physiology ; China ; *Genome, Bacterial ; *Seawater/microbiology ; RNA, Ribosomal, 16S/genetics ; DNA, Bacterial/genetics ; Genomics ; *Geologic Sediments/microbiology ; Ecosystem ; Sequence Analysis, DNA ; },
abstract = {BACKGROUND: Tidal flats are vital coastal ecosystems that play a significant role in organic carbon accumulation and biogeochemical cycles. Members of the family Flavobacteriaceae is known for its ability to degrade complex organic matter, including polysaccharides. However, the ecological roles and metabolic capabilities of Flavobacteriaceae in tidal flat environments remain underexplored.

RESULTS: In this study, we isolated and characterized a novel bacterium, strain NBU2967[T], from the tidal flats of Meishan Island in the East China Sea. Phylogenetic and genomic analyses identified this strain as a new genus and species within the family Flavobacteriaceae, for which we propose the name Meishania litoralis gen. nov., sp. nov. Comprehensive polyphasic characterization, including morphological, physiological, chemotaxonomic, and genomic analyses, confirmed its distinct taxonomic status. Genomic analysis revealed a diverse set of carbohydrate-active enzymes (CAZymes), along with multiple metabolic pathways associated with carbon and sulfur cycling, highlighting the strain's potential adaptation to organic-rich marine environments. Comparative genomic and pangenome analyses further demonstrated significant genetic divergence from related taxa. Environmental distribution data revealed that the newly proposed genus Meishania is widely distributed across global marine ecosystems.

CONCLUSIONS: We isolated and characterized a novel bacterium, designated NBU2967[T] (= KCTC 82912[ T] = MCCC 1K06391[T]), for which we propose the name Meishania litoralis gen. nov., sp. nov. This strain is classified as a new genus within the family Flavobacteriaceae. The strain's ability to process both carbon and sulfur compounds underscores its ecological significance in marine ecosystems. These findings provide novel insights into the ecological functions of the family Flavobacteriaceae in coastal tidal flats environments and enhance our understanding of microbial-mediated degradation and transformation of chemical compounds in dynamic coastal ecosystems.},
}

Phylogeny
*Flavobacteriaceae/classification/genetics/isolation & purification/physiology
China
*Genome, Bacterial
*Seawater/microbiology
RNA, Ribosomal, 16S/genetics
DNA, Bacterial/genetics
Genomics
*Geologic Sediments/microbiology
Ecosystem
Sequence Analysis, DNA

@article {pmid40442154,
year = {2025},
author = {Seong, HJ and Park, YM and Kim, BS and Yoo, HJ and Kim, T and Yoon, SM and Kim, JH and Lee, SY and Lee, YK and Lee, DW and Nam, MH and Hong, SJ},
title = {Integrated multi-omics reveals different host crosstalk of atopic dermatitis-enriched Bifidobacterium longum Strains.},
journal = {NPJ biofilms and microbiomes},
volume = {11},
number = {1},
pages = {91},
pmid = {40442154},
issn = {2055-5008},
mesh = {Humans ; *Dermatitis, Atopic/microbiology ; *Gastrointestinal Microbiome ; Infant ; *Bifidobacterium longum/genetics/isolation & purification/classification/metabolism ; Female ; Male ; Metabolomics ; Metagenomics/methods ; Feces/microbiology ; *Host Microbial Interactions ; Clostridium/genetics/isolation & purification ; Transcriptome ; Multiomics ; },
abstract = {The infant gut microbiome is essential for long-term health and is linked to atopic dermatitis (AD), although the underlying mechanisms are not fully understood. This study investigated gut microbiome-host interactions in 31 infants with AD and 29 healthy controls using multi-omics approaches, including metagenomic, host transcriptomic, and metabolomic analyses. Microbial diversity was significantly altered in AD, with Bifidobacterium longum and Clostridium innocuum associated with these changes. At the strain-level, only B. longum differed significantly between groups, with pangenome analyses identifying genetic variations potentially affecting amino acid and lipid metabolites. Notably, B. longum subclade I, which was more prevalent in healthy controls, correlated with host transcriptomic pathways involved in phosphatidylinositol 3-kinase-AKT signaling and neuroactive ligand-receptor pathways, as well as specific metabolites, including tetrahydrocortisol and ornithine. These findings highlight the role of B. longum strain-level variation in infants, offering new insights into microbiome-host interactions related to AD.},
}

Humans
*Dermatitis, Atopic/microbiology
*Gastrointestinal Microbiome
Infant
*Bifidobacterium longum/genetics/isolation & purification/classification/metabolism
Female
Male
Metabolomics
Metagenomics/methods
Feces/microbiology
*Host Microbial Interactions
Clostridium/genetics/isolation & purification
Transcriptome
Multiomics

@article {pmid40442108,
year = {2025},
author = {Meng, Q and Xie, P and Xu, Z and Tang, J and Hui, L and Gu, J and Gu, X and Jiang, S and Rong, Y and Zhang, J and Udall, JA and Grover, CE and Zheng, K and Chen, Q and Kong, J and Wang, M and Nie, X and Lin, Z and Jin, S and Wendel, JF and Zhang, X and Yuan, D},
title = {Pangenome analysis reveals yield- and fiber-related diversity and interspecific gene flow in Gossypium barbadense L.},
journal = {Nature communications},
volume = {16},
number = {1},
pages = {4995},
pmid = {40442108},
issn = {2041-1723},
mesh = {*Gossypium/genetics ; *Cotton Fiber ; *Genome, Plant/genetics ; Genome-Wide Association Study ; *Gene Flow ; Genetic Variation ; Quantitative Trait Loci ; },
abstract = {Gossypium barbadense is renowned for its superior fiber quality, particularly its extra-long fibers, although its fiber yield is lower compared to G. hirsutum. Here, to further reveal fiber-related genomic variants of G. barbadense, we de novo assemble 12 genomes of G. barbadense that span the wild-to-domesticated continuum, and construct a graph-based pangenome by integrating these assemblies and 17 publicly available tetraploid cotton genome assemblies. We uncover the divergent evolutionary trajectories and subsequent exchanges between G. barbadense and G. hirsutum through investigation of structural variants (SVs). We perform the SV-based GWAS analysis in G. barbadense and identify four, three, and seven candidate SVs for fiber length, fiber strength, and lint percentage, respectively. Furthermore, we detect the underlying candidate genes and uncover the origin and distribution of favorable alleles, and reveal the tradeoff between lint percentage and fiber quality. These pangenome and trait-associated SVs provide insights into and resources for improving cotton fiber.},
}

*Gossypium/genetics
*Cotton Fiber
*Genome, Plant/genetics
Genome-Wide Association Study
*Gene Flow
Genetic Variation
Quantitative Trait Loci

@article {pmid40438217,
year = {2025},
author = {Zhou, G and Yu, Y and Ge, T and Tang, C and Zhang, H and He, M},
title = {Whole-genome probe capture sequencing reveals genomic diversity and characteristics of Mycoplasma pneumoniae in Nanjing, China.},
journal = {Frontiers in microbiology},
volume = {16},
number = {},
pages = {1589971},
pmid = {40438217},
issn = {1664-302X},
abstract = {Mycoplasma pneumoniae (M. pneumoniae), a slow-growing, fastidious Gram-negative bacterium and a leading cause of community-acquired pneumonia globally, remains understudied and underreported across numerous geographical areas in China despite its worldwide significance. This study employed probe capture sequencing for targeted enrichment and direct sequencing of M. pneumoniae from clinical samples, combined with comparative genomic analyses of contemporary and historical global genomes. Core genome and pan-genome revealed that the M. pneumoniae genomes were classified into two distinct clades, P1-I and P1-II, each associated with a specific sequence type (ST). Most of the genomes sequenced in this study were identified as P1-I (86.96%, 20/23), contrasting with the previously reported predominance of P1-II in the area. A limited number of single-nucleotide variations were identified in the virulence-associated genes between P1-I and P1-II, leading to amino acid substitutions. The A2063G point mutation in the 23S rRNA gene was detected in all sequenced genomes (23/23), demonstrating a 100% mutation rate. This study provides the first reported application of probe capture methodology for M. pneumoniae, highlighting the critical importance of sustained surveillance efforts to monitor the evolution and epidemiology of this pathogen.},
}

