Language selection

Government of Canada / Gouvernement du Canada

Search

Conversational drug editing using retrieval and domain feedback

From National Research Council Canada

Linkhttps://iclr.cc/virtual/2024/poster/17419
AuthorSearch for: ; Search for: ; Search for: ; Search for: ; Search for: ; Search for: 1ORCID identifier: https://orcid.org/0000-0002-7663-2421; Search for:
Affiliation
  1. National Research Council of Canada. Digital Technologies
FormatText, Poster
Conference12th International Conference on Learning Representations (ICLR 2024), May 7-11, 2024, Vienna, Austria
Physical description1 p.
Abstract
Recent advancements in conversational large language models (LLMs), such as ChatGPT, have demonstrated remarkable promise in various domains, including drug discovery. However, existing works mainly focus on investigating the capabilities of conversational LLMs on chemical reactions and retrosynthesis. While drug editing, a critical task in the drug discovery pipeline, remains largely unexplored. To bridge this gap, we propose ChatDrug, a framework to facilitate the systematic investigation of drug editing using LLMs. ChatDrug jointly leverages a prompt module, a retrieval and domain feedback module, and a conversation module to streamline effective drug editing. We empirically show that ChatDrug reaches the best performance on all 39 drug editing tasks, encompassing small molecules, peptides, and proteins. We further demonstrate, through 10 case studies, that ChatDrug can successfully identify the key substructures for manipulation, generating diverse and valid suggestions for drug editing. Promisingly, we also show that ChatDrug can offer insightful explanations from a domain-specific perspective, enhancing interpretability and enabling informed decision-making.
Publication date
PublisherInternational Conference on Learning Representations, ICLR
Open Review
In
  • ICLR 2024: The 12th International Conference on Learning Representations (7 May 2024).
Other format
LanguageEnglish
Peer reviewedNo
Export citationExport as RIS
Report a correctionReport a correction (opens in a new tab)
Record identifier0eb0340c-c79c-4be0-892f-691b0bce0285
Record created2024-10-25
Record modified2025-07-16
Date modified: