2021
DOI: 10.48550/arxiv.2107.12375
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Geometric Deep Learning on Molecular Representations

Abstract: Geometric deep learning (GDL), which is based on neural network architectures that incorporate and process symmetry information, has emerged as a recent paradigm in artificial intelligence. GDL bears particular promise in molecular modeling applications, in which various molecular representations with different symmetry properties and levels of abstraction exist. This review provides a structured and harmonized overview of molecular GDL, highlighting its applications in drug discovery, chemical synthesis predi… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
7
0

Year Published

2021
2021
2023
2023

Publication Types

Select...
3
3
1

Relationship

0
7

Authors

Journals

citations
Cited by 7 publications
(7 citation statements)
references
References 157 publications
(214 reference statements)
0
7
0
Order By: Relevance
“…Molecular properties are roto-translation invariant (Atz et al, 2021). However, some molecules are chiral and their chiral properties are dependent to the absolute configuration of their stereogenic centers, and thus non-invariant to reflection, as we claim in Proposition 1.…”
Section: A3 Encoding Chiral Molecules With Absolute Positionsmentioning
confidence: 66%
“…Molecular properties are roto-translation invariant (Atz et al, 2021). However, some molecules are chiral and their chiral properties are dependent to the absolute configuration of their stereogenic centers, and thus non-invariant to reflection, as we claim in Proposition 1.…”
Section: A3 Encoding Chiral Molecules With Absolute Positionsmentioning
confidence: 66%
“…In the field of deep learning, geometry-based methods have shown prominent performance (Bronstein et al 2017;Zhou et al 2020;Li et al 2020). Since molecules have geometric structures intrinsically, a few attempts have also been made to develop geometric graph learning models for the molecular graphs (Atz, Grisoni, and Schneider 2021). From the 2D view of the molecular graph, Recent works (Maziarka et al 2020;Ying et al 2021) are designed to encode interatomic distances with augmenting the attention mechanism in a transformer architecture.…”
Section: Geometric Learning On Molecular Graphsmentioning
confidence: 99%
“…Generative ML, the unsupervised learning from input data to generate new data that is similar to the provided data, allows to perform fully datadriven molecule generation and is an active research area (Elton et al, 2019;Faez et al, 2021;Gaudelet et al, 2021;Atz et al, 2021). Various works have developed string-based ML models in order to generate molecules with optimal properties based on SMILES (Kadurin et al, 2017;Gómez-Bombarelli et al, 2018;Mario Krenn et al, 2020;Blaschke et al, 2018;Lim et al, 2018;Bjerrum and Sattarov, 2018;Prykhodko et al, 2019;Griffiths and Hernández-Lobato, 2020), InChI (Winter et al, 2019a), or SELFIES (Mario Krenn et al, 2020), the latter being a more robust string representation of molecules.…”
Section: Generative Modelsmentioning
confidence: 99%