Representing chemical and enzymatic reactions in fingerprint space for applicability filtering and classification
Abstract
Molecular and reaction fingerprints are widely used as static descriptors, but their relationship to graph-level reaction application remains unclear. We address this question in counted Extended-Connectivity Fingerprint (ECFP) space, representing reactions as signed differences between product and substrate fingerprints. We define ECFP-compatible templates, for which graph-level reaction application induces a constant fingerprint displacement, yielding a functorial mapping from graph transformations to affine translations in fingerprint space. We also introduce reaction-center ECFPs to encode the local environments required for template application and to provide a fast coordinate-wise prefilter for graph-level reaction applicability. We evaluate this framework on USPTO-50k and MetaNetX reactions across a range of ECFP radii. Both representations carry predictive information for reaction-class and enzyme-class classification, with reaction-center ECFPs contributing information not captured by reaction ECFPs alone. This framework connects reaction templates and reaction fingerprints to molecular pathway search and reaction-property prediction in fingerprint space.
Versions
Related
- Multiscale Neural Network Potential with Anisotropic Message Passing for the Fast and Accurate Simulation of Protein Dynamics and Enzymatic Reactions
- Morgan Fingerprint Classification Prioritizes Autophagy Modulators While Transcriptome Regression Fails to Distinguish Opposing Modulators
- Efficient tensorized evaluation of permutation invariant polynomials for representing potential energy surfaces
- BigFingerprint: A Topology-aware Extended-connectivity Fingerprint for Polymers
- Auditing frozen chemical language model embeddings for drug-delivery screening: fingerprint baselines, random-initialization controls, and scaffold-memorization control tasks
BibTeX
@article{meyer2026representing,
title = {{Representing chemical and enzymatic reactions in fingerprint space for applicability filtering and classification}},
author = {Philippe Meyer and Thomas Duigou and Guillaume Gricourt and Jean-Loup Faulon},
journal = {Journal of Cheminformatics},
year = {2026},
month = nov,
doi = {10.1186/s13321-026-01322-2},
url = {https://link.springer.com/article/10.1186/s13321-026-01322-2},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Representing chemical and enzymatic reactions in fingerprint space for applicability filtering and classification
AU - Philippe Meyer
AU - Thomas Duigou
AU - Guillaume Gricourt
AU - Jean-Loup Faulon
PY - 2026
DA - 2026/11/06
JO - Journal of Cheminformatics
DO - 10.1186/s13321-026-01322-2
UR - https://link.springer.com/article/10.1186/s13321-026-01322-2
AB - Molecular and reaction fingerprints are widely used as static descriptors, but their relationship to graph-level reaction application remains unclear. We address this question in counted Extended-Connectivity Fingerprint (ECFP) space, representing reactions as signed differences between product and substrate fingerprints. We define ECFP-compatible templates, for which graph-level reaction application induces a constant fingerprint displacement, yielding a functorial mapping from graph transformations to affine translations in fingerprint space. We also introduce reaction-center ECFPs to encode the local environments required for template application and to provide a fast coordinate-wise prefilter for graph-level reaction applicability. We evaluate this framework on USPTO-50k and MetaNetX reactions across a range of ECFP radii. Both representations carry predictive information for reaction-class and enzyme-class classification, with reaction-center ECFPs contributing information not captured by reaction ECFPs alone. This framework connects reaction templates and reaction fingerprints to molecular pathway search and reaction-property prediction in fingerprint space.
SN - 1758-2946
ER -