Briefings in bioinformatics最新文献

{"title":"From conservation scores to language models: a feature engineering perspective on machine learning for genetic variant interpretation.","authors":"Matteo Bulloni, Martina Vescio, Federico De Mori Bajolin, Linda Pattini","doi":"10.1093/bib/bbag552","DOIUrl":"https://doi.org/10.1093/bib/bbag552","url":null,"abstract":"<p><p>The interpretation of genetic variants remains central to precision medicine, and machine-learning-based variant effect prediction tools have become indispensable for supporting decision-making processes. In this review we trace the progression from hand-crafted features and traditional machine learning classifiers, through supervised ensembles, to deep-learning architectures and foundation models that learn representations directly from biological sequences. We classify methods for genetic variant effect prediction by underlying machine learning model and variant type handled, from missense to non-coding and structural, as well as across feature categories, describing their biological rationale, adoption rate, and known limitations. We further examine three cross-cutting methodological challenges-feature orthogonality, data circularity, and training data bias-that affect reliability and clinical applicability, providing a critical overview of the current landscape and the challenges that lie ahead.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":"27 5","pages":""},"PeriodicalIF":7.3,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13654181/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149164039","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"PGpath: recommending population-adapted linear reference genomes from pangenome subpaths.","authors":"Zhengfa Xue, Xuwen Wang, Jiajing Yuan, Tianci Wang, Xiaoqi Sheng, Tinghe Zhang, Jiayin Wang, Hongmin Cai","doi":"10.1093/bib/bbag547","DOIUrl":"https://doi.org/10.1093/bib/bbag547","url":null,"abstract":"<p><p>Large-scale population sequencing requires reference genomes that accurately represent the genetic background of target populations. Although high-quality linear references such as T2T-CHM13 have improved the completeness of human genome representation, a single reference genome remains insufficient to capture genetic diversity across populations. Pangenome graphs provide a richer representation of multi-source genomic variation, but translating pangenome diversity into practical reference genomes remains challenging. First, the direct application of pangenome graphs in routine large-scale sequencing analysis is limited by graph complexity and poor compatibility with existing linear-reference workflows. Second, existing pangenome-driven personalized references mainly target individual samples rather than populations, and current path recommendation strategies may overlook local source consistency during branch-node selection. In this study, we propose PGpath, a pangenome-based method for recommending population-adapted linear reference genomes. PGpath generates a reference from a selected pangenome subpath, preserving pangenome diversity while retaining a linear format compatible with standard downstream pipelines. In this study, we characterize the shared genetic background of samples using population-level k-mer frequency features and reformulate reference recommendation as branch-node prediction in the pangenome graph. To encourage local source consistency, we develop a topology-constrained multi-task neural network incorporating source-consistency relationships between adjacent branch nodes. Experiments on Human Pangenome Reference Consortium (HPRC) population datasets and HG002 variant detection benchmarks showed that PGpath-derived references improved read mapping performance and reduced downstream variant detection errors compared with commonly used references. PGpath provides a practical strategy for translating pangenome diversity into population-adapted linear references for large-scale genomic analysis.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":"27 5","pages":""},"PeriodicalIF":7.3,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149164047","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"spMosaic: multi-sample integration for scalable spatial domain discovery based on spatial transcriptomics.","authors":"Shiwei Fu, Han Li, Wei Vivian Li","doi":"10.1093/bib/bbag527","DOIUrl":"https://doi.org/10.1093/bib/bbag527","url":null,"abstract":"<p><p>Spatial transcriptomics enables high-resolution profiling of gene expression within intact tissue architecture, providing new opportunities to study the spatial organization of tissue structures and cell types. However, identifying spatial domains that are reproducible across samples and individuals remains challenging due to batch effects, inter-individual heterogeneity, increasing dataset sizes and the incomparability of spatial coordinates across independently processed tissue sections. We propose spMosaic, a scalable computational framework for multi-sample spatial domain identification. The method integrates two key components: (i) generalized additive model-based spatial smoothing to identify spatially variable genes shared across samples, and (ii) a batch-aware dual-encoder autoencoder that learns low-dimensional