Bioinformatics (Oxford, England)最新文献_第8页

A semi-supervised Bayesian approach for marker gene trajectory inference from single-cell RNA-seq data. 从单细胞RNA-Seq数据推断标记基因轨迹的半监督贝叶斯方法。

IF 5.4

Bioinformatics (Oxford, England) Pub Date : 2025-09-01 DOI: 10.1093/bioinformatics/btaf454

Junchao Wang, Ling Sun, Nana Wei, Yisheng Huang, Naiqian Zhang

{"title":"A semi-supervised Bayesian approach for marker gene trajectory inference from single-cell RNA-seq data.","authors":"Junchao Wang, Ling Sun, Nana Wei, Yisheng Huang, Naiqian Zhang","doi":"10.1093/bioinformatics/btaf454","DOIUrl":"10.1093/bioinformatics/btaf454","url":null,"abstract":"Motivation: Trajectory inference methods are essential for extracting temporal ordering from static single-cell transcriptomic profiles, thus facilitating the accurate delineation of cellular developmental hierarchies and cell-fate transitions. However, numerous existing methods treat trajectory inference as an unsupervised learning task, rendering them susceptible to technical noise and data sparsity, which often lead to unstable reconstructions and ambiguous lineage assignments.Results: Here, we introduce BayesTraj, a semi-supervised Bayesian framework that incorporates prior knowledge of lineage topology and marker-gene expression to robustly reconstruct differentiation trajectories from scRNA-seq data. BayesTraj models cellular differentiation as a probabilistic mixture of latent lineages and captures marker-gene dynamics through parametric functions. Posterior inference is conducted using Hamiltonian Monte Carlo (HMC), yielding estimates of pseudotime, lineage proportions, and gene activation parameters. Evaluations on both simulated and real datasets with diverse branching structures demonstrate that BayesTraj consistently outperforms state-of-the-art methods in pseudotime inference. In addition, it provides per-cell branch-assignment probabilities, enabling the quantification of differentiation potential using Shannon entropy and the detection of lineage-specific gene expression via Bayesian model comparison.Availability and implementation: BayesTraj is written in R and available at https://github.com/SDU-W-Zhanglab/BayesTraj and has been archived on Zenodo (DOI: 10.5281/zenodo.16758038).","PeriodicalId":93899,"journal":{"name":"Bioinformatics (Oxford, England)","volume":" ","pages":""},"PeriodicalIF":5.4,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12410927/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144850018","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

NanoFilter: enhancing phasing performance by utilizing highly consistent INDELs and SNVs in nanopore sequencing. 纳米过滤器：利用高度一致的INDELs和snv在纳米孔测序中增强相位性能。

IF 5.4

Bioinformatics (Oxford, England) Pub Date : 2025-09-01 DOI: 10.1093/bioinformatics/btaf453

Shanming Chen, Fan Nie, Jianxin Wang

{"title":"NanoFilter: enhancing phasing performance by utilizing highly consistent INDELs and SNVs in nanopore sequencing.","authors":"Shanming Chen, Fan Nie, Jianxin Wang","doi":"10.1093/bioinformatics/btaf453","DOIUrl":"10.1093/bioinformatics/btaf453","url":null,"abstract":"Motivation: Nanopore sequencing data offer longer reads compared to other technologies, which is beneficial for phasing and genome assembly. INDELs provide valuable haplotype information and have significant potential to improve phasing performance. However, accurately identifying INDELs with variant callers is challenging, and incorporating INDELs into phasing remains a complex task. To address these issues, we developed NanoFilter, a novel filtering strategy designed to filter out INDELs that contain wrong phasing information based on their consistency.Results: Our assessment using Nanopore R10 simplex data shows that filtering out low-consistency INDELs increases their precision from 88.3% to 98.8%, nearly matching the precision of SNVs. In the phasing results of Margin, incorporating these filtered INDELs leads to a 12.77% increase in N50 length and fewer switch errors. Furthermore, we found that SNVs filtered by NanoFilter will enhance assembly performance. When NanoFilter is integrated into the HapDup assembly pipeline, NanoFilter reduces the Hamming error rate and increases N50 length by 7.8%.Availability and implementation: NanoFilter is available at https://github.com/Chenshanming-repo/NanoFilter (DOI: 10.5281/zenodo.16777826) and HapDup-NanoFilter is available at https://github.com/Chenshanming-repo/HapDup-NanoFilter (DOI: 10.5281/zenodo.16777890).","PeriodicalId":93899,"journal":{"name":"Bioinformatics (Oxford, England)","volume":" ","pages":""},"PeriodicalIF":5.4,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12448842/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144850031","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