@article {pmid40437759,
year = {2025},
author = {Xia, Z and Du, Z and Zhou, X and Jiang, S and Zhu, T and Wang, L and Chen, F and Carvalho, L and Zou, M and Becerra López-Lavalle, LA and Zhang, X and Xu, L and Wang, Z and Chen, M and Guo, X and Wang, S and Li, M and Li, Y and Wang, H and Liu, S and Bao, Y and Zhao, L and Zhang, C and Xiao, J and Guo, F and Shen, X and Li, H and Lu, C and Qiao, F and Ceballos, H and Yan, H and Qin, X and Ma, L and Zhang, H and He, S and Zhao, W and Wan, Y and Chen, Y and Huang, D and Li, K and Liu, B and Peng, M and Zhang, W and Møller, BL and Chen, X and Luo, MC and Xiao, J and Wang, W},
title = {Pan-genome and Haplotype Map of Cassava Cultivars and Wild Ancestors Provide Insights into its Adaptive Evolution and Domestication.},
journal = {Molecular plant},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.molp.2025.05.014},
pmid = {40437759},
issn = {1752-9867},
abstract = {Cassava is an important, resilient tropical crop that produces large starchy storage roots and high biomass. But how did cassava´s remarkable environmental adaptability and key economic traits evolve from its wild species? We constructed nearly T2T genomes and their haplotype forms for the cultivar AM560, wild ancestors FLA4047 and W14, a graphic pan-genome of 30 representatives with 1.15 Gb, and built a clarified evolutionary tree of 486 accessions. A comparison of structural variations (SVs) and single-nucleotide variations (SNVs) between the ancestors and cultivated cassavas reveals predominant expansions and contractions of genes and gene families, which are mainly driven by transposons. Significant selective sweeping occurred in 122 footprints of genomes and affects 1,519 domesticated genes. We identify selective mutations in MeCSK and MeFNR2 that could promote photoreactions associated with MeNADP-ME in C4 photosynthesis in modern cassava. Co-evolution of retard floral primordia and initiation of storage roots may arise from MeCOL5 variants with altered bindings to MeFT1, MeFT2, and MeTFL2. Mutations of MeMATE1 and MeGTR occur in sweet cassava, and MeAHL19 has evolved to regulate the biosynthesis, transport, and endogenous remobilization of cyanogenic glucosides in cassava. These extensive genomic and gene resources provided here and the findings of the evolutionary mechanisms responsible for beneficial traits in modern cultivars represent a stepping-stone in future breeding of cassava.},
}

@article {pmid40437706,
year = {2025},
author = {Kim, J and Zhang, J and Kinch, L and Shen, J and Field, S and Khan, S and Klapproth, JM and Forsberg, KJ and Harris-Tryon, T and Orth, K and Cong, Q and Ni, J},
title = {Genetic and Microbial Analysis of Invasiveness for Escherichia coli Strains Associated With Inflammatory Bowel Disease.},
journal = {Cellular and molecular gastroenterology and hepatology},
volume = {19},
number = {4},
pages = {101451},
doi = {10.1016/j.jcmgh.2024.101451},
pmid = {40437706},
issn = {2352-345X},
mesh = {Humans ; *Escherichia coli/genetics/pathogenicity/isolation & purification/drug effects ; *Inflammatory Bowel Diseases/microbiology ; *Escherichia coli Infections/microbiology ; Phenotype ; Epithelial Cells/microbiology ; Genotype ; Whole Genome Sequencing ; Virulence/genetics ; Drug Resistance, Bacterial/genetics ; Virulence Factors/genetics ; },
abstract = {BACKGROUND & AIMS: The adherent-invasive Escherichia coli (AIEC) pathotype is implicated in inflammatory bowel disease (IBD) pathogenesis. AIEC strains are currently defined by phenotypic measurement of their pathogenicity, including invasion of epithelial cells. This broad definition, combined with the genetic diversity of AIEC across patients with IBD, has complicated the identification of virulence determinants. We sought to quantify the invasion phenotype of clinical isolates from patients with IBD and identify the genetic basis for their invasion into epithelial cells.

METHODS: A pangenome with core and accessory genes (genotype) was assembled using whole genome sequencing of 168 E coli samples isolated from 13 patients with IBD. A modified assay for invasion of epithelial cells (phenotype) was established with consideration of antibiotic resistance phenotypes. Isolate genotype was correlated to invasiveness phenotype to identify genetic factors that cosegregate with invasion.

RESULTS: Pangenome-wide comparisons of E coli clinical isolates identified accessory genes that can cosegregate with invasion phenotype. These correlations found the acquisition of antibiotic resistance genes in clinical isolates compromised the traditional gentamicin protection assays used to quantify invasion. Therefore, an alternate assay, based on amikacin resistance, identified genes cosegregating with invasion. These genes encode an arylsulfatase, a glycoside hydrolase, and genetic islands carrying propanediol utilization and sulfoquinovose metabolism pathways.

CONCLUSIONS: This study highlights the importance of incorporating antibiotic resistance screening for invasion assays used in AIEC identification. Accurately screened invasion phenotypes identified accessory genome elements among E coli IBD isolates that correlate with their ability to invade epithelial cells. These results help explain why single genetic markers for the AIEC phylotype are challenging to identify.},
}

Humans
*Escherichia coli/genetics/pathogenicity/isolation & purification/drug effects
*Inflammatory Bowel Diseases/microbiology
*Escherichia coli Infections/microbiology
Phenotype
Epithelial Cells/microbiology
Genotype
Whole Genome Sequencing
Virulence/genetics
Drug Resistance, Bacterial/genetics
Virulence Factors/genetics

@article {pmid40437092,
year = {2025},
author = {Lynch, RC and Padgitt-Cobb, LK and Garfinkel, AR and Knaus, BJ and Hartwick, NT and Allsing, N and Aylward, A and Bentz, PC and Carey, SB and Mamerto, A and Kitony, JK and Colt, K and Murray, ER and Duong, T and Chen, HI and Trippe, A and Harkess, A and Crawford, S and Vining, K and Michael, TP},
title = {Domesticated cannabinoid synthases amid a wild mosaic cannabis pangenome.},
journal = {Nature},
volume = {},
number = {},
pages = {},
pmid = {40437092},
issn = {1476-4687},
abstract = {Cannabis sativa is a globally important seed oil, fibre and drug-producing plant species. However, a century of prohibition has severely restricted development of breeding and germplasm resources, leaving potential hemp-based nutritional and fibre applications unrealized. Here we present a cannabis pangenome, constructed with 181 new and 12 previously released genomes from a total of 144 biological samples including both male (XY) and female (XX) plants. We identified widespread regions of the cannabis pangenome that are surprisingly diverse for a single species, with high levels of genetic and structural variation, and propose a novel population structure and hybridization history. Across the ancient heteromorphic X and Y sex chromosomes, we observed a variable boundary at the sex-determining and pseudoautosomal regions as well as genes that exhibit male-biased expression, including genes encoding several key flowering regulators. Conversely, the cannabinoid synthase genes, which are responsible for producing cannabidiol acid and delta-9-tetrahydrocannabinolic acid, contained very low levels of diversity, despite being embedded within a variable region with multiple pseudogenized paralogues, structural variation and distinct transposable element arrangements. Additionally, we identified variants of acyl-lipid thioesterase genes that were associated with fatty acid chain length variation and the production of the rare cannabinoids, tetrahydrocannabivarin and cannabidivarin. We conclude that the C. sativa gene pool remains only partially characterized, the existence of wild relatives in Asia is likely and its potential as a crop species remains largely unrealized.},
}

@article {pmid40436163,
year = {2025},
author = {Gagneja, S and Capalash, N and Sharma, P},
title = {Whole genome sequence analysis of an environmental isolate Bacillus subtilis K3C: Genome plasticity and acquisition of hyaluronic acid capsule traits through horizontal multigene transfer.},
journal = {International journal of biological macromolecules},
volume = {},
number = {},
pages = {144696},
doi = {10.1016/j.ijbiomac.2025.144696},
pmid = {40436163},
issn = {1879-0003},
abstract = {B. subtilis K3C was isolated from an environmental sample. Genomic analysis revealed that the GRAS strain harbors a circular chromosome of 4,120,051 bp composed of 4361 protein coding sequences with a GC content of 43.4 %, 80 tRNA, and 3 rRNA genes. Two regions containing complete assembly of prophages encoded by 83 prophage genes were present suggesting the role of bacteriophage infection in evolutionary accumulation of strain-specific genes contributing towards strain diversification. Strong recombination, repair, transfer and competence systems were identified, suggesting their role in strain fitness and evolutionary process. Pan-genomic analysis revealed 3824 protein homologs as the bacterial core genome shared among different strains and 390 singletons in the pan-genome orthologous groups. The hyaluronic acid capsule trait in the isolate seems to be acquired through selective pressure to adapt in environmentally stressed niches. Phyloproteomic analysis showed that the acquired genes responsible for HA production were phylogenetically closer to Streptococcal clade, evidencing the role of horizontal gene transfer. The bacterial genome showed the presence of multiple HA genes translating HasB and HasC proteins suggesting gene dosage in the strain. However, no gene rearrangement events seem to have taken course as the HA genes were integrated in different contigs of the genome.},
}

