Briefings in bioinformatics最新文献

{"title":"VF-Fuse: a dual-path feature fusion and iterative update architecture for virulence factor prediction.","authors":"Liang Huang, Xiangyu Yu, Shumei Li, Qingwei Chen, Dan Xu, Zhao Qi","doi":"10.1093/bib/bbaf481","DOIUrl":"10.1093/bib/bbaf481","url":null,"abstract":"<p><p>Accurate prediction of bacterial virulence factors (VFs) is crucial for combating infectious diseases, yet traditional methods often fail to capture their complex sequence properties. We address this challenge by leveraging deep, context-aware representations from large-scale protein language models (PLMs). Our framework begins with a systematic engineering of features from ESM-2 and ProtT5, which confirmed their complementary nature but also revealed that simple concatenation is a suboptimal fusion strategy due to a \"feature overshadowing\" effect. To overcome this, we developed two novel architectures: VF-Iter, for robust feature enhancement via iterative low-rank updates, and the Dual-Path Feature Fusion (DPF) network, for intelligently integrating the complementary embeddings. The construction of our final model, VF-Fuse, involved a two-stage process. First, we selected four powerful and diverse base models representing our distinct feature strategies (ESM-2 only, ProtT5 only, simple concatenation, and DPF). Second, we empirically determined the best method for combining their predictions by benchmarking 15 ensemble techniques, from which Majority Voting emerged as the superior choice. On the independent test set, VF-Fuse establishes a new state of the art, achieving a superior F1-Score of 87.15% and a Matthews Correlation Coefficient of 73.61%. This F1-Score marks a significant 3.3% improvement over the previous best method, driven by an excellent balance between a high Sensitivity of 90.1% and a strong Specificity of 83.33%. Crucially, in-depth interpretability analyses validated our architectural design, demonstrating how the DPF model learns to intelligently route complementary features to specialized pathways.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":"26 5","pages":""},"PeriodicalIF":7.7,"publicationDate":"2025-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12451104/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145111956","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":"CKG-TPI: integrating collaborative knowledge graph with sequence interactions for TCR-peptide binding specificity.","authors":"Yue Liu, Haoyan Wang, Guohua Wang, Yadong Liu, Tao Jiang, Yadong Wang","doi":"10.1093/bib/bbaf486","DOIUrl":"10.1093/bib/bbaf486","url":null,"abstract":"<p><p>Accurately identifying interactions between T-cell receptors (TCRs) and peptides is a fundamental challenge in immunology, with significant implications for vaccine design and immunotherapy. While computational methods offer efficient alternatives to labor-intensive experimental screening, achieving robust and accurate TCR-peptide binding prediction remains a challenging task. To address this, we propose collaborative knowledge graph (CKG-TPI), a novel prediction framework based on graph neural networks that integrates both interaction patterns between TCR and peptide sequences and their higher-order biological context through a constructed collaborative knowledge graph. Experimental results on multiple publicly available independent datasets demonstrate that CKG-TPI consistently outperforms state-of-the-art models. Specifically, it achieves a 9.89% improvement in area under the ROC curve compared to the strongest baseline model UnifyImmun, and a 23.93% increase in area under the precision-recall curve over the leading baseline method. Moreover, attention weight visualization and peptide-specific TCR screening validate the model's effectiveness, underscoring its potential as a powerful tool for immunological research and therapeutic discovery.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":"26 5","pages":""},"PeriodicalIF":7.7,"publicationDate":"2025-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12451105/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145112003","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":"Alignment-free unique molecular identifier clustering suppresses sequencing errors for accurate detection of low-frequency DNA variants.","authors":"Fei Yu, Haojie Xiao, Dongyang Song, Xiao Yang, Shiyue Huang, Yu Wang, Mingze Bai, Xiaoming Yao, Kunxian Shu, Dan Pu","doi":"10.1093/bib/bbaf483","DOIUrl":"10.1093/bib/bbaf483","url":null,"abstract":"<p><p>Accurate detection of low-frequency DNA variants (below 1%) is essential in diverse biological and clinical contexts, yet remains fundamentally constrained by the high intrinsic error rates of next-generation sequencing technologies. Although unique molecular identifiers (UMIs) have significantly mitigated these errors by uniquely indexing original template molecules, their efficacy is compromised by UMI collisions and by artifacts introduced during polymerase chain reaction (PCR) amplification and sequencing, which collectively engender false-positive variant calls. Here, we present AFUMIC, an alignment-free UMI clustering framework that systematically addresses these limitations through collision-resilient UMI grouping and a consensus quality score (CQS)-guided strategy for high-fidelity consensus sequence generation. AFUMIC reduces singleton families, enhances clustering precision, and maximizes data retention, yielding 