Proteins-Structure Function and Bioinformatics最新文献

筛选
英文 中文
Engaging the Community: CASP Special Interest Groups. 参与社区:CASP特别兴趣小组。
IF 3.2 4区 生物学
Proteins-Structure Function and Bioinformatics Pub Date : 2025-04-30 DOI: 10.1002/prot.26833
Arne Elofsson, Rachael C Kretsch, Marcin Magnus, Gaetano T Montelione
{"title":"Engaging the Community: CASP Special Interest Groups.","authors":"Arne Elofsson, Rachael C Kretsch, Marcin Magnus, Gaetano T Montelione","doi":"10.1002/prot.26833","DOIUrl":"https://doi.org/10.1002/prot.26833","url":null,"abstract":"<p><p>The Critical Assessment of Structure Prediction (CASP) brings together a diverse group of scientists, from deep learning experts to NMR specialists, all aimed at developing accurate prediction algorithms that can effectively characterize the structural aspects of biomolecules relevant to their functions. Engagement within the CASP community has traditionally been limited to the prediction season and the conference, with limited discourse in the 1.5 years between CASP seasons. CASP special interest groups (SIGs) were established in 2023 to encourage continuous dialogue within the community. The online seminar series has drawn global participation from across disciplines and career stages. This has facilitated cross-disciplinary discussions fostering collaborations. The archives of these seminars have become a vital learning tool for newcomers to the field, lowering the barrier to entry.</p>","PeriodicalId":56271,"journal":{"name":"Proteins-Structure Function and Bioinformatics","volume":" ","pages":""},"PeriodicalIF":3.2,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144043417","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Structure and Dynamics of Cannabinoid Binding to the GABAA Receptor. 大麻素与GABAA受体结合的结构和动力学。
IF 3.2 4区 生物学
Proteins-Structure Function and Bioinformatics Pub Date : 2025-04-24 DOI: 10.1002/prot.26831
Lautaro Damian Alvarez, N R Carina Alves
{"title":"Structure and Dynamics of Cannabinoid Binding to the GABA<sub>A</sub> Receptor.","authors":"Lautaro Damian Alvarez, N R Carina Alves","doi":"10.1002/prot.26831","DOIUrl":"https://doi.org/10.1002/prot.26831","url":null,"abstract":"<p><p>Research on medical cannabis is progressing, with several cannabinoids emerging as promising compounds for clinical use. The available evidence suggests that cannabinoids may modulate the glycine receptor (GlyR) and GABA<sub>A</sub> receptor, which are part of the pentameric ligand-gated ion channels (pLGICs) superfamily and facilitate chemical communication in the nervous system. In a previous study, we employed molecular dynamics (MD) simulations to elucidate the dynamics of the GlyR/Δ<sup>9</sup>-tetrahydrocannabinol (THC) complex and successfully identified a representative binding mode. Given the structural similarity between GlyR and GABA<sub>A</sub>R, we employed a similar strategy to investigate GABA<sub>A</sub>R-cannabinoid interactions. We initially assessed the binding mode of THC to GABA<sub>A</sub>R-α1β2γ2 at the equivalent binding site of the GlyR-that is, on its two α-subunits-as well as the impact of this binding on the channel's dimensions. Our results indicate, first, that the binding modes of THC to GABA<sub>A</sub>R and GlyR exhibit comparable characteristics and, second, that THC may function as a potentiator of GABA activity due to a significant opening of the channel pore. Additionally, we aimed to reduce the overall computational cost associated with exploring binding modes. To this end, we developed and validated a simplified model comprising a single-monomer system for cannabinoid binding studies. This model proved to be accurate and cost-effective, accelerating the in silico screening process and allowing for the study of GABA<sub>A</sub>R-cannabinoid binding through docking and MD simulations. Moreover, the analysis of different cannabinoids in this system suggests that cannabigerol (CBG) and cannabichromene (CBC) could act as ligands for GABA<sub>A</sub>R, opening unexplored avenues for research.</p>","PeriodicalId":56271,"journal":{"name":"Proteins-Structure Function and Bioinformatics","volume":" ","pages":""},"PeriodicalIF":3.2,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144014204","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
In Silico Discovery of Potential Inhibitors Targeting the MEIG1-PACRG Complex for Male Contraceptive Development. 针对MEIG1-PACRG复合物的男性避孕药开发的潜在抑制剂的计算机发现。
IF 3.2 4区 生物学
Proteins-Structure Function and Bioinformatics Pub Date : 2025-04-23 DOI: 10.1002/prot.26829
Timothy Hasse, Zhibing Zhang, Yu-Ming M Huang
