Protein complex prediction with AlphaFold-Multimer
Open Access
- 4 October 2021
- preprint content
- research article
- Published by Cold Spring Harbor Laboratory
Abstract
While the vast majority of well-structured single protein chains can now be predicted to high accuracy due to the recent AlphaFold [1] model, the prediction of multi-chain protein complexes remains a challenge in many cases. In this work, we demonstrate that an AlphaFold model trained specifically for multimeric inputs of known stoichiometry, which we call AlphaFold-Multimer, significantly increases accuracy of predicted multimeric interfaces over input-adapted single-chain AlphaFold while maintaining high intra-chain accuracy. On a benchmark dataset of 17 heterodimer proteins without templates (introduced in [2]) we achieve at least medium accuracy (DockQ [3] ≥ 0.49) on 13 targets and high accuracy (DockQ ≥ 0.8) on 7 targets, compared to 9 targets of at least medium accuracy and 4 of high accuracy for the previous state of the art system (an AlphaFold-based system from [2]). We also predict structures for a large dataset of 4,446 recent protein complexes, from which we score all non-redundant interfaces with low template identity. For heteromeric interfaces we successfully predict the interface (DockQ ≥ 0.23) in 70% of cases, and produce high accuracy predictions (DockQ ≥ 0.8) in 26% of cases, an improvement of +27 and +14 percentage points over the flexible linker modification of AlphaFold [4] respectively. For homomeric inter-faces we successfully predict the interface in 72% of cases, and produce high accuracy predictions in 36% of cases, an improvement of +8 and +7 percentage points respectively.Keywords
This publication has 24 references indexed in Scilit:
- The ClusPro web server for protein–protein dockingNature Protocols, 2017
- DockQ: A Quality Measure for Protein-Protein Docking ModelsPLOS ONE, 2016
- Sequence co-evolution gives 3D contacts and structures of protein complexeseLife, 2014
- Robust and accurate prediction of residue–residue interactions across protein interfaces using evolutionary informationeLife, 2014
- Mapping Monomeric Threading to Protein–Protein Structure PredictionJournal of Chemical Information and Modeling, 2013
- SwarmDock: a server for flexible protein–protein dockingBioinformatics, 2013
- Detection of gene pathways with predictive power for breast cancer prognosisBMC Bioinformatics, 2010
- TM-align: a protein structure alignment algorithm based on the TM-scoreNucleic Acids Research, 2005
- Detecting putative orthologsBioinformatics, 2003
- ZDOCK: An initial‐stage protein‐docking algorithmProteins, 2003