Saved in:
Bibliographic Details
Main Authors: Xu, Jiaxin, Liu, Gang, Guo, Ruilan, Jiang, Meng, Luo, Tengfei
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.23491
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910899166511104
author Xu, Jiaxin
Liu, Gang
Guo, Ruilan
Jiang, Meng
Luo, Tengfei
author_facet Xu, Jiaxin
Liu, Gang
Guo, Ruilan
Jiang, Meng
Luo, Tengfei
contents The advancement of polymer informatics has been significantly propelled by the integration of machine learning (ML) techniques, enabling the rapid prediction of polymer properties and expediting the discovery of high-performance polymeric materials. However, the field lacks a standardized workflow that encompasses prediction accuracy, uncertainty quantification, ML interpretability, and polymer synthesizability. In this study, we introduce POINT$^{2}$ (POlymer INformatics Training and Testing), a comprehensive benchmark database and protocol designed to address these critical challenges. Leveraging the existing labeled datasets and the unlabeled PI1M dataset, a collection of approximately one million virtual polymers generated via a recurrent neural network trained on the realistic polymers, we develop an ensemble of ML models, including Quantile Random Forests, Multilayer Perceptrons with dropout, Graph Neural Networks, and pretrained large language models. These models are coupled with diverse polymer representations such as Morgan, MACCS, RDKit, Topological, Atom Pair fingerprints, and graph-based descriptors to achieve property predictions, uncertainty estimations, model interpretability, and template-based polymerization synthesizability across a spectrum of properties, including gas permeability, thermal conductivity, glass transition temperature, melting temperature, fractional free volume, and density. The POINT$^{2}$ database can serve as a valuable resource for the polymer informatics community for polymer discovery and optimization.
format Preprint
id arxiv_https___arxiv_org_abs_2503_23491
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle POINT$^{2}$: A Polymer Informatics Training and Testing Database
Xu, Jiaxin
Liu, Gang
Guo, Ruilan
Jiang, Meng
Luo, Tengfei
Materials Science
Artificial Intelligence
Machine Learning
The advancement of polymer informatics has been significantly propelled by the integration of machine learning (ML) techniques, enabling the rapid prediction of polymer properties and expediting the discovery of high-performance polymeric materials. However, the field lacks a standardized workflow that encompasses prediction accuracy, uncertainty quantification, ML interpretability, and polymer synthesizability. In this study, we introduce POINT$^{2}$ (POlymer INformatics Training and Testing), a comprehensive benchmark database and protocol designed to address these critical challenges. Leveraging the existing labeled datasets and the unlabeled PI1M dataset, a collection of approximately one million virtual polymers generated via a recurrent neural network trained on the realistic polymers, we develop an ensemble of ML models, including Quantile Random Forests, Multilayer Perceptrons with dropout, Graph Neural Networks, and pretrained large language models. These models are coupled with diverse polymer representations such as Morgan, MACCS, RDKit, Topological, Atom Pair fingerprints, and graph-based descriptors to achieve property predictions, uncertainty estimations, model interpretability, and template-based polymerization synthesizability across a spectrum of properties, including gas permeability, thermal conductivity, glass transition temperature, melting temperature, fractional free volume, and density. The POINT$^{2}$ database can serve as a valuable resource for the polymer informatics community for polymer discovery and optimization.
title POINT$^{2}$: A Polymer Informatics Training and Testing Database
topic Materials Science
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2503.23491