AUTHOR=Johansson-Åkhe Isak , Wallner Björn 

TITLE=Improving peptide-protein docking with AlphaFold-Multimer using forced sampling

JOURNAL=Frontiers in Bioinformatics

VOLUME=Volume 2 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/bioinformatics/articles/10.3389/fbinf.2022.959160

DOI=10.3389/fbinf.2022.959160

ISSN=2673-7647

ABSTRACT=Protein interactions are key in vital biological process. In many cases, particularly in regulation, this interaction is between a protein and a shorter peptide fragment. Such peptides are often part of larger disor- dered regions of other proteins. The flexible nature of peptides enables rapid, yet specific, regulation of important functions in the cell, such as the cell life-cycle. Because of this, knowledge of the molecular details of peptide-protein interactions is crucial to understand and alter their func- tion, and many specialized computational methods have been developed to study them.
The recent release of AlphaFold and AlphaFold-Multimer has caused a leap in accuracy for computational modeling of proteins. In this study, the ability of AlphaFold to predict which peptides and proteins interact, as well as its accuracy in modeling the resulting interaction complexes are benchmarked against established methods in the fields of peptide-protein interaction prediction and modeling.
We find that AlphaFold-Multimer predicts the structure of peptide- protein complexes with acceptable or better quality (DockQ≥0.23) for 66 of the 112 complexes investigated with 25 complexes of high quality (DockQ≥0.8). This is a massive improvement compared to previous methods with 23 or 47 acceptable models and only 4 or 8 high quality models using energy-based docking or interaction templates, respectively. In addition, AlphaFold-Multimer can be used to predict if a peptide and a protein will interact. At 1% false positives AlphaFold-Multimer founds 26% of the possible interactions with a precision of 85%, the best among the methods benchmarked.
However, the most interesting result is the possibility to improve Al- phaFold by randomly perturb the neural network weights to force the network to sample a wider part of the conformational space. This in- creases the number of acceptable models from 66 to 75 and improves the median DockQ from 0.47 to 0.55 (17%) for first ranked models. The best possible DockQ improves from 0.58 to 0.72 (24%) indicating that select- ing the best possible model is still a challenge. This scheme of generating more structures with AlphaFold should be generally useful for many ap- plications involving multiple states, flexible regions and disorder.