2022
DOI: 10.1039/d2cp00834c
|View full text |Cite
|
Sign up to set email alerts
|

Δ-Quantum machine-learning for medicinal chemistry

Abstract: Many molecular design tasks benefit from fast and accurate calculations of quantum-mechanical (QM) properties. 3D message-passing neural networks for Δ-quantum machine-learning enable fast access to DFT-level QM properties for drug-like molecules.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

1
35
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
4
3
2
1

Relationship

1
9

Authors

Journals

citations
Cited by 44 publications
(36 citation statements)
references
References 78 publications
1
35
0
Order By: Relevance
“…Remarkably, for models using default ground-state features (Fig. 3C, red lines), we noticed a rank reversal behavior between direct-learning and delta-learning models as more training samples became available, mirroring similar observations from a recent Atomistic ML study (56). The absence of this cross-over when (D β h , D β p ) are provided (Fig.…”
Section: Resultssupporting
confidence: 82%
“…Remarkably, for models using default ground-state features (Fig. 3C, red lines), we noticed a rank reversal behavior between direct-learning and delta-learning models as more training samples became available, mirroring similar observations from a recent Atomistic ML study (56). The absence of this cross-over when (D β h , D β p ) are provided (Fig.…”
Section: Resultssupporting
confidence: 82%
“…For many applications such as organic electronics, organic photovoltaics, and organic lightemitting diodes, the energy of the highest occupied molecular orbital (HOMO), the lowest unoccupied MO (LUMO), and the optical gap are of high importance for the device efficiency. These properties can therefore be found in numerous databases 62,90,[173][174][175][176][177] . Related properties include (transition) dipole moment 62,178 , ionization potential, and electron affinity 90 .…”
Section: Applicationsmentioning
confidence: 99%
“…86,87 For small molecules, state-of-the-art methods range from fast bond charge corrections applied to charges derived from semiempirical quantum chemical methods (such as AM1-BCC 28,29 or CGenFF charge increments 47 ) to expensive multiconformer restrained electrostatic potential (RESP) fits to high-level quantum chemistry. 88,89 Surprisingly little attention has been paid to the divergence of methods used for assigning partial charges to small molecules and biopolymers, and the potential impact this inconsistency has on accuracy or ease of use—indeed, developing charges for post-translational modifications to biopolymer residues 90,91 or covalent ligands can prove to be a significant technical challenge in attempting to bridge these two worlds.…”
Section: Espaloma Can Learn Self-consistent Charge Models In An End-t...mentioning
confidence: 99%