Briefings in bioinformatics最新文献

{"title":"Comprehensive evaluation of artificial intelligence-empowered approaches for protein-aptamer complex prediction.","authors":"Jiani Zhao, Kha Tram, Hongbin Yan, Yifeng Li","doi":"10.1093/bib/bbag206","DOIUrl":"10.1093/bib/bbag206","url":null,"abstract":"<p><p>Drug discovery is a time-consuming, expensive, and high-risk process. Recent advances in artificial intelligence (AI) have enabled major breakthroughs in small-molecule and protein therapeutics. However, AI-driven design of aptamer drugs remains largely unexplored. Aptamers are short (15-100 nt) single-stranded DNAs or RNAs that exhibit high binding affinity, high specificity, and low immunogenicity, making them promising candidates for disease (such as cancer) therapeutics. Compared with protein-ligand or protein-protein systems, protein-aptamer complexes are under-represented in public structural databases, and aptamers themselves are highly flexible and relatively large molecules. These characteristics present distinct challenges for AI-based structural modeling. Here, we systematically evaluate recent AI frameworks, including AlphaFold3, Chai-1, Boltz-2, and RoseTTAFold2NA, along with a template-based approach, in predicting protein-aptamer complex structures and estimating binding free energies. We establish an independent benchmark to assess their performance in structural accuracy, stability, and energetic consistency. This study provides a foundation for the application of AI in aptamer drug design and offers a reference framework for future research in nucleic-acid therapeutics and biomolecular modeling.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":"27 3","pages":""},"PeriodicalIF":7.7,"publicationDate":"2026-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13137337/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147811279","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":"MLN2SVG: domain-aware spatially variable gene detection using contrastive variational autoencoder and multi-level neighbor search.","authors":"Shabir Hussain, Muhammad Ayoub, Fei Ye, Xiao Liu","doi":"10.1093/bib/bbag210","DOIUrl":"10.1093/bib/bbag210","url":null,"abstract":"<p><p>Spatial transcriptomics (ST) technologies have transformed our ability to examine gene expression within intact tissues, yet accurately identifying spatially variable genes (SVGs) remains challenging due to spatial heterogeneity, data sparsity, and incomplete modeling of domain-level dependencies. To address these limitations, we propose MLN2SVG, a domain-aware framework that integrates contrastive variational autoencoding with a multi-level neighbor (MLN) search algorithm to jointly learn tissue domains and SVGs. MLN2SVG constructs a weighted spatial graph to capture both local and long-range spatial relationships, employing a deep contrastive variational autoencoder to align augmented and original data representations while preserving biological diversity. The MLN algorithm dynamically expands neighborhood connectivity to mitigate sparsity and enhance domain coherence. Across multiple human and mouse ST datasets, including dorsolateral prefrontal cortex, breast cancer, and brain tissues, MLN2SVG consistently outperformed existing methods in clustering accuracy, robustness, and biological interpretability. Notably, in breast cancer tissues, MLN2SVG uncovers fine-grained spatial organization of tertiary lymphoid structures, delineating region-specific immune architectures spanning intratumoral, tumor-edge, and extratumoral compartments. Through the integration of spatial domain discovery and SVG detection, MLN2SVG delivers a robust and biologically interpretable framework for uncovering the molecular and structural complexity of tissue organization.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":"27 3","pages":""},"PeriodicalIF":7.7,"publicationDate":"2026-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13137336/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147811257","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":"Benchmarking computational methods for multi-omics biomarker discovery in cancer.","authors":"Athan Z Li, Yuxuan Du, Yan Liu, Liang Chen, Ruishan Liu","doi":"10.1093/bib/bbag200","DOIUrl":"10.1093/bib/bbag200","url":null,"abstract":"<p><p>Multi-omics profiling characterizes cancer biology and supports biomarker discovery for prognosis and therapy selection. Although numerous computational multi-omics biomarker identification methods have been proposed, their ability to identify clinically relevant biomarkers has not been systematically evaluated, leaving it unclear whether the resulting biomarker nominations are reliable for downstream validation. Here, we systematically benchmark 20 representative statistical, machine learning and deep learning methods using curated gold-standard prognostic and therapeutic biomarkers across five real-world datasets. We evaluate performance in terms of both biomarker identification accuracy and stability. Overall, DeePathNet and DeepKEGG achieve the best performance. Across methods, effective biomarker recovery is