![Author ORCID: We display the ORCID iD icon alongside authors names on our website to acknowledge that the ORCiD has been authenticated when entered by the user. To view the users ORCiD record click the icon. [opens in a new tab]](https://chemrxiv.org/engage/assets/public/chemrxiv/images/logos/orcid.png)
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 enables chemists to design 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 factor receptor inhibitors), exemplifying single- and multiobjective molecule optimization scenarios, respectively. ChatChemTS is provided as an open-source package on GitHub at https://github.com/molecule-generator-collection/ChatChemTS.
Supplementary materials
Title
Supporting Information
Description
Snapshot UI of prediction model builder tool when building the prediction models to predict absorption wavelength (Fig.~S1); Snapshot UI of prediction model builder tool when building the prediction model to predict inhibitory activity against EGFR (Fig.~S2); Comparizon of QED optimization processes between generating molecules considering inhibitory activity against EGFR and QED score and generating molecules solely considering the inhibitory activity (Fig.~S3); System message used in the agent of ChatChemTS (Listing~S1); Few-shot prompting for the reward generator tool (Listing~S2); Few-shot prompting for config generator tool (Listing~S3).
Actions
Supplementary weblinks
Title
GitHub Repository of ChatChemTS
Description
Links to GitHub repository of ChatChemTS
Actions
View 