representations while encouraging sample-associated variation to be represented separately from domain-relevant biological variation. A subsequent deep embedded clustering refinement step further improves the separation and compactness of inferred domain assignments. We evaluated spMosaic against nine existing methods in both single-individual and multi-individual settings across diverse datasets spanning five technologies. spMosaic consistently achieved strong clustering performance relative to existing methods while maintaining competitive sample integration. In addition, under the computational settings used in our benchmark, spMosaic was the only method among those evaluated that successfully scaled to a large cohort, enabling the analysis of 378 918 spatial spots from 31 frontal cortex samples across 12 mice. These results demonstrate that spMosaic provides an integrative and scalable approach for multi-sample spatial transcriptomics analysis, enabling accurate and interpretable characterization of spatial tissue organization.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":"27 5","pages":""},"PeriodicalIF":7.3,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13625658/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149104220","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Decoding cellular vulnerabilities for interpretable drug response prediction.","authors":"Chonghao Chen, Yulei Du, Yaxin Jiang, Yuanfang Wang, Di Tang, Xiaofan Ding, Mian He","doi":"10.1093/bib/bbag559","DOIUrl":"10.1093/bib/bbag559","url":null,"abstract":"<p><p>Accurate prediction of anticancer drug response remains challenging because conventional approaches based on chemical structures and baseline molecular profiles do not directly capture drug-induced perturbations or cellular dependencies. Here, we present vulnerability-guided cascaded attention transformer (VCAT), which integrates Connectivity Map (CMap)/Library of Integrated Network-based Cellular Signatures (LINCS)-derived consensus transcriptional signatures with clustered regularly interspaced short palindromic repeats (CRISPR)-supervised cellular representations through adaptive encoders and dual stream cascaded attention. Across four data splitting strategies, VCAT outperformed conventional machine learning and published deep learning models, achieving the best performance in 11 of 12 classification split metric comparisons. Ablation analyses showed that CRISPR-derived vulnerability features complement baseline gene expression and that the proposed interaction architecture further improves prediction. VCAT also enhanced continuous IC50 prediction and generalized across Cancer Therapeutics Response Portal (CTRP), Profiling Relative Inhibition Simultaneously in Mixtures (PRISM), patient-derived organoids, and hepatocellular carcinoma cohorts. Attention based prioritization and integrated gradients jointly highlighted biologically relevant genes, while knockdown of cytosolic iron-sulfur assembly component 3 (CIAO3), methylenetetrahydrofolate dehydrogenase 2 (MTHFD2), and WD repeat domain 1 (WDR1) increased sorafenib sensitivity in hepatocellular carcinoma cell lines. These findings support integrating drug-induced perturbations with genetic vulnerabilities for accurate, interpretable, and transferable anticancer drug response prediction.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":"27 5","pages":""},"PeriodicalIF":7.3,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13671233/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149191111","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Correction to: DeepDrugs: a mechanism-aware tri-linear attention framework for synergistic drug-combination prediction.","authors":"","doi":"10.1093/bib/bbag585","DOIUrl":"10.1093/bib/bbag585","url":null,"abstract":"","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":"27 5","pages":""},"PeriodicalIF":7.3,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13669789/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149191163","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prediction of bacteria-specific drug metabolism using a cross-attention-based model.","authors":"Jaehyeon Park, Si Eun Kim, Heeyoung Yang, Nam-Chul Cho, Hyunho Kim, Hyun Kil Shin","doi":"10.1093/bib/bbag578","DOIUrl":"10.1093/bib/bbag578","url":null,"abstract":"<p><p>Drug metabolism by gut microorganisms is bacteria-specific and can have clinically significant consequences, including prodrug activation, drug inactivation, and the generation of toxic metabolites. However, existing computational approaches have primarily focused on community-level predictions or drug-to-microbe effects, without resolving the metabolic contributions of individual bacterial strains or the bidirectional nature of drug-bacteria interactions, despite advances in computational frameworks. Here, we propose a bidirectional cross-attention architecture, multimodal Bi-MHA, that integrates atom-level molecular embeddings and protein-level bacterial embeddings from pretrained models to generate a combined representation for classification. The proposed model was developed using reliability stratification and a $mathrm{lambda}$-scaled loss function on the training dataset and achieved consistent performance