Chemistry-Informed Multimodal Model for Structure Elucidation in Automated Reaction Discovery
- 1Organisch-Chemisches Institut
- 2Universität Münster
- 3NXT Spectra, ChemInnovation GmbH
Abstract
Rapid and reliable structure elucidation remains a central bottleneck in automated reaction discovery, where highthroughput experimentation can generate large numbers of crude reaction mixtures faster than they can be interpreted. Gas chromatography coupled with mass spectrometry (GC-MS) provides rapid and information-rich analytical data, but identification of unknown reaction products still relies heavily on expert interpretation or spectral library matching, limiting applicability to novel compounds. Here we introduce Dynamic Mass-Aware Identification from Reaction Knowledge (DynaMAIK), a multimodal transformer framework for reaction-aware structure elucidation from GC-MS data. DynaMAIK combines electron ionization mass spectra with reaction context encoded as reactant and reagent SMILES to predict product structures and molecular formulas. Trained on more than three million reaction–spectrum pairs derived from curated reaction databases, spectral simulation and experimental spectra, DynaMAIK achieved 87% top-1 and 94% top-10 structure accuracy on a held-out experimental test set. Comparisons with spectrum-only and reaction-only models, together with ablation and scrambling experiments, show that spectral evidence and reaction-derived context provide complementary constraints for product identification. Application to high-throughput thiolation reactions demonstrates accurate product assignment directly from experimental screening data. DynaMAIK establishes context-aware GC-MS interpretation as a scalable route toward automated analytical feedback in reaction discovery workflows.
Related
- Pushing the Limits of One-Dimensional NMR Spectroscopy for Automated Structure Elucidation Using Artificial Intelligence
- End-to-end multimodal structure elucidation from raw spectra combining contrastive learning and evolutionary algorithms
- Context-Aware Automated NMR Structure Elucidation
- A Modular Rapid-Injection NMR for Structure Elucidation and Kinetic Analysis.
- MAST: Motif-Augmented Diffusion with Search Tree for Spectroscopic Molecular Structure Elucidation
BibTeX
@misc{niedziella2026chemistryinformed,
title = {{Chemistry-Informed Multimodal Model for Structure Elucidation in Automated Reaction Discovery}},
author = {Maik G. Niedziella and Philipp M. Pflüger and Ajnabiul Hoque and Frank Glorius},
howpublished = {ChemRxiv},
year = {2026},
month = sep,
doi = {10.26434/chemrxiv.15008991/v1},
url = {https://chemrxiv.org/doi/full/10.26434/chemrxiv.15008991/v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Chemistry-Informed Multimodal Model for Structure Elucidation in Automated Reaction Discovery
AU - Maik G. Niedziella
AU - Philipp M. Pflüger
AU - Ajnabiul Hoque
AU - Frank Glorius
PY - 2026
DA - 2026/09/17
PB - ChemRxiv
DO - 10.26434/chemrxiv.15008991/v1
UR - https://chemrxiv.org/doi/full/10.26434/chemrxiv.15008991/v1
AB - Rapid and reliable structure elucidation remains a central bottleneck in automated reaction discovery, where highthroughput experimentation can generate large numbers of crude reaction mixtures faster than they can be interpreted. Gas chromatography coupled with mass spectrometry (GC-MS) provides rapid and information-rich analytical data, but identification of unknown reaction products still relies heavily on expert interpretation or spectral library matching, limiting applicability to novel compounds. Here we introduce Dynamic Mass-Aware Identification from Reaction Knowledge (DynaMAIK), a multimodal transformer framework for reaction-aware structure elucidation from GC-MS data. DynaMAIK combines electron ionization mass spectra with reaction context encoded as reactant and reagent SMILES to predict product structures and molecular formulas. Trained on more than three million reaction–spectrum pairs derived from curated reaction databases, spectral simulation and experimental spectra, DynaMAIK achieved 87% top-1 and 94% top-10 structure accuracy on a held-out experimental test set. Comparisons with spectrum-only and reaction-only models, together with ablation and scrambling experiments, show that spectral evidence and reaction-derived context provide complementary constraints for product identification. Application to high-throughput thiolation reactions demonstrates accurate product assignment directly from experimental screening data. DynaMAIK establishes context-aware GC-MS interpretation as a scalable route toward automated analytical feedback in reaction discovery workflows.
ER -