CENsible: Interpretable Insights into Small-Molecule Binding with Context Explanation Networks

J Chem Inf Model. 2024 Jun 24;64(12):4651-4660. doi: 10.1021/acs.jcim.4c00825. Epub 2024 Jun 7.

Abstract

We present a novel and interpretable approach for assessing small-molecule binding using context explanation networks. Given the specific structure of a protein/ligand complex, our CENsible scoring function uses a deep convolutional neural network to predict the contributions of precalculated terms to the overall binding affinity. We show that CENsible can effectively distinguish active vs inactive compounds for many systems. Its primary benefit over related machine-learning scoring functions, however, is that it retains interpretability, allowing researchers to identify the contribution of each precalculated term to the final affinity prediction, with implications for subsequent lead optimization.

MeSH terms

  • Ligands
  • Machine Learning
  • Neural Networks, Computer*
  • Protein Binding*
  • Proteins* / chemistry
  • Proteins* / metabolism
  • Small Molecule Libraries* / chemistry
  • Small Molecule Libraries* / metabolism
  • Small Molecule Libraries* / pharmacology

Substances

  • Ligands
  • Small Molecule Libraries
  • Proteins