AFsample: improving multimer prediction with AlphaFold using massive sampling.

IF 4.4 3区生物学 Q1 BIOCHEMICAL RESEARCH METHODS

Bioinformatics Pub Date : 2023-09-02 DOI:10.1093/bioinformatics/btad573

Björn Wallner

{"title":"AFsample: improving multimer prediction with AlphaFold using massive sampling.","authors":"Björn Wallner","doi":"10.1093/bioinformatics/btad573","DOIUrl":null,"url":null,"abstract":"Summary: The AlphaFold2 neural network model has revolutionized structural biology with unprecedented performance. We demonstrate that by stochastically perturbing the neural network by enabling dropout at inference combined with massive sampling, it is possible to improve the quality of the generated models. We generated ∼6000 models per target compared with 25 default for AlphaFold-Multimer, with v1 and v2 multimer network models, with and without templates, and increased the number of recycles within the network. The method was benchmarked in CASP15, and compared with AlphaFold-Multimer v2 it improved the average DockQ from 0.41 to 0.55 using identical input and was ranked at the very top in the protein assembly category when compared with all other groups participating in CASP15. The simplicity of the method should facilitate the adaptation by the field, and the method should be useful for anyone interested in modeling multimeric structures, alternate conformations, or flexible structures.Availability and implementation: AFsample is available online at http://wallnerlab.org/AFsample.","PeriodicalId":8903,"journal":{"name":"Bioinformatics","volume":" ","pages":""},"PeriodicalIF":4.4000,"publicationDate":"2023-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10534052/pdf/","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Bioinformatics","FirstCategoryId":"99","ListUrlMain":"https://doi.org/10.1093/bioinformatics/btad573","RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"BIOCHEMICAL RESEARCH METHODS","Score":null,"Total":0}

引用次数: 3

Abstract

Summary: The AlphaFold2 neural network model has revolutionized structural biology with unprecedented performance. We demonstrate that by stochastically perturbing the neural network by enabling dropout at inference combined with massive sampling, it is possible to improve the quality of the generated models. We generated ∼6000 models per target compared with 25 default for AlphaFold-Multimer, with v1 and v2 multimer network models, with and without templates, and increased the number of recycles within the network. The method was benchmarked in CASP15, and compared with AlphaFold-Multimer v2 it improved the average DockQ from 0.41 to 0.55 using identical input and was ranked at the very top in the protein assembly category when compared with all other groups participating in CASP15. The simplicity of the method should facilitate the adaptation by the field, and the method should be useful for anyone interested in modeling multimeric structures, alternate conformations, or flexible structures.

Availability and implementation: AFsample is available online at http://wallnerlab.org/AFsample.

Abstract Image

查看原文本刊更多论文

AFsample：使用大量采样改进AlphaFold的多聚体预测。

综述：AlphaFold2神经网络模型以前所未有的性能彻底改变了结构生物学。我们证明，通过使推理时的丢弃与大规模采样相结合，对神经网络进行随机扰动，可以提高生成模型的质量。我们为每个目标生成了约6000个模型，而AlphaFold Multimer的默认值为25个，具有v1和v2多机网络模型，有模板和没有模板，并增加了网络内的回收次数。该方法在CASP15中进行了基准测试，与AlphaFold Multimer v2相比，它使用相同的输入将平均DockQ从0.41提高到0.55，并且与参与CASP15的所有其他组相比，在蛋白质组装类别中排名最靠前。该方法的简单性应便于该领域的适应，并且该方法应适用于对多聚体结构、交替构象或柔性结构建模感兴趣的任何人。可用性和实施：AFsample可在线访问http://wallnerlab.org/AFsample.

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Bioinformatics 生物-生化研究方法

CiteScore

11.20

自引率

5.20%

发文量

753

审稿时长

2.1 months

期刊介绍： The leading journal in its field, Bioinformatics publishes the highest quality scientific papers and review articles of interest to academic and industrial researchers. Its main focus is on new developments in genome bioinformatics and computational biology. Two distinct sections within the journal - Discovery Notes and Application Notes- focus on shorter papers; the former reporting biologically interesting discoveries using computational methods, the latter exploring the applications used for experiments.