Machine learning models for hydrogen bond donor and acceptor strengths using large and diverse training data generated by first-principles interaction free energies

• Published in: Journal of cheminformatics Vol. 11; no. 1; pp. 59 - 16
• Main Authors: Bauer, Christoph A., Schneider, Gisbert, Göller, Andreas H.
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 11.09.2019; Springer Nature B.V; BMC
• Subjects: Acetone; Artificial intelligence; Cheminformatics; Chemistry; Chemistry and Materials Science; Complex formation; Computational Biology/Bioinformatics; Computational chemistry; Computer Applications in Chemistry; Data points; Density functional theory; Documentation and Information in Chemistry; First principles; Free energy prediction; Hydrogen; Hydrogen bond strength; Hydrogen bonding; Hydrogen bonds; Learning algorithms; Machine learning; Organic chemistry; Quantum chemistry; Research Article; Test sets; Theoretical and Computational Chemistry; Computational chemistry; Density functional theory; Cheminformatics; Hydrogen bond strength; Free energy prediction

We present machine learning (ML) models for hydrogen bond acceptor (HBA) and hydrogen bond donor (HBD) strengths. Quantum chemical (QC) free energies in solution for 1:1 hydrogen-bonded complex formation to the reference molecules 4-fluorophenol and acetone serve as our target values. Our acceptor a...