MOLEonline: a web-based tool for analysing channels, tunnels, and pores (2025 update). MOLEonline：一个基于网络的分析渠道、隧道和孔隙的工具（2025年更新）。

IF 5.4

Bioinformatics (Oxford, England) Pub Date : 2025-09-01 DOI: 10.1093/bioinformatics/btaf486

Tomáš Raček, Dušan Vel'ký, Gabriela Bučeková, Ondřej Schindler, Ivana Hutařová Vařeková, Anna Špačková, Václav Bazgier, Karel Berka, Radka Svobodová

{"title":"MOLEonline: a web-based tool for analysing channels, tunnels, and pores (2025 update).","authors":"Tomáš Raček, Dušan Vel'ký, Gabriela Bučeková, Ondřej Schindler, Ivana Hutařová Vařeková, Anna Špačková, Václav Bazgier, Karel Berka, Radka Svobodová","doi":"10.1093/bioinformatics/btaf486","DOIUrl":"10.1093/bioinformatics/btaf486","url":null,"abstract":"Summary: MOLEonline is an interactive, web-based tool designed to detect and analyse channels (pores and tunnels) within protein structures. The latest version of MOLEonline addresses the limitations of its predecessor by integrating the Mol* viewer for visualization and offering a streamlined, fully interactive user experience. The new features include colouring tunnels in the 3D viewer based on their physicochemical properties. A 2D representation of the protein structure and calculated tunnels is generated using 2DProts. Users can now store tunnels directly in the mmCIF file format, facilitating sharing via the community-standard FAIR format for structural data. In addition, the ability to store and load computation settings ensures the reproducibility of tunnel computation results. Integration with the ChannelsDB 2.0 database allows users to access precomputed tunnels.Availability and implementation: The MOLEonline application is freely available at https://moleonline.cz with no login requirement, its source code is stored at GitHub under the MIT licence at https://github.com/sb-ncbr/moleonline-web, and archived at Figshare at https://doi.org/10.6084/m9.figshare.29816174.","PeriodicalId":93899,"journal":{"name":"Bioinformatics (Oxford, England)","volume":" ","pages":""},"PeriodicalIF":5.4,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12448857/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144982400","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The impact of tokenizer selection in genomic language models. 标记器选择对基因组语言模型的影响。

IF 5.4

Bioinformatics (Oxford, England) Pub Date : 2025-09-01 DOI: 10.1093/bioinformatics/btaf456

LeAnn M Lindsey, Nicole L Pershing, Anisa Habib, Keith Dufault-Thompson, W Zac Stephens, Anne J Blaschke, Xiaofang Jiang, Hari Sundar

{"title":"The impact of tokenizer selection in genomic language models.","authors":"LeAnn M Lindsey, Nicole L Pershing, Anisa Habib, Keith Dufault-Thompson, W Zac Stephens, Anne J Blaschke, Xiaofang Jiang, Hari Sundar","doi":"10.1093/bioinformatics/btaf456","DOIUrl":"10.1093/bioinformatics/btaf456","url":null,"abstract":"Motivation: Genomic language models have recently emerged as a new method to decode, interpret, and generate genetic sequences. Existing genomic language models have utilized various tokenization methods, including character tokenization, overlapping and nonoverlapping k-mer tokenization, and byte-pair encoding, a method widely used in natural language models. Genomic sequences differ from natural language because of their low character variability, complex and overlapping features, and inconsistent directionality. These features make subword tokenization in genomic language models significantly different from both traditional language models and protein language models.Results: This study explores the impact of tokenization in genomic language models by evaluating their downstream performance on 44 classification fine-tuning tasks. We also perform a direct comparison of byte pair encoding and character tokenization in Mamba, a state-space model. Our results indicate that character tokenization outperforms subword tokenization methods on tasks that rely on nucleotide-level resolution, such as splice site prediction and promoter detection. While byte-pair tokenization had stronger performance on the SARS-CoV-2 variant classification task, we observed limited statistically significant differences between tokenization methods on the remaining downstream tasks.Availability and implementation: Detailed results of all benchmarking experiments are available in https://github.com/leannmlindsey/DNAtokenization. Training datasets and pretrained models are available at https://huggingface.co/datasets/leannmlindsey. Datasets and processing scripts are available at doi: 10.5281/zenodo.16287401 and doi: 10.5281/zenodo.16287130.","PeriodicalId":93899,"journal":{"name":"Bioinformatics (Oxford, England)","volume":" ","pages":""},"PeriodicalIF":5.4,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12453675/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144877239","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