7.27-fold and 3.84-fold increases in single-strand consensus sequence and duplex consensus sequence output, respectively, compared to Du Novo. It further decreases the per-base error rate from $3.01 times 10^{-4}$ to $2.10 times 10^{-5}$ and raises the proportion of error-free positions from 45.27% to 99.85%, enabling confident detection of variants at variant allele frequencies as low as $1.0 times 10^{-5}$. Notably, AFUMIC exhibits superior computational efficiency, rendering it well-suited for high-throughput analysis of UMI-tagged libraries in large-scale genomic studies. Collectively, AFUMIC represents an efficient methodology for ultrasensitive variant detection and establishes a broadly applicable and computationally efficient framework for error-corrected sequencing that can be readily deployed in both clinical diagnostics and large-scale genomic research.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":"26 5","pages":""},"PeriodicalIF":7.7,"publicationDate":"2025-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12452285/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145124026","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":"Network based simultaneous embedding of cells and marker genes from scRNA-seq studies.","authors":"Namrata Bhattacharya, Swagatam Chakraborti, Stuti Kumari, Bernadette Mathew, Abhishek Halder, Sakshi Gujral, Krishan Gupta, Aayushi Mittal, Debajyoti Sinha, Colleen Nelson, Tanmoy Chakraborty, Gaurav Ahuja, Debarka Sengupta","doi":"10.1093/bib/bbaf537","DOIUrl":"https://doi.org/10.1093/bib/bbaf537","url":null,"abstract":"<p><p>The complexity of scRNA-sequencing datasets highlights the urgent need for enhanced clustering and visualization methods. Here, we propose Stardust, an iterative, force-directed graph layout algorithm that enables the simultaneous embedding of cells and marker genes. Stardust, for the first time, allows a single-stop visualization of cells and marker genes on a single 2D map. While Stardust provides its own visualization pipeline, it can be plugged in with state-of-the-art methods such as Uniform Manifold Approximation and Projection (UMAP) and t-Distributed Stochastic Neighbor Embedding (t-SNE). We benchmarked Stardust against popular visualization and clustering tools on both scRNA-seq and spatial transcriptomics datasets. In all cases, Stardust performs competitively in identifying and visualizing cell types in an accurate and spatially coherent manner.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":"26 5","pages":""},"PeriodicalIF":7.7,"publicationDate":"2025-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145238047","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":"The current landscape and emerging challenges of benchmarking single-cell methods.","authors":"Yue Cao, Lijia Yu, Marni Torkel, Sanghyun Kim, Yingxin Lin, Pengyi Yang, Terence P Speed, Shila Ghazanfar, Jean Yee Hwa Yang","doi":"10.1093/bib/bbaf380","DOIUrl":"10.1093/bib/bbaf380","url":null,"abstract":"<p><p>With the rapid development of computational methods for single-cell sequencing data, benchmarking serves as a valuable resource. As the number of benchmarking studies surges, it is timely to assess the current state of the field. We conducted a systematic literature search and assessed 282 papers, including all 130 benchmark-only papers from the search and an additional 152 method development papers containing benchmarking. This collective effort provides the most comprehensive quantitative summary of the current landscape of single-cell benchmarking studies. We examine performances across nine broad categories, including often ignored aspects such as role of datasets, robustness of methods and downstream evaluation. Our analysis highlights challenges such as how to effectively combine knowledge across multiple benchmarking studies and in what ways can the community recognize the risk and prevent benchmarking fatigue. This paper highlights the importance of adopting a community-led research paradigm to tackle these challenges and establish best practice standards.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":"26 5","pages":""},"PeriodicalIF":7.7,"publicationDate":"2025-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12495992/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145228313","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":"Predicting disease associations based on the higher order structure of ceRNA networks.","authors":"Zhaoliang Chai, Ying Su, Xuecong Tian, Chen Chen, Xiaoyi Lv, Cheng Chen","doi":"10.1093/bib/bbaf518","DOIUrl":"10.1093/bib/bbaf518","url":null,"abstract":"<p><p>Competitive endogenous RNA (ceRNA) network regulation is an important posttranscriptional regulatory mechanism that plays an important role in physiological and pathological processes, and has been widely used in biomarker screening and regulatory factor studies of disease-related genes. However, existing studies have mainly focused on the association of a single type of RNA with disease, while studies targeting the application of ceRNA networks in disease prediction are still limited, so it is crucial to explore the potential of ceRNA networks in disease prediction. In this study, we propose CERDA-HOSR, a computational method for mining ceRNA network-disease associations based on higher order graph attention networks. The method uses higher order graph convolutional networks to aggregate neighborhood information to generate representations