Combining machine learning and quantum mechanics yields more chemically aware molecular descriptors for medicinal chemistry applications. Issue 29 (19th August 2021)

• Record Type: Journal Article
• Authors: Tortorella, Sara; Carosati, Emanuele; Sorbi, Giulia; Bocci, Giovanni; Cross, Simon; Cruciani, Gabriele; Storchi, Loriano
• Is Part Of: Journal of computational chemistry. Volume 42:Issue 29(2021)
• Page Start: 2068
• Page End: 2078
• Publication Date: 2021-08-19
• Subjects: drug discovery -- machine learning -- medicinal chemistry applications -- molecular descriptors -- molecular interaction fields; Chemistry -- Data processing -- Periodicals; 542.85
• DOI: 10.1002/jcc.26737
• Languages: English
• ISSNs: 0192-8651

Abstract

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. Abstract : Approximately 66, 000 molecules were subjected to density functional theory calculations. The extracted molecular electrostatic potential has been used to derive new hydrogen‐bonding (HB) energy contributions; this was subsequently combined with a fingerprint‐based description of the structural environment via partial least squares modeling. The newly derived molecular interaction fields 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.