PyVADesign: a python-based cloning tool for one-step generation of large mutant libraries. pyvaddesign：一个基于python的克隆工具，用于一步生成大型突变库。

IF 5.4

Bioinformatics (Oxford, England) Pub Date : 2025-09-01 DOI: 10.1093/bioinformatics/btaf433

R C M Kuin, M H Lamers, G J P van Westen

{"title":"PyVADesign: a python-based cloning tool for one-step generation of large mutant libraries.","authors":"R C M Kuin, M H Lamers, G J P van Westen","doi":"10.1093/bioinformatics/btaf433","DOIUrl":"10.1093/bioinformatics/btaf433","url":null,"abstract":"Motivation: The generation and analysis of diverse mutants of a protein is a powerful tool for understanding protein function. However, generating such mutants can be time-consuming, while the commercial option of buying a series of mutant plasmids can be expensive. In contrast, the insertion of a synthesized double-stranded DNA (dsDNA) fragment into a plasmid is a fast and low-cost method to generate a large library of mutants with one or more point mutations, insertions, or deletions.Results: To aid in the design of these DNA fragments, we have developed PyVADesign: a Python package that makes the design and ordering of dsDNA fragments straightforward and cost-effective. In PyVADesign, the mutations of interest are clustered in different cloning groups for efficient exchange into the target plasmid. Additionally, primers that prepare the target plasmid for insertion of the dsDNA fragment, as well as primers for sequencing, are automatically designed within the same program.Availability and implementation: PyVADesign is open source and available at https://github.com/CDDLeiden/PyVADesign and archived via Zenodo (https://doi.org/10.5281/zenodo.15057525).","PeriodicalId":93899,"journal":{"name":"Bioinformatics (Oxford, England)","volume":" ","pages":""},"PeriodicalIF":5.4,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12449254/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144982357","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

ProteinLIPs: a web server for identifying highly polar and poorly packed interfaces in proteins. ProteinLIPs：一个用于识别蛋白质中高极性和低包装界面的web服务器。

IF 5.4

Bioinformatics (Oxford, England) Pub Date : 2025-09-01 DOI: 10.1093/bioinformatics/btaf499

Helena García-Cebollada, Alfonso López, Vladimir E Angarica, Juan José Galano-Frutos, Javier Sancho

{"title":"ProteinLIPs: a web server for identifying highly polar and poorly packed interfaces in proteins.","authors":"Helena García-Cebollada, Alfonso López, Vladimir E Angarica, Juan José Galano-Frutos, Javier Sancho","doi":"10.1093/bioinformatics/btaf499","DOIUrl":"10.1093/bioinformatics/btaf499","url":null,"abstract":"Motivation: The stability of protein interfaces influences protein dynamics and unfolding cooperativity. Although in some cases the dynamics of proteins can be deduced from their topology, much of the stability of an interface is related to the complementarity of the interacting parts. It is also important to note that proteins that display non-cooperative unfolding cannot be rationally stabilized unless the regions that unfold first are known. Being able to identify protein interfaces that are significantly less stable would contribute to our understanding of protein dynamics and be very valuable in guiding the rational stabilization of proteins with non-two-state unfolding equilibria.Results: We introduce ProteinLIPs, a web server that detects interfaces of high polarity and low packing density, termed LIPs. Each LIP consist of a continuous sequence segment (mLIP) plus its contacting residues (cLIP). ProteinLIPs scans monomeric and oligomeric proteins and provides graphical sequence profiles and interactive 3D visualizations of the detected LIPs. Statistical analysis of 53 protein domains from 10 superfamilies shows the two parts of a LIP present distinct characteristics. mLIPs are conserved, structurally unstable and enriched in polar residues, whereas cLIPs are more stable, less conserved, and enriched in apolar residues. Besides, cLIPs are enriched in small-molecule binding site residues, suggesting they play a role in ligand interaction, likely facilitated by instability of the associated mLIPs. ProteinLIPs provides a user-friendly platform for the automated identification and visualization of LIPs and can be used to guide the engineering of non-two-state proteins where LIPs constitute preferential targets for thermostabilization.Availability and implementation: ProteinLIPs is publicly available at https://lips.bifi.es/.","PeriodicalId":93899,"journal":{"name":"Bioinformatics (Oxford, England)","volume":" ","pages":""},"PeriodicalIF":5.4,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12457736/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145034732","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Graph neural network and diffusion model for modeling RNA interatomic interactions. 基于图神经网络和扩散模型的RNA原子间相互作用建模。

