TorsionNet: A Deep Neural Network to Rapidly Predict Small Molecule Torsion Energy Profiles with the Accuracy of Quantum Mechanics

24 December 2020, Version 1
This content is a preprint and has not undergone peer review at the time of posting.


TorsionNet: A Deep Neural Network to Rapidly Predict Small Molecule Torsion Energy Profiles with the Accuracy of Quantum Mechanics

Brajesh K. Rai*,1, Vishnu Sresht1, Qingyi Yang2, Ray Unwalla2, Meihua Tu2, Alan M. Mathiowetz2, and Gregory A. Bakken3

1Simulation and Modeling Sciences and 2Medicine Design, Pfizer Worldwide Research Development and Medical, 610 Main Street, Cambridge, Massachusetts 02139, United States

3Digital, Pfizer, Eastern Point Road, Groton, Connecticut 06340, United States


Fast and accurate assessment of small molecule dihedral energetics is crucial for molecular design and optimization in medicinal chemistry. Yet, accurate prediction of torsion energy profiles remains a challenging task as current molecular mechanics methods are limited by insufficient coverage of druglike chemical space and accurate quantum mechanical (QM) methods are too expensive. To address this limitation, we introduce TorsionNet, a deep neural network (DNN) model specifically developed to predict small molecule torsion energy profiles with QM-level accuracy. We applied active learning to identify nearly 50k fragments (with elements H, C, N, O, F, S, and Cl) that maximized the coverage of our corporate library and leveraged massively parallel cloud computing resources to perform DFT torsion scan of these fragments, generating a training dataset of 1.2 million DFT energies. By training TorsionNet on this dataset, we obtain a model that can rapidly predict the torsion energy profile of typical druglike fragments with DFT-level accuracy. Importantly, our method also provides a direct estimate of the uncertainty in the predicted profiles without any additional calculations. In this report, we show that TorsionNet can reliably identify the preferred dihedral geometries observed in crystal structures. We also present practical applications of TorsionNet that demonstrate how consideration of DNN-based strain energy leads to substantial improvement in existing lead discovery and design workflows. A benchmark dataset (TorsionNet500) comprising 500 chemically diverse fragments with DFT torsion profiles (12k DFT-optimized geometries and energies) has been created and is made freely available.


Neural network
Deep learning
Machine learning
Quantum mechanics
Strain energy
Conformational strain
Cloud computing

Supplementary materials

Brajesh Rai Torsion strain model manuscript SI


Comments are not moderated before they are posted, but they can be removed by the site moderators if they are found to be in contravention of our Commenting Policy [opens in a new tab] - please read this policy before you post. Comments should be used for scholarly discussion of the content in question. You can find more information about how to use the commenting feature here [opens in a new tab] .
This site is protected by reCAPTCHA and the Google Privacy Policy [opens in a new tab] and Terms of Service [opens in a new tab] apply.