DrugAssist: a large language model for molecule optimization
Top Cited Papers
Open Access
- 22 November 2024
- journal article
- research article
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 26 (1)
Abstract
Recently, the impressive performance of large language models (LLMs) on a wide range of tasks has attracted an increasing number of attempts to apply LLMs in drug discovery. However, molecule optimization, a critical task in the drug discovery pipeline, is currently an area that has seen little involvement from LLMs. Most of existing approaches focus solely on capturing the underlying patterns in chemical structures provided by the data, without taking advantage of expert feedback. These non-interactive approaches overlook the fact that the drug discovery process is actually one that requires the integration of expert experience and iterative refinement. To address this gap, we propose DrugAssist, an interactive molecule optimization model which performs optimization through human–machine dialogue by leveraging LLM’s strong interactivity and generalizability. DrugAssist has achieved leading results in both single and multiple property optimization, simultaneously showcasing immense potential in transferability and iterative optimization. In addition, we publicly release a large instruction-based dataset called ‘MolOpt-Instructions’ for fine-tuning language models on molecule optimization tasks. We have made our code and data publicly available at https://github.com/blazerye/DrugAssist, which we hope to pave the way for future research in LLMs’ application for drug discovery.Keywords
All Related Versions
Funding Information
- National Science and Technology Major Project (2023ZD0120902)
- National Natural Science Foundation of China (U22A2037, 62425204, 62122025, 62450002, 62432011)
- Beijing Natural Science Foundation (L248013)
This publication has 22 references indexed in Scilit:
- An effective framework for predicting drug–drug interactions based on molecular substructures and knowledge graph neural networkComputers in Biology and Medicine, 2023
- Combination of chemotherapy and gaseous signaling molecular therapy: Novel β‐elemene nitric oxide donor derivatives against leukemiaDrug Development Research, 2023
- Accelerated Discovery of Macrocyclic CDK2 Inhibitor QR-6401 by Generative Models and Structure-Based Drug DesignACS Medicinal Chemistry Letters, 2023
- Races of small molecule clinical trials for the treatment of COVID‐19: An up‐to‐date comprehensive reviewDrug Development Research, 2021
- mmpdb: An Open-Source Matched Molecular Pair Platform for Large Multiproperty Data SetsJournal of Chemical Information and Modeling, 2018
- Reinforced Adversarial Neural Computer for de Novo Molecular DesignJournal of Chemical Information and Modeling, 2018
- Generating Focused Molecule Libraries for Drug Discovery with Recurrent Neural NetworksACS Central Science, 2017
- Molecular de-novo design through deep reinforcement learningJournal of Cheminformatics, 2017
- druGAN: An Advanced Generative Adversarial Autoencoder Model for de Novo Generation of New Molecules with Desired Molecular Properties in SilicoMolecular Pharmaceutics, 2017
- ZINC − A Free Database of Commercially Available Compounds for Virtual ScreeningJournal of Chemical Information and Modeling, 2004