@article {pmid40431301,
year = {2025},
author = {Wang, K and Zhang, C and Munang'andu, HM and Xu, C and Cai, W and Yan, X and Tao, Z},
title = {Comparative Genomic Analysis of Two Vibrio harveyi Strains from Larimichthys crocea with Divergent Virulence Profiles.},
journal = {Microorganisms},
volume = {13},
number = {5},
pages = {},
pmid = {40431301},
issn = {2076-2607},
support = {42376108//National Natural Science Foundation of China/ ; },
abstract = {Vibrio harveyi is a significant pathogen in marine aquaculture, causing vibriosis in various marine species. This study presents a comparative genomic analysis of two V. harveyi strains, N8T11 and 45T2, which exhibit differing virulence profiles. Virulence assays revealed that N8T11 caused 92% mortality in infected fish, while 45T2 resulted in 0% mortality. Whole-genome sequencing revealed that strain N8T11 harbors five plasmids (pN8T11a, pN8T11b, pN8T11c, pN8T11d and pN8T11e) absent in 45T2, encoding genes potentially linked to virulence, such as siderophore-mediated iron acquisition and stress response mechanisms. Pan-genome analysis highlighted substantial genomic plasticity within V. harveyi, with mobile genetic elements, including plasmids and prophages, contributing to horizontal gene transfer. Conjugation experiments demonstrated that all five N8T11 plasmids can transfer to 45T2 with efficiencies up to 87%, with pN8T11b remaining stable across multiple subcultures, enabling the dissemination of virulence-associated genes. These findings suggest that plasmid-mediated gene transfer plays a role in the virulence variability observed between V. harveyi strains. This study contributes to understanding the genomic factors underlying pathogenicity in V. harveyi and provides insights for future research aimed at controlling vibriosis in aquaculture.},
}

@article {pmid40431107,
year = {2025},
author = {Shi, F and Li, L and Chen, M and Chang, J and Tu, M and He, G and Li, Y and Yang, G},
title = {Genus-Wide Pan-Genome Analysis of Oryza Calcium-Dependent Protein Kinase Genes and Their Related Kinases Highlights the Complexity of Protein Domain Architectures and Expression Dynamics.},
journal = {Plants (Basel, Switzerland)},
volume = {14},
number = {10},
pages = {},
pmid = {40431107},
issn = {2223-7747},
support = {31570261//National Natural Science Foundation of China/ ; 2016CFB549//National Natural Science Foundation of Hubei China/ ; 5001170128//the Research Support Programs for the HUST Research Facilities and Bases/ ; 2024EHA056//the International Science and Technology Collaboration Project of Hubei Province/ ; 2021XXJS070, 3004170157//the Fundamental Research Funds for Central Universities, HUST/ ; 2024AFB955//Natural Science Foundation of Hubei Province of China/ ; 2021RZ100, 53210052172//Start-Up Research Funding of Wuhan Polytechnic University/ ; },
abstract = {The Oryza genus serves not only as a gene pool for rice improvement but also as a model system for plant evolutionary research. Calcium-dependent protein kinases (CPKs) function as both effectors and sensors in calcium signaling and play versatile roles in plant development and stress responses. Four kinase families, namely CPK-related kinases (CRKs), phosphoenolpyruvate carboxylase kinases (PPCKs), PPCK-related kinases (PEPRKs), and calcium- and calmodulin-dependent kinases (CCaMKs), are frequently called CPK-related kinases. This study utilized evolutionary genomics approaches and provided the pan-genome repertoires of CPKs and their related kinases in 34 Oryza genomes by leveraging the rich genomics resources of the Orzya genus. Gene duplication analysis revealed that distinct duplication types contributed to expanding CPKs and their related kinases in wild rice. We depicted the protein domain architectures of CPKs and their related kinases, highlighting the complexity of EF-hand motifs in CPKs and CCaMKs. Transcriptome analysis determined that alternative splicing was a mechanism contributing to the diversity in the domain architectures of CPKs and CCaMKs. We also generated the expression atlas of CPKs and their related kinases in multiple species of Oryza genus, emphasizing divergent homoeolog expression patterns across tissues and species in allotetraploid wild rice. Collectively, our Oryza-wide analysis of CPKs and their related kinases revealed their evolutionary trajectories and highlighted their diversified domain architectures and expression dynamics, providing gene resources of wild relatives for rice improvement.},
}

@article {pmid40430797,
year = {2025},
author = {Kuufire, E and Bentum, KE and Nyarku, R and Osei, V and Elrefaey, A and James, T and Woube, Y and Folitse, R and Samuel, T and Abebe, W},
title = {Identification of Novel Gene-Specific Markers for Differentiating Various Pathogenic Campylobacter Species Using a Pangenome Analysis Approach.},
journal = {Pathogens (Basel, Switzerland)},
volume = {14},
number = {5},
pages = {},
pmid = {40430797},
issn = {2076-0817},
mesh = {*Campylobacter/genetics/classification/isolation & purification ; Genetic Markers ; *Genome, Bacterial ; *Campylobacter Infections/microbiology/diagnosis ; Humans ; Phylogeny ; Animals ; Genomics/methods ; },
abstract = {Campylobacter spp. are the causative agents of campylobacteriosis, a major foodborne illness globally, with millions of cases reported annually. These pathogens pose significant risks to both human and animal health. Conventional culture-based diagnostic methods are labor-intensive and time-consuming, underscoring the need for more efficient molecular detection strategies. This study employed a pangenomic analysis to identify novel gene-specific markers for pathogenic Campylobacter species and subspecies, laying the groundwork for their application in diverse diagnostic assays. A curated dataset of 105 high-quality genomes, representing 33 species and 9 subspecies, was analyzed using the Roary ILP Bacterial Annotation Pipeline. The results revealed substantial genomic diversity within the genus, with core gene counts varying across different nucleotide identity thresholds. Ribosomal genes such as rpsL, rpsJ, rpsS, rpmA, rpsK, rpsU, rpsG, rpmH, and rpsZ were consistently identified in the core genome, whereas accessory genes exhibited marked variability. This study uncovered novel and highly specific genetic markers for various Campylobacter species, including petB, clpX, and carB for C. coli; hypothetical proteins for C. jejuni and C. fetus; porA2 for C. lari; and mdtJ for C. upsaliensis. These markers demonstrated a specificity of at least 90% with minimal cross-reactivity with non-target organisms. The findings underscore the genomic heterogeneity within Campylobacter and provide essential genetic targets for the enhanced molecular detection of its pathogenic species, subspecies, and biovars.},
}

*Campylobacter/genetics/classification/isolation & purification
Genetic Markers
*Genome, Bacterial
*Campylobacter Infections/microbiology/diagnosis
Humans
Phylogeny
Animals
Genomics/methods

