Utilizing Reinforcement Learning for de novo Drug Design

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Svensson, Hampus Gummesson, Tyrchan, Christian, Engkvist, Ola, Chehreghani, Morteza Haghir
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929716162723840
author Svensson, Hampus Gummesson
Tyrchan, Christian
Engkvist, Ola
Chehreghani, Morteza Haghir
author_facet Svensson, Hampus Gummesson
Tyrchan, Christian
Engkvist, Ola
Chehreghani, Morteza Haghir
contents Deep learning-based approaches for generating novel drug molecules with specific properties have gained a lot of interest in the last few years. Recent studies have demonstrated promising performance for string-based generation of novel molecules utilizing reinforcement learning. In this paper, we develop a unified framework for using reinforcement learning for de novo drug design, wherein we systematically study various on- and off-policy reinforcement learning algorithms and replay buffers to learn an RNN-based policy to generate novel molecules predicted to be active against the dopamine receptor DRD2. Our findings suggest that it is advantageous to use at least both top-scoring and low-scoring molecules for updating the policy when structural diversity is essential. Using all generated molecules at an iteration seems to enhance performance stability for on-policy algorithms. In addition, when replaying high, intermediate, and low-scoring molecules, off-policy algorithms display the potential of improving the structural diversity and number of active molecules generated, but possibly at the cost of a longer exploration phase. Our work provides an open-source framework enabling researchers to investigate various reinforcement learning methods for de novo drug design.
format Preprint
id arxiv_https___arxiv_org_abs_2303_17615
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Utilizing Reinforcement Learning for de novo Drug Design
Svensson, Hampus Gummesson
Tyrchan, Christian
Engkvist, Ola
Chehreghani, Morteza Haghir
Biomolecules
Machine Learning
Deep learning-based approaches for generating novel drug molecules with specific properties have gained a lot of interest in the last few years. Recent studies have demonstrated promising performance for string-based generation of novel molecules utilizing reinforcement learning. In this paper, we develop a unified framework for using reinforcement learning for de novo drug design, wherein we systematically study various on- and off-policy reinforcement learning algorithms and replay buffers to learn an RNN-based policy to generate novel molecules predicted to be active against the dopamine receptor DRD2. Our findings suggest that it is advantageous to use at least both top-scoring and low-scoring molecules for updating the policy when structural diversity is essential. Using all generated molecules at an iteration seems to enhance performance stability for on-policy algorithms. In addition, when replaying high, intermediate, and low-scoring molecules, off-policy algorithms display the potential of improving the structural diversity and number of active molecules generated, but possibly at the cost of a longer exploration phase. Our work provides an open-source framework enabling researchers to investigate various reinforcement learning methods for de novo drug design.
title Utilizing Reinforcement Learning for de novo Drug Design
topic Biomolecules
Machine Learning
url https://arxiv.org/abs/2303.17615