Briefings in bioinformatics最新文献

{"title":"Development of a novel multimodal deep learning approach to improve diagnostic precision in ovarian cancer.","authors":"Po-Chun Chiu, Chia-Yi Lee, Heng-Cheng Hsu, Yi-Jou Tai, Ying-Cheng Chiang, Tzu-Pin Lu","doi":"10.1093/bib/bbag224","DOIUrl":"10.1093/bib/bbag224","url":null,"abstract":"<p><strong>Background: </strong>Ovarian cancer represents the primary cause of mortality from gynecological malignancies among women. Treatment strategies for benign versus malignant ovarian tumors differ significantly, making accurate preoperative diagnosis essential for clinical decision-making. Traditional ultrasound diagnosis is highly operator-dependent, introducing subjectivity and variability. To improve diagnostic precision in ovarian tumor classification, we developed a multimodal deep learning system that combines ultrasound images with corresponding clinical text reports.</p><p><strong>Methods: </strong>We retrospectively analyzed 1342 ultrasound images from 1062 patients who received surgical treatment for ovarian tumors at National Taiwan University Hospital from 2011 to 2021. Patients were classified into benign (n = 612) and malignant (including borderline, n = 450) groups based on pathology. A multimodal deep learning architecture was developed, incorporating DenseNet-121 and Swin Transformer for image feature extraction and Bio-Clinical BERT for processing clinical text reports. The dataset was split using subject-level stratification with five-fold cross-validation and a 15% independent test set. Furthermore, an external validation cohort of 268 effective cases from 3 independent medical centers was utilized to evaluate the model's generalizability.</p><p><strong>Results: </strong>The multimodal model achieved superior performance at the subject level with 81.77% (95% CI: 75.89%, 86.48%) accuracy, 79.59% (95% CI: 70.57%, 86.38%) sensitivity, 83.81% (95% CI: 75.59%, 89.64%) specificity, and an area under the curve (AUC) of 0.88 (95% CI: 0.83, 0.93). In the external validation, the model maintained robust performance with an accuracy of 88.81%, sensitivity of 92.59%, and specificity of 84.96%, outperforming the International Ovarian Tumor Analysis Simple Rules (accuracy 86.4%). Integration of clinical text information significantly improved diagnostic performance compared to image-only models. Backward selection analysis revealed that both uterine findings and ovarian tumor descriptions contributed synergistically to the final diagnosis.</p><p><strong>Conclusions: </strong>This study successfully developed a multimodal deep learning model with diagnostic performance superior to traditional operator-dependent approaches. The model shows promise as a diagnostic tool for ovarian tumor classification, offering clinicians a way to improve preoperative diagnostic accuracy and enhance patient care quality.</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/PMC13147446/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147833683","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":"Master of Metals2: a graph neural network based architecture for the prediction of zinc binding sites in protein structures.","authors":"Vincenzo Laveglia, Cosimo Ciofalo, Enrico Morelli, Claudia Andreini, Antonio Rosato","doi":"10.1093/bib/bbag078","DOIUrl":"10.1093/bib/bbag078","url":null,"abstract":"<p><p>Zinc ions play essential structural and catalytic roles in a wide range of proteins. Accurate prediction of their binding sites is crucial for structural and functional annotation. We present MoM2, a web-accessible tool for predicting zinc-binding sites in protein 3D structures. MoM2 employs a graph neural network trained exclusively on spatial features specifically, Cα and Cβ coordinates eliminating the need for templates or sequence-based heuristics. The tool efficiently processes entire proteomes within hours and demonstrates strong predictive performance. In a benchmark of 412 experimentally determined apo-structures, MoM2 outperformed existing methods, achieving the highest F1-score (55.7%) and the lowest false discovery rate (44.1%). The web interface supports input via structure files, PDB or UniProt IDs, and allows batch processing with customizable thresholds. As an independent validation, MoM2 correctly identified 18 out of 20 predicted zinc sites in SARS-CoV-2 proteins. The tool is freely available at https://mom2.cerm.unifi.it.