of different RNAs and diseases. Given the higher order complexity of biological networks and sample imbalance problem, traditional random negative sampling is difficult to effectively capture global information; for this reason, a higher order negative sampling strategy is designed to optimize the quality of negative samples by combining the network structure and higher order neighborhood relations to improve the generalization ability and prediction accuracy of the model. Finally, LightGBM calculates the ceRNA network-disease association probability based on the learned embedding. A large number of simulation experiments validate the superiority of CERDA-HOSR, and its practical application is further demonstrated by case studies of cardiovascular disease, acute myeloid leukemia, and papillary thyroid cancer. In addition, ablation experiments and exploratory analyses further enhance its robustness and provide an effective tool for disease prediction and biomarker screening.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":"26 5","pages":""},"PeriodicalIF":7.7,"publicationDate":"2025-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12495994/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145228526","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":"Beyond rigid docking: deep learning approaches for fully flexible protein-ligand interactions.","authors":"John Lee, Canh Hao Nguyen, Hiroshi Mamitsuka","doi":"10.1093/bib/bbaf454","DOIUrl":"10.1093/bib/bbaf454","url":null,"abstract":"<p><p>Sparked by AlphaFold2's groundbreaking success in protein structure prediction, recent years have seen a surge of interest in developing deep learning (DL) models for molecular docking. Molecular docking is a computational approach for predicting how proteins interact with small molecules known as ligands. It has become an essential tool in drug discovery, enabling structure-based virtual screening (VS) methods to efficiently explore vast libraries of drug-like molecules and identify potential therapeutic candidates. However, traditional docking methods primarily rely on search-and-score algorithms, which are computationally demanding. To be viable for VS applications, these methods often sacrifice accuracy for speed by simplifying their search algorithms and scoring functions. Recent advancements in DL have transformed molecular docking, offering accuracy that rivals-or even surpasses-traditional approaches while significantly reducing computational costs. Despite these advancements, DL-based molecular docking still faces major challenges. DL models often struggle to generalize beyond their training data and frequently mispredict key molecular properties, such as stereochemistry, bond lengths, and steric interactions, leading to physically unrealistic predictions. To overcome these limitations, a new generation of models is using DL to incorporate protein flexibility into docking predictions, aiming to more accurately capture the dynamic nature of biomolecular interactions-a long-standing challenge for traditional methods. This review explores how DL has reshaped molecular docking, examines its current shortcomings, and highlights emerging solutions. Finally, we discuss future opportunities to further bridge the gap between computational predictions and real-world molecular interactions.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":"26 5","pages":""},"PeriodicalIF":7.7,"publicationDate":"2025-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12406700/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144943395","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":"TCM-navigator, a deep learning-based workflow for generation and evaluation of traditional Chinese medicine-like compounds for drug development.","authors":"Feiying Chen, Victor Jun Yu Lim, Mingyu Li, Hao Fan","doi":"10.1093/bib/bbaf498","DOIUrl":"10.1093/bib/bbaf498","url":null,"abstract":"<p><p>Traditional Chinese Medicine (TCM) has long been regarded as a valuable resource for modern drug discovery. However, the limited availability of recorded entities and information, the complexity and sparsity of the herb-ingredient-target-disease network, and inconsistencies in data representation hinder the effectiveness of high-throughput screening approaches. While some therapeutically valuable compounds from TCM have been discovered through manual experimental screening, such methods are time-consuming and require substantial human resources. To address these challenges, we developed a data-driven and deep learning-based workflow, TCM-navigator, which enables the in-silico generation, quality control, and physics-based evaluation of TCM-like molecules. The generation is done by TCM-Generator, a transfer learning- and Long Short-Term Memory (LSTM)-based chemical language model that generates standardized, hierarchically structured, and high-throughput-friendly datasets of TCM-like molecules. In this study, we generated a target-nonspecific dataset comprising 3.7 million TCM-like molecules, expanding the number of entities in existing TCM datasets by more than 100-fold. The workflow also enables flexible, goal-driven molecule generation customized for specific targets, yielding three target-specific datasets and multiple high-potential target-ligand pairs. The quality control is done by TCM-Identifier, the first quantitative model specifically designed to capture unique characteristics of TCM, using an AttentiveFP framework with message passing neural networks. TCM-Identifier is expected to serve as an essential evaluation and guidance tool for TCM-related drug development. Our workflow bridges cutting-edge data science-including deep learning-with biomedical research to tackle longstanding challenges in target identification and molecular design. Its adaptable framework is also transferable to interdisciplinary innovation beyond drug development.