IF 5.4

Bioinformatics (Oxford, England) Pub Date : 2025-09-01 DOI: 10.1093/bioinformatics/btaf515

Marek Justyna, Craig Zirbel, Maciej Antczak, Marta Szachniuk

{"title":"Graph neural network and diffusion model for modeling RNA interatomic interactions.","authors":"Marek Justyna, Craig Zirbel, Maciej Antczak, Marta Szachniuk","doi":"10.1093/bioinformatics/btaf515","DOIUrl":"10.1093/bioinformatics/btaf515","url":null,"abstract":"Motivation: Ribonucleic acid (RNA) function is inherently linked to its 3D structure, traditionally determined by X-ray crystallography, Nuclear Magnetic Resonance, and Cryo-EM. However, these techniques often lack atomic-level resolution, highlighting the need for accurate in silico RNA structure prediction tools. Current state-of-the-art methods, such as AlphaFold3, Boltz1, RhoFold, or trRosettaRNA, rely on deep learning models that represent residues as frames and use transformers to learn relative positions. While effective for known RNA families, their performance drops for synthetic or novel families.Results: In this work, we explore the potential of graph neural networks and denoising diffusion probabilistic models for learning interatomic interactions. We model RNA as a graph in a coarse-grained, five-atom representation and evaluate our approach on a dataset of small RNA substructures, known as local RNA descriptors, which recur even in non-homologous structures. Generalization is assessed using a dataset partitioned by RNA family: the training set consists of rRNA and tRNA structures, while the test set includes descriptors from all other families. Our results demonstrate that the proposed method reliably predicts the structures of unseen descriptors and effectively adheres to user-defined constraints, such as Watson-Crick-Franklin interactions.Availability and implementation: The GraphaRNA source code is available on GitHub (github.com/mjustynaPhD/GraphaRNA); training/test datasets and pre-trained model weights are provided on Zenodo (zenodo.org/records/13750967).","PeriodicalId":93899,"journal":{"name":"Bioinformatics (Oxford, England)","volume":" ","pages":""},"PeriodicalIF":5.4,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12472125/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145093118","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

MRDagent: iterative and adaptive parameter optimization for stable ctDNA-based MRD detection in heterogeneous samples. MRDagent：迭代和自适应参数优化稳定的基于ctdna的MRD检测在异质样品。

IF 5.4

Bioinformatics (Oxford, England) Pub Date : 2025-09-01 DOI: 10.1093/bioinformatics/btaf485

Tianci Wang, Xin Lai, Shenjie Wang, Yuqian Liu, Xiaoyan Zhu, Jiayin Wang

{"title":"MRDagent: iterative and adaptive parameter optimization for stable ctDNA-based MRD detection in heterogeneous samples.","authors":"Tianci Wang, Xin Lai, Shenjie Wang, Yuqian Liu, Xiaoyan Zhu, Jiayin Wang","doi":"10.1093/bioinformatics/btaf485","DOIUrl":"10.1093/bioinformatics/btaf485","url":null,"abstract":"Motivation: Minimal residual disease (MRD) as critical biomarker for cancer prognosis and management plays a crucial role in improving patient outcomes. However, detecting MRD via next-generation sequencing-based circulating tumor DNA variant calling remains unstable due to the extremely low variant allele frequency and significant inter- and intra-sample heterogeneity. Although parameter optimization can theoretically enhance the detection performance of variants, achieving stable MRD detection remains challenging due to three key factors: (i) the necessity for individualized parameter tuning across numerous heterogeneous genomic intervals within each sample, (ii) the tightly interdependent parameter requirements across different stages of variant detection workflows, and (iii) the limitations of current automated parameter optimization methods.Results: In this study, we propose MRDagent, a novel variant detection tool designed specifically for MRD detection. MRDagent incorporates an iterative and self-adaptive optimization framework capable of handling unknown objectives, varying constraints, and highly coupled parameters across stages. A key innovation of MRDagent is the integration of a convolutional neural network-based meta-model, trained on historical data to enable rapid parameter prediction. This significantly enhances computational efficiency and generalization performance. Extensive evaluations on simulated and real-world datasets demonstrate MRDagent's superior and stable performance, providing an efficient, reliable solution for MRD detection in clinical and high-throughput research applications.Availability and implementation: MRDagent is freely available at https://github.com/aAT0047/MRDagent.git. The corresponding dataset and software archive are available at Zenodo: https://doi.org/10.5281/zenodo.15458496.","PeriodicalId":93899,"journal":{"name":"Bioinformatics (Oxford, England)","volume":" ","pages":""},"PeriodicalIF":5.4,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12462387/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144982366","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

