Attention-based generative models for de novo molecular design-Reference-Cited by-同舟云学术

Attention-based generative models for de novo molecular design

Published:2021 Issue: Volume: Page:
ISSN:2041-6520
Container-title:Chemical Science
language:en
Short-container-title:Chem. Sci.

Author:

Dollar Orion¹²³⁴^ORCID,Joshi Nisarg¹²³⁴^ORCID,Beck David A. C.¹²³⁴⁵,Pfaendtner Jim¹²³⁴^ORCID

Affiliation:

1. Department of Chemical Engineering

2. University of Washington

3. Seattle 98185

4. USA

5. eScience Institute

Abstract

An implementation of attention within the variational autoencoder framework for continuous representation of molecules. The addition of attention significantly increases model performance for complex tasks such as exploration of novel chemistries.

Funder

National Science Foundation

U.S. Department of Energy

Publisher

Royal Society of Chemistry (RSC)

Subject

General Chemistry

Link

http://pubs.rsc.org/en/content/articlepdf/2021/SC/D1SC01050F

Reference56 articles.

1. C.Kuhn and D. N.Beratan , Inverse Strategies for Molecular Design , 1996

2. Inverse molecular design using machine learning: Generative models for matter engineering

3. Estimation of the size of drug-like chemical space based on GDB-17 data

4. D. C.Elton , Z.Boukouvalas , M. D.Fuge and P. W.Chung , 2019 , arXiv:1903.04388 [cs.LG]

5. Continuous Molecular Representations of Ionic Liquids

Cited by 44 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Molecular similarity: Theory, applications, and perspectives;Artificial Intelligence Chemistry;2024-12

2. CardioGenAI: A Machine Learning-Based Framework for Re-Engineering Drugs for Reduced hERG Liability;2024-09-10

3. Crystal Composition Transformer: Self‐Learning Neural Language Model for Generative and Tinkering Design of Materials;Advanced Science;2024-08-05

4. Advancing drug discovery with deep attention neural networks;Drug Discovery Today;2024-08

5. Inverse mapping of quantum properties to structures for chemical space of small organic molecules;Nature Communications;2024-07-18