@article {pmid40425278,
year = {2025},
author = {Nakashima, T and Miyauchi, T and Takeuchi, R and Sugihara, Y and Funakoshi, Y and Ohka, F and Maeda, S and Hirato, J and Yoshioka, T and Okita, H and Narita, Y and Kanemura, Y and Kojima, Y and Watanabe, Y and Saito, R and Suzuki, H},
title = {Diversity of U1 Small Nuclear RNAs and Diagnostic Methods for Their Mutations.},
journal = {Cancer science},
volume = {},
number = {},
pages = {},
doi = {10.1111/cas.70110},
pmid = {40425278},
issn = {1349-7006},
support = {//Astellas Foundation for Research on Metabolic Disorders/ ; 2024-D-01//Japan Health Research Promotion Bureau/ ; //MSD Life Science Foundation, Public Interest Incorporated Foundation/ ; //National Cancer Center Japan/ ; JST FOREST Program JPMJFR210Q//Japan Science and Technology Agency/ ; //Takeda Science Foundation/ ; //Uehara Memorial Foundation/ ; 21K21001//Japan Society for the Promotion of Science/ ; 22H03190//Japan Society for the Promotion of Science/ ; 22K19591//Japan Society for the Promotion of Science/ ; //Cell Science Research Foundation/ ; //Kobayashi Foundation for Cancer Research/ ; 22ck0106693h0002//Japan Agency for Medical Research and Development/ ; 23ck0106877h0001//Japan Agency for Medical Research and Development/ ; 23ama221525h00//Japan Agency for Medical Research and Development/ ; //Authorized NPO (Non Profit Organization) Gold Ribbon Network/ ; },
abstract = {U1 small nuclear RNA (snRNA) mutations are recurrent non-coding alterations found in various malignancies, yet their identification has proven challenging due to their repetitive nature. We characterized the complex interindividual diversity and genomic architecture of U1 snRNA loci using sequencing data and a pangenome reference. Our analysis uncovered copy number variations and the diversity of single-nucleotide variants in regions not predicted to have significant functional impact. Compared to traditional linear reference-based analyses for mutations, the pangenome graph demonstrated the best accuracy, successfully identifying previously undetectable mutations. This underscores the utility of pangenome graph references for cancer genome research, particularly in repetitive and highly diverse genomic regions. Additionally, we developed mutation detection methods employing targeted capture sequencing, rapid quantitative polymerase chain reaction, and a machine learning approach based on splicing patterns, all exhibiting high precision in identifying U1 snRNA mutations. Our findings elucidate the structural complexity of U1 snRNA loci and establish robust methodologies for precise mutation detection in these regions.},
}

@article {pmid40422680,
year = {2025},
author = {Bai, R and Wang, Q and Bao, H},
title = {Whole-Genome Characterization of Inonotus hispidus from Ulmus macrocarpa and Its Comparative Genomics with Strains from Morus alba and Acer truncatum.},
journal = {Journal of fungi (Basel, Switzerland)},
volume = {11},
number = {5},
pages = {},
pmid = {40422680},
issn = {2309-608X},
support = {No.20240180//the research and development of authentic medicinal materials and high-quality new varieties of Sanghuang in the old course of the Yellow River/ ; No.32070021//the national natural science foundation of China/ ; },
abstract = {Inonotus hispidus growing on Morus alba is traditionally regarded as the authentic source of the medicinal fungus. However, this species is also found on other host trees, such as Ulmus macrocarpa and Acer truncatum; yet, whether these strains share comparable genomic and functional traits with Morus-derived strains remains unknown. Here, we performed whole-genome sequencing of a strain isolated from U. macrocarpa (UMI) using Illumina and PacBio platforms and conducted comparative genomic analysis with strains from M. alba (MAI) and A. truncatum (AMI). Antagonistic interactions were also evaluated via dual-culture confrontation assays. The UMI genome was 36.44 Mb in size, comprising 9097 predicted genes, of which 6991 and 1672 were annotated in the KEGG and COG databases, respectively. SNP analysis revealed 623,498 and 335,343 variants in AMI and MAI, with AMI showing greater genomic variation. Core-pan genome analysis identified 2651 core genes and 1046, 1424, and 1217 strain-specific genes in UMI, AMI, and MAI, respectively. Phenotypic assays demonstrated distinct mycelial growth dynamics and antagonistic behaviors, which likely reflect host-related environmental adaptation. Overall, I. hispidus strains from non-Morus hosts exhibit unique genomic and phenotypic features, providing a valuable basis for resource evaluation, artificial domestication, and the medicinal development of wild Sanghuang strains beyond traditional sources.},
}

@article {pmid40421466,
year = {2025},
author = {Catalano Gonzaga, O and McKenna, S and O'Neill, I and Cotter, PD and McAuliffe, FM and Coffey, A and van Sinderen, D and Bottacini, F},
title = {Gene-trait matching among Bifidobacterium dentium strains reveals various glycan metabolism loci including a strain-specific fucosyllactose utilization cluster.},
journal = {Frontiers in microbiology},
volume = {16},
number = {},
pages = {1584694},
pmid = {40421466},
issn = {1664-302X},
abstract = {In contrast to other human-associated bifidobacteria, Bifidobacterium dentium is commonly classified as an opportunistic pathogen as its presence in the oral cavity has been associated with the development of dental caries. While B. dentium is frequently isolated from the oral cavity of children with caries, recent microbiome investigations and preliminary genomic analyses have suggested that this species is also adapted to colonize the gastrointestinal tract. Understanding the genetic and metabolic adaptations that enable this flexible colonization ability is crucial to clarify its role in human health and disease. To assess B. dentium genomic diversity and metabolic potential, the current study presents analysis and characterization of 10 complete genome sequences from recently isolated B. dentium strains obtained from human fecal samples together with 48 publicly available genome sequences. We investigated genetic loci predicted to be involved in host interaction and carbohydrate utilization in this species by means of comparative genomics, pan-genome analysis, and gene-trait matching. These analyses identified gene clusters involved in the utilization of plant-derived glycans and, for the first time, revealed B. dentium strains capable of utilizing human milk oligosaccharides (HMOs) through a fucosyllactose utilization cluster homologous to the one found in several infant-derived bifidobacterial species. Moreover, additional investigations of strain-specific genetic features highlighted a taxon that is evolved to colonize multiple niches and to compete with other colonizers. These findings challenge the narrow classification of B. dentium as an opportunist and underscore its ecological versatility.},
}

@article {pmid40417475,
year = {2024},
author = {Marini, S and Barquero, A and Wadhwani, AA and Bian, J and Ruiz, J and Boucher, C and Prosperi, M},
title = {OCTOPUS: Disk-based, Multiplatform, Mobile-friendly Metagenomics Classifier.},
journal = {AMIA ... Annual Symposium proceedings. AMIA Symposium},
volume = {2024},
number = {},
pages = {798-807},
pmid = {40417475},
issn = {1942-597X},
mesh = {*Metagenomics/methods ; *Software ; *Mobile Applications ; },
abstract = {Portable genomic sequencers such as Oxford Nanopore's MinION enable real-time applications in clinical and environmental health. However, there is a bottleneck in the downstream analytics when bioinformatics pipelines are unavailable, e.g., when cloud processing is unreachable due to absence of Internet connection, or only low-end computing devices can be carried on site. Here we present a platform-friendly software for portable metagenomic analysis of Nanopore data, the Oligomer-based Classifier of Taxonomic Operational and Pan-genome Units via Singletons (OCTOPUS). OCTOPUS is written in Java, reimplements several features of the popular Kraken2 and KrakenUniq software, with original components for improving metagenomics classification on incomplete/sampled reference databases, making it ideal for running on smartphones or tablets. OCTOPUS obtains sensitivity and precision comparable to Kraken2, while dramatically decreasing (4- to 16-fold) the false positive rate, and yielding high correlation on real-word data. OCTOPUS is available along with customized databases at https://github.com/DataIntellSystLab/OCTOPUS and https://github.com/Ruiz-HCI-Lab/OctopusMobile.},
}

*Metagenomics/methods
*Software
*Mobile Applications

@article {pmid40414962,
year = {2025},
author = {Pearl, S and Anbarasu, A},
title = {Genomic landscape of nosocomial Acinetobacter baumannii: A comprehensive analysis of the resistome, virulome, and mobilome.},
journal = {Scientific reports},
volume = {15},
number = {1},
pages = {18203},
pmid = {40414962},
issn = {2045-2322},
mesh = {*Acinetobacter baumannii/genetics/pathogenicity/drug effects ; *Genome, Bacterial ; Humans ; *Cross Infection/microbiology ; *Acinetobacter Infections/microbiology ; *Drug Resistance, Multiple, Bacterial/genetics ; Multilocus Sequence Typing ; Virulence Factors/genetics ; Genomics/methods ; Anti-Bacterial Agents/pharmacology ; Whole Genome Sequencing ; },
abstract = {Acinetobacter baumannii (A. baumannii) is a major multidrug-resistant pathogen, posing serious threats in the healthcare settings. This study provides a comprehensive genomic analysis of nosocomial A. baumannii whole-genome sequences retrieved from NCBI Genome database. Multilocus sequence typing and capsule typing were performed to investigate the clonal diversity. The genomes were characterized to identify antimicrobial resistance genes (ARGs), virulence factors, and mobile genetic elements. Further, pangenome analysis was conducted to examine the core and accessory genomes of A. baumannii. Our dataset comprised of 609 genomes deposited from diverse geographic regions worldwide between 2004 and 2024. The genomes showed high clonal heterogeneity, with sequence type ST2 being the predominant sequence type. A total of 185 unique ARGs were identified, with majority of them associated with efflux pump and β-lactamase coding genes. Over 25,000 IS elements were detected, with IS4 family being the prevalent type. High abundance of integron-mediated resistance determinants, especially for aminoglycosides and β-lactams, were identified. The open pangenome window due to its larger accessory genome suggested substantial genome plasticity. Our findings highlight A. baumannii's rapid evolution and resistance potential, emphasizing need for alternative therapeutic strategies. Enhanced surveillance, infection control measures, and antimicrobial stewardship are crucial to combat this persistent threat.},
}