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":"27 2","pages":""},"PeriodicalIF":7.7,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12951075/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147324763","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":"Co-expression network multivariate regression.","authors":"Hwiyoung Lee, Yezhi Pan, Shuo Chen","doi":"10.1093/bib/bbag125","DOIUrl":"10.1093/bib/bbag125","url":null,"abstract":"<p><p>Accounting for dependence among high-dimensional variables in omics data analysis is critical to obtain accurate and reliable statistical inference. Although latent, omics variables often exhibit structured correlation/co-expression patterns. However, there are few methods explicitly accounting for such structured dependence in the statistical analysis of omics data (e.g. differential expression analysis). To address this methodological gap, we propose a Coexpression network multivariate Regression (CoReg), which integrates co-expression network structure into multivariate regression analysis to precisely account for the inter-correlations (dependence) among omics variables. We show in simulations that CoReg substantially improves the accuracy of statistical inference and replicability across studies. These findings suggest that CoReg provides an alternative approach for omics data association analysis with dependence adjustment, analogous to the role of mixed-effects models in handling repeated measures in lower-dimensional settings.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":"27 2","pages":""},"PeriodicalIF":7.7,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13006977/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147497659","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":"AI-driven computational methods and benchmarking for T-cell antigen identification.","authors":"Yang Deng, Jinhao Que, Guangfu Xue, Yideng Cai, Wenyi Yang, Yilin Wang, Yi Hui, Zuxiang Wang, Yi Lin, Wenyang Zhou, Zhaochun Xu, Qinghua Jiang, Haoxiu Sun","doi":"10.1093/bib/bbag123","DOIUrl":"10.1093/bib/bbag123","url":null,"abstract":"<p><p>The rise of mRNA vaccines highlights the pivotal role of T-cell antigen identification in modern vaccinology and personalized medicine. T-cell recognition relies on the sophisticated ternary interaction between the T-cell receptor (TCR), the major histocompatibility complex (MHC) molecule, and the peptide antigen, which forms the peptide-MHC (pMHC) complex. Computational methods, particularly artificial intelligence (AI), are indispensable for accurately predicting these complex bindings. This review systematically surveys the rapidly evolving AI-driven landscape for T-cell antigen identification, providing a comprehensive categorization of methods for MHC-I, MHC-II, and the highly complex TCR-pMHC binding prediction, alongside foundational data resources. Crucially, we conduct a rigorous, standardized benchmarking of 18 state-of-the-art TCR-pMHC prediction models across diverse training data sources. Our evaluation on two distinct and challenging out-of-distribution (OOD) unseen epitope variant datasets reveals a significant and concerning generalization gap in current predictors. Notably, the overall absolute predictive gain remains marginal across all models under OOD conditions. This result underscores a severe and persistent generalization challenge when faced with novel epitope variants. To address these limitations, we emphasize the urgent need for enhanced structural modeling, the integration of multi-omics data, and the development of generative models for de novo TCR design. By advancing these computational frontiers, our community can accelerate the transition from prediction to rational design in immunoinformatics.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":"27 2","pages":""},"PeriodicalIF":7.7,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12993716/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147472678","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 TCR recognition via geometric deep learning of immunological fingerprints.","authors":"Chun Shang, Kevin C Chan, Ruhong Zhou","doi":"10.1093/bib/bbag048","DOIUrl":"10.1093/bib/bbag048","url":null,"abstract":"<p><p>T cell receptor (TCR) recognition of peptide-major histocompatibility complex (pMHC) molecules is the critical first step in adaptive immune activation, shaping immunity against pathogens and tumors, as well as tolerance to self. Despite extensive structural characterization of TCR-pMHC complexes, the molecular principles underlying this process remain incompletely understood, hindered by the inherent duality of TCR specificity and cross-reactivity. Traditional structural analyses often fall short in capturing the multidimensional features that govern TCR-pMHC engagement. Here, we introduce a multimodal geometric deep learning framework that systematically extracts and learns various physicochemical and spatial features from pMHC interfaces, which encode key immunological cues for TCR recognition. Applied to a curated dataset of human leukocyte antigens HLA-A*02-peptide-TCR crystal structures, our model robustly predicts TCR binding preferences and uncovers interfacial \"immunological fingerprints\" that inform receptor engagement. Through an integrated explainability module, we identify critical contact residues and interaction motifs, thus providing interpretable insights into the determinants of TCR specificity. We further demonstrate the model's generalizability by analyzing HLA-B*27-peptide complexes, revealing potential TCR cross-reactivity between self-derived and bacterial peptides-highlighting its utility in probing molecular mimicry. This work establishes a scalable, structure-based approach for decoding T cell recognition and offers a powerful tool for guiding antigen design, vaccine development, and TCR-based immunotherapies.