associated with the integration of biological knowledge, global feature interactions, multivariate feature attribution, and effective regularization. Analysis of omics type contributions reveals method- and modality-specific biases, highlighting the importance of broader omics integration. We further evaluate methods on simulated datasets to probe sensitivity with controlled signal and noise. By aggregating results from top-performing methods, we construct consensus biomarker panels that nominate candidates for potential investigations. Finally, we provide user-friendly interfaces to allow researchers to benchmark new methods against the 20 baselines or apply selected methods for biomarker identification on custom multi-omics datasets. Our benchmark is publicly available at https://github.com/athanzli/CancerMOBI-Bench.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":"27 3","pages":""},"PeriodicalIF":7.7,"publicationDate":"2026-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13147463/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147833657","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":"DiSCO: deconvoluting spatial transcriptomics via combinatorial optimization with a foundational diffusion model.","authors":"Jing Liu, Yahao Wu, Limin Li","doi":"10.1093/bib/bbag207","DOIUrl":"https://doi.org/10.1093/bib/bbag207","url":null,"abstract":"<p><p>Deciphering the cellular composition of spatial spots in spatial transcriptomics (ST) data is fundamental for elucidating the heterogeneity of tissue spatial structures. However, existing models often require retraining for each new deconvolution task, reflecting limitations in both generalization performance and computational efficiency. To address this problem, we design a foundational diffusion model to deconvoluting spatial transcriptomics based on combinatorial optimization, termed DiSCO. DiSCO formulates the deconvolution of ST data as a task-specific deconvolutional combinatorial optimization (CO) problem, wherein single cells (SCs) are assigned to spatial spots to optimally preserve the gene expression profiles of each spot. DiSCO introduces a bipartite graph diffusion model as an optimization solver, specifically designed to be generalizable to any new deconvolutional CO problem. Pretrained on a large number of deconvolution tasks using gene expression profiles of both SCs and spatial spots as inputs, DiSCO learns the distribution of true solutions and generates approximate solutions through sampling, thereby enabling the determination of the cellular composition for each spot. As a generalizable deconvolution solver, the DiSCO is evaluated by experiments on both simulated datasets and real datasets, demonstrating that the pretrained DiSCO model performs effectively and efficiently on datasets with varying resolutions and different numbers of genes, thus highlighting its capacity to effectively generalize to diverse datasets.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":"27 3","pages":""},"PeriodicalIF":7.7,"publicationDate":"2026-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147855876","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":"A systematic review of machine learning on clinical MALDI-TOF MS.","authors":"Lucía Schmidt-Santiago, Alejandro Guerrero-López, Carlos Sevilla-Salcedo, David Rodríguez-Temporal, Belén Rodríguez-Sánchez, Vanessa Gómez-Verdejo","doi":"10.1093/bib/bbag208","DOIUrl":"https://doi.org/10.1093/bib/bbag208","url":null,"abstract":"<p><p>Bacterial identification, antimicrobial resistance prediction, and strain typification are critical tasks in clinical microbiology, essential for guiding patient treatment and controlling the spread of infectious diseases. While machine learning (ML) has shown immense promise in enhancing Matrix-Assisted Laser Desorption/Ionization-Time of Flight Mass Spectrometry (MALDI-TOF MS) applications for these tasks, there is currently no comprehensive review that fully addresses this from a technical ML perspective. To address this gap, we systematically reviewed 115 studies published between 2004 and 2025, focusing on key ML aspects such as data size and balance, preprocessing pipelines, model selection and evaluation, open-source data, and code availability. Our analysis highlights the predominant use of classical ML models like Random Forest and Support Vector Machines, alongside emerging interest in deep learning approaches for handling complex, high-dimensional data. Despite significant progress, challenges such as inconsistent preprocessing workflows, reliance on black-box models, limited external validation, and insufficient open-source resources persist, hindering transparency, reproducibility, and broader adoption. This review offers actionable insights to enhance ML-driven bacterial diagnostics, advocating for standardized methodologies, greater transparency, and improved data accessibility. In addition, we provide guidelines on how to approach ML for MALDI-TOF MS analysis, helping researchers navigate key decisions in model development and evaluation.