Scalable Low-Energy Molecular Conformer Generation with Quantum Mechanical Accuracy
Filipp Nikitin, Dylan M. Anstine, Roman Zubatyuk, Saee Gopal Paliwal, Olexandr Isayev
Highlight
Molecular geometry is crucial for biological activity and chemical reactivity; however, computational methods for generating 3D structures are limited by the vast scale of conformational space and the complexities of stereochemistry.
Abstract
Molecular geometry is crucial for biological activity and chemical reactivity; however, computational methods for generating 3D structures are limited by the vast scale of conformational space and the complexities of stereochemistry. Here we present an approach that combines an expansive dataset of molecular conformers with generative diffusion models to address this problem. We introduce ChEMBL3D, which contains over 250 million molecular geometries for 1.8 million drug-like compounds, optimized using AIMNet2 neural network potentials to a near-quantum mechanical accuracy with implicit solvent effects included. This dataset captures complex organic molecules in various protonation states and stereochemical configurations. We then developed LoQI, a stereochemistry-aware diffusion model that learns molecular geometry distributions directly from this data. Through graph augmentation, LoQI accurately generates molecular structures with targeted stereochemistry, representing a significant advance in modeling capabilities over previous generative methods. The model outperforms traditional approaches, achieving up to tenfold improvements in energy accuracy and effective recovery of optimal conformations. Benchmark tests on complex systems, including macrocycles and flexible molecules, as well as validation with crystal structures, show LoQI can perform low energy conformer search efficiently. The model code and dataset are available at https: //github.com/isayevlab/LoQI.
Keywords
Cite This Paper
@article{Nikitin2025,
author = {Nikitin, Filipp and Anstine, Dylan M. and Zubatyuk, Roman and Paliwal, Saee Gopal and Isayev, Olexandr},
title = {Scalable Low-Energy Molecular Conformer Generation with Quantum Mechanical Accuracy},
year = {2025},
doi = {10.26434/chemrxiv-2025-k4h7v},
url = {http://dx.doi.org/10.26434/chemrxiv-2025-k4h7v},
publisher = {American Chemical Society (ACS)},
keywords = {neural network},
researchAreas = {ml-potentials, generative-ai, drug-discovery},
highlight = {Molecular geometry is crucial for biological activity and chemical reactivity; however, computational methods for generating 3D structures are limited by the vast scale of conformational space and the complexities of stereochemistry.}
} Copied to clipboard!
Related Research Areas
Related Publications
Generative and reinforcement learning approaches for the automated de novo design of bioactive compounds
Communications Chemistry, 5 (2022)
AbstractDeep generative neural networks have been used increasingly in computational chemistry for de novo design of molecules with desired properties.
Teaching a neural network to attach and detach electrons from molecules
Nature Communications, 12 (2021)
Abstract Interatomic potentials derived with Machine Learning algorithms such as Deep-Neural Networks (DNNs), achieve the accuracy of high-fidelity quantum mechanical (QM) methods in areas traditionally dominated by empirical force fields and allow performing massive simulations.
AIQM3: Targeting Coupled-Cluster Accuracy with Semi-Empirical Speed Across Seven Main Group Elements
(2025)
The AIQM series methods are successful neural network-based models that target coupled-cluster accuracy while maintaining high robustness and transferability across various tasks by leveraging Δ-learning.
Teaching a Neural Network to Attach and Detach Electrons from Molecules
(2020)
Physics-inspired Artificial Intelligence (AI) is at the forefront of methods development in molecular modeling and computational chemistry.
A Bag of Tricks for Automated De Novo Design of Molecules with the Desired Properties: Application to EGFR Inhibitor Discovery
(2021)
Deep generative neural networks have been used increasingly in computational chemistry for de novo design of molecules with desired properties.