biostudies-literatureYoshizawa TJapan Agency for Medical Research and DevelopmentMinistry of Education, Culture, Sports, Science and Technology5351-5360https://www.ebi.ac.uk/biostudies/studies/S-EPMC9709912biostudies-literatureUnknown62(22)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 <i>de novo</i> structure generator based on reinforcement leJournal of chemical information and modelingSelective Inhibitor Design for Kinase Homologs Using Multiobjective Monte Carlo Tree Search.PMC9709912JP22ama121023JP22nk0101111Sato THonma TTerayama KIshida SYoshizawa TOhta MfalseSelective Inhibitor Design for Kinase Homologs Using Multiobjective Monte Carlo Tree Search.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 <i>de novo</i> structure generator based on reinforcement le2022-01-01T00:00:00Z2022 Nov2025-04-04T19:37:57.728Z2025-04-04T19:37:57.728ZS-EPMC97099123633409410.1021/acs.jcim.2c00787