*Acinetobacter baumannii/genetics/pathogenicity/drug effects
*Genome, Bacterial
Humans
*Cross Infection/microbiology
*Acinetobacter Infections/microbiology
*Drug Resistance, Multiple, Bacterial/genetics
Multilocus Sequence Typing
Virulence Factors/genetics
Genomics/methods
Anti-Bacterial Agents/pharmacology
Whole Genome Sequencing

@article {pmid40407329,
year = {2025},
author = {Eripogu, KK and Yu, C-P and Tsai, A and Lin, J-J and Lin, H-C and Li, W-H},
title = {Nocardia genomes are a large reservoir of diverse gene content, biosynthetic gene clusters, and species-specific genes.},
journal = {mBio},
volume = {},
number = {},
pages = {e0094725},
doi = {10.1128/mbio.00947-25},
pmid = {40407329},
issn = {2150-7511},
abstract = {UNLABELLED: The Nocardia genus represents a largely untapped source of valuable secondary metabolites, yet its biosynthetic potential, gene content, and evolutionary history remain underexplored. By analyzing 263 genomes across 88 species, we found that Nocardia varies greatly in genome size and gene content. It exhibits an open pangenome with a small core genome (<900 genes) and high genomic fluidity (0.76), indicating high gene turnover. A large proportion (75%) of its genes are species-specific, indicating high genomic plasticity. Average nucleotide identity (ANI) analysis confirmed taxonomic relationships, with most species showing ANI values (80-85%). N. globerula showed an ANI of ~84% with Rhodococcus erythropolis, supporting its reclassification under Rhodococcus. The biosynthetic capabilities of the Nocardia genus are striking, with the presence of >8,000 biosynthetic gene clusters (BGCs), dominated by type 1 polyketide synthase, terpenes, and non-ribosomal polypeptide synthetases, establishing Nocardia as the Actinomycetota genus that has the largest biosynthetic repertoire. Around 35% of BGCs remain uncharacterized, suggesting Nocardia's high potential for novel natural product discoveries. Our study is the first to identify a prodigiosin BGC in Nocardia. Network analysis revealed complex evolutionary connections between Nocardia's gene cluster families (GCFs) and MIBiG reference BGCs, suggesting evolutionary changes, including gene gains and losses, that may have influenced the genus's BGC diversity and composition. Synteny analysis uncovered conserved and unique gene arrangements across Nocardia and related genera, mostly with core genes conserved in Actinomycetota. Our study addressed unmet clinical and biotechnological challenges while revealing evolutionary mechanisms that shape microbial diversity and adaptability.

IMPORTANCE: Understanding the genomic diversity and biosynthetic potential of microorganisms is instrumental for addressing issues in microbial evolution, natural product discovery, and host-microbe interactions. Nocardia, a bacterial genus known for its opportunistic pathogenicity, represents an underexplored group of immense genomic diversity and biosynthetic capabilities. This study employed genome mining to reveal the open pangenome of Nocardia and identified an extensive repertoire of BGCs, including novel clusters with the potential to produce therapeutically significant compounds such as prodigiosin-related compounds. By integrating genome mining, phylogenetics, and synteny analysis, this study provides insights into how genomic plasticity, species-specific genes, and evolutionary changes such as gene gains and losses that contribute to Nocardia's biosynthetic diversity and evolution. These findings contribute to advancing microbial genomics, evolution, and biotechnology by uncovering the potential of Nocardia to address challenges in infectious diseases and natural product discovery. This study exemplifies how genome mining can illuminate the ecological and clinical significance of microbial diversity.},
}

@article {pmid40405275,
year = {2025},
author = {Cui, Y and Peng, C and Xia, Z and Yang, C and Guo, Y},
title = {A survey of sequence-to-graph mapping algorithms in the pangenome era.},
journal = {Genome biology},
volume = {26},
number = {1},
pages = {138},
pmid = {40405275},
issn = {1474-760X},
support = {6210242//National Natural Science Foundation of China/ ; },
mesh = {*Algorithms ; Humans ; *Genomics/methods ; *Chromosome Mapping/methods ; Genetic Variation ; Sequence Analysis, DNA/methods ; *Genome ; },
abstract = {A pangenome can reveal the genetic diversity across different individuals simultaneously. It offers a more comprehensive reference for genome analysis compared to a single linear genome that may introduce allele bias. Pangenomes are often represented as genome graphs, making sequence-to-graph mapping a fundamental task for pangenome construction and analysis. Numerous sequence-to-graph mapping algorithms have been developed over the past few years. Here, we provide a review of the advancements in sequence-to-graph mapping algorithms in the pangenome era. We also discuss the challenges and opportunities that arise in the context of pangenome graphs.},
}

*Algorithms
Humans
*Genomics/methods
*Chromosome Mapping/methods
Genetic Variation
Sequence Analysis, DNA/methods
*Genome

@article {pmid40404560,
year = {2025},
author = {Thaden, JT and Cox, P and Ankrah, PK and Khandelwal, S and Bourgeois, JS and Poteete, O and Ruffin, F and Arepally, G and Sutton, G and Brinkac, L and Clarke, TH and Ko, DC and Fouts, DE and Fowler, VG},
title = {Escherichia coli Type III Secretion System 2 (ETT2) is Associated with Patient Mortality in Bloodstream Infections.},
journal = {The Journal of infectious diseases},
volume = {},
number = {},
pages = {},
doi = {10.1093/infdis/jiaf265},
pmid = {40404560},
issn = {1537-6613},
abstract = {BACKGROUND: Escherichia coli has an extensive accessory genome, though its role in impacting patient mortality is unknown.

METHODS: We performed whole genome sequencing with E. coli bloodstream infection isolates from inpatients at Duke University. Pan-genome analysis was used to identify flexible genomic islands associated with in-hospital attributable mortality (death due to infection). The functions of the flexible genomic islands of interest were investigated with serum growth assays and bacterial-host cell interaction assays.

RESULTS: We included 193 E. coli genomes. Two separate genomic islands were co-present within 41 (21%) E. coli isolates and associated with increased attributable mortality (22% [9/41]) vs. 11% [17/152]) in an adjusted analysis (Mortality odds ratio 3.0; 95% confidence interval 1.1-7.9; p=0.03). The two genomic islands together contain genes homologous to a type III secretion system (T3SS): 1) E. coli type III secretion system 2 (ETT2), encoding 35 genes homologous to a T3SS basal body and needle complex, and 2) an ETT2 accessory region (ETT2-AR) encoding six genes homologous to a T3SS needle tip, translocases, and adhesin. ETT2/ETT2-AR altered bacterial virulence through two mechanisms. First, ETT2/ETT2-AR increased resistance to complement-mediated growth restriction by inhibiting classical complement pathway activation. Second, ETT2/ETT2-AR influenced E. coli-host cell interactions by increasing adhesion to and death of mammalian cells.