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":"27 2","pages":""},"PeriodicalIF":7.7,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12989321/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147462628","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":"Are we ready for causal discovery in biological systems using deep learning?","authors":"Hock Chuan Yeo, Kumar Selvarajoo","doi":"10.1093/bib/bbag127","DOIUrl":"10.1093/bib/bbag127","url":null,"abstract":"<p><p>The field of causal discovery has advanced considerably over the past three decades, in terms of perspectives, computational methods, and foundational concepts. Nevertheless, their application to biological systems that are commonly found in nature (i.e. large-scale, self-regulating), continues to face significant challenges. In this regard, we highlight emerging approaches that go beyond the traditional assumption of global acyclicity, instead leveraging efficient and scalable neural methods to infer pairwise causal relationships, directly from the data. Nonetheless, there remains five key technological hurdles, which must be overcome, to realize the deeper understanding and stronger inference biological causal networks promise.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":"27 2","pages":""},"PeriodicalIF":7.7,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13034813/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147580537","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":"Hybrid deep learning with protein language models and dual-path architecture for predicting IDP functions.","authors":"Jiahui Liang, Yuxian Luo, Baoquan Su, Zhenling Peng","doi":"10.1093/bib/bbag126","DOIUrl":"10.1093/bib/bbag126","url":null,"abstract":"<p><p>Intrinsically disordered regions (IDRs) drive essential cellular functions but resist conventional structural-function annotation due to their dynamic conformations. Current computational methods struggle with cross-dataset generalization and functional subtype discrimination. We present IDPFunNet, a hybrid deep learning model integrating convolutional neural networks, bidirectional LSTM, residual MLP, and the protein language model ProtT5 to predict six IDR functional classes: five binding subtypes and disordered flexible linkers (DFLs). Its dual-path architecture decouples binding prediction from DFL identification. Leveraging ProtT5 evolutionary embeddings, which outperformed ESM-family models and AlphaFold2 structural features (by ≥1.3% average AUC and ≥ 12.7% average APS), IDPFunNet achieves state-of-the-art performance. Across six independent benchmarks, including CAID2/3 blind tests, it consistently surpasses existing general predictors DisoFLAG and DeepDISOBind in protein-binding prediction, with AUCs of 0.866 (TE210) and 0.832 (TE83), representing significant gains of 1.5%-8.1% in AUC and 13.5%-26.7% in APS (p-value < 0.05), while remaining competitive with specialized DFL predictors. Further analyses show multi-task learning enhances protein/lipid/small molecule-binding (3.1%-35.1% AUC gains), BiLSTMs are optimal for DFL identification, and self-attention shows potential for nucleic acid-binding (AUC 0.831). IDPFunNet thus provides an interpretable and generalizable framework for comprehensive IDR functional mapping. The webserver of IDPFunNet is freely available at https://yanglab.qd.sdu.edu.cn/IDPFunNet/ and the standalone package can be downloaded from https://github.com/IDRIDP/IDPFunNet/tree/master.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":"27 2","pages":""},"PeriodicalIF":7.7,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13043015/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147589882","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":"Quantifying transcript complexity via the condition number of gene-specific random matrix.","authors":"Bo Zhang, Yaohui Guo, Guoping Liu, Meng Zou","doi":"10.1093/bib/bbag134","DOIUrl":"10.1093/bib/bbag134","url":null,"abstract":"<p><p>Accurate transcript quantification remains a central challenge, as expression levels estimated by different computational tools (e.g. Cufflinks, StringTie, featureCounts, RSEM) often exhibit substantial discrepancies. The observed variability stems from intrinsic transcriptional architectures and is termed transcript complexity. Here we