{"title":"In Silico Discovery of Potential Inhibitors Targeting the MEIG1-PACRG Complex for Male Contraceptive Development.","authors":"Timothy Hasse, Zhibing Zhang, Yu-Ming M Huang","doi":"10.1002/prot.26829","DOIUrl":"https://doi.org/10.1002/prot.26829","url":null,"abstract":"<p><p>The interaction between meiosis-expressed gene 1 (MEIG1) and Parkin co-regulated gene (PACRG) is a critical determinant of spermiogenesis, the process by which round spermatids mature into functional spermatozoa. Disruption of the MEIG1-PACRG complex can impair sperm development, highlighting its potential as a therapeutic target for addressing male infertility or for the development of non-hormonal contraceptive methods. This study used virtual screening, molecular docking, and molecular dynamics (MD) simulations to identify small molecule inhibitors targeting the MEIG1-PACRG interface. MD simulations provided representative protein conformations, which were used to virtually screen a library of 821 438 compounds, resulting in 48 high-ranking candidates for each protein. PACRG emerged as a favorable target due to its flexible binding pockets and better docking scores compared to MEIG1. Key binding residues with compounds included W50, Y68, N70, and E74 on MEIG1, and K93, W96, E101, and H137 on PACRG. MD simulations revealed that compound stability in MEIG1 complexes is primarily maintained by hydrogen bonding with E74 and π-π stacking interactions with W50 and Y68. In PACRG complexes, compound stabilization is facilitated by hydrogen bonding with E101 and π-π interactions involving W96 and H137. These findings highlight distinct molecular determinants of ligand binding for each protein. Our work provides mechanistic insights and identifies promising compounds for further experimental validation, establishing a foundation for developing MEIG1-PACRG interaction inhibitors as male contraceptives.</p>","PeriodicalId":56271,"journal":{"name":"Proteins-Structure Function and Bioinformatics","volume":" ","pages":""},"PeriodicalIF":3.2,"publicationDate":"2025-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144059657","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
β-ATPase of the Insect Panstrongylus megistus: Cloning, Bioinformatics Analysis, and Study of Its Interaction With Lipophorin. 昆虫大圆线虫β- atp酶的克隆、生物信息学分析及其与脂磷脂相互作用研究
IF 3.2 4区 生物学
Proteins-Structure Function and Bioinformatics Pub Date : 2025-04-23 DOI: 10.1002/prot.26830
Leonardo L Fruttero, Jimena Leyria, Rodrigo Ligabue-Braun, Pedro Clop, Pedro A Paglione, Maria A Perillo, Celia R Carlini, Estela Arrese, Lilián E Canavoso
{"title":"β-ATPase of the Insect Panstrongylus megistus: Cloning, Bioinformatics Analysis, and Study of Its Interaction With Lipophorin.","authors":"Leonardo L Fruttero, Jimena Leyria, Rodrigo Ligabue-Braun, Pedro Clop, Pedro A Paglione, Maria A Perillo, Celia R Carlini, Estela Arrese, Lilián E Canavoso","doi":"10.1002/prot.26830","DOIUrl":"https://doi.org/10.1002/prot.26830","url":null,"abstract":"<p><p>Lipophorin is the main lipoprotein of the insect's hemolymph. Although its role in lipid metabolism has been extensively analyzed, the mechanisms of lipid delivery to target tissues mediated by lipophorin are not completely understood. It has been reported that the β-chain of the ATP synthase complex (β-ATPase) acts as a nonendocytic receptor for lipophorin in the hematophagous insect Panstrongylus megistus, and this function is relevant for the transfer of lipids. The aim of this study was to gather new information regarding the β-ATPase, including its sequence and interaction with lipophorin. A β-ATPase cDNA encoding a 521-amino acid protein was cloned from P. megistus. β-ATPase is highly conserved, and molecular phylogenetic analyses grouped the deduced amino acid sequences according to their respective taxa. Structural modeling of β-ATPase revealed a conserved folding pattern and three-dimensional architecture that allows docking with a modeled lipophorin, suggesting potential interaction between the two proteins. Recombinant β-ATPase (rβ-ATPase) was expressed in Escherichia coli, and the rβ-ATPase was purified by affinity chromatography. rβ-ATPase was combined with lipophorin at various ratios, and the sedimentation properties of these mixtures were analyzed by analytical ultracentrifugation. The changes in sedimentation behavior of the protein mixture compared to that of the individual proteins are consistent with binding between rβ-ATPase and lipophorin. This finding, which confirms the interaction of β-ATPase and lipophorin, provides additional support for the role of β-ATPase in the uptake of lipids by tissues.</p>","PeriodicalId":56271,"journal":{"name":"Proteins-Structure Function and Bioinformatics","volume":" ","pages":""},"PeriodicalIF":3.2,"publicationDate":"2025-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144020676","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Assessing Structural Classification Using AlphaFold2 Models Through ECOD-Based Comparative Analysis. 通过基于ecod的比较分析,使用AlphaFold2模型评估结构分类。