CONCLUSIONS: Genomic islands ETT2 and ETT2-AR are homologous to a T3SS, co-localize within specific E. coli lineages, associate with increased mortality in patients with E. coli bloodstream infection, and increase bacterial virulence through resistance to complement and enhanced host cell adhesion and death.},
}

@article {pmid40403067,
year = {2025},
author = {Swali, P and Booth, T and Tan, CCS and McCabe, J and Anastasiadou, K and Barrington, C and Borrini, M and Bricking, A and Buckberry, J and Büster, L and Carlin, R and Gilardet, A and Glocke, I and Irish, JD and Kelly, M and King, M and Petchey, F and Peto, J and Silva, M and Speidel, L and Tait, F and Teoaca, A and Valoriani, S and Williams, M and Madgwick, R and Mullan, G and Wilson, L and Cootes, K and Armit, I and Gutierrez, MG and van Dorp, L and Skoglund, P},
title = {Ancient Borrelia genomes document the evolutionary history of louse-borne relapsing fever.},
journal = {Science (New York, N.Y.)},
volume = {388},
number = {6749},
pages = {eadr2147},
doi = {10.1126/science.adr2147},
pmid = {40403067},
issn = {1095-9203},
mesh = {*Borrelia/genetics/classification/pathogenicity ; *Relapsing Fever/microbiology/transmission/history ; *Genome, Bacterial ; Animals ; *Evolution, Molecular ; Humans ; Phylogeny ; Biological Evolution ; },
abstract = {Several bacterial pathogens have transitioned from tick-borne to louse-borne transmission, which often involves genome reduction and increasing virulence. However, the timing of such transitions remains unclear. We sequenced four ancient Borrelia recurrentis genomes, the agent of louse-borne relapsing fever, dating from 2300 to 600 years ago. We estimated the divergence from its closest tick-borne relative to 6000 to 4000 years ago, which suggests an emergence coinciding with human lifestyle changes such as the advent of wool-based textiles. Pan-genome analysis indicated that much of the evolution characteristic of B. recurrentis had occurred by ~2300 years ago, though further gene turnover, particularly in plasmid partitioning, persisted until ~1000 years ago. Our findings provide a direct genomic chronology of the evolution of this specialized vector-borne pathogen.},
}

*Borrelia/genetics/classification/pathogenicity
*Relapsing Fever/microbiology/transmission/history
*Genome, Bacterial
Animals
*Evolution, Molecular
Humans
Phylogeny
Biological Evolution

@article {pmid40401527,
year = {2025},
author = {Shahin, K and Abdel-Glil, M and Saticıoğlu, IB and Duman, M and Altun, S and Colussi, S and Esposito, G and Acutis, PL and Marino, P and Spondler, B and Altinok, I and Kotzamanidis, C and Vela, AI and Soto, E and Leal, CAG and Ajmi, N and Aoki, S},
title = {Diving Into the Depths: Unveiling the Main Etiologies of Piscine Lactococcosis With a Novel Multiplex qPCR Assay.},
journal = {Journal of fish diseases},
volume = {},
number = {},
pages = {e14147},
doi = {10.1111/jfd.14147},
pmid = {40401527},
issn = {1365-2761},
abstract = {Piscine lactococcosis poses a significant threat to a wide range of cultured and wild fish populations worldwide, typically presenting as acute haemorrhagic septicemia with high morbidity and mortality. Although Lactococcus garvieae was historically considered the sole causative agent of piscine lactococcosis, recent studies have identified L. petauri and L. formosensis as additional, highly pathogenic species. In this study, we developed a novel TaqMan-based multiplex qPCR assay for the simultaneous detection and differentiation of L. garvieae, L. petauri and L. formosensis, following a pangenome analysis of the publicly available genomes of these bacterial species. The assay demonstrated high sensitivity and specificity across 156 bacterial isolates obtained from various cultured fish species and geographical locations between 2008 and 2024, as well as against a panel of non-target bacteria. It also successfully detected target pathogens in 146 field tissue samples, including tissues preserved in 70% ethanol, formalin-fixed paraffin-embedded (FFPE) tissues and tissues fixed on FTA cards. Compared to classical bacteriology, the multiplex qPCR assay yielded higher detection rates and enabled precise identification of the causative species of piscine lactococcosis. Overall, the multiplex qPCR assay developed in this study provides a reliable, rapid, highly sensitive and species-specific molecular approach for diagnosing piscine lactococcosis, contributing to better surveillance and management of the disease in aquaculture.},
}

@article {pmid40394957,
year = {2025},
author = {Coluzzi, C and Piscon, B and Dérozier, S and Chiapello, H and Gal-Mor, O},
title = {Comparative genomics of Salmonella enterica serovars Paratyphi A, Typhi and Typhimurium reveals distinct profiles of their pangenome, mobile genetic elements, antimicrobial resistance and defense systems repertoire.},
journal = {Virulence},
volume = {16},
number = {1},
pages = {2504658},
doi = {10.1080/21505594.2025.2504658},
pmid = {40394957},
issn = {2150-5608},
mesh = {*Genome, Bacterial ; Phylogeny ; Humans ; *Salmonella typhi/genetics/drug effects ; Genomics ; *Interspersed Repetitive Sequences ; Serogroup ; *Salmonella paratyphi A/genetics/drug effects ; *Salmonella enterica/genetics/drug effects ; *Salmonella typhimurium/genetics/drug effects ; Whole Genome Sequencing ; *Drug Resistance, Bacterial ; Anti-Bacterial Agents/pharmacology ; },
abstract = {Salmonella enterica (S. enterica) is a highly ubiquitous and diverse animal and human pathogen. Distinct S. enterica serovars may present varying host-specificity and cause different diseases. While the human-restricted serovars S. Typhi (STY) and S. Paratyphi A (SPA) cause in humans a systemic life-threatening enteric fever, the host-generalist serovar, S. Typhimurium (STM) causes in immunocompetent individuals a self-limited gastroenteritis. Here, we have performed whole-genome sequencing and hybrid assembly of new SPA and STY typhoidal strains and took a comparative genomics approach to examine their phylogeny, pangenome structure and accessory genome content in comparison to the reference non-typhoidal serovar, STM. Our results identified previously uncharacterized lineages of SPA and refined the presence and distribution of core pseudogenes in typhoidal serovars. Pangenome analysis showed that while these serovars have a relatively similar core-genome size, the accessory genome of STM is more than four times larger than those of typhoidal Salmonellae and that STY and SPA display a more closed pangenome than STM. Unexpectedly, we demonstrate that STY and SPA present distinct differences in their pangenome composition, with a noticeable lower number of prophages, conjugative elements and antimicrobial genes per genome in SPA vs. STY. These results suggest that although SPA and STY are closely related at the DNA level, share a similar lifestyle and cause a symptomatic-indistinguishable disease, their genomic evolution and accessory genomes are markedly different. Moreover, these results may provide genomic explanation to phenotypic and epidemiological differences in antimicrobial resistance profiles associated with these serovars globally.},
}

*Genome, Bacterial
Phylogeny
Humans
*Salmonella typhi/genetics/drug effects
Genomics
*Interspersed Repetitive Sequences
Serogroup
*Salmonella paratyphi A/genetics/drug effects
*Salmonella enterica/genetics/drug effects
*Salmonella typhimurium/genetics/drug effects
Whole Genome Sequencing
*Drug Resistance, Bacterial
Anti-Bacterial Agents/pharmacology

@article {pmid40393508,
year = {2025},
author = {Bao, H and Xue, N and Wang, B and Yu, H and Huang, M and He, J and Dong, S and Zhou, Y and Gao, Q and Tian, Y},
title = {Exploration of gene presence/absence variations in Oncorhynchus mykiss and their differentiation between wild and selection populations.},
journal = {Open biology},
volume = {15},
number = {5},
pages = {240382},
pmid = {40393508},
issn = {2046-2441},
support = {//The Taishan Industrial Program/ ; //Technology plan project of Tangshan/ ; //China Postdoctoral Science Foundation/ ; //the Key R&D Project of Shandong Province/ ; //National Natural Science Foundation of China/ ; //Shandong Provincial Natural Science Foundation/ ; //Marine Science and Technology Innovation Demonstration Project of Qingdao/ ; //China National Postdoctoral Program for Innovative Talents/ ; },
mesh = {Animals ; *Oncorhynchus mykiss/genetics/classification ; Phylogeny ; *Selection, Genetic ; Genome-Wide Association Study ; *Genetic Variation ; Genetics, Population ; Polymorphism, Single Nucleotide ; Genotype ; },
abstract = {Gene presence/absence variations (PAVs) have been considered as the important determinants of genome evolution and phenotypic diversity. However, studies on gene PAVs have been poorly documented, especially in fishes. In the present study, the pan-genome of rainbow trout was constructed based on 268 whole-genome re-sequencing accessions (4.38 Tb data). It recovered an additional 62 Mb sequences and 1288 protein-coding genes. Then, 9831 (22.77%) gene PAVs were genotyped across the 268 individuals. PAV-based PCA analysis, together with phylogenetic topology and STRUCTURE, revealed the clear separation among the different wild and selection populations. Additionally, a PAV-based genome-wide association study (GWAS) identified three candidate PAVs significantly associated with artificial selection. Meanwhile, fixation index analysis revealed 35 PAVs with significant frequency differences between wild and selection populations in Canada, while 15 candidate PAVs were detected between the populations in America. Their biological functions have been reported to participate in the regulation of growth performance and stress response. The present study deepens our understanding of widespread gene PAVs and facilitates the identification of key candidates that contribute to important traits.},
}