PEtab.jl: advancing the efficiency and utility of dynamic modelling. PEtab。[1]：提高动态建模的效率和效用。

IF 5.4

Bioinformatics (Oxford, England) Pub Date : 2025-09-01 DOI: 10.1093/bioinformatics/btaf497

Sebastian Persson, Fabian Fröhlich, Stephan Grein, Torkel Loman, Damiano Ognissanti, Viktor Hasselgren, Jan Hasenauer, Marija Cvijovic

{"title":"PEtab.jl: advancing the efficiency and utility of dynamic modelling.","authors":"Sebastian Persson, Fabian Fröhlich, Stephan Grein, Torkel Loman, Damiano Ognissanti, Viktor Hasselgren, Jan Hasenauer, Marija Cvijovic","doi":"10.1093/bioinformatics/btaf497","DOIUrl":"10.1093/bioinformatics/btaf497","url":null,"abstract":"Summary: Dynamic models represent a powerful tool for studying complex biological processes, ranging from cell signalling to cell differentiation. Building such models often requires computationally demanding modelling workflows, such as model exploration and parameter estimation. We developed two Julia-based tools: SBMLImporter.jl, an SBML importer, and PEtab.jl, an importer for parameter estimation problems in the PEtab format, designed to streamline modelling processes. These tools leverage Julia's high-performance computing capabilities, including symbolic pre-processing and advanced ODE solvers. PEtab.jl aims to be a Julia-accessible toolbox that supports the entire modelling pipeline from parameter estimation to identifiability analysis.Availability and implementation: SBMLImporter.jl and PEtab.jl are implemented in the Julia programming language. Both packages are available on GitHub (github.com/sebapersson/SBMLImporter.jl and github.com/sebapersson/PEtab.jl) as officially registered Julia packages, installable via the Julia package manager. Each package is continuously tested and supported on Linux, macOS, and Windows.","PeriodicalId":93899,"journal":{"name":"Bioinformatics (Oxford, England)","volume":" ","pages":""},"PeriodicalIF":5.4,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12457741/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145031483","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

MVSO-PPIS: a structured objective learning model for protein-protein interaction sites prediction via multi-view graph information integration. MVSO-PPIS：基于多视图图信息集成的蛋白质相互作用位点预测的结构化目标学习模型。

IF 5.4

Bioinformatics (Oxford, England) Pub Date : 2025-09-01 DOI: 10.1093/bioinformatics/btaf470

Shuang Wang, Tianle Ma, Kaiyu Dong, Peifu Han, Xue Li, Junteng Ma, Mao Li, Tao Song

{"title":"MVSO-PPIS: a structured objective learning model for protein-protein interaction sites prediction via multi-view graph information integration.","authors":"Shuang Wang, Tianle Ma, Kaiyu Dong, Peifu Han, Xue Li, Junteng Ma, Mao Li, Tao Song","doi":"10.1093/bioinformatics/btaf470","DOIUrl":"10.1093/bioinformatics/btaf470","url":null,"abstract":"Motivation: Predicting protein-protein interaction (PPI) sites is essential for advancing our understanding of protein interactions, as accurate predictions can significantly reduce experimental costs and time. While considerable progress has been made in identifying binding sites at the level of individual amino acid residues, the prediction accuracy for residue subsequences at transitional boundaries-such as those represented by patterns like singular structures (mutation characteristics of contiguous interacting-residue segments) or edge structures (boundary transitions between interacting/non-interacting residue segments) still requires improvement.Results: we propose a novel PPI site prediction method named MVSO-PPIS. This method integrates two complementary feature extraction modules, a subgraph-based module and an enhanced graph attention module. The extracted features are fused using an attention-based fusion mechanism, producing a composite representation that captures both local protein substructures and global contextual dependencies. MVSO-PPIS is trained to jointly optimize three objectives: overall PPI site prediction accuracy, edge structural consistency, and recognition of unique structural patterns in PPI site sequences. Experimental results on benchmark datasets demonstrate that MVSO-PPIS outperforms existing baseline models in both accuracy and structural interpretability.Availability and implementation: The datasets, source codes, and models of MVSO-PPIS are all available at https://github.com/Edwardblue282/MVSO-PPIS.","PeriodicalId":93899,"journal":{"name":"Bioinformatics (Oxford, England)","volume":" ","pages":""},"PeriodicalIF":5.4,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12462378/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144982384","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0