Resolving Positional Markush Structures for Chemical Reaction Extraction
- 1Institut de Chimie Moléculaire de l’Université de Bourgogne (UMR, Université Bourgogne Europe, 9, av. Alain Savary, Dijon, France, 21000
Abstract
The automated extraction of chemical reaction data from scientific literature remains very challenging mainly due to the visual complexity and heterogeneity of published graphical schemes. In particular, substrate scopes containing positional Markush structures pose a significant challenge for current Optical Chemical Structure Recognition (OCSR) and reaction-extraction systems, as their resolution requires combining molecular recognition with precise spatial reasoning. Herein, we introduce a deterministic, coordinate-based extraction pipeline designed to resolve positional Markush structures in reaction schemes. Building upon a fine-tuned version of the graph-prediction OCSR module MolScribe, our approach uses deterministic geometric rules based on 2D molecular coordinates to infer R-group attachment points and generate topologically valid molecular representations. To evaluate this approach, we introduce two curated benchmarks: MIPub-2k (Molecular Images from Publication - Université Bourgogne Europe) comprising 2,128 literature-derived molecular image crops for OCSR evaluation and MIReactPub (Markush template-based Image of Reaction from Publication – Université Bourgogne Europe) comprising 450 reactions from 23 schemes containing positional Markush structures for reaction-level assessment. The complete pipeline achieves an end-to-end F1 score of 0.46, increasing to 0.54 for schemes without textual-dependent ambiguities. Slightly reorganizing figures doubles the F1 score, demonstrating the robustness of the underlying geometric resolution while highlighting the substantial impact of visual heterogeneity in published literature on end-to-end performance. By explicitly encoding chemical and spatial constraints, our proposed approach provides a transparent and reproducible framework for resolving complex molecular representations from literature images. The resulting open-source pipeline and benchmarks provide a specialized component that can be further integrated into automated workflows for large-scale chemical information extraction.
Related
- Automated Extraction and FAIRification of Chemical Structures from Scientific Publications
- Precise Positional Readout of Molecular Barcode Structures using Solid-State Nanopores
- Resolving Photochemical Reaction Pathways Using Field-Induced Surface Hopping Simulation of fs-EUV-TRPES: The Case of Furan
- pdb2reaction: End-to-End Reaction-Path Elucidation from PDB Structures Using Machine-Learning Interatomic Potentials
- C-MAGE: Automated Extraction and Organization Engine for Molecular Representations in Chemical Documents
BibTeX
@misc{randriharimanamizara2026resolving,
title = {{Resolving Positional Markush Structures for Chemical Reaction Extraction}},
author = {Ulrick Fineddie Randriharimanamizara and Atif Anwer and Julien Roger and Fabrice Meriaudeau and Paul Fleurat-Lessard},
howpublished = {ChemRxiv},
year = {2026},
month = sep,
doi = {10.26434/chemrxiv.15009037/v1},
url = {https://chemrxiv.org/doi/full/10.26434/chemrxiv.15009037/v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - Resolving Positional Markush Structures for Chemical Reaction Extraction
AU - Ulrick Fineddie Randriharimanamizara
AU - Atif Anwer
AU - Julien Roger
AU - Fabrice Meriaudeau
AU - Paul Fleurat-Lessard
PY - 2026
DA - 2026/09/18
PB - ChemRxiv
DO - 10.26434/chemrxiv.15009037/v1
UR - https://chemrxiv.org/doi/full/10.26434/chemrxiv.15009037/v1
AB - The automated extraction of chemical reaction data from scientific literature remains very challenging mainly due to the visual complexity and heterogeneity of published graphical schemes. In particular, substrate scopes containing positional Markush structures pose a significant challenge for current Optical Chemical Structure Recognition (OCSR) and reaction-extraction systems, as their resolution requires combining molecular recognition with precise spatial reasoning. Herein, we introduce a deterministic, coordinate-based extraction pipeline designed to resolve positional Markush structures in reaction schemes. Building upon a fine-tuned version of the graph-prediction OCSR module MolScribe, our approach uses deterministic geometric rules based on 2D molecular coordinates to infer R-group attachment points and generate topologically valid molecular representations. To evaluate this approach, we introduce two curated benchmarks: MIPub-2k (Molecular Images from Publication - Université Bourgogne Europe) comprising 2,128 literature-derived molecular image crops for OCSR evaluation and MIReactPub (Markush template-based Image of Reaction from Publication – Université Bourgogne Europe) comprising 450 reactions from 23 schemes containing positional Markush structures for reaction-level assessment. The complete pipeline achieves an end-to-end F1 score of 0.46, increasing to 0.54 for schemes without textual-dependent ambiguities. Slightly reorganizing figures doubles the F1 score, demonstrating the robustness of the underlying geometric resolution while highlighting the substantial impact of visual heterogeneity in published literature on end-to-end performance. By explicitly encoding chemical and spatial constraints, our proposed approach provides a transparent and reproducible framework for resolving complex molecular representations from literature images. The resulting open-source pipeline and benchmarks provide a specialized component that can be further integrated into automated workflows for large-scale chemical information extraction.
ER -