Animals
*Oncorhynchus mykiss/genetics/classification
Phylogeny
*Selection, Genetic
Genome-Wide Association Study
*Genetic Variation
Genetics, Population
Polymorphism, Single Nucleotide
Genotype

@article {pmid40390692,
year = {2025},
author = {Raza, A and Zaman, QU and Shabala, S and Tester, M and Munns, R and Hu, Z and Varshney, RK},
title = {Genomics-assisted breeding for designing salinity-smart future crops.},
journal = {Plant biotechnology journal},
volume = {},
number = {},
pages = {},
doi = {10.1111/pbi.70104},
pmid = {40390692},
issn = {1467-7652},
support = {UMU2303-003RTX//Grains Research and Development Corporation/ ; UMU2403-009RTX//Grains Research and Development Corporation/ ; UMU2404-003RTX//Grains Research and Development Corporation/ ; WSU2303-001RTX//Grains Research and Development Corporation/ ; //Murdoch University/ ; 2022B010//Shenzhen University/ ; XMHT20220104019//The Engineering Research Center Support Program from Development and Reform Commission of Shenzhen Municipality/ ; 2022B1111070005//Guangdong Key R & D Project/ ; KCXFZ20211020164013021//Shenzhen Special Fund for Sustainable Development/ ; GuikeAA24263042//Guangxi Major Program for Science and Technology/ ; 32273118//National Natural Science Foundation of China/ ; 2021B1212040015//Guangdong Provincial Key Laboratory of Functional Substances in Medicinal Edible Resources and Healthcare Products/ ; },
abstract = {Climate change induces many abiotic stresses, including soil salinity, significantly challenging global agriculture. Salinity stress tolerance (SST) is a complex trait, both physiologically and genetically, and is conferred at various levels of plant functional organization. As both the sustainability and profitability of agricultural production systems are critically dependent on SST, plant breeders are trying to design and develop salinity-smart crop plants capable of thriving under high salinity conditions. The accessibility of extreme-quality reference genomes for cultivated crops, naturally salinity-smart plants, and crop wild relatives has fast-tracked the discovery of key genes and quantitative trait loci (QTLs), marker development, genotyping assays and molecular breeding products with improved SST. Employing fast-forward breeding tools, namely genomic selection (GS), haplotype-based breeding (HBB), artificial intelligence (AI) and high-throughput phenotyping (HTP), has shown influence not only for fast-tracking genetic gains but also for reducing the time and cost of developing commercial cultivars with enhanced SST and yield stability. This review discusses the advancement and prospects of various genomics-assisted breeding (GAB) tools, including genome sequencing, QTL mapping, GWAS, GS, HBB, pan-genomics, single-cell/tissue genomics and phenotyping, epigenomics and transgenomics, to exploit the genetic landscape for improving SST. Additionally, we explore the integration of HTP and AI, which demonstrates how these innovative approaches can optimize breeding efficiency and guide large-scale breeding efforts for designing salinity-smart crops to ensure sustainable agriculture and global food security. The collective adoption of these tools suggests bridging the gap between research and field application to deliver stress-smart varieties designed for saline-affected regions worldwide.},
}

@article {pmid40390271,
year = {2025},
author = {Salmaso, N and Cerasino, L and Di Brizio, M and Pindo, M and Boscaini, A},
title = {Phylogenomic and Pangenomic Assessment of a Mediterranean Strain of Raphidiopsis raciborskii Extends Knowledge of the Global Distribution and Characteristics of a Potentially Toxigenic Cyanobacterium.},
journal = {Environmental microbiology reports},
volume = {17},
number = {3},
pages = {e70098},
pmid = {40390271},
issn = {1758-2229},
support = {CN00000033//National Biodiversity Future Center, European Union Next-GenerationEU, PNRR/ ; CUPD43C22001280006//National Biodiversity Future Center, European Union Next-GenerationEU, PNRR/ ; },
mesh = {*Cyanobacteria/genetics/classification/isolation & purification ; *Phylogeny ; *Genome, Bacterial ; *Lakes/microbiology ; Mediterranean Region ; Bacterial Toxins/genetics ; Italy ; Genomics ; },
abstract = {Among potentially toxigenic cyanobacteria, Raphidiopsis raciborskii has attracted considerable attention due to its ability to produce massive blooms and its recent spread to temperate regions. In this work, we reported for the first time a taxonomic and functional assessment of a R. raciborskii strain isolated from the Mediterranean region, contributing to filling a gap in the global distribution and characteristics of this species. The strain LT_0923 was isolated from Lake Trasimeno, a large and shallow lake in central Italy. The phylogenomic analyses based on selected marker genes and the core genome obtained from a pangenomic analysis based on a selection of available high-quality genomes showed a strong correspondence of the Lake Trasimeno strain with the North American and, at a lower average nucleotide identity, with the South American genomes. The LT_0923 genome did not show the presence of gene clusters encoding legacy cyanotoxins or emerging toxigenic compounds. The open pangenome and the large fraction of distinct gene families identified in the cloud and partly shell genome, enriched with genes specialised in environmental-specific functions and defence mechanisms, are consistent with the development of Raphidiopsis in geographically distinct regions.},
}

*Cyanobacteria/genetics/classification/isolation & purification
*Phylogeny
*Genome, Bacterial
*Lakes/microbiology
Mediterranean Region
Bacterial Toxins/genetics
Italy
Genomics

@article {pmid40389286,
year = {2025},
author = {Mastoras, M and Asri, M and Brambrink, L and Hebbar, P and Kolesnikov, A and Cook, DE and Nattestad, M and Lucas, J and Won, TS and Chang, PC and Carroll, A and Paten, B and Shafin, K},
title = {Highly accurate assembly polishing with DeepPolisher.},
journal = {Genome research},
volume = {},
number = {},
pages = {},
doi = {10.1101/gr.280149.124},
pmid = {40389286},
issn = {1549-5469},
abstract = {Accurate genome assemblies are essential for biological research, but even the highest quality assemblies retain errors caused by the technologies used to construct them. Base-level errors are typically fixed with an additional polishing step that uses reads aligned to the draft assembly to identify necessary edits. However, current methods struggle to find a balance between over- and under-polishing. Here, we present an encoder-only transformer model for assembly polishing called DeepPolisher, which predicts corrections to the underlying sequence using PacBio HiFi read alignments to a diploid assembly. Our pipeline introduces a method, PHARAOH (Phasing Reads in Areas Of Homozygosity), which uses ultra-long ONT data to ensure alignments are accurately phased and to correctly introduce heterozygous edits in falsely homozygous regions. We demonstrate that the DeepPolisher pipeline can reduce assembly errors by approximately half, mostly driven by reductions in indel errors. We have applied our DeepPolisher-based pipeline to 180 assemblies from the next Human Pangenome Reference Consortium (HPRC) data release, producing an average predicted Quality Value (QV) improvement of 3.4 (54% error reduction) for the majority of the genome.},
}

@article {pmid40389285,
year = {2025},
author = {Antipov, D and Rautiainen, M and Nurk, S and Walenz, BP and Solar, SJ and Phillippy, AM and Koren, S},
title = {Verkko2 integrates proximity ligation data with long-read De Bruijn graphs for efficient telomere-to-telomere genome assembly, phasing, and scaffolding.},
journal = {Genome research},
volume = {},
number = {},
pages = {},
doi = {10.1101/gr.280383.124},
pmid = {40389285},
issn = {1549-5469},
abstract = {The Telomere-to-Telomere Consortium recently finished the first truly complete sequence of a human genome. To resolve the most complex repeats, this project relied on the semi-manual combination of long, accurate PacBio HiFi and ultra-long Oxford Nanopore sequencing reads. The Verkko assembler later automated this process, achieving complete assemblies for approximately half of the chromosomes in a diploid human genome. However, the first version of Verkko was computationally expensive and could not resolve all regions of a typical human genome. Here we present Verkko2, which implements a more efficient read correction algorithm, improves repeat resolution and gap closing, introduces proximity-ligation-based haplotype phasing and scaffolding, and adds support for multiple long-read data types. These enhancements allow Verkko to assemble all regions of a diploid human genome, including the short arms of the acrocentric chromosomes and both sex chromosomes. Together, these changes increase the number of telomere-to-telomere scaffolds by twofold, reduce runtime by fourfold, and improve assembly correctness. On a panel of 19 human genomes, Verkko2 assembles an average of 39 of 46 complete chromosomes as scaffolds, with 21 of these assembled as gapless contigs. Together, these improvements enable telomere-to-telomere comparative genomics and pangenomics, at scale.},
}

