Author:
Wei Lai,Fu Nihang,Song Yuqi,Wang Qian,Hu Jianjun
Abstract
AbstractSelf-supervised neural language models have recently found wide applications in the generative design of organic molecules and protein sequences as well as representation learning for downstream structure classification and functional prediction. However, most of the existing deep learning models for molecule design usually require a big dataset and have a black-box architecture, which makes it difficult to interpret their design logic. Here we propose the Generative Molecular Transformer (GMTransformer), a probabilistic neural network model for generative design of molecules. Our model is built on the blank filling language model originally developed for text processing, which has demonstrated unique advantages in learning the “molecules grammars” with high-quality generation, interpretability, and data efficiency. Benchmarked on the MOSES datasets, our models achieve high novelty and Scaf compared to other baselines. The probabilistic generation steps have the potential in tinkering with molecule design due to their capability of recommending how to modify existing molecules with explanation, guided by the learned implicit molecule chemistry. The source code and datasets can be accessed freely at https://github.com/usccolumbia/GMTransformer
Funder
Big Data Health Science Center (BDHSC) of the University of South Carolina
National Science Foundation
Publisher
Springer Science and Business Media LLC
Subject
Library and Information Sciences,Computer Graphics and Computer-Aided Design,Physical and Theoretical Chemistry,Computer Science Applications
Reference48 articles.
1. Meyers Joshua, Fabian Benedek, Brown Nathan (2021) De novo molecular design and generative models. Drug Discov Today 26(11):2707–2715
2. Alex Zunger, Malyi Oleksandr I (2021) Understanding doping of quantum materials. Chem Rev 121(5):3031–3060
3. Du Y, Fu T, Sun J, Liu S (2022) Molgensurvey: a systematic survey in machine learning models for molecule design. arXiv preprint. arXiv:2203.14500
4. Fergus Imrie, Bradley Anthony R, Mihaela Schaar, van der, Deane Charlotte M, (2020) Deep generative models for 3d linker design. J Chem Inform Model 60(4):1983–1995
5. Lyle Regenwetter, Heyrani Nobari Amin, Faez Ahmed (2022) Deep generative models in engineering design: a review. J Mech Des 144(7):071704