A Machine-Learned Symbolic Committor for a Chemical Reaction: Isomerization in Retinal and p‑Coumaric Acid
6 affiliations
- 1Department of Biology, Chemistry and Pharmacy, Freie Universität Berlin, 14195 Berlin, Germany
- 2Institute of Computer Science, Goethe University Frankfurt, 60325 Frankfurt am Main, Germany
- 3Department of Cellular, Computational and Integrative Biology, University of Trento, 38123 Trento, Italy
- 4Frankfurt Institute for Advanced Studies, 60438 Frankfurt am Main, Germany
- 5Department of Physics, University of Trento, 38123 Trento, Italy
- 6Cluster of Excellence SubCellular Architecture of Life (SCALE), Goethe University Frankfurt, Frankfurt 60629, Germany
Abstract
The thermal cis-trans isomerization of CC double bonds in chromophores is a prototypical high-barrier reaction whose mechanism hinges on subtle out-of-plane bending motions. Combining machine-learning-guided path sampling (AIMMD) with symbolic regression, we learn an interpretable committor for two chemically distinct chromophores, N-retinylidene-lysine and p-coumaric acid anion, in vacuo from unbiased molecular dynamics trajectories generated by two-way shooting. Parametrizing the committor with a neural network and sampling it uniformly across the full range allows the model to resolve the reaction coordinate across the full transition region, not only at the isocommittor surface pB (x) = 0.5. A feature-attribution analysis identifies four proper dihedrals around the reactive bond as the informative coordinates, while the improper dihedrals at the sp2-hybridized carbon atoms prove unsuitable because reactant, transition, and product states share the same values. Symbolic regression then distills the committor into compact analytical expressionsto our knowledge the first committor both learned and distilled into closed form for a chemical reactionand shows that a coupling of all four dihedrals is required to reproduce the S-shaped, stepwise pathway seen in the transition-path ensemble. This S-shape is absent from the minimum free-energy path: it arises from the dynamics of the short transition events combined with the mass asymmetry between heavy-atom and hydrogen-bearing dihedrals, and the larger asymmetry of p-coumaric acid yields the more pronounced S-shape this picture predicts. An interpretable, machine-learned committor, though a function of configuration alone, thus exposes dynamical features of the mechanism to which the free-energy surface is blind. The workflow requires no prior assumptions about the reaction coordinate and extends naturally to other high-barrier isomerizations and, combined with a reactive potential, opens a path toward bond-breaking chemical reactions.
Related
- All Paths All at Once: A Quantum Monte Carlo and Neural Committor Approach to Reaction Pathway Search
- External Force-free Unpinning and Wave-Break of Pinned Spirals in a Chemical Reaction-Diffusion System
- AuditRxn: Auditable Fast-Weight Memories for Multi-Step Chemical Reaction Prefix-Prediction
- Phase Resetting of the Pinned Pair of Spirals through Transient Chaotic Dynamics in a Chemical Reaction-Diffusion System
- Simulating Chemical Reaction Dynamics Using Sample Based Quantum Diagonalization: A Quantum-Centric Supercomputing Approach
BibTeX
@article{topfer2026machinelearned,
title = {{A Machine-Learned Symbolic Committor for a Chemical Reaction: Isomerization in Retinal and p‑Coumaric Acid}},
author = {Kai Töpfer and Gianmarco Lazzeri and Vittoria Ossanna and Christopher J. I. Bläß and Florian Renner and Gianluca Lattanzi and Roberto Covino and Bettina G. Keller},
journal = {Journal of Chemical Theory and Computation},
year = {2026},
month = oct,
doi = {10.1021/acs.jctc.6c01496},
url = {https://doi.org/10.1021/acs.jctc.6c01496},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - A Machine-Learned Symbolic Committor for a Chemical Reaction: Isomerization in Retinal and p‑Coumaric Acid
AU - Kai Töpfer
AU - Gianmarco Lazzeri
AU - Vittoria Ossanna
AU - Christopher J. I. Bläß
AU - Florian Renner
AU - Gianluca Lattanzi
AU - Roberto Covino
AU - Bettina G. Keller
PY - 2026
DA - 2026/10/30
JO - Journal of Chemical Theory and Computation
DO - 10.1021/acs.jctc.6c01496
UR - https://doi.org/10.1021/acs.jctc.6c01496
AB - The thermal cis-trans isomerization of CC double bonds in chromophores is a prototypical high-barrier reaction whose mechanism hinges on subtle out-of-plane bending motions. Combining machine-learning-guided path sampling (AIMMD) with symbolic regression, we learn an interpretable committor for two chemically distinct chromophores, N-retinylidene-lysine and p-coumaric acid anion, in vacuo from unbiased molecular dynamics trajectories generated by two-way shooting. Parametrizing the committor with a neural network and sampling it uniformly across the full range allows the model to resolve the reaction coordinate across the full transition region, not only at the isocommittor surface pB (x) = 0.5. A feature-attribution analysis identifies four proper dihedrals around the reactive bond as the informative coordinates, while the improper dihedrals at the sp2-hybridized carbon atoms prove unsuitable because reactant, transition, and product states share the same values. Symbolic regression then distills the committor into compact analytical expressionsto our knowledge the first committor both learned and distilled into closed form for a chemical reactionand shows that a coupling of all four dihedrals is required to reproduce the S-shaped, stepwise pathway seen in the transition-path ensemble. This S-shape is absent from the minimum free-energy path: it arises from the dynamics of the short transition events combined with the mass asymmetry between heavy-atom and hydrogen-bearing dihedrals, and the larger asymmetry of p-coumaric acid yields the more pronounced S-shape this picture predicts. An interpretable, machine-learned committor, though a function of configuration alone, thus exposes dynamical features of the mechanism to which the free-energy surface is blind. The workflow requires no prior assumptions about the reaction coordinate and extends naturally to other high-barrier isomerizations and, combined with a reactive potential, opens a path toward bond-breaking chemical reactions.
SN - 1549-9618
SN - 1549-9626
ER -