IF 3.2 4区 生物学
Proteins-Structure Function and Bioinformatics Pub Date : 2025-04-19 DOI: 10.1002/prot.26828
Takeshi Kawabata, Kengo Kinoshita
{"title":"Assessing Structural Classification Using AlphaFold2 Models Through ECOD-Based Comparative Analysis.","authors":"Takeshi Kawabata, Kengo Kinoshita","doi":"10.1002/prot.26828","DOIUrl":"https://doi.org/10.1002/prot.26828","url":null,"abstract":"<p><p>Identifying homologous proteins is a fundamental task in structural bioinformatics. While AlphaFold2 has revolutionized protein structure prediction, the extent to which structure comparison of its models can reliably detect homologs remains unclear. In this study, we evaluate the feasibility of homology detection using AlphaFold2-predicted structures through structural comparisons. We considered the classification of the ECOD database for experimental structures as the correct standard and obtained their corresponding predicted models from AlphaFoldDB. To ensure blind assessment, we divided the structures into test and train sets according to their release date. Predicted and experimental 3D structures in the test and train sets were compared using 3D structure comparisons (MATRAS, Dali, and Foldseek) and sequence comparisons (BLAST and HHsearch). The results were evaluated based on the homology annotations in the ECOD database. For top-1 accuracy, the performance of structural comparisons was comparable to that of HHsearch. However, when considering metrics that included all structural pairs, including more remote homology, structural comparisons outperformed HHsearch. No significant differences were observed between comparisons of experimental versus experimental, predicted versus experimental, and predicted versus predicted structures with pLDDT (prediction confidence) values greater than 60. We also demonstrate that predicted protein structures, determined by NMR, had lower pLDDT values and contained fewer coils than their experimental counterparts. These findings highlight the potential of AlphaFold2 models in structural classification and suggest that 3D structural searches should be conducted not only against the PDB but also against AlphaFoldDB to identify more potential homologs.</p>","PeriodicalId":56271,"journal":{"name":"Proteins-Structure Function and Bioinformatics","volume":" ","pages":""},"PeriodicalIF":3.2,"publicationDate":"2025-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144035619","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Prediction and Evaluation of Coronavirus and Human Protein-Protein Interactions Integrating Five Different Computational Methods. 冠状病毒与人类蛋白质相互作用的预测与评价——整合五种不同计算方法
IF 3.2 4区 生物学
Proteins-Structure Function and Bioinformatics Pub Date : 2025-04-15 DOI: 10.1002/prot.26826
Binghua Li, Xiaoyu Li, Xian Tang, Jia Wang
{"title":"Prediction and Evaluation of Coronavirus and Human Protein-Protein Interactions Integrating Five Different Computational Methods.","authors":"Binghua Li, Xiaoyu Li, Xian Tang, Jia Wang","doi":"10.1002/prot.26826","DOIUrl":"https://doi.org/10.1002/prot.26826","url":null,"abstract":"<p><p>The high lethality and infectiousness of coronaviruses, particularly SARS-Cov-2, pose a significant threat to human society. Understanding coronaviruses, especially the interactions between these viruses and humans, is crucial for mitigating the coronavirus pandemic. In this study, we conducted a comprehensive comparison and evaluation of five prevalent computational methods: interolog mapping, domain-domain interaction methodology, domain-motif interaction methodology, structure-based approaches, and machine learning techniques. These methods were assessed using unbiased datasets that include C1, C2h, C2v, and C3 test sets. Ultimately, we integrated these five methodologies into a unified model for predicting protein-protein interactions (PPIs) between coronaviruses and human proteins. Our final model demonstrates relatively better performance, particularly with the C2v and C3 test sets, which are frequently used datasets in practical applications. Based on this model, we further established a high-confidence PPI network between coronaviruses and humans, consisting of 18,012 interactions between 3843 human proteins and 129 coronavirus proteins. The reliability of our predictions was further validated through the current knowledge framework and network analysis. This study is anticipated to enhance mechanistic understanding of the coronavirus-human relationship a while facilitating the rediscovery of antiviral drug targets. The source codes and datasets are accessible at https://github.com/covhppilab/CoVHPPI.</p>","PeriodicalId":56271,"journal":{"name":"Proteins-Structure Function and Bioinformatics","volume":" ","pages":""},"PeriodicalIF":3.2,"publicationDate":"2025-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144014202","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Protein-RNA Docking Benchmark v3.0 Integrated With Binding Affinity. 结合亲和力的蛋白质- rna对接基准v3.0