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":"27 3","pages":""},"PeriodicalIF":7.7,"publicationDate":"2026-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147855660","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":"When intelligence begins to act: a thoughtful appraisal of agentic AI in biomedicine.","authors":"Partha Pratim Ray","doi":"10.1093/bib/bbag213","DOIUrl":"10.1093/bib/bbag213","url":null,"abstract":"<p><p>The expanding role of intelligent systems in biomedical science marks a shift from passive analysis towards active participation in discovery and care. Recent scholarship has begun to frame these systems not merely as models, but as agents capable of planning, interaction, and adaptation. This letter reflects on such developments, acknowledging their conceptual clarity and practical ambition, while raising questions about evaluation, responsibility, human judgement, and long-term scientific culture. The intent is to encourage careful reflection as these technologies move closer to real-world integration.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":"27 3","pages":""},"PeriodicalIF":7.7,"publicationDate":"2026-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13147451/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147833809","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":"MuRaL-indel: a deep learning framework for building insertion and deletion mutation rate maps.","authors":"Shuyi Deng, Hui Song, Cai Li","doi":"10.1093/bib/bbag212","DOIUrl":"10.1093/bib/bbag212","url":null,"abstract":"<p><p>Germline short insertions and deletions (INDELs) are pervasive genetic variants that shape genome evolution and contribute to human disease. However, accurately quantifying fine-scale INDEL mutation rates remains challenging due to data limitations and the diversity of INDEL subtypes. Here, we present Mutation Rate Learner for INDELs (MuRaL-indel), a deep learning framework that predicts germline INDEL mutation rates by leveraging long-range sequence context through a U-Net architecture. Using extensive rare variant data from large population cohorts, MuRaL-indel generates base-resolution, length-specific mutation rate maps for the human genome, and achieves superior accuracy compared with existing models across multiple genomic scales. We successfully apply MuRaL-indel to three non-human species (Macaca mulatta, Drosophila melanogaster, and Arabidopsis thaliana), demonstrating its broad applicability across taxa. Using the predicted mutation rate maps, we reveal the mutational landscape around human coding genes and show that MuRaL-indel-derived constraint scores better prioritize pathogenic INDELs than previous models. Through deep learning interpretability analyses, we uncovered sequence motifs-including both repeat and non-repeat elements-associated with elevated INDEL mutability, providing insights into underlying mutational mechanisms. Together, MuRaL-indel establishes a generalizable and scalable framework for building high-resolution INDEL mutation rate maps, offering a valuable resource for studies of genome evolution, mutational mechanism, variant interpretation, and genetic disease.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":"27 3","pages":""},"PeriodicalIF":7.7,"publicationDate":"2026-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13147462/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147833830","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":"From early-onset asthma to chronic obstructive pulmonary disease: potential mediating proteins and therapeutic targets.","authors":"Yuhan Jiang, Ju Guo, Yifan Wang, Run Guo, Yongjian Wei, Tianchun Li, Xuelin Wang, Ruiwen Xia, Wanyi Li, Yingxue Zou, Hongxi Yang","doi":"10.1093/bib/bbag209","DOIUrl":"10.1093/bib/bbag209","url":null,"abstract":"<p><strong>Background and objective: </strong>Early-onset asthma (EOA) significantly increases the risk of chronic obstructive pulmonary disease (COPD), yet the causal mechanisms and molecular mediators underlying this progression remain poorly understood. Multi-omics integration provides a powerful framework for prioritizing potential mediating proteins and disease-specific therapeutic candidates.</p><p><strong>Methods: </strong>This study integrated large-scale genetic and proteomic data using Mendelian randomization (MR) approaches to investigate the progression from EOA to COPD. Proteome-wide MR evaluated protein quantitative trait loci (pQTLs) in relation to EOA and COPD risk, with mediation analysis evaluating their roles and single-cell transcriptomics defining the cell-type-specific expression of the mediating proteins. Finally, colocalization, multi-tissue expression quantitative trait loci (eQTLs), and druggability assessment were used to prioritize potential disease-specific therapeutic targets.