Improving Targeted Molecule Generation through Language Model Fine-Tuning Via Reinforcement Learning
This addresses the costly and time-consuming process of drug discovery for pharmaceutical research, though it appears incremental as it builds on existing language model and RL methods.
The paper tackled targeted drug design by fine-tuning a language model with reinforcement learning to generate molecules for specific proteins, achieving improvements in molecular validity and interaction efficacy with metrics like 65.37 QED and 4.47 logP.
Developing new drugs is laborious and costly, demanding extensive time investment. In this paper, we introduce a de-novo drug design strategy, which harnesses the capabilities of language models to devise targeted drugs for specific proteins. Employing a Reinforcement Learning (RL) framework utilizing Proximal Policy Optimization (PPO), we refine the model to acquire a policy for generating drugs tailored to protein targets. The proposed method integrates a composite reward function, combining considerations of drug-target interaction and molecular validity. Following RL fine-tuning, the proposed method demonstrates promising outcomes, yielding notable improvements in molecular validity, interaction efficacy, and critical chemical properties, achieving 65.37 for Quantitative Estimation of Drug-likeness (QED), 321.55 for Molecular Weight (MW), and 4.47 for Octanol-Water Partition Coefficient (logP), respectively. Furthermore, out of the generated drugs, only 0.041% do not exhibit novelty.