Applying deep learning to iterative screening of medium-sized molecules for protein-protein interaction-targeted drug discovery.

Journal: Chemical communications (Cambridge, England)
PMID:

Abstract

We combined a library of medium-sized molecules with iterative screening using multiple machine learning algorithms that were ligand-based, which resulted in a large increase of the hit rate against a protein-protein interaction target. This was demonstrated by inhibition assays using a PPI target, Kelch-like ECH-associated protein 1/nuclear factor erythroid 2-related factor 2 (Keap1/Nrf2), and a deep neural network model based on the first-round assay data showed a highest hit rate of 27.3%. Using the models, we identified novel active and non-flat compounds far from public datasets, expanding the chemical space.

Authors

  • Yugo Shimizu
    Division of Physics for Life Functions, Faculty of Pharmacy, Keio University, 1-5-30 Shibakoen, Minato-ku, Tokyo, 105-8512, Japan.
  • Tomoki Yonezawa
    Division of Physics for Life Functions, Faculty of Pharmacy, Keio University, 1-5-30 Shibakoen, Minato-ku, Tokyo, 105-8512, Japan.
  • Yu Bao
    Laboratory of Mathematical Bioinformatics, Bioinformatics Center, Institute for Chemical Research, Kyoto University, Gokasho, Uji, Kyoto, 611-0011, Japan. houu@kuicr.kyoto-u.ac.jp.
  • Junichi Sakamoto
    Axcelead Drug Discovery Partners, Inc., 26-1, Muraoka-Higashi 2-chome, Fujisawa, Kanagawa, 251-0012, Japan.
  • Mariko Yokogawa
    Division of Physics for Life Functions, Keio University Faculty of Pharmacy, 1-5-30 Shibakoen, Minato-ku, Tokyo 105-8512, Japan. ikeda-kz@pha.keio.ac.jp.
  • Toshio Furuya
    Drug Discovery Department, Research and Development Division, PharmaDesign, Inc., Hatchobori 2-19-8, Chuo-ku, Tokyo, 104-0032, Japan.
  • Masanori Osawa
    Division of Physics for Life Functions, Faculty of Pharmacy, Keio University, 1-5-30 Shibakoen, Minato-ku, Tokyo, 105-8512, Japan.
  • Kazuyoshi Ikeda
    Division of Physics for Life Functions, Faculty of Pharmacy, Keio University, 1-5-30 Shibakoen, Minato-ku, Tokyo, 105-8512, Japan. ikeda-kz@pha.keio.ac.jp.