Building a Physically Interpretable Compressed Chemical Space via Grid-Based Optimization
- 1Department of Pharmacology and Toxicology, Michigan State University, East Lansing, Michigan 48824, United States
- 2Department of Computational Mathematics, Science, and Engineering, Michigan State University, East Lansing, Michigan 48824, United States
- 3Department of Biochemistry and Molecular Biology, Michigan State University, East Lansing, Michigan 48824, United States
Abstract
In recent years, deep generative models have been increasingly adopted for molecular optimization and design. In many such models, molecules are encoded into latent spaces that provide compact representations of their features. However, these latent spaces remain difficult to interpret in physical terms, and it is unclear how much structural and molecular information is retained under compression. This limitation becomes especially important when molecular behavior depends on specific three-dimensional arrangements embedded in an environmental context. Here, we introduce COMPRESS (Compression Of Molecular Physical fields into Reduced Spatial Sites), an optimization framework that represents a small molecule using a fixed number of physically parametrized spatial sites. Each site is defined by three spatial coordinates and three interaction parameters, yielding a fixed-size representation that remains directly interpretable in physical terms. To preserve molecular information, COMPRESS representations are optimized to reproduce the density, electrostatic, and van der Waals fields of the corresponding all-atom molecule on discretized three-dimensional grids. We systematically evaluate how molecular information is retained as the number of sites, K, is reduced. Our analysis covers benzene, 20 chemically diverse chemical scaffolds, benzene dimers, protein–ligand complexes, and 10,000 molecules chosen from the GEOM-Drugs data set. Across systems, field agreement deteriorates slowly at high resolution and then undergoes a rapid, pronounced transition at lower resolution. We further find that K = 25 conformers capture about 97% of the molecules from GEOM-Drugs under a loss threshold of 0.05, which we use as an indicator of fidelity. These results show that COMPRESS can provide a fixed-size, physically interpretable molecular representation, enabling compression to be evaluated directly using molecular interaction fields and resulting physical quantities. We also introduce a decoder that reconstructs all-atom structures directly from a COMPRESS representation, showing that the representation can support molecular generation in addition to field-preservation analysis. Finally, rationally modified COMPRESS representations through changes to site charge and size or the addition or removal of sites are shown to generate realistic chemical compounds upon decoding.
Related
- From Molecular Building Blocks to Corrugated Graphitic Carbon Nitride: Chemical Origins of Structural Preference and Electronic Diversity
- Optimization of Coagulation-Flocculation with Aluminum Sulfate for the Treatment of Chemical Industry Effluent
- Interpretable Machine Learning-Guided Optimization of Laser-Driven Photocatalytic Degradation of Tetracycline Hydrochloride over ZnO/Cu1.35O/g-C3N4 Composites
- GLOSS: A Multi-Strategy Sampling Algorithm for Optimization in Vast Chemical Spaces
- Stepwise quantum chemical optimization reveals the origin of layered herringbone packing and polymorphism in polyacenes
BibTeX
@article{yoon2026building,
title = {{Building a Physically Interpretable Compressed Chemical Space via Grid-Based Optimization}},
author = {Seungmin Yoon and Alex Dickson},
journal = {Journal of Chemical Information and Modeling},
year = {2026},
month = oct,
doi = {10.1021/acs.jcim.6c01542},
url = {https://doi.org/10.1021/acs.jcim.6c01542},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Building a Physically Interpretable Compressed Chemical Space via Grid-Based Optimization
AU - Seungmin Yoon
AU - Alex Dickson
PY - 2026
DA - 2026/10/15
JO - Journal of Chemical Information and Modeling
DO - 10.1021/acs.jcim.6c01542
UR - https://doi.org/10.1021/acs.jcim.6c01542
AB - In recent years, deep generative models have been increasingly adopted for molecular optimization and design. In many such models, molecules are encoded into latent spaces that provide compact representations of their features. However, these latent spaces remain difficult to interpret in physical terms, and it is unclear how much structural and molecular information is retained under compression. This limitation becomes especially important when molecular behavior depends on specific three-dimensional arrangements embedded in an environmental context. Here, we introduce COMPRESS (Compression Of Molecular Physical fields into Reduced Spatial Sites), an optimization framework that represents a small molecule using a fixed number of physically parametrized spatial sites. Each site is defined by three spatial coordinates and three interaction parameters, yielding a fixed-size representation that remains directly interpretable in physical terms. To preserve molecular information, COMPRESS representations are optimized to reproduce the density, electrostatic, and van der Waals fields of the corresponding all-atom molecule on discretized three-dimensional grids. We systematically evaluate how molecular information is retained as the number of sites, K, is reduced. Our analysis covers benzene, 20 chemically diverse chemical scaffolds, benzene dimers, protein–ligand complexes, and 10,000 molecules chosen from the GEOM-Drugs data set. Across systems, field agreement deteriorates slowly at high resolution and then undergoes a rapid, pronounced transition at lower resolution. We further find that K = 25 conformers capture about 97% of the molecules from GEOM-Drugs under a loss threshold of 0.05, which we use as an indicator of fidelity. These results show that COMPRESS can provide a fixed-size, physically interpretable molecular representation, enabling compression to be evaluated directly using molecular interaction fields and resulting physical quantities. We also introduce a decoder that reconstructs all-atom structures directly from a COMPRESS representation, showing that the representation can support molecular generation in addition to field-preservation analysis. Finally, rationally modified COMPRESS representations through changes to site charge and size or the addition or removal of sites are shown to generate realistic chemical compounds upon decoding.
SN - 1549-9596
SN - 1549-960X
ER -