Prediction of interresidue contacts with DeepMetaPSICOV in CASP13

Proteins. 2019 Dec;87(12):1092-1099. doi: 10.1002/prot.25779. Epub 2019 Jul 27.

Abstract

In this article, we describe our efforts in contact prediction in the CASP13 experiment. We employed a new deep learning-based contact prediction tool, DeepMetaPSICOV (or DMP for short), together with new methods and data sources for alignment generation. DMP evolved from MetaPSICOV and DeepCov and combines the input feature sets used by these methods as input to a deep, fully convolutional residual neural network. We also improved our method for multiple sequence alignment generation and included metagenomic sequences in the search. We discuss successes and failures of our approach and identify areas where further improvements may be possible. DMP is freely available at: https://github.com/psipred/DeepMetaPSICOV.

Keywords: deep learning; machine learning; metagenomics; neural networks; protein contact prediction; protein structure prediction.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Algorithms
  • Amino Acid Sequence / genetics
  • Computational Biology*
  • Deep Learning
  • Machine Learning
  • Metagenome / genetics
  • Neural Networks, Computer
  • Protein Conformation*
  • Proteins / chemistry
  • Proteins / genetics
  • Proteins / ultrastructure*
  • Sequence Analysis, Protein

Substances

  • Proteins