Strain Problems got you in a Twist? Try StrainRelief: A Quantum-Accurate Tool for Ligand Strain Calculations

2025-03-17

AI Summary

In structure-based drug design, accurately computing ligand strain energy—the energy difference between bound and unbound conformations—remains a persistent challenge. To address this, we present the first application of the equivariant many-body atomic cluster expansion (MACE) neural network potential (NNP) model to predict small-molecule ligand strain energies. Trained on a large-scale dataset of neutral organic molecules at the DFT level, the model is specifically optimized for conformational strain assessment. On standard benchmark sets, it achieves a mean absolute error of 1.4 kcal/mol—approaching DFT-level quantum chemical accuracy and substantially outperforming existing NNP approaches. This work constitutes the first validation of MACE for predicting critical physical quantities in drug discovery. It establishes a new computational paradigm that enables efficient, high-accuracy screening of low-strain ligands, thereby advancing structure-based ligand optimization.

Technology Category

• Machine Learning: Deep Neural Architectures and Foundation Models
• Cognitive Modeling & Cognitive Systems: (Computational) Cognitive Architectures
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

Ligand strain energy, the energy difference between the bound and unbound conformations of a ligand, is an important component of structure-based small molecule drug design. A large majority of observed ligands in protein-small molecule co-crystal structures bind in low-strain conformations, making strain energy a useful filter for structure-based drug design. In this work we present a tool for calculating ligand strain with a high accuracy. StrainRelief uses a MACE Neural Network Potential (NNP), trained on a large database of Density Functional Theory (DFT) calculations to estimate ligand strain of neutral molecules with quantum accuracy. We show that this tool estimates strain energy differences relative to DFT to within 1.4 kcal/mol, more accurately than alternative NNPs. These results highlight the utility of NNPs in drug discovery, and provide a useful tool for drug discovery teams.

Problem

• Develops a tool for accurate ligand strain calculations.
• Uses quantum-accurate neural network potential for strain estimation.
• Improves drug design by filtering low-strain ligand conformations.

Innovation

• Uses MACE Neural Network Potential (NNP)
• Trained on DFT calculations database
• Estimates ligand strain with quantum accuracy