across three unseen tasks: unseen drug (receiver operating characteristic area under the curve [ROC AUC]: 0.690), unseen bacteria (ROC AUC: 0.920), and unseen interaction (ROC AUC: 0.949), ranking first among all compared models in the rank-sum metric. Beyond prediction, attention-based analysis not only indicated enzymatic reaction sites that were experimentally validated in previous studies but also prioritized candidate bacterial proteins, demonstrating interpretability at both the atom and protein levels. The proposed model also achieved a 15 percentage point improvement in accuracy over the KNN baseline on an external validation dataset of 85 out-of-distribution drug-bacteria pairs. Furthermore, the model was extended to community-level prediction as a proof-of-concept application using a weighted-abundance pipeline on an independent microbiome dataset. These results demonstrate the model's potential as an interpretable screening tool for drug safety evaluation and personalized medicine. The source code is available at https://github.com/Jaehyeon-O-Ob/Bacteria-Specific_Drug_Metabolism.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":"27 5","pages":""},"PeriodicalIF":7.3,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13677792/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149219880","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Systematic benchmarking of multi-ancestry fine-mapping under variant heterogeneity and LD mismatch.","authors":"Guangxin Chen, Peristera Paschou, Boran Gao","doi":"10.1093/bib/bbag574","DOIUrl":"10.1093/bib/bbag574","url":null,"abstract":"<p><p>Increasingly diverse, multi-ancestry genome-wide association studies (GWASs) provide unprecedented opportunities to better understand the genetic architecture of complex traits. In particular, differences in linkage disequilibrium (LD) patterns across populations can be leveraged to improve the resolution and reliability of statistical fine-mapping. However, cross-ancestry effect heterogeneity, population-specific variant support, and LD mismatches pose substantial challenges, motivating a systematic evaluation of multi-ancestry fine-mapping methods to provide practical guidance for analyses across diverse populations. We conducted a comprehensive benchmarking of nine methods, spanning joint probabilistic models that explicitly model cross-ancestry LD and effect sharing, and univariate-based integration approaches that aggregate ancestry-specific results. We evaluated fine-mapping accuracy, robustness, and computational efficiency using realistic simulations derived from UK Biobank genotype data, with real-data validation in the All of Us Research Program. Our study revealed that joint modeling approaches achieve improved power and resolution for causal variants shared across populations. In comparison, post-hoc integration is more robust in recovering causal variants present in only a subset of populations by accommodating differences in variant availability. Moreover, methods are generally underpowered in the presence of systematic discrepancies between GWAS summary statistics and external LD reference panels. Motivated by these complementary performance profiles, we propose the multi-ancestry fine-mapping decision strategy, which avoids a priori method selection by adaptively selecting approaches based on locus-level evidence of ancestry-specific variants. Together, our benchmarking and decision strategy offer practical guidance for robust multi-ancestry fine-mapping and highlight the importance of joint modeling that effectively accounts for ancestry-specific variant availability and LD mismatch.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":"27 5","pages":""},"PeriodicalIF":7.3,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13677793/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149219898","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Decoding cell-cell communication in spatial transcriptomics: mechanistic insights, modeling constraints, and analytical caveats.","authors":"Yuesong Wu, Haohao Su, Yuehua Cui","doi":"10.1093/bib/bbag477","DOIUrl":"10.1093/bib/bbag477","url":null,"abstract":"<p><p>Cell-cell communication (CCC) is essential for maintaining tissue organization and driving biological progression, yet its inference from transcriptomic data has long been limited by the absence of spatial context. Advances in spatial transcriptomics (ST) now enable mechanistically grounded analyses of CCC by preserving the physical organization of cells and their microenvironments. In this review, we examine recent methodological developments in CCC inference from ST data, focusing on how statistical, optimal transport, and deep learning frameworks incorporate spatial information to model ligand-receptor (LR) interactions and downstream signaling. We also summarize key mechanism-driven components shared across spatial and non-spatial CCC approaches. In addition, we discuss how tissue heterogeneity and spatial architecture can introduce context-dependent biases, particularly for permutation-based inference, and outline mechanistic considerations such as LR biochemistry, signal transduction, and condition-specific communication. We further highlight databases that curate intercellular conduction and intracellular signaling processes. By integrating spatial constraints with biochemical and computational principles, this review offers an integrated assessment of the opportunities and limitations of current approaches. We conclude by identifying key methodological challenges and future directions for developing robust, scalable, and mechanistically interpretable CCC inference as ST technologies continue to advance.