IF 3.2 4区 生物学
Proteins-Structure Function and Bioinformatics Pub Date : 2025-04-09 DOI: 10.1002/prot.26825
Shri Kant, Chandran Nithin, Sunandan Mukherjee, Atanu Maity, Ranjit Prasad Bahadur
{"title":"Protein-RNA Docking Benchmark v3.0 Integrated With Binding Affinity.","authors":"Shri Kant, Chandran Nithin, Sunandan Mukherjee, Atanu Maity, Ranjit Prasad Bahadur","doi":"10.1002/prot.26825","DOIUrl":"https://doi.org/10.1002/prot.26825","url":null,"abstract":"<p><p>We introduce an updated non-redundant protein-RNA docking benchmark version 3.0 (PRDBv3.0) containing 197 test cases curated from 288 unique protein-RNA complexes available in the Protein Data Bank until July 2024. Among these, 27 are unbound-unbound (UU) type where both the binding partners are available in their unbound states, 160 are unbound-bound (UB) type where only the protein is available in unbound state and remaining 10 are bound-unbound (BU) type where only the RNA is available in unbound state. The benchmark is categorized into three classes based on the conformational flexibility of the protein interface: 117 rigid-body (R) complexes with minimal structural changes, 41 semi-flexible (S) complexes showing moderate conformational changes and 29 full-flexible (F) complexes with significant conformational changes. The current benchmark represents a 62% increase in the number of test cases compared to its previous version. Binding affinity (K<sub>d</sub>) values for a subset of 105 protein-RNA complexes from PRDBv3.0 are catalogued along with additional experimental details to develop a comprehensive protein-RNA affinity benchmark. Moreover, a total of 255 unique RNA-binding domains, present in RNA-binding proteins, are also catalogued in this updated benchmark. PRDBv3.0 will facilitate the evaluation of both rigid-body and flexible docking methods as well as the methods that aim to predict binding affinity. The updated benchmark is freely available at http://www.csb.iitkgp.ac.in/applications/PRDBv3/PRDBv3.php.</p>","PeriodicalId":56271,"journal":{"name":"Proteins-Structure Function and Bioinformatics","volume":" ","pages":""},"PeriodicalIF":3.2,"publicationDate":"2025-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143813025","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Protein-Ligand Structure and Affinity Prediction in CASP16 Using a Geometric Deep Learning Ensemble and Flow Matching. 基于几何深度学习集成和流匹配的CASP16蛋白-配体结构和亲和力预测
IF 3.2 4区 生物学
Proteins-Structure Function and Bioinformatics Pub Date : 2025-04-08 DOI: 10.1002/prot.26827
Alex Morehead, Jian Liu, Pawan Neupane, Nabin Giri, Jianlin Cheng
{"title":"Protein-Ligand Structure and Affinity Prediction in CASP16 Using a Geometric Deep Learning Ensemble and Flow Matching.","authors":"Alex Morehead, Jian Liu, Pawan Neupane, Nabin Giri, Jianlin Cheng","doi":"10.1002/prot.26827","DOIUrl":"https://doi.org/10.1002/prot.26827","url":null,"abstract":"<p><p>Predicting the structure of ligands bound to proteins is a foundational problem in modern biotechnology and drug discovery, yet little is known about how to combine the predictions of protein-ligand structure (poses) produced by the latest deep learning methods to identify the best poses and how to accurately estimate the binding affinity between a protein target and a list of ligand candidates. Further, a blind benchmarking and assessment of protein-ligand structure and binding affinity prediction is necessary to ensure it generalizes well to new settings. Towards this end, we introduce MULTICOM_ligand, a deep learning-based protein-ligand structure and binding affinity prediction ensemble featuring structural consensus ranking for unsupervised pose ranking and a new deep generative flow matching model for joint structure and binding affinity prediction. Notably, MULTICOM_ligand ranked among the top-5 ligand prediction methods in both protein-ligand structure prediction and binding affinity prediction in the 16th Critical Assessment of Techniques for Structure Prediction (CASP16), demonstrating its efficacy and utility for real-world drug discovery efforts. The source code for MULTICOM_ligand is freely available on GitHub.</p>","PeriodicalId":56271,"journal":{"name":"Proteins-Structure Function and Bioinformatics","volume":" ","pages":""},"PeriodicalIF":3.2,"publicationDate":"2025-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143804833","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Homocysteine Thiolactone Modification of Ribonuclease A: Thermodynamics and Kinetics. 同半胱氨酸硫内酯修饰核糖核酸酶 A:热力学和动力学。
