GEOM-drugs revisited: toward more chemically accurate benchmarks for 3D molecule generation
Filipp Nikitin, Ian Dunn, David Ryan Koes, Olexandr Isayev
Highlight
Revisiting GEOM drugs: corrected metrics and novel energy-based structural benchmark enable rigorous evaluation of 3D molecule generative models.
Abstract
Revisiting GEOM drugs: corrected metrics and novel energy-based structural benchmark enable rigorous evaluation of 3D molecule generative models.
Keywords
Cite This Paper
@article{Nikitin2025a,
author = {Nikitin, Filipp and Dunn, Ian and Koes, David Ryan and Isayev, Olexandr},
title = {GEOM-drugs revisited: toward more chemically accurate benchmarks for 3D molecule generation},
year = {2025},
journal = {Digital Discovery},
volume = {4},
number = {11},
pages = {3282--3291},
doi = {10.1039/d5dd00206k},
url = {http://dx.doi.org/10.1039/D5DD00206K},
publisher = {Royal Society of Chemistry (RSC)},
keywords = {generative model},
researchAreas = {generative-ai},
highlight = {Revisiting GEOM drugs: corrected metrics and novel energy-based structural benchmark enable rigorous evaluation of 3D molecule generative models.},
citations = {4}
} Copied to clipboard!
Related Research Areas
Related Publications
De novo molecule design towards biased properties via a deep generative framework and iterative transfer learning
Digital Discovery, 3, 410–421 (2024)
The RRCGAN, validated through DFT, demonstrates success in generating chemically valid molecules targeting energy gap values with 75% of the generated molecules have RE of <20% of the targeted values.
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.
Less is more: Sampling chemical space with active learning
The Journal of Chemical Physics, 148 (2018)
The development of accurate and transferable machine learning (ML) potentials for predicting molecular energetics is a challenging task.
Scalable Low-Energy Molecular Conformer Generation with Quantum Mechanical Accuracy
(2025)
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.
Discovery of Crystallizable Organic Semiconductors with Machine Learning
(2024)
Crystalline organic semiconductors are known to have improved charge carrier mobility and exciton diffusion length in comparison to their amorphous counterparts.