Training recurrent neural networks as generative neural networks for molecular structures: how does it impact drug discovery?

Journal: Expert opinion on drug discovery
Published Date:

Abstract

INTRODUCTION: Deep learning approaches have become popular in recent years in de novo drug design. Generative models for molecule generation and optimization have shown promising results. Molecules trained on different chemical data could regenerate molecules that were similar to the query molecule, thus supporting lead optimization. Recurrent neural network-based generative models have demonstrated application in low-data drug discovery, fragment-based drug design and in lead optimization.

Authors

  • Sofia D'Souza
    Department of Computer Science and Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, 576104, Karnataka, India.
  • Prema Kv
    Department of Computer Science and Engineering, Manipal Institute of Technology, MAHE, Manipal, India.
  • Seetharaman Balaji
    Department of Biotechnology, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, 576104, Karnataka, India. Electronic address: s.balaji@manipal.edu.