IF 3.2 4区 生物学
Proteins-Structure Function and Bioinformatics Pub Date : 2025-04-04 DOI: 10.1002/prot.26824
Kabira Sabnam, Swagata Dasgupta
{"title":"Homocysteine Thiolactone Modification of Ribonuclease A: Thermodynamics and Kinetics.","authors":"Kabira Sabnam, Swagata Dasgupta","doi":"10.1002/prot.26824","DOIUrl":"https://doi.org/10.1002/prot.26824","url":null,"abstract":"<p><p>Homocysteine thiolactone is a metabolite associated with various diseases at elevated levels in humans. Lysine residues in proteins are modified through N-homocysteinylation and homocysteinylated proteins are prone to form dimers and oligomers through disulfide cross-linkages. This study investigates the effects of N-homocysteinylation on Ribonuclease A (RNase A). The formation of dimers and higher oligomers in RNase A have been confirmed by SDS-PAGE and MALDI-ToF. Agarose-gel assays revealed an altered ribonucleolytic activity due to Lys modification. Fluorescence spectroscopy indicates local changes in the Tyr microenvironment. CD melting studies reveal that β-sheet formation is slightly enhanced with a reduction in the α-helical content in case of modified RNase A. However, the similar melting temperature of both native and modified RNase A indicates overall structural integrity with local changes in secondary structural components. ITC and UV-visible kinetics show reduced ribonucleolytic activity in homocysteinylated RNase A compared to the unmodified enzyme. These findings provide insights into the structural and functional consequences of RNase A homocysteinylation, contributing to our understanding of hyperhomocysteinemia-related pathologies.</p>","PeriodicalId":56271,"journal":{"name":"Proteins-Structure Function and Bioinformatics","volume":" ","pages":""},"PeriodicalIF":3.2,"publicationDate":"2025-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143782132","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Enhancing Enzyme Commission Number Prediction With Contrastive Learning and Agent Attention. 利用对比学习和智能体注意增强酶委托数预测。
IF 3.2 4区 生物学
Proteins-Structure Function and Bioinformatics Pub Date : 2025-04-02 DOI: 10.1002/prot.26822
Wendi Zhao, Qiaoling Han, Fan Yang, Yue Zhao
{"title":"Enhancing Enzyme Commission Number Prediction With Contrastive Learning and Agent Attention.","authors":"Wendi Zhao, Qiaoling Han, Fan Yang, Yue Zhao","doi":"10.1002/prot.26822","DOIUrl":"https://doi.org/10.1002/prot.26822","url":null,"abstract":"<p><p>The accurate prediction of enzyme function is crucial for elucidating disease mechanisms and identifying drug targets. Nevertheless, existing enzyme commission (EC) number prediction methods are limited by database coverage and the depth of sequence information mining, hindering the efficiency and precision of enzyme function annotation. Therefore, this study introduces ProteEC-CLA (Protein EC number prediction model with Contrastive Learning and Agent Attention). ProteEC-CLA utilizes contrastive learning to construct positive and negative sample pairs, which not only enhances sequence feature extraction but also improves the utilization of unlabeled data. This process helps the model learn the differences in sequence features, thereby enhancing its ability to predict enzyme function. Integrating the pre-trained protein language model ESM2, the model generates informative sequence embeddings for deep functional correlation analysis, significantly enhancing prediction accuracy. With the incorporation of the Agent Attention mechanism, ProteEC-CLA's ability to comprehensively capture local details and global features is enhanced, ensuring high-accuracy predictions on complex sequences. The results demonstrate that ProteEC-CLA performs exceptionally well on two independent and representative datasets. In the standard dataset, it achieves 98.92% accuracy at the EC4 level. In the more challenging clustered split dataset, ProteEC-CLA achieves 93.34% accuracy and an F1-score of 94.72%. With only enzyme sequences as input, ProteEC-CLA can accurately predict EC numbers up to the fourth level, significantly enhancing annotation efficiency and accuracy, which makes it a highly efficient and precise functional annotation tool for enzymology research and applications.</p>","PeriodicalId":56271,"journal":{"name":"Proteins-Structure Function and Bioinformatics","volume":" ","pages":""},"PeriodicalIF":3.2,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143764399","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信