Molecular De Novo Design through Transformer-based Reinforcement Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Pengcheng, Feng, Tao, Fu, Tianfan, Laghuvarapu, Siddhartha, Sun, Jimeng
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913257425469440
author Xu, Pengcheng
Feng, Tao
Fu, Tianfan
Laghuvarapu, Siddhartha
Sun, Jimeng
author_facet Xu, Pengcheng
Feng, Tao
Fu, Tianfan
Laghuvarapu, Siddhartha
Sun, Jimeng
contents In this work, we introduce a method to fine-tune a Transformer-based generative model for molecular de novo design. Leveraging the superior sequence learning capacity of Transformers over Recurrent Neural Networks (RNNs), our model can generate molecular structures with desired properties effectively. In contrast to the traditional RNN-based models, our proposed method exhibits superior performance in generating compounds predicted to be active against various biological targets, capturing long-term dependencies in the molecular structure sequence. The model's efficacy is demonstrated across numerous tasks, including generating analogues to a query structure and producing compounds with particular attributes, outperforming the baseline RNN-based methods. Our approach can be used for scaffold hopping, library expansion starting from a single molecule, and generating compounds with high predicted activity against biological targets.
format Preprint
id arxiv_https___arxiv_org_abs_2310_05365
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Molecular De Novo Design through Transformer-based Reinforcement Learning
Xu, Pengcheng
Feng, Tao
Fu, Tianfan
Laghuvarapu, Siddhartha
Sun, Jimeng
Machine Learning
Artificial Intelligence
In this work, we introduce a method to fine-tune a Transformer-based generative model for molecular de novo design. Leveraging the superior sequence learning capacity of Transformers over Recurrent Neural Networks (RNNs), our model can generate molecular structures with desired properties effectively. In contrast to the traditional RNN-based models, our proposed method exhibits superior performance in generating compounds predicted to be active against various biological targets, capturing long-term dependencies in the molecular structure sequence. The model's efficacy is demonstrated across numerous tasks, including generating analogues to a query structure and producing compounds with particular attributes, outperforming the baseline RNN-based methods. Our approach can be used for scaffold hopping, library expansion starting from a single molecule, and generating compounds with high predicted activity against biological targets.
title Molecular De Novo Design through Transformer-based Reinforcement Learning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2310.05365