AF3复合物可提高蛋白质复合物的结构预测能力。

AF3Complex Yields Improved Structural Predictions of Protein Complexes.

作者信息

Feldman Jonathan, Skolnick Jeffrey

机构信息

Center for the Study of Systems Biology/School of Biological Sciences, Georgia Institute of Technology, 950 Atlantic Drive, 30332, Georgia.

School of Computer Science, Georgia Institute of Technology, 266 Ferst Dr, Atlanta, 30332, Georgia.

出版信息

bioRxiv. 2025 Mar 3:2025.02.27.640585. doi: 10.1101/2025.02.27.640585.

DOI:10.1101/2025.02.27.640585

PMID:40093092

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11908126/

Abstract

MOTIVATION

Accurate structures of protein complexes are essential for understanding biological pathway function. A previous study showed how downstream modifications to AlphaFold 2 could yield AF2Complex, a model better suited for protein complexes. Here, we introduce AF3Complex, a model equipped with the same improvements as AF2Complex, along with a novel method for excluding ligands, built on AlphaFold 3.

RESULTS

Benchmarking AF3Complex and AlphaFold 3 on a large dataset of protein complexes, it was shown that AF3Complex outperforms AlphaFold 3 to a significant degree. Moreover, by evaluating the structures generated by AF3Complex on a dataset of protein-peptide complexes and antibody-antigen complexes, it was established that AF3Complex could create high-fidelity structures for these challenging complex types. Additionally, when deployed to generate structural predictions for the two antibody-antigen and seven protein-protein complexes used in the recent CASP16 competition, AF3Complex yielded structures that would have placed it among the top models in the competition.

AVAILABILITY

The AF3Complex code is freely available at https://github.com/Jfeldman34/AF3Complex.git.

CONTACT

Please contact skolnick@gatech.edu.

摘要

动机

蛋白质复合物的精确结构对于理解生物途径功能至关重要。先前的一项研究展示了对AlphaFold 2进行下游修改如何产生AF2Complex，这是一种更适合蛋白质复合物的模型。在此，我们引入AF3Complex，一种配备了与AF2Complex相同改进的模型，以及一种基于AlphaFold 3的排除配体的新方法。

结果

在一个大型蛋白质复合物数据集上对AF3Complex和AlphaFold 3进行基准测试，结果表明AF3Complex在很大程度上优于AlphaFold 3。此外，通过在蛋白质-肽复合物和抗体-抗原复合物数据集上评估AF3Complex生成的结构，确定AF3Complex可以为这些具有挑战性的复合物类型创建高保真结构。此外，当部署AF3Complex为最近的CASP16竞赛中使用的两个抗体-抗原复合物和七个蛋白质-蛋白质复合物生成结构预测时，AF3Complex生成的结构在竞赛中可使其跻身顶级模型之列。