Your browser doesn't support javascript.
loading
Selective Inhibitor Design for Kinase Homologs Using Multiobjective Monte Carlo Tree Search.
Yoshizawa, Tatsuya; Ishida, Shoichi; Sato, Tomohiro; Ohta, Masateru; Honma, Teruki; Terayama, Kei.
Affiliation
  • Yoshizawa T; Graduate School of Medical Life Science, Yokohama City University, Tsurumi-ku, Yokohama230-0045, Japan.
  • Ishida S; Graduate School of Medical Life Science, Yokohama City University, Tsurumi-ku, Yokohama230-0045, Japan.
  • Sato T; RIKEN Center for Biosystems Dynamics Research, 1-7-22 Suehiro-cho, Tsurumi-ku, Yokohama230-0045, Japan.
  • Ohta M; HPC- and AI-driven Drug Development Platform Division, Center for Computational Science, RIKEN, Yokohama230-0045, Japan.
  • Honma T; RIKEN Center for Biosystems Dynamics Research, 1-7-22 Suehiro-cho, Tsurumi-ku, Yokohama230-0045, Japan.
  • Terayama K; Graduate School of Medical Life Science, Yokohama City University, Tsurumi-ku, Yokohama230-0045, Japan.
J Chem Inf Model ; 62(22): 5351-5360, 2022 11 28.
Article de En | MEDLINE | ID: mdl-36334094
ABSTRACT
Designing highly selective molecules for a drug target protein is a challenging task in drug discovery. This task can be regarded as a multiobjective problem that simultaneously satisfies criteria for various objectives, such as selectivity for a target protein, pharmacokinetic endpoints, and drug-like indices. Recent breakthroughs in artificial intelligence have accelerated the development of molecular structure generation methods, and various researchers have applied them to computational drug designs and successfully proposed promising drug candidates. However, designing efficient selective inhibitors with releasing activities against various homologs of a target protein remains a difficult issue. In this study, we developed a de novo structure generator based on reinforcement learning that is capable of simultaneously optimizing multiobjective problems. Our structure generator successfully proposed selective inhibitors for tyrosine kinases while optimizing 18 objectives consisting of inhibitory activities against 9 tyrosine kinases, 3 pharmacokinetics endpoints, and 6 other important properties. These results show that our structure generator and optimization strategy for selective inhibitors will contribute to the further development of practical structure generators for drug designs.
Sujet(s)

Texte intégral: 1 Collection: 01-internacional Base de données: MEDLINE Sujet principal: Intelligence artificielle / Méthode de Monte Carlo Type d'étude: Health_economic_evaluation / Prognostic_studies Langue: En Journal: J Chem Inf Model Sujet du journal: INFORMATICA MEDICA / QUIMICA Année: 2022 Type de document: Article Pays d'affiliation: Japon

Texte intégral: 1 Collection: 01-internacional Base de données: MEDLINE Sujet principal: Intelligence artificielle / Méthode de Monte Carlo Type d'étude: Health_economic_evaluation / Prognostic_studies Langue: En Journal: J Chem Inf Model Sujet du journal: INFORMATICA MEDICA / QUIMICA Année: 2022 Type de document: Article Pays d'affiliation: Japon