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":"27 5","pages":""},"PeriodicalIF":7.3,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13548332/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148900045","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Contrastive learning of adverse events to provide effective and interpretable vector representations for machine-assisted pharmacovigilance.","authors":"Olivér M Balogh, Mátyás Pétervári, Áron M Csernák, Eszter Puhl, András Horváth, Péter Ferdinandy, Bence Ágg","doi":"10.1093/bib/bbag463","DOIUrl":"10.1093/bib/bbag463","url":null,"abstract":"<p><p>Post-marketing surveillance is crucial for drug safety, yet the tools of pharmacovigilance rely solely on text-based data that may limit contemporary machine learning methodologies in the support of decision-making. With the recent surge of employing large language models (LLMs) for text-based tasks, there also arises an unmet need for a different approach which is not grounded in the linguistic patterns of unfiltered natural text, like LLMs, but rather based on real-world drug safety data. Here, we adapt contrastive learning algorithms to generate adverse event vector representations from spontaneous adverse event reports to serve as machine-readable (i.e. numerical) resources for downstream pharmacovigilance applications, such as drug-event association prediction for signal detection or causality assessment. We present comprehensive interpretability analyses of the resulting representations through density-based clustering, semantic evaluation, and comparison of multivariate dispersions, revealing patterns that reflect both functional and causal relations of the adverse events while also capturing drug-safety-related information better than existing medical terminologies and encoder-only LLMs. Furthermore, we demonstrate the applicability of our representations as input features in our downstream classifier model, outperforming the reporting odds ratio method, commonly used by regulatory agencies, and also LLM-generated representations (area under the receiver operating characteristic curve: 0.88 versus 0.76-0.83) on drug-event association prediction benchmarks. Therefore, we propose an interpretable adverse event vector representation, serving as a general resource that could enable the development of a wide array of machine learning applications to support decision-making in pharmacovigilance and facilitate patient safety.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":"27 5","pages":""},"PeriodicalIF":7.3,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13541282/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148886328","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MHCXGraph: a graph-based approach to detecting T-cell receptor cross-reactivity.","authors":"Carlos D M S Simões, Rocío L B R Maidana, Samuel C de Assis, João V S Guerra, Helder V Ribeiro-Filho","doi":"10.1093/bib/bbag555","DOIUrl":"10.1093/bib/bbag555","url":null,"abstract":"<p><p>The T-cell receptor (TCR) recognition of multiple peptides presented by the major histocompatibility complex (MHC) is a key natural phenomenon, enabling the T-cell repertoire to respond to a broad array of antigens. Despite its importance to the immune response, T-cell cross-reactivity poses a major challenge for the development of novel T cell-based therapies. In this study, we present MHCXGraph, a graph-based computational approach for identifying conserved and immunologically relevant regions across multiple structures of peptides bound to MHC molecules (pMHC). Our approach provides three operational modes: Multiple, Pairwise, and Screening, with user-defined parameters, allowing flexible configuration according to specific scientific needs while delivering fully interpretable results through user-friendly interfaces. We evaluated MHCXGraph across several case studies, including peptides bound to classical MHC Class I, MHC Class II, unbound human leukocyte antigen (HLA) alleles, and pMHCs containing noncanonical amino acids, demonstrating its ability to capture conserved structural determinants beyond sequence similarity. By integrating structural information with efficient graph-based analysis, MHCXGraph addresses key limitations of sequence-based methods while maintaining computational scalability. Collectively, these results indicate that MHCXGraph can be readily integrated into computational pipelines for T-cell cross-reactivity discovery, especially in the context of $textit{de novo}$ pMHC engager design and T cell-based vaccine development.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":"27 5","pages":""},"PeriodicalIF":7.3,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13647279/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149135222","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}