present a theoretical framework to quantify the transcript complexity via the Condition Number (CN) of a gene-specific random matrix, which is based on two key factors: the repertoire of transcripts generated by alternative splicing and the length distribution of reads by RNA-seq. The CN defines a theoretical bound for quantification error and strongly correlates with inter-tool concordance in real data. The CN decreases with increasing read length, thereby explaining the advantages of long-read sequencing. Moreover, hybrid-seq, integrating short- and long-read, is mathematically guaranteed to achieve error rates no worse than either approach alone, with an optimal mixing ratio yielding further improvements. Notably, this optimal ratio can be determined through grid search. These findings establish the CN as a principled standard for assessing transcript complexity, elucidating a fundamental source of quantification uncertainty and guiding sequencing strategies.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":"27 2","pages":""},"PeriodicalIF":7.7,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13023374/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147526900","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":"miRBiT: a rules-based single-sample serum miRNA classifier for pan-cancer detection with multi-cohort validation.","authors":"Pandikannan Krishnamoorthy, Madhavan Parthasarathy, Nilanjana Das, Athira S Raj, Ganakalyan Behera, Ashok Kumar, Vikas Gupta, Saikat Das, Himanshu Kumar","doi":"10.1093/bib/bbag189","DOIUrl":"https://doi.org/10.1093/bib/bbag189","url":null,"abstract":"<p><p>Liquid biopsy offers a minimally invasive approach to early cancer diagnosis. MicroRNAs (miRNAs) are small, non-coding RNAs showing excellent diagnostic potential due to their stability and dysregulation upon different physiological conditions. However, existing miRNA-based cancer classifiers rely on cohort-based comparisons, limiting their clinical utility. Extensive analyses in this study present miRNA binary trend (miRBiT), a miRNA rules-based single-sample classifier, trained on 16,190 samples, tested across nine independent datasets, and further validated on 8 distinct disease cohorts. miRBiT utilizes miRNA expression signatures at an intra-sample level to classify 'cancer' and 'non_cancer' samples, including healthy and other diseases with high sensitivity and specificity, enabling personalized predictions. Additionally, an interactive web application, miRBiT Explorer serum miRNA expression resource, is developed to visualize and validate serum miRNA expression patterns in 46,349 samples. This study highlights the potential of miRNAs in robust cancer classification, enabling personalized, minimally invasive cancer screening and early detection at an unprecedented scale.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":"27 2","pages":""},"PeriodicalIF":7.7,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13109054/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147762544","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":"Generative design and validation of therapeutic peptides for glioblastoma based on a potential target ATP5A.","authors":"Hao Qian, Pu You, Lin Zeng, Jingyuan Zhou, Dengdeng Huang, Kaicheng Li, Shikui Tu, Lei Xu","doi":"10.1093/bib/bbag188","DOIUrl":"https://doi.org/10.1093/bib/bbag188","url":null,"abstract":"<p><p>Glioblastoma (GBM) remains the most aggressive tumor, urgently requiring novel therapeutic strategies. Here, we present a dry-to-wet framework combining generative modeling and experimental validation to optimize peptides targeting ATP5A, a potential peptide-binding protein for GBM. Our framework introduces the first lead-conditioned generative model, which focuses exploration on geometrically relevant regions around lead peptides and mitigates the combinatorial complexity of de novo methods. Specifically, we propose POTFlow, a Prior and Optimal Transport-based Flow-matching model for peptide optimization. POTFlow employs secondary structure information (e.g. helix, sheet, and loop) as geometric constraints, which are further refined by optimal transport to produce shorter flow paths. With this design, our method achieves state-of-the-art performance compared with five popular approaches. When applied to GBM, our method generates peptides that selectively inhibit cell viability and significantly prolong survival in a patient-derived xenograft model. As the first lead peptide-conditioned flow matching model, POTFlow holds strong potential as a generalizable framework for therapeutic peptide design.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":"27 2","pages":""},"PeriodicalIF":7.7,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13109590/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147762549","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}