Enhanced Deep-Learning Prediction of Molecular Properties via Augmentation of Bond Topology.

Enhanced Deep-Learning Prediction of Molecular Properties via Augmentation of Bond Topology.
ChemMedChem. 2019 Aug 07;:
Authors: Cho H, Choi IS
Abstract
Deep learning has made great strides in tackling chemical problems, but still lacks full-fledged representations for three-dimensional (3D) molecular structures for its inner working. For example, the molecular graph, commonly used in chemistry and recently adapted to the graph convolutional network (GCN), is inherently a 2D representation of 3D molecules. Herein we propose an advanced version of the GCN, called 3DGCN, which receives the 3D molecular information from a molecular graph augmented by the information on the bond direction. While outperforming the state-of-the art deep-learning models in the prediction of chemical and biological properties, the 3DGCN has the ability of generalizing and also distinguishing the molecular rotations in 3D, beyond 2D, which has great impact on drug discovery and development, not to mention the design of chemical reactions.
PMID: 31389167 [PubMed - as supplied by publisher]

Source: ChemMedChem - August 6, 2019 Category: Chemistry Authors: Cho H, Choi IS Tags: ChemMedChem Source Type: research