Title: Predicting Small Molecule Transfer Free Energies by Combining Molecular Dynamics Simulations and Deep Learning

Abstract

Accurately predicting small molecule partitioning and hydrophobicity is critical in the drug discovery process. There are many heterogeneous chemical environments within a cell and entire human body. For example, drugs must be able to cross the hydrophobic cellular membrane to reach their intracellular targets, and hydrophobicity is an important driving force for drug–protein binding. Atomistic molecular dynamics (MD) simulations are routinely used to calculate free energies of small molecules binding to proteins, crossing lipid membranes, and solvation but are computationally expensive. Machine learning (ML) and empirical methods are also used throughout drug discovery but rely on experimental data, limiting the domain of applicability. We present atomistic MD simulations calculating 15,000 small molecule free energies of transfer from water to cyclohexane. This large data set is used to train ML models that predict the free energies of transfer. We show that a spatial graph neural network model achieves the highest accuracy, followed closely by a 3D-convolutional neural network, and shallow learning based on the chemical fingerprint is significantly less accurate. A mean absolute error of ~4 kJ/mol compared to the MD calculations was achieved for our best ML model. We also show that including data from the MD simulation improves themore » predictions, tests the transferability of each model to a diverse set of molecules, and show multitask learning improves the predictions. This work provides insight into the hydrophobicity of small molecules and ML cheminformatics modeling, and our data set will be useful for designing and testing future ML cheminformatics methods.« less

Authors:

Bennett, W. F. Drew  ^[1];

• Search DOE PAGES for author "Bennett, W. F. Drew"
• Search DOE PAGES for ORCID "0000-0003-3993-9077"

He, Stewart ^[2]; Bilodeau, Camille L. ^[1]; Jones, Derek ^[2]; Sun, Delin ^[1]; Kim, Hyojin ^[3]; Allen, Jonathan E. ^[2]; Lightstone, Felice C. ^[1]; Ingólfsson, Helgi I.  ^[1]

• Search DOE PAGES for author "Ingólfsson, Helgi I."
• Search DOE PAGES for ORCID "0000-0002-7613-9143"

---

+ Show Author Affiliations

1. Biochemical and Biophysical Systems Group, Biosciences and Biotechnology Division, Lawrence Livermore National Laboratory, 7000 East Avenue, Livermore, California, United States
2. Global Security Computing Applications, Lawrence Livermore National Laboratory, 7000 East Avenue, Livermore, California, United States
3. Center for Applied Scientific Computing, Lawrence Livermore National Laboratory, 7000 East Avenue, Livermore, California, United States

Publication Date:

Fri Aug 14 00:00:00 EDT 2020

Research Org.:

Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)

Sponsoring Org.:

USDOE National Nuclear Security Administration (NNSA); USDOE Laboratory Directed Research and Development (LDRD) Program; American Heart Association (AHA)

OSTI Identifier:

1657273

Alternate Identifier(s):

OSTI ID: 1729734

Report Number(s):

LLNL-JRNL-774697
Journal ID: ISSN 1549-9596

Grant/Contract Number:  

AC52-07NA27344

Resource Type:

Published Article

Journal Name:

Journal of Chemical Information and Modeling

Additional Journal Information:

Journal Name: Journal of Chemical Information and Modeling; Journal ID: ISSN 1549-9596

Publisher:

American Chemical Society

Country of Publication:

United States

Language:

English

Subject:

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY; Free energy; Interfaces; Molecular modeling; Molecules; Small molecules