MATCHERS: a ‘chemistry-infused’ representation bridging molecular graphs and strings
4 affiliations
- 1Department of Biomedical Engineering
- 2Institute for Complex Molecular Systems (ICMS), Eindhoven University of Technology
- 3Department of Mathematics and Computer Science
- 4Freie Universität Berlin
Abstract
Molecular graphs and molecular strings are two well-established molecular representations for deep learning, with complementary strengths: while graphs make atom and bond properties explicit, strings are sequential and straightforward to generate. Here, we introduce a novel molecular representation than bridges these two representations: Multichannel Atom and Topology for Chemical Representation Series (MATCHERS). In a single representation, MATCHERS encode user-defined atomic properties, explicit molecular topology, as well as bond properties, while maintaining the sequential character typical of molecular strings. In this proof-of-concept, we show that MATCHERS outperform sequential string representations (SMILES and SELFIES) for bioactivity prediction, and that they can be used for de novo molecular design. MATCHERS illustrate the untapped opportunity of explicitly encoding chemical knowledge into new molecular representations that remain compatible with deep learning.
Related
- Chemistry-infused bandit framework for interpretable autonomous campaign of electrocatalysis
- Accept or abstain? A pre-specified test of reliability gates calibrated on held-out chemistry for molecular property and reaction-yield models
- Literature-Scale Mössbauer Data Enable Prediction, Electronic-State Interpretation, and Chemical Insight in Molecular Iron Chemistry
- A Molecular Generation–Validation Workflow Combining Reversible Junction Tree Reinforcement Learning and Semi-empirical Quantum Chemistry: A Case Study on Molecular Solar Thermal Fuels
- Performance of a minimally empirical local-hybrid density functional for molecular chemistry
BibTeX
@misc{brinkmann2026matchers,
title = {{MATCHERS: a ‘chemistry-infused’ representation bridging molecular graphs and strings}},
author = {Helena Brinkmann and Rıza Özçelik and Katarina Elez and Francesca Grisoni},
howpublished = {ChemRxiv},
year = {2026},
month = oct,
doi = {10.26434/chemrxiv.15011134/v1},
url = {https://chemrxiv.org/doi/full/10.26434/chemrxiv.15011134/v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - MATCHERS: a ‘chemistry-infused’ representation bridging molecular graphs and strings
AU - Helena Brinkmann
AU - Rıza Özçelik
AU - Katarina Elez
AU - Francesca Grisoni
PY - 2026
DA - 2026/10/27
PB - ChemRxiv
DO - 10.26434/chemrxiv.15011134/v1
UR - https://chemrxiv.org/doi/full/10.26434/chemrxiv.15011134/v1
AB - Molecular graphs and molecular strings are two well-established molecular representations for deep learning, with complementary strengths: while graphs make atom and bond properties explicit, strings are sequential and straightforward to generate. Here, we introduce a novel molecular representation than bridges these two representations: Multichannel Atom and Topology for Chemical Representation Series (MATCHERS). In a single representation, MATCHERS encode user-defined atomic properties, explicit molecular topology, as well as bond properties, while maintaining the sequential character typical of molecular strings. In this proof-of-concept, we show that MATCHERS outperform sequential string representations (SMILES and SELFIES) for bioactivity prediction, and that they can be used for de novo molecular design. MATCHERS illustrate the untapped opportunity of explicitly encoding chemical knowledge into new molecular representations that remain compatible with deep learning.
ER -