PolyBench: A Reproducible Open Benchmark Platform for Repeat-Unit-Based Polymer Property Prediction
- 1State Key Laboratory of Polymer Science and Technology, Changchun Institute of Applied Chemistry, Chinese Academy of Sciences, Changchun 130022, P. R. China
- 2School of Applied Chemistry and Engineering, University of Science and Technology of China, Hefei 230026, P. R. China
Abstract
Polymer informatics currently lacks shared benchmarks that enable reproducible comparison of property prediction methods across datasets, representations, and models. Here, we present PolyBench, a public benchmark platform comprising 39 literature-derived prediction tasks with 42,169 curated structure–property records covering 14,717 distinct repeat-unit structures, seven repeat-unit molecular representation types (five fingerprint families, physicochemical descriptors, and task-trained graph embeddings), 30 supervised baseline models (22 traditional machine-learning and 8 deep-learning methods), fixed train/test splits, and an interactive leaderboard. Across more than 10,000 supervised model evaluations spanning all 39 tasks, physicochemical descriptor-based tree ensembles emerge as strong baselines under the PolyBench protocol, though no single method achieves consistent superiority across all properties; matched repeated-split analyses on three representative tasks show that the winning configuration is stable across five seeds for the two larger tasks but not for the smallest, condition-sensitive task. The current release evaluates repeat-unit-centered polymer property prediction and does not explicitly encode higher-order factors such as molecular-weight distributions, tacticity, morphology, processing history, device architecture, or measurement protocol; tasks are therefore grouped into three provisional interpretation tiers, with condition-sensitive tasks explicitly treated as exploratory repeat-unit baselines. PolyBench is intended as a reproducible infrastructure resource for controlled method comparison, not as a complete model of chain-, sample-, or process-dependent polymer behavior, and is available at http://polybench.ciac.jl.cn (http://202.98.16.11)
Related
- MatUQ: a benchmark for uncertainty-aware out-of-distribution materials property prediction with graph neural networks
- When Do Models Win? A Learning Curve Benchmark for Molecular Property Prediction in Low-Data Regimes
- Accuracy, Reliability, and Efficiency of a MACE Machine-Learning Interatomic Potential for Aspirin: A Reproducible Benchmark for Molecular Simulation
- RaX-DT: An Open-Source Platform for Automated Molecular Docking Workflows and Reproducible Pipeline Validation
- Materials Property Prediction with a Site-Resolved Three-Dimensional Voxel Convolution Neural Network
BibTeX
@article{feng2026polybench,
title = {{PolyBench: A Reproducible Open Benchmark Platform for Repeat-Unit-Based Polymer Property Prediction}},
author = {Wenzhuo Feng and Lunyang Liu and Hongfei Li},
journal = {Polymer science \& technology (Washington, D.C.)},
year = {2026},
month = aug,
doi = {10.1021/polymscitech.6c00094},
url = {https://europepmc.org/article/PMC/PMC13721469},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - PolyBench: A Reproducible Open Benchmark Platform for Repeat-Unit-Based Polymer Property Prediction
AU - Wenzhuo Feng
AU - Lunyang Liu
AU - Hongfei Li
PY - 2026
DA - 2026/08/31
JO - Polymer science & technology (Washington, D.C.)
DO - 10.1021/polymscitech.6c00094
UR - https://europepmc.org/article/PMC/PMC13721469
AB - Polymer informatics currently lacks shared benchmarks that enable reproducible comparison of property prediction methods across datasets, representations, and models. Here, we present PolyBench, a public benchmark platform comprising 39 literature-derived prediction tasks with 42,169 curated structure–property records covering 14,717 distinct repeat-unit structures, seven repeat-unit molecular representation types (five fingerprint families, physicochemical descriptors, and task-trained graph embeddings), 30 supervised baseline models (22 traditional machine-learning and 8 deep-learning methods), fixed train/test splits, and an interactive leaderboard. Across more than 10,000 supervised model evaluations spanning all 39 tasks, physicochemical descriptor-based tree ensembles emerge as strong baselines under the PolyBench protocol, though no single method achieves consistent superiority across all properties; matched repeated-split analyses on three representative tasks show that the winning configuration is stable across five seeds for the two larger tasks but not for the smallest, condition-sensitive task. The current release evaluates repeat-unit-centered polymer property prediction and does not explicitly encode higher-order factors such as molecular-weight distributions, tacticity, morphology, processing history, device architecture, or measurement protocol; tasks are therefore grouped into three provisional interpretation tiers, with condition-sensitive tasks explicitly treated as exploratory repeat-unit baselines. PolyBench is intended as a reproducible infrastructure resource for controlled method comparison, not as a complete model of chain-, sample-, or process-dependent polymer behavior, and is available at http://polybench.ciac.jl.cn (http://202.98.16.11)
SN - 2997-3279
ER -