RIKEN Center for Computational Science Medicinal Chemistry Applied AI Unit

Research Summary

At each stage of drug discovery, "hit to lead"(from initial hits to lead compounds showing in vivo efficacy) stage has become a bottleneck along with phase II clinical trials, and the stagnation of small molecule drug discovery in recent years. This unit aims to improve the time required and cost of the hit-to-lead and lead optimization process (so-called medicinal chemistry process) by AI. The cause of the increased time and cost of the medicinal chemistry process is the difficulty of optimizing potency and ADMET (pharmacokinetics and toxicity) at the same time. In collaboration with Kyoto University and LINC, we are building AI models for new structure generation, synthetic pathway prediction, and potency / ADMET prediction in order to speed up the medicinal chemistry process.

Main Research Fields

• Computer Science

Related Research Fields

• Chemistry
• Pharmacology & Toxicology

Keywords

• In silico screening
• ADMET
• FMO method
• Artificial intelligence
• Deep learning

Selected Publications

• 1. Watanabe C, Okiyama Y, Tanaka S, Fukuzawa K, Honma T.:
  "Molecular Recognition of SARS-CoV-2 Spike Glycoprotein: Quantum Chemical Hot Spot and Epitope Analyses"
  DOI: 10.1039/D0SC06528E (Edge Article) Chem. Sci., (2021).
• 2. Takaya D, Watanabe C, Nagase S, Kamisaka K, Okiyama Y, Moriwaki H, Yuki H, Sato T, Kurita N, Yagi Y, Takagi T, Kawashita N, Takaba K, Ozawa T, Takimoto-Kamimura M, Tanaka S, Fukuzawa K, Honma T.:
  "FMODB: The World's First Database of Quantum Mechanical Calculations for Biomacromolecules Based on the Fragment Molecular Orbital Method"
  J Chem Inf Model. 22;61(2):777-794. (2021).
• 3. Komura H, Watanabe R, Kawashima H, Ohashi R, Kuroda M, Sato T, Honma T, Mizuguchi K.:
  "A public-private partnership to enrich the development of in silico predictive models for pharmacokinetic and cardiotoxic properties"
  Drug Discov Today. 28:S1359-6446(21)00055-6. (2021)
• 4. Kato K, Honma T, Fukuzawa K.:
  "Intermolecular interaction among Remdesivir, RNA and RNA-dependent RNA polymerase of SARS-CoV-2 analyzed by fragment molecular orbital calculation"
  J Mol Graph Model. 100:107695. (2020).
• 5. Kato K, Masuda T, Watanabe C, Miyagawa N, Mizouchi H, Nagase S, Kamisaka K, Oshima K, Ono S, Ueda H, Tokuhisa A, Kanada R, Ohta M, Ikeguchi M, Okuno Y, Fukuzawa K, Honma T.:
  "High-precision Atomic Charge Prediction for Protein Systems Using Fragment Molecular Orbital Calculation and Machine Learning"
  J Chem Inf Model. 27;60(7):3361-3368. (2020)
• 6. Kojima R, Ishida S, Ohta M, Iwata H, Honma T, Okuno Y.:
  "kGCN: a graph-based deep learning framework for chemical structures"
  Journal of Cheminformatics 12: 1-10. (2020)
• 7. Ogura K, Sato T, Yuki H, Honma T.:
  "Support Vector Machine model for hERG inhibitory activities based on the integrated hERG database using descriptor selection by NSGA-II"
  Scientific reports, 9(1), 1-12. (2019).
• 8. Watanabe C, Watanabe H, Okiyama Y, Takaya D, Fukuzawa K, Tanaka S, Honma T.:
  "Development of an automated fragment molecular orbital (FMO) calculation protocol toward construction of quantum mechanical calculation database for large biomolecules"
  Chem-Bio Informatics Journal, 19, 5-18. (2019).
• 9. Yoshikawa N, Terayama K, Honma T, Oono K, Tsuda K.:
  "Population-based de novo molecule generation, using grammatical evolution"
  Chem Lett, 47(11), 1431-143. (2018).
• 10. Sato T, Yuki H, Ogura K, Honma T.:
  "Construction of an integrated database for hERG blocking small molecules"
  PLoS ONE, 13(7), e0199348. (2018).

Related Links

Lab Members

Contact Information