PolyNet: A Python Package for Polymer Informatics
13 affiliations
- 1School of Chemistry
- 2University of Nottingham University Park
- 3GSK Carbon Neutral Laboratories for Sustainable Chemistry, University of Nottingham, Jubilee Campus, Triumph Road, Nottingham, UK, NG7 2TU
- 4Digital Research Service, University of Nottingham, Kings Meadow Campus, Lenton Lane, Nottingham, UK, NG7 2NR
- 5School of Pharmacy
- 6University Park
- 7Monash Institute of Pharmaceutical Sciences
- 8Monash University
- 9Biomedicine and Environment
- 10La Trobe University
- 11La Trobe Institute for Molecular Sciences
- 12Medical School
- 13University of Nottingham
Abstract
Polymers are used in a wide range of industries for diverse applications but formulating them to attain desired properties remains a challenging task. Polymer informatics has emerged as a powerful approach for the rational design of materials. Here, we present PolyNet, an open-source Python package that provides an end-to-end workflow for polymer informatics. PolyNet: 1) reads and validates datasets of polymer properties, including the monomer structures and their molar ratios; 2) creates vector- and graph-based representations of the polymers; 3) trains and optimises traditional machine learning (ML) models and graph neural networks (GNNs); 4) compares representations and models statistically; 5) deploys the models to screen in silico libraries of polymers, flagging polymers outside the applicability domain of the models and estimating their expected prediction error; and 6) interprets the models to understand structure–property relationships. PolyNet provides unique features such as: modelling of homopolymers and copolymers with any number of components, using the molar ratio of monomers in both vector- and graph-based representations; acceptance of textual representations of monomers or repeating units; calculation of polyBERT fingerprints and PolyMetriX and RDKit descriptors and fingerprints and accepting standalone user precalculated representations; benchmarking of all representation–model combinations on identical data splits using paired statistical tests; and chemically interpretable explanations through fragment-level attribution for GNNs and SHAP analysis for traditional ML models. Every experiment automatically records its configuration, data splits, hyperparameter search spaces and trained models, supporting full reproducibility in line with FAIR principles. PolyNet can be used through Python scripts, a command-line interface, or a graphical user interface for researchers without programming experience. We exemplify PolyNet by two case studies: glass transition temperature prediction for homopolymers, where cluster-based data splits showed that random splits overestimate model performance, the applicability domain identified less reliable predictions, and the model explanations recovered the known effect of chain mobility on T g ; and ¹⁹F MRI signal-to-noise ratio prediction for copolymers, where encoding monomer molar ratios is key to accurate predictions.
Related
- TASTET: a Python package for geometry-driven selection of representative atomistic structures from large configurational spaces
- A review on foundation models for polymer informatics
- AdaptDelivery: a polymer informatics platform for predicting structural properties of polymers via machine learning
- Polymer Informatics Atlas: Property-Specific Representations, Chemistry-Aware Generalization, and Reliability-Aware Machine Learning Across Five Polymer Properties
- Polymer Informatics in the Era of Foundation Models: From Representation to Autonomous Design
BibTeX
@misc{aguilarbejarano2026polynet,
title = {{PolyNet: A Python Package for Polymer Informatics}},
author = {Eduardo Aguilar-Bejarano and Morgan R Alexander and David Winkler and Grazziela Figueredo},
howpublished = {ChemRxiv},
year = {2026},
month = oct,
doi = {10.26434/chemrxiv.15010453/v1},
url = {https://chemrxiv.org/doi/full/10.26434/chemrxiv.15010453/v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - PolyNet: A Python Package for Polymer Informatics
AU - Eduardo Aguilar-Bejarano
AU - Morgan R Alexander
AU - David Winkler
AU - Grazziela Figueredo
PY - 2026
DA - 2026/10/14
PB - ChemRxiv
DO - 10.26434/chemrxiv.15010453/v1
UR - https://chemrxiv.org/doi/full/10.26434/chemrxiv.15010453/v1
AB - Polymers are used in a wide range of industries for diverse applications but formulating them to attain desired properties remains a challenging task. Polymer informatics has emerged as a powerful approach for the rational design of materials. Here, we present PolyNet, an open-source Python package that provides an end-to-end workflow for polymer informatics. PolyNet: 1) reads and validates datasets of polymer properties, including the monomer structures and their molar ratios; 2) creates vector- and graph-based representations of the polymers; 3) trains and optimises traditional machine learning (ML) models and graph neural networks (GNNs); 4) compares representations and models statistically; 5) deploys the models to screen in silico libraries of polymers, flagging polymers outside the applicability domain of the models and estimating their expected prediction error; and 6) interprets the models to understand structure–property relationships. PolyNet provides unique features such as: modelling of homopolymers and copolymers with any number of components, using the molar ratio of monomers in both vector- and graph-based representations; acceptance of textual representations of monomers or repeating units; calculation of polyBERT fingerprints and PolyMetriX and RDKit descriptors and fingerprints and accepting standalone user precalculated representations; benchmarking of all representation–model combinations on identical data splits using paired statistical tests; and chemically interpretable explanations through fragment-level attribution for GNNs and SHAP analysis for traditional ML models. Every experiment automatically records its configuration, data splits, hyperparameter search spaces and trained models, supporting full reproducibility in line with FAIR principles. PolyNet can be used through Python scripts, a command-line interface, or a graphical user interface for researchers without programming experience. We exemplify PolyNet by two case studies: glass transition temperature prediction for homopolymers, where cluster-based data splits showed that random splits overestimate model performance, the applicability domain identified less reliable predictions, and the model explanations recovered the known effect of chain mobility on T g ; and ¹⁹F MRI signal-to-noise ratio prediction for copolymers, where encoding monomer molar ratios is key to accurate predictions.
ER -