AlphaFold激酶优化器：通过自动优化基于AlphaFold的激酶结构来增强虚拟筛选性能。

IF 2.8 4区生物学 Q2 BIOCHEMISTRY & MOLECULAR BIOLOGY

Proteins-Structure Function and Bioinformatics Pub Date : 2025-09-16 DOI:10.1002/prot.70056

Sergei Evteev, Yan Ivanenkov, Andrew Aiginin, Maksim Kuznetsov, Rim Shayakhmetov, Maksim Knyazev, Dmitry Bezrukov, Alex Malyshev, Maxim Malkov, Alex Aliper, Alex Zhavoronkov

{"title":"AlphaFold激酶优化器：通过自动优化基于AlphaFold的激酶结构来增强虚拟筛选性能。","authors":"Sergei Evteev, Yan Ivanenkov, Andrew Aiginin, Maksim Kuznetsov, Rim Shayakhmetov, Maksim Knyazev, Dmitry Bezrukov, Alex Malyshev, Maxim Malkov, Alex Aliper, Alex Zhavoronkov","doi":"10.1002/prot.70056","DOIUrl":null,"url":null,"abstract":"AlphaFold (AF) is a valuable tool for generating protein 3D structures, but its application in structure-based drug design is limited. In this study, we introduce AF Optimizer-a new deep learning-assisted approach that refines binding site geometry based on neural network scores and calculated free binding energy. We refined TTK protein geometry using AF Optimizer and performed virtual screening using the optimized version of the AF-generated protein model. The application of the model showed a decrease in steric clashes with ligands from known crystal complexes, more precise results of molecular docking and virtual screening, and hits enrichment during a prospective in vitro study.","PeriodicalId":56271,"journal":{"name":"Proteins-Structure Function and Bioinformatics","volume":" ","pages":""},"PeriodicalIF":2.8000,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"AlphaFold Kinase Optimizer: Enhancing Virtual Screening Performance Through Automated Refinement of AlphaFold-Based Kinase Structures.\",\"authors\":\"Sergei Evteev, Yan Ivanenkov, Andrew Aiginin, Maksim Kuznetsov, Rim Shayakhmetov, Maksim Knyazev, Dmitry Bezrukov, Alex Malyshev, Maxim Malkov, Alex Aliper, Alex Zhavoronkov\",\"doi\":\"10.1002/prot.70056\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"AlphaFold (AF) is a valuable tool for generating protein 3D structures, but its application in structure-based drug design is limited. In this study, we introduce AF Optimizer-a new deep learning-assisted approach that refines binding site geometry based on neural network scores and calculated free binding energy. We refined TTK protein geometry using AF Optimizer and performed virtual screening using the optimized version of the AF-generated protein model. The application of the model showed a decrease in steric clashes with ligands from known crystal complexes, more precise results of molecular docking and virtual screening, and hits enrichment during a prospective in vitro study.\",\"PeriodicalId\":56271,\"journal\":{\"name\":\"Proteins-Structure Function and Bioinformatics\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":2.8000,\"publicationDate\":\"2025-09-16\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proteins-Structure Function and Bioinformatics\",\"FirstCategoryId\":\"99\",\"ListUrlMain\":\"https://doi.org/10.1002/prot.70056\",\"RegionNum\":4,\"RegionCategory\":\"生物学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"BIOCHEMISTRY & MOLECULAR BIOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proteins-Structure Function and Bioinformatics","FirstCategoryId":"99","ListUrlMain":"https://doi.org/10.1002/prot.70056","RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"BIOCHEMISTRY & MOLECULAR BIOLOGY","Score":null,"Total":0}

引用次数: 0

摘要

AlphaFold （AF）是生成蛋白质三维结构的宝贵工具，但其在基于结构的药物设计中的应用受到限制。在这项研究中，我们引入了AF优化器——一种新的深度学习辅助方法，它基于神经网络评分和计算的自由结合能来优化结合位点的几何形状。我们使用AF Optimizer优化了TTK蛋白的几何形状，并使用AF生成的蛋白模型的优化版本进行了虚拟筛选。该模型的应用表明，在前瞻性的体外研究中，该模型减少了与已知晶体配合物配体的空间冲突，分子对接和虚拟筛选的结果更加精确，命中富集。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

AlphaFold Kinase Optimizer: Enhancing Virtual Screening Performance Through Automated Refinement of AlphaFold-Based Kinase Structures.

AlphaFold (AF) is a valuable tool for generating protein 3D structures, but its application in structure-based drug design is limited. In this study, we introduce AF Optimizer-a new deep learning-assisted approach that refines binding site geometry based on neural network scores and calculated free binding energy. We refined TTK protein geometry using AF Optimizer and performed virtual screening using the optimized version of the AF-generated protein model. The application of the model showed a decrease in steric clashes with ligands from known crystal complexes, more precise results of molecular docking and virtual screening, and hits enrichment during a prospective in vitro study.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Proteins-Structure Function and Bioinformatics 生物-生化与分子生物学

CiteScore

5.90

自引率

3.40%

发文量

172

审稿时长

3 months

期刊介绍： PROTEINS : Structure, Function, and Bioinformatics publishes original reports of significant experimental and analytic research in all areas of protein research: structure, function, computation, genetics, and design. The journal encourages reports that present new experimental or computational approaches for interpreting and understanding data from biophysical chemistry, structural studies of proteins and macromolecular assemblies, alterations of protein structure and function engineered through techniques of molecular biology and genetics, functional analyses under physiologic conditions, as well as the interactions of proteins with receptors, nucleic acids, or other specific ligands or substrates. Research in protein and peptide biochemistry directed toward synthesizing or characterizing molecules that simulate aspects of the activity of proteins, or that act as inhibitors of protein function, is also within the scope of PROTEINS. In addition to full-length reports, short communications (usually not more than 4 printed pages) and prediction reports are welcome. Reviews are typically by invitation; authors are encouraged to submit proposed topics for consideration.