A deep learning framework to predict binding preference of RNA constituents on protein surface

Nat Commun. 2019 Oct 30;10(1):4941. doi: 10.1038/s41467-019-12920-0.

Abstract

Protein-RNA interaction plays important roles in post-transcriptional regulation. However, the task of predicting these interactions given a protein structure is difficult. Here we show that, by leveraging a deep learning model NucleicNet, attributes such as binding preference of RNA backbone constituents and different bases can be predicted from local physicochemical characteristics of protein structure surface. On a diverse set of challenging RNA-binding proteins, including Fem-3-binding-factor 2, Argonaute 2 and Ribonuclease III, NucleicNet can accurately recover interaction modes discovered by structural biology experiments. Furthermore, we show that, without seeing any in vitro or in vivo assay data, NucleicNet can still achieve consistency with experiments, including RNAcompete, Immunoprecipitation Assay, and siRNA Knockdown Benchmark. NucleicNet can thus serve to provide quantitative fitness of RNA sequences for given binding pockets or to predict potential binding pockets and binding RNAs for previously unknown RNA binding proteins.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Adenine / metabolism
  • Animals
  • Area Under Curve
  • Argonaute Proteins / metabolism*
  • Cytosine / metabolism
  • Deep Learning*
  • Gene Knockdown Techniques
  • Guanine / metabolism
  • Humans
  • Mice
  • Phosphates / metabolism
  • Protein Binding
  • RNA / metabolism*
  • RNA, Small Interfering
  • RNA-Binding Proteins / metabolism
  • ROC Curve
  • Ribonuclease III / metabolism*
  • Ribose / metabolism
  • Uracil / metabolism

Substances

  • Argonaute Proteins
  • Phosphates
  • RNA, Small Interfering
  • RNA-Binding Proteins
  • Uracil
  • Guanine
  • RNA
  • Ribose
  • Cytosine
  • Ribonuclease III
  • Adenine