Steerable Single-step Retrosynthesis with Electron-pushing Discrete Flow Matching and Feynman-Kac Steering
Abstract
Expert chemists perform retrosynthetic analysis in a strategic manner, where each reaction in a route is employed with a specific purpose, combined with mechanistic reasoning represented as electron-pushing arrows to visualize how bonds are formed or broken via electron redistribution. Yet contemporary single-step retrosynthesis models exhibit neither of these properties: their learned reaction distribution is fixed to that of the training data, and reactions are predicted via de-novo generation of the precursors or molecular graph edits, omitting the electron redistribution that governs the chemical transformations. We introduce Verso MAELLE, the first electron-pushing-based single-step retrosynthetic model, representing disconnections as continuous-time Markov chains (CTMC) comprised of edits in the electron space, and is trainable using a discrete flow matching formulation. Being a generative model, Verso MAELLE is optionally steerable at inference time through the Feynman-Kac (FK) framework, using rewards that promote certain types of disconnections. We show that besides in-distribution learning, Verso MAELLE can be steered toward cyclization reactions which are scaffold-constructive but underrepresented in the training corpus, via a ring-breaking reward. As a proof of concept, we show how the electron-pushing reasoning, learned from patented data, combined with a domino incentivizing reward, could steer Verso MAELLE toward creative and strategic disconnections, demonstrated on the key domino sequence that was used to synthesize Punctaporonin U, a complex natural product of the sesquiterpene family.
Related
- MIRRA: Fast, High-Fidelity Molecular Generation with Chemistry-Informed Discrete Flow Matching
- Equivariant Flow Matching for Electron Density Prediction
- RetroAgent: Harnessing LLMs to Search Over Structured Memory for Agentic Retrosynthesis Planning
- Chemist-aligned retrosynthesis by ensembling diverse inductive bias models
- RetroMol: Knowledge Distillation of Energy-Based Retrosynthesis Models
BibTeX
@misc{susanu2026steerable,
title = {{Steerable Single-step Retrosynthesis with Electron-pushing Discrete Flow Matching and Feynman-Kac Steering}},
author = {Octavian Susanu and Nguyen Xuan-Vu and Philippe Schwaller},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.03696},
eprint = {2611.03696},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.03696},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Steerable Single-step Retrosynthesis with Electron-pushing Discrete Flow Matching and Feynman-Kac Steering
AU - Octavian Susanu
AU - Nguyen Xuan-Vu
AU - Philippe Schwaller
PY - 2026
DA - 2026/11/01
PB - arXiv
DO - 10.48550/arxiv.2611.03696
UR - https://arxiv.org/abs/2611.03696
AB - Expert chemists perform retrosynthetic analysis in a strategic manner, where each reaction in a route is employed with a specific purpose, combined with mechanistic reasoning represented as electron-pushing arrows to visualize how bonds are formed or broken via electron redistribution. Yet contemporary single-step retrosynthesis models exhibit neither of these properties: their learned reaction distribution is fixed to that of the training data, and reactions are predicted via de-novo generation of the precursors or molecular graph edits, omitting the electron redistribution that governs the chemical transformations. We introduce Verso MAELLE, the first electron-pushing-based single-step retrosynthetic model, representing disconnections as continuous-time Markov chains (CTMC) comprised of edits in the electron space, and is trainable using a discrete flow matching formulation. Being a generative model, Verso MAELLE is optionally steerable at inference time through the Feynman-Kac (FK) framework, using rewards that promote certain types of disconnections. We show that besides in-distribution learning, Verso MAELLE can be steered toward cyclization reactions which are scaffold-constructive but underrepresented in the training corpus, via a ring-breaking reward. As a proof of concept, we show how the electron-pushing reasoning, learned from patented data, combined with a domino incentivizing reward, could steer Verso MAELLE toward creative and strategic disconnections, demonstrated on the key domino sequence that was used to synthesize Punctaporonin U, a complex natural product of the sesquiterpene family.
ER -