A compact review of molecular property prediction with graph neural networks.
AI
Computational chemistry
Deep-learning
Drug discovery
Graph neural-networks
Molecular property
Molecular representation
Neural-networks
Journal
Drug discovery today. Technologies
ISSN: 1740-6749
Titre abrégé: Drug Discov Today Technol
Pays: England
ID NLM: 101235076
Informations de publication
Date de publication:
Dec 2020
Dec 2020
Historique:
received:
08
07
2020
revised:
25
11
2020
accepted:
30
11
2020
entrez:
13
12
2021
pubmed:
14
12
2021
medline:
15
12
2021
Statut:
ppublish
Résumé
As graph neural networks are becoming more and more powerful and useful in the field of drug discovery, many pharmaceutical companies are getting interested in utilizing these methods for their own in-house frameworks. This is especially compelling for tasks such as the prediction of molecular properties which is often one of the most crucial tasks in computer-aided drug discovery workflows. The immense hype surrounding these kinds of algorithms has led to the development of many different types of promising architectures and in this review we try to structure this highly dynamic field of AI-research by collecting and classifying 80 GNNs that have been used to predict more than 20 molecular properties using 48 different datasets.
Identifiants
pubmed: 34895648
pii: S1740-6749(20)30030-5
doi: 10.1016/j.ddtec.2020.11.009
pii:
doi:
Types de publication
Journal Article
Review
Langues
eng
Sous-ensembles de citation
IM
Pagination
1-12Informations de copyright
Copyright © 2020 The Authors. Published by Elsevier Ltd.. All rights reserved.