DeepRank: a deep learning framework for data mining 3D protein-protein interfaces

Nicolas Renaud,Manon F Réau,Lars Ridder,Francesco Ambrosetti,Dario F Marzella,Cunliang Geng,Alexandre M J J Bonvin,Li C Xue,Sonja Georgievska

doi:10.1038/s41467-021-27396-0

Abstract

Three-dimensional (3D) structures of protein complexes provide fundamental information to decipher biological processes at the molecular scale. The vast amount of experimentally and computationally resolved protein-protein interfaces (PPIs) offers the possibility of training deep learning models to aid the predictions of their biological relevance. We present here DeepRank, a general, configurable deep learning framework for data mining PPIs using 3D convolutional neural networks (CNNs). DeepRank maps features of PPIs onto 3D grids and trains a user-specified CNN on these 3D grids. DeepRank allows for efficient training of 3D CNNs with data sets containing millions of PPIs and supports both classification and regression. We demonstrate the performance of DeepRank on two distinct challenges: The classification of biological versus crystallographic PPIs, and the ranking of docking models. For both problems DeepRank is competitive with, or outperforms, state-of-the-art methods, demonstrating the versatility of the framework for research in structural biology.

Highlights

Three-dimensional (3D) structures of protein complexes provide fundamental information to decipher biological processes at the molecular scale
One outstanding illustration of the potential of deep neural networks in structural biology is the recent breakthrough in single-chain protein structure predictions by AlphaFold[210–12] in the latest CASP14 (Critical Assessment of protein Structure Prediction round 14)
We present the performance of DeepRank for the scoring of models of proteinprotein complexes generated by computational docking

Summary

Introduction

Three-dimensional (3D) structures of protein complexes provide fundamental information to decipher biological processes at the molecular scale. We present here DeepRank, a general, configurable deep learning framework for data mining PPIs using 3D convolutional neural networks (CNNs). We demonstrate the performance of DeepRank on two distinct challenges: The classification of biological versus crystallographic PPIs, and the ranking of docking models For both problems DeepRank is competitive with, or outperforms, state-of-the-art methods, demonstrating the versatility of the framework for research in structural biology. Predicting the 3D structure of protein complexes remains an open challenge: in CASP14 no single assembly was correctly predicted unless a known template was available This calls for open-source frameworks that can be modified and extended by the community for data mining protein complexes and can expedite knowledge discovery on related scientific questions. Some complexes may be driven by hydrophobicity, and others by electrostatic forces

Methods

Results

Conclusion