@article {pmid40388514,
year = {2025},
author = {Zhou, Y and Anthony, R and Wang, S and Xia, H and Ou, X and Zhao, B and Song, Y and Zheng, Y and He, P and Liu, D and Zhao, Y and van Soolingen, D},
title = {Understanding the epidemiology and pathogenesis of Mycobacterium tuberculosis with non-redundant pangenome of epidemic strains in China.},
journal = {PloS one},
volume = {20},
number = {5},
pages = {e0324152},
doi = {10.1371/journal.pone.0324152},
pmid = {40388514},
issn = {1932-6203},
mesh = {*Mycobacterium tuberculosis/genetics/pathogenicity/classification ; China/epidemiology ; Humans ; *Tuberculosis/epidemiology/microbiology ; *Genome, Bacterial ; Epidemics ; Evolution, Molecular ; Phylogeny ; Genetic Variation ; },
abstract = {Tuberculosis is a major public health threat resulting in more than one million lives lost every year. Many challenges exist to defeat this deadly infectious disease which address the importance of a thorough understanding of the biology of the causative agent Mycobacterium tuberculosis (MTB). We generated a non-redundant pangenome of 420 epidemic MTB strains from China including 344 Lineage 2 strains, 69 Lineage 4 strains, six Lineage 3 strains, and one Lineage 1 strain. We estimate that MTB strains have a pangenome of 4,278 genes encoding 4,183 proteins, of which 3,438 are core genes. However, due to 99,694 interruptions in 2,447 coding genes, we can only confidently confirm 1,651 of these genes are translated in all samples. Of these interruptions, 67,315 (67.52%) could be classified by various genetic variations detected by currently available tools, and more than half of them are due to structural variations, mostly small indels. Assuming a proportion of these interruptions are artifacts, the number of active core genes would still be much lower than 3,438. We further described differential evolutionary patterns of genes under the influences of selective pressure, population structure and purifying selection. While selective pressure is ubiquitous among these coding genes, evolutionary adaptations are concentrated in 1,310 genes. Genes involved in cell wall biogenesis are under the strongest selective pressure, while the biological process of disruption of host organelles indicates the direction of the most intensive positive selection. This study provides a comprehensive view on the genetic diversity and evolutionary patterns of coding genes in MTB which may deepen our understanding of its epidemiology and pathogenicity.},
}

*Mycobacterium tuberculosis/genetics/pathogenicity/classification
China/epidemiology
Humans
*Tuberculosis/epidemiology/microbiology
*Genome, Bacterial
Epidemics
Evolution, Molecular
Phylogeny
Genetic Variation

@article {pmid40387325,
year = {2025},
author = {Yang, F and Li, M and Wu, H and Yu, C and Liu, W and Chen, H},
title = {Comparative genomics-based insights into Pantoea ananatis strains, isolated from white spot diseased leaves of maize with plant growth-promoting attributes.},
journal = {Applied and environmental microbiology},
volume = {},
number = {},
pages = {e0032925},
doi = {10.1128/aem.00329-25},
pmid = {40387325},
issn = {1098-5336},
abstract = {Pantoea ananatis is a member of the Enterobacteriaceae family known for its broad host adaptability. This study isolated 10 P. ananatis strains from white spot (MWS)-diseased leaves of maize (Zea mays) grown in Yunnan Province, China, and analyzed their putative functions, genomic diversity, and variation. The inoculation tests revealed that none of the 10 isolates caused MWS symptoms in maize. Nine maize isolates, except for S47, induced a hypersensitive response (HR) in tobacco and caused rot symptoms in onion. Most isolates exhibited plant growth-promoting characteristics, with strains JCC14, JCY1, and S47 significantly enhancing maize seedling growth parameters. Genomic sequencing of 10 maize isolates and two rice isolates revealed that 12 isolates clustered into three groups, with an open pan-genome identified. Ancestral reconstruction indicated that the genome size increased in Group A and then decreased in Group B, with significant gains in orthologous groups at Node 14, the most recent common ancestor (MRCA) of Group A and Group B, and at Node 19, the MRCA of seven maize-isolated strains and other Group B strains. Additionally, 11 single-copy orthologous groups were under positive selection. Furthermore, the HIVir (high virulence, also known as PASVIL, P. ananatis-specific virulence locus) cluster and type VI secretion system-related genes were conserved in certain P. ananatis strains but were not related to their group divergences. This study not only reveals the diverse functions of MWS-diseased maize P. ananatis isolates, but also enhances our understanding of divergent genome evolution and environmental adaptation across P. ananatis species.IMPORTANCEPantoea ananatis is a bacterium commonly found in various agronomic crops. Maize white spot (MWS) has been one of the most destructive diseases affecting maize, leading to significant economic losses. This study clarified that P. ananatis strains colonized maize leaves but were not the causal agents of MWS in Yunnan Province, China. Moreover, most of these P. ananatis strains exhibited plant growth-promoting (PGP) activities, induced hypersensitive response (HR) activity on tobacco, and caused rot symptoms in onion. Notably, the analysis of divergence throughout the evolutionary process revealed significant genomic evolution and environmental adaptation in these P. ananatis strains. This highlights the genetic exchange that has shaped the genome of P. ananatis. These findings improve our understanding of the functional diversity of P. ananatis strains across different hosts and their positions within the evolutionary lineages of P. ananatis species.},
}

@article {pmid40380089,
year = {2025},
author = {Wang, X and Yan, M and Cui, S and Li, F and Zhao, Q and Wang, Q and Jiang, B and Huang, Y and Sun, Y and Kong, X},
title = {Common bean pan-genome reveals abundant variation patterns and relationships of stress response genes and pathways.},
journal = {BMC genomics},
volume = {26},
number = {1},
pages = {495},
pmid = {40380089},
issn = {1471-2164},
support = {32100352, 32100355, 31871964//National Natural Science Foundation of China/ ; 1908085QC93//Natural Science Fund of Anhui Province/ ; KJ2020A0094//Natural Science Foundation of Universities of Anhui Province/ ; 202003a06020009//Major Science and Technology Projects in Anhui Province/ ; 2019FY101800//National Science & Technology Fundamental Resources Investigation Program of China/ ; },
mesh = {*Phaseolus/genetics/microbiology ; *Stress, Physiological/genetics ; *Genome, Plant ; Quantitative Trait Loci ; Gene Expression Regulation, Plant ; *Genetic Variation ; Gene Expression Profiling ; Disease Resistance/genetics ; Pseudomonas syringae ; },
abstract = {Long-term geographical isolation and the different directions of domestication can cause a large number of genome variations. Population genetic analysis based on a single reference genome cannot capture all the variation information. Pan-genome construction is an effective way to overcome this problem. Resequencing data from 683 common bean landraces and breeding lines provided a pan-genome construction data resource. For the first time, for common bean pan-genome construction, 305 Mb non-reference contigs and 10,452 novel genes were identified. Among these new genes, 373 resistance gene analogs containing 372 variable genes were identified and used to narrow down the candidate genes in Pseudomonas syringae pv. phaseolicola resistance quantitative trait locus interval of the common bean. Transcriptome analysis of multiple biotic and abiotic stresses reveals that gene expression patterns are organ-, stress-, and gene conservation-specific. Core and shell genes may be co-expressed in all samples and may have functional complementarity to maintain the stability of plant growth. Within pathways, 8990 and 30,272 mutual exclusivity and co-occurrence gene presence-absence variations (PAVs) were discovered respectively, providing further insights into the functional complementarity of genes. In conclusion, our study provides a comprehensive genome resource, which will be useful for further common bean breeding and study.},
}

*Phaseolus/genetics/microbiology
*Stress, Physiological/genetics
*Genome, Plant
Quantitative Trait Loci
Gene Expression Regulation, Plant
*Genetic Variation
Gene Expression Profiling
Disease Resistance/genetics
Pseudomonas syringae

@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.},
}