Predicting Strategies for Lead Optimization via Learning to Rank

• Yasuo Nobuaki

  Department of Computer Science, Tokyo Institute of Technology Japan Society for the Promotion of Science

• Watanabe Keisuke

  Department of Computer Science, Tokyo Institute of Technology

• Hara Hideto

  Shonan Research Center, Takeda Pharmaceutical Company Limited

• Rikimaru Kentaro

  Shonan Research Center, Takeda Pharmaceutical Company Limited

• Sekijima Masakazu

  Department of Computer Science, Tokyo Institute of Technology Advanced Computational Drug Discovery Unit, Tokyo Institute of Technology

抄録

Lead optimization is an essential step in drug discovery in which the chemical structures of compounds are modified to improve characteristics such as binding affinity, target selectivity, physicochemical properties, and toxicity. We present a concept for a computational compound optimization system that outputs optimized compounds from hit compounds by using previous lead optimization data from a pharmaceutical company. In this study, to predict the drug-likeness of compounds in the evaluation function of this system, we evaluated and compared the ability to correctly predict lead optimization strategies through learning to rank methods.

収録刊行物

• IPSJ Transactions on Bioinformatics

  IPSJ Transactions on Bioinformatics 11 (0), 41-47, 2018

  一般社団法人 情報処理学会

キーワード

• lead optimization
• learning to rank
• computer-aided drug design
• machine learning

詳細情報

• CRID: 1390564238051179904
• NII論文ID: 130007528710
• DOI: 10.2197/ipsjtbio.11.41
• ISSN: 18826679
• Web Site: https://www.jstage.jst.go.jp/article/ipsjtbio/11/0/11_41/_pdf
• 本文言語コード: en
• データソース種別:
  • JaLC
  • Crossref
  • CiNii Articles
  • KAKEN
• 抄録ライセンスフラグ: 使用不可