Molecule generation using transformers and policy gradient reinforcement learning

Abstract Generating novel valid molecules is often a difficult task, because the vast chemical space relies on the intuition of experienced chemists. In recent years, deep learning models have helped accelerate this process. These advanced models can also help identify suitable molecules for disease...

Full description

Bibliographic Details
Published in:Scientific Reports
Main Authors: Eyal Mazuz, Guy Shtar, Bracha Shapira, Lior Rokach
Format: Article in Journal/Newspaper
Language:English
Published: Nature Portfolio 2023
Subjects:
R
Q
Online Access:https://doi.org/10.1038/s41598-023-35648-w
https://doaj.org/article/43421964cb2b49f9889efbc7f325dfb3
Description
Summary:Abstract Generating novel valid molecules is often a difficult task, because the vast chemical space relies on the intuition of experienced chemists. In recent years, deep learning models have helped accelerate this process. These advanced models can also help identify suitable molecules for disease treatment. In this paper, we propose Taiga, a transformer-based architecture for the generation of molecules with desired properties. Using a two-stage approach, we first treat the problem as a language modeling task of predicting the next token, using SMILES strings. Then, we use reinforcement learning to optimize molecular properties such as QED. This approach allows our model to learn the underlying rules of chemistry and more easily optimize for molecules with desired properties. Our evaluation of Taiga, which was performed with multiple datasets and tasks, shows that Taiga is comparable to, or even outperforms, state-of-the-art baselines for molecule optimization, with improvements in the QED ranging from 2 to over 20 percent. The improvement was demonstrated both on datasets containing lead molecules and random molecules. We also show that with its two stages, Taiga is capable of generating molecules with higher biological property scores than the same model without reinforcement learning.