Rxivist logo

Structure-Based Function Prediction using Graph Convolutional Networks

By Vladimir Gligorijevic, P. Douglas Renfrew, Tomasz Kosciolek, Julia Koehler Leman, Kyunghyun Cho, Tommi Vatanen, Daniel Berenberg, Bryn Taylor, Ian M Fisk, Ramnik J. Xavier, Rob Knight, Richard Bonneau

Posted 04 Oct 2019
bioRxiv DOI: 10.1101/786236

Recent massive increases in the number of sequences available in public databases challenges current experimental approaches to determining protein function. These methods are limited by both the large scale of these sequences databases and the diversity of protein functions. We present a deep learning Graph Convolutional Network (GCN) trained on sequence and structural data and evaluate it on ~40k proteins with known structures and functions from the Protein Data Bank (PDB). Our GCN predicts functions more accurately than Convolutional Neural Networks trained on sequence data alone and competing methods. Feature extraction via a language model removes the need for constructing multiple sequence alignments or feature engineering. Our model learns general structure-function relationships by robustly predicting functions of proteins with ≤ 30% sequence identity to the training set. Using class activation mapping, we can automatically identify structural regions at the residue-level that lead to each function prediction for every protein confidently predicted, advancing site-specific function prediction. De-noising inherent in the trained model allows an only minor drop in performance when structure predictions are used, including multiple de novo protocols. We use our method to annotate all proteins in the PDB, making several new confident function predictions spanning both fold and function trees.

Download data

  • Downloaded 2,460 times
  • Download rankings, all-time:
    • Site-wide: 2,383 out of 83,960
    • In bioinformatics: 449 out of 8,046
  • Year to date:
    • Site-wide: 1,258 out of 83,960
  • Since beginning of last month:
    • Site-wide: 1,702 out of 83,960

Altmetric data

Downloads over time

Distribution of downloads per paper, site-wide


Sign up for the Rxivist weekly newsletter! (Click here for more details.)