<HashMap><database>biostudies-literature</database><scores/><additional><submitter>Ishida S</submitter><funding>Japan Agency for Medical Research and Development</funding><funding>Ministry of Education, Culture, Sports, Science and Technology</funding><pagination>36</pagination><full_dataset_link>https://www.ebi.ac.uk/biostudies/studies/S-EPMC11934680</full_dataset_link><repository>biostudies-literature</repository><omics_type>Unknown</omics_type><volume>17(1)</volume><pubmed_abstract>Recent advancements in artificial intelligence (AI)-based molecular design methodologies have offered synthetic chemists new ways to design functional molecules with their desired properties. While various AI-based molecule generators have significantly advanced toward practical applications, their effective use still requires specialized knowledge and skills concerning AI techniques. Here, we develop a large language model (LLM)-powered chatbot, ChatChemTS, that assists users in designing new molecules using an AI-based molecule generator through only chat interactions, including automated construction of reward functions for the specified properties. Our study showcases the utility of ChatChemTS through de novo design cases involving chromophores and anticancer drugs (epidermal growth fa</pubmed_abstract><journal>Journal of cheminformatics</journal><pubmed_title>Large language models open new way of AI-assisted molecule design for chemists.</pubmed_title><pmcid>PMC11934680</pmcid><funding_grant_id>no.JP22ama121023</funding_grant_id><funding_grant_id>JPMXP1122683430</funding_grant_id><funding_grant_id>no.JP23nk0101111</funding_grant_id><pubmed_authors>Sato T</pubmed_authors><pubmed_authors>Honma T</pubmed_authors><pubmed_authors>Terayama K</pubmed_authors><pubmed_authors>Ishida S</pubmed_authors></additional><is_claimable>false</is_claimable><name>Large language models open new way of AI-assisted molecule design for chemists.</name><description>Recent advancements in artificial intelligence (AI)-based molecular design methodologies have offered synthetic chemists new ways to design functional molecules with their desired properties. While various AI-based molecule generators have significantly advanced toward practical applications, their effective use still requires specialized knowledge and skills concerning AI techniques. Here, we develop a large language model (LLM)-powered chatbot, ChatChemTS, that assists users in designing new molecules using an AI-based molecule generator through only chat interactions, including automated construction of reward functions for the specified properties. Our study showcases the utility of ChatChemTS through de novo design cases involving chromophores and anticancer drugs (epidermal growth fa</description><dates><release>2025-01-01T00:00:00Z</release><publication>2025 Mar</publication><modification>2026-06-03T02:36:14.995Z</modification><creation>2025-07-09T03:04:51.487Z</creation></dates><accession>S-EPMC11934680</accession><cross_references><pubmed>40128788</pubmed><doi>10.1186/s13321-025-00984-8</doi></cross_references></HashMap>