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":"26 5","pages":""},"PeriodicalIF":7.7,"publicationDate":"2025-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12466116/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145147658","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":"Assessing tissue-specific gene expression of essential genes from human and mouse.","authors":"Huiwen Zheng, Atefeh Taherian Fard, Jessica Cara Mar","doi":"10.1093/bib/bbaf487","DOIUrl":"10.1093/bib/bbaf487","url":null,"abstract":"<p><p>A gene is defined as essential when its functional loss compromises an organism's viability. Identifying essential genes is critical for identifying the components that regulate a biological system. Advances in gene editing techniques like CRISPR-Cas9 provide a capacity to interrogate a genome to elucidate the genes that are essential. However, these techniques are often applied for a single-cell line and rarely probed at a level of a tissue or organ. The recent availability of large-scale single-cell RNA-sequencing (scRNA-seq) atlases provides an unprecedented opportunity to investigate essential gene expression in a more comprehensive context. Our study leverages information from benchmarking datasets, single-cell tissue atlases, and databases of essential genes, to develop a method, scEssentials, that uses a statistical framework to investigate the robustness and specificity of essential genes across multiple cell types. Using scEssentials, mouse and human models showed consistently high expression and exhibited limited variability across more than 60 cell types. We demonstrate a substantial number of significantly correlated gene pairs that produce densely connected co-expression networks with functional annotation. Finally, we develop a score to quantify the relative essentiality of genes within scEssentials, further validating their significant association with gene mutation frequency and chromatin accessibility. Using ageing as an application, we demonstrate how scEssentials identifies robust gene expression profiles. Only one-fifth of scEssentials genes showed significant ageing-related differential expression among age groups. Collectively, the robustness of scEssentials serves as a reference for analysing scRNA-seq data and provides insight into the heterogeneous nature such as ageing.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":"26 5","pages":""},"PeriodicalIF":7.7,"publicationDate":"2025-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12459261/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145129885","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":"A simple workflow to identify novel small linear motif (SLiM)-mediated interactions with AlphaFold.","authors":"Martin Veinstein, Victor Janssens, Bogdan I Iorga, Raphaël Helaers, Thomas Michiels, Frederic Sorgeloos","doi":"10.1093/bib/bbaf501","DOIUrl":"10.1093/bib/bbaf501","url":null,"abstract":"<p><p>Short linear motifs (SLiMs) are highly compact interaction modules embedded within disordered protein regions and are increasingly recognized for their central role in maintaining cellular homeostasis. Due to their small size, degeneracy and transient binding, SLiMs remain difficult to detect both experimentally and computationally. Here, we show that AlphaFold (AF), used via ColabFold, offers a practical and accessible alternative for in-silico screening of new SLiMs targeting a protein of interest. Unlike previous studies that evaluated AlphaFold2 (AF2) using structure-derived benchmarks, we extend this by assessing both AF2 and AF3, using a structure-independent benchmark of 26 interactions absent from PDB homology, and showing that MiniPAE is the most suited AlphaFold metric for SLiM screening. We also generated an unbalanced dataset with a large excess of non-binders mimicking real-world blind screening, revealing a critical limitation in AlphaFold's specificity for SLiM detection. To circumvent this constraint, we propose both a SLiM screening strategy and an adaptative scoring threshold. For greater accessibility, we provide a streamlined and cost-effective AF analysis workflow requiring no local installation or computation. To overcome challenges associated with SLiM validation, we also introduce a highly sensitive detection method based on proximity labeling in living cells. This workflow was used to identify and experimentally validate 13 new SLiMs that mediate binding to ribosomal protein S6 kinase A3 (RPS6KA3 or RSK2). By leveraging ColabFold and MiniPAE available through Colab notebooks, our approach provides a scalable and widely accessible strategy for identifying functional SLiMs in proteins of interest. MiniPAE can be accessed at https://github.com/martinovein/MiniPAE.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":"26 5","pages":""},"PeriodicalIF":7.7,"publicationDate":"2025-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12476836/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145184622","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}