ChemRxiv
These are preliminary reports that have not been peer-reviewed. They should not be regarded as conclusive, guide clinical practice/health-related behavior, or be reported in news media as established information. For more information, please see our FAQs.
1/1
2 files

ClassicalGSG: Prediction of logP Using Classical Molecular Force Fields and Geometric Scattering for Graphs

preprint
submitted on 18.11.2020, 19:51 and posted on 19.11.2020, 12:44 by Nazanin Donyapour, Matthew Hirn, Alex Dickson

This work examines methods for predicting the partition coecient (log P) for a dataset of small molecules. Here, we use atomic attributes such as radius and partial charge, which are typically used as forcefield parameters in classical molecular dynamics simulations. These atomic features 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 a ClassicalGSG log P predictor with neural networks using 10722 molecules from the ChEMBL21 dataset and apply it 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 neural networks (GCNNs). Our results show that the best prediction accuracies are obtained using atomic attributes generated with the CHARMM generalized Force Field (CGenFF) and 2D molecular structures.

Funding

Revealing the Ligand Binding Landscape with Advanced Molecular Simulation Methods

National Institute of General Medical Sciences

Find out more...

Kinetics-Driven Drug Discovery Using Persistent Homology, Rare-Event Molecular Dynamics and Experimental Data

Directorate for Mathematical & Physical Sciences

Find out more...

Finding emergent structure in multi-sample biological data with the dual geometry of cells and features

National Institute of General Medical Sciences

Find out more...

CAREER: Understanding Invariant Convolutional Neural Networks through Many Particle Physics

Directorate for Mathematical & Physical Sciences

Find out more...

Collaborative Research: Data-driven Path Metrics for Machine Learning

Directorate for Mathematical & Physical Sciences

Find out more...

History

Email Address of Submitting Author

alexrd@msu.edu

Institution

Michigan State University

Country

USA

ORCID For Submitting Author

0000-0002-9640-1380

Declaration of Conflict of Interest

None

Exports