</p><p><strong>Results: </strong>Evidence from genetic instruments supports a causal relationship between EOA and COPD. Proteome-wide analyses of 7847 pQTLs identified 339 proteins with potential effects on EOA and 389 on COPD. Six proteins, KREMEN1, BLMH, CNTN5, IL1RN, MIA, and PILRA, showed statistically significant mediation effects in the EOA-to-COPD pathway. PILRA strongly colocalized at shared genetic loci between the two diseases and was significantly downregulated in macrophages from COPD patients. For disease-specific targets, immune-tissue eQTL validation supported ITPKA in EOA. Integration of druggability assessment with multi-tissue eQTL analyses prioritized FES, CCN3, NMI, and NMT1 as promising therapeutic candidates for COPD.</p><p><strong>Conclusion: </strong>These findings provide genetic evidence supporting a causal relationship between EOA and COPD, reveal putative mediating proteins, and prioritize therapeutic candidates with translational potential, offering new insights into pathogenesis, prevention, and intervention.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":"27 3","pages":""},"PeriodicalIF":7.7,"publicationDate":"2026-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13147455/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147833739","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":"When complexity does not pay: benchmarking deep learning and ensemble methods for biomarker discovery.","authors":"Cyrille Mesue Njume, Irene Petracci, Sonia Bellini, Katarzyna Goljanek-Whysall, Leo R Quinlan, Agnieszka Fiszer, Barbara Borroni, Roberta Ghidoni, Asli Kumbasar, Ali Cakmak","doi":"10.1093/bib/bbag211","DOIUrl":"https://doi.org/10.1093/bib/bbag211","url":null,"abstract":"<p><p>The integration of multi-omics data holds great promise for identifying robust and clinically relevant biomarkers, yet the increasing complexity of computational methods raises questions about their practical utility. In this study, we present a comprehensive benchmarking framework that evaluates 27 feature selection strategies and 11 predictive models across three real-world disease cohorts: Alzheimer's disease, progressive supranuclear palsy, and breast cancer. We compare traditional machine learning, ensemble-based methods, and state-of-the-art deep learning models in terms of predictive performance, stability, and biological interpretability. Our results reveal that ensemble feature selection consistently improves robustness and accuracy, particularly for compact biomarker panels. Surprisingly, deep learning models did not outperform simpler classifiers such as logistic regression (L.Regression), support vector machines, or multilayer perceptrons, which often achieved comparable or superior results with lower computational cost and greater interpretability. Triple-omics yielded the highest validation, followed by dual-omics and then single-omics (Triple > Dual > Single). Biological validation against five independent databases confirmed the clinical relevance of the identified biomarkers, including both well-established and novel candidates. To support reproducibility and community adoption, we provide a web-based tool for applying our benchmarking pipeline. Our findings advocate for a pragmatic approach to biomarker discovery-prioritizing methodological transparency, reproducibility, and biological insight over algorithmic complexity.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":"27 3","pages":""},"PeriodicalIF":7.7,"publicationDate":"2026-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147855919","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":"Strategies for constructing context-specific protein-protein interaction networks.","authors":"Shiyan Nie, Xiangren Kong, Dong Li","doi":"10.1093/bib/bbag004","DOIUrl":"https://doi.org/10.1093/bib/bbag004","url":null,"abstract":"<p><p>Protein-protein interactions (PPIs) are fundamental to virtually all biological processes. However, their highly dynamic and context-dependent nature poses significant challenges to traditional general network models in capturing their true biological significance. Here, we introduce the formation of context-specific PPI networks, emphasizing the importance of the biological context in which PPIs occur. We systematically compare traditional experimental methods, mass spectrometry (MS)-based high-throughput technologies, and structure- and biophysics-based approaches across six dimensions. Although these experimental methods have generated valuable data resources, they still suffer from limitations, including low capture efficiency for transient or weak interactions and a lack of gold-standard datasets with specific biological contexts. Furthermore, we review recent advances in context-specific PPI inference strategies centered on omics data integration, and highlight the emerging potential of large cellular models (LCMs) to generate context-aware representations that support the construction of context-specific PPI networks. In the future, comprehensive context-specific PPI networks are expected to more accurately reflect the biological system, thereby enabling deeper mechanistic insights, improving disease interpretation, and accelerating the discovery of therapeutic targets.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":"27 3","pages":""},"PeriodicalIF":7.7,"publicationDate":"2026-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147855860","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}