Combining machine learning and quantum mechanics yields more chemically aware molecular descriptors for medicinal chemistry applications

9Citations
Citations of this article
22Readers
Mendeley users who have this article in their library.

This article is free to access.

Abstract

Molecular interaction fields (MIFs), describing molecules in terms of their ability to interact with any chemical entity, are one of the most established and versatile concepts in drug discovery. Improvement of this molecular description is highly desirable for in silico drug discovery and medicinal chemistry applications. In this work, we revised a well-established molecular mechanics' force field and applied a hybrid quantum mechanics and machine learning approach to parametrize the hydrogen-bonding (HB) potentials of small molecules, improving this aspect of the molecular description. Approximately 66,000 molecules were chosen from available drug databases and subjected to density functional theory calculations (DFT). For each atom, the molecular electrostatic potential (EP) was extracted and used to derive new HB energy contributions; this was subsequently combined with a fingerprint-based description of the structural environment via partial least squares modeling, enabling the new potentials to be used for molecules outside of the training set. We demonstrate that parameter prediction for molecules outside of the training set correlates with their DFT-derived EP, and that there is correlation of the new potentials with hydrogen-bond acidity and basicity scales. We show the newly derived MIFs vary in strength for various ring substitution in accordance with chemical intuition. Finally, we report that this derived parameter, when extended to non-HB atoms, can also be used to estimate sites of reaction.

References Powered by Scopus

Density-functional thermochemistry. III. The role of exact exchange

97085Citations
N/AReaders
Get full text

General atomic and molecular electronic structure system

20090Citations
N/AReaders
Get full text

PLS-regression: A basic tool of chemometrics

7906Citations
N/AReaders
Get full text

Cited by Powered by Scopus

Structural Reshaping of the Zinc-Finger Domain of the SARS-CoV-2 nsp13 Protein Using Bismuth(III) Ions: A Multilevel Computational Study

15Citations
N/AReaders
Get full text

Advances in Drug Discovery based on Genomics, Proteomics and Bioin-formatics in Malaria

8Citations
N/AReaders
Get full text

Homodimeric complexes of the 90–231 human prion: a multilayered computational study based on FMO/GRID-DRY approach

7Citations
N/AReaders
Get full text

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Cite

CITATION STYLE

APA

Tortorella, S., Carosati, E., Sorbi, G., Bocci, G., Cross, S., Cruciani, G., & Storchi, L. (2021). Combining machine learning and quantum mechanics yields more chemically aware molecular descriptors for medicinal chemistry applications. Journal of Computational Chemistry, 42(29), 2068–2078. https://doi.org/10.1002/jcc.26737

Readers' Seniority

Tooltip

PhD / Post grad / Masters / Doc 7

47%

Researcher 6

40%

Professor / Associate Prof. 2

13%

Readers' Discipline

Tooltip

Chemistry 9

69%

Pharmacology, Toxicology and Pharmaceut... 2

15%

Chemical Engineering 1

8%

Social Sciences 1

8%

Article Metrics

Tooltip
Social Media
Shares, Likes & Comments: 13

Save time finding and organizing research with Mendeley

Sign up for free