Improving Targeted Molecule Generation through Language Model Fine-Tuning Via Reinforcement Learning

TL;DR

This paper presents a novel drug design approach that fine-tunes language models with reinforcement learning to generate targeted, valid, and novel molecules for specific proteins, improving key chemical properties.

Contribution

It introduces a reinforcement learning framework with a composite reward for targeted molecule generation using language models, enhancing drug-likeness and interaction efficacy.

Findings

Achieved 65.37 QED score indicating high drug-likeness

Generated molecules with 0.041% non-novel compounds

Improved molecular validity and target interaction metrics

Abstract

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.