Geometric Transformers for Protein Interface Contact Prediction

by   Alex Morehead, et al.

Computational methods for predicting the interface contacts between proteins come highly sought after for drug discovery as they can significantly advance the accuracy of alternative approaches, such as protein-protein docking, protein function analysis tools, and other computational methods for protein bioinformatics. In this work, we present the Geometric Transformer, a novel geometry-evolving graph transformer for rotation and translation-invariant protein interface contact prediction, packaged within DeepInteract, an end-to-end prediction pipeline. DeepInteract predicts partner-specific protein interface contacts (i.e., inter-protein residue-residue contacts) given the 3D tertiary structures of two proteins as input. In rigorous benchmarks, DeepInteract, on challenging protein complex targets from the new Enhanced Database of Interacting Protein Structures (DIPS-Plus) and the 13th and 14th CASP-CAPRI experiments, achieves 17% and 13% top L/5 precision (L: length of a protein unit in a complex), respectively. In doing so, DeepInteract, with the Geometric Transformer as its graph-based backbone, outperforms existing methods for interface contact prediction in addition to other graph-based neural network backbones compatible with DeepInteract, thereby validating the effectiveness of the Geometric Transformer for learning rich relational-geometric features for downstream tasks on 3D protein structures.



There are no comments yet.


page 14


DIPS-Plus: The Enhanced Database of Interacting Protein Structures for Interface Prediction

How and where proteins interface with one another can ultimately impact ...

MEGADOCK-GUI: a GUI-based complete cross-docking tool for exploring protein-protein interactions

Information on protein-protein interactions (PPIs) not only advances our...

PGR: A Graph Repository of Protein 3D-Structures

Graph theory and graph mining constitute rich fields of computational te...

DProQ: A Gated-Graph Transformer for Protein Complex Structure Assessment

Proteins interact to form complexes to carry out essential biological fu...

Generalizable Protein Interface Prediction with End-to-End Learning

Predicting how proteins interact with one another - that is, which surfa...

Combining docking pose rank and structure with deep learning improves protein-ligand binding mode prediction

We present a simple, modular graph-based convolutional neural network th...

AlphaDesign: A graph protein design method and benchmark on AlphaFoldDB

While DeepMind has tentatively solved protein folding, its inverse probl...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.