Work

ClassicalGSG : Prediction of log P using classical molecular force fields and geometric scattering for graphs

Year: 2021

Type: article

Abstract: This work examines methods for predicting the partition coefficient (log P) for a dataset of small molecules. Here, we use atomic attributes such as radius and partial charge, which are typically used as force field parameters in classical molecular dynamics simulations. These atomic attributes are transformed into index-invariant molecular features using a recently developed method called geometric scattering for graphs (GSG). We call this approach "ClassicalGSG" and examine its performance under a broad range of conditions and hyperparameters. We train ClassicalGSG log P predictors with neural networks using 10,722 molecules from the OpenChem dataset and apply them to predict the log P values from four independent test sets. The ClassicalGSG method's performance is compared to a baseline model that employs graph convolutional networks. Our results show that the best prediction accuracies are obtained using atomic attributes generated with the CHARMM generalized force field and 2D molecular structures.

Source: Journal of Computational Chemistry

DOI: 10.1002/jcc.26519

Authors: Nazanin Donyapour, Matthew Hirn, Alex Dickson

Institution: Michigan State University

Language: English

Topic: Computational Drug Discovery Methods

Subfield: Computational Theory and Mathematics

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: National Science Foundation, National Institute of General Medical Sciences, Division of Mathematical Sciences

Awards: G3838524108, G5993125988, CAREER: Understanding Invariant Convolutional Neural Networks through Many Particle Physics, Finding emergent structure in multi-sample biological data with the dual geometry of cells and features , Revealing pathways and kinetics of molecular recognition with advanced molecular simulation algorithms