- Cao, X., Zhang, Y., Sun, Z., Yin, H. & Feng, Y. Machine learning in polymer science: A new lens for physical and chemical exploration. Progress in Materials Science 156, 101544 (2026). https://doi.org:https://doi.org/10.1016/j.pmatsci.2025.101544
This table lists various databases that are valuable for conducting big data studies on polymer materials. Each database is accompanied by its link/source and the property data it provides.
| Database | Link/Source | Property data |
|---|---|---|
| Polymer: a property database | Book | Parameters of solution and bulk properties, and manufacturing procedures, which are associated with polymer manufacturing, processing, and applications. |
| Handbook of polymers | Book | Polymer information of polymeric material used by the plastics and other polymer-related industries, and also used in the polymer research in the electronics, pharmaceutical, medical, and space fields. |
| Prediction of polymer properties | Book | Summary of fundamental models and derived polymers, including the van der Waals volume, cohesive energy, heat capacity, glass transition temperature, density, solubility parameter, and modulus etc. |
| Polymer synthesis: theory and practice | Book | Recipes and examples of polymer synthesis, from traditional polymers to functional polymers. |
| Polymer handbook | Book | A comprehensive source of information that refers to the polymer molecule, the solid state of polymers, and polymer solutions. |
| Handbook of Phase Equilibria and Thermodynamic Data of Aqueous Polymer Solutions | Book | Providing a comprehensive collection of thermodynamic data of polymer solutions. |
| PolyInfo | https://polymer.nims.go.jp | About 100 types of properties including thermal, electrical and mechanical properties are covered. The main data source is academic literature on polymers. |
| CROW: polymer properties database | https://polymerdatabase.com | Glass transition temperature , melting point, degradation temperature, density, tensile strength, elasticity, heat capacity, dielectric constant, glass transition temperature, transparency. |
| Polymer: a property database | https://poly-dbmanual.com | Including capabilities, melting-point, density, heat conductivity, tensile strength, elasticity modulus, elongation, and chemical information. |
| CAMPUS plastics | https://www.campusplastics.com | Thermal properties, mechanical properties, fire resistivity, dielectric constant, volume resistivity, refractive index. |
| Landolt-Börnstein | https://materials.springer.com | Mainly providing rheological, mechanical, thermal and electrical properties of materials. |
| Khazana database | https://khazana.gatech.edu | Atomization energy, bandgaps, dielectric constant, glass transition temperature, density, solubility parameter. |
| Polymer Genome Platform | https://polymergenome.org | Thermal properties, mechanical properties, fire resistivity, tensile strength, elasticity modulus, glass transition temperature, mechanical properties or predicting melting stability, electronic structure properties. |
| Materials Project | https://materialsproject.org | A single repository of information about the 3D structures of protein, nucleic acids, and complex assemblages. |
| Protein Data Bank (PDB) | https://www.wwpdb.org | Curating and sharing publicly-available 3D structure data on proteins. |
| NanoMine | https://materialsmine.org | Creating an integrated data resource to characterize and analyze tools with the long-term objective of promoting data-driven, multiobjective design. |
| Polymer Property Predictor and Database | https://ppdb.uchicago.edu | Demonstrating a broad methodology for multicomponent composite materials spanning metals and polymers for structural and multifunctional applications. |
| ACD/Labs NMR Databases | https://www.acdlabs.com/products/nmr/ | Providing a large collection of NMR spectral libraries available for ¹H, ¹³C, ¹⁹F, and ³¹P nucleus, and a Predictor to predict a wide range of information for polymers. |
| Polymer Science Learning Center Spectral Database | https://pslc.uwsp.edu/ | Providing databases for basic polymer and chemical information. |
| NET Synthetic Polymer MALDI Recipes Database | https://maldi.nist.gov | Consisting of methods and matrix-assisted laser desorption ionization mass spectrometry on a wide variety of synthetic polymers. |
| MATWEB Material Property Data | https://www.matweb.com | Mechanical properties, thermal properties, physical and chemical properties, and processing parameters. |
| Material Properties Database | https://www.makeitfrom.com | Thermal, thermal and electrical properties of metals, polymers and ceramics. |
| PIIM | https://piim1996.pfim | Providing data from literature, including density, glass transition temperature, melting point, and dielectric constant. |
| Polymer Scholar | https://polymerscholar.org | Glass transition temperature, melting point, tensile strength, electrical conductivity, molecular weight, solubility parameter. |
| OMG | https://zenodo.org/record/ | Focusing on the reverse polymer design by performance dynamics of synthetic polymers. |
| HTPMD | https://www.hyundai-matrl.co.kr | Full-chain data support for design and performance of polymers by molecular simulation, machine learning and high-throughput screening technologies. |
- Long, T. et al. Recent Progress of Artificial Intelligence Application in Polymer Materials. Polymers 17 (2025). https://doi.org:10.3390/polym17121667
| No. | Database | Origin of Data | Description | URL |
|---|---|---|---|---|
| 1 | Khazazna | computational | thermoplastic; mechanical, thermal, electrical properties | https://khazana.gatech.edu/dataset/ (accessed on 18 February 2020) |
| 2 | PolyInfo | empirical | thermoplastic; mechanical, optical, thermal, rheological properties | https://polymer.nims.go.jp/ (accessed on 22 January 2021) |
| 3 | Polymer property predictor and database | empirical | Flory–Huggins parameter, glass transition temperature, binary polymer solution cloud point | https://pppdb.uchicago.edu/ (accessed on 30 March 2016) |
| 4 | Material properties database | empirical/computational | thermoplastic, thermoset, rubber; mechanical, thermal, electrical properties | https://www.makeitfrom.com/ (accessed on 16 April 2020) |
| 5 | CROW polymer properties database | empirical/computational | thermoplastic, rubber, fiber; physical, thermal properties | https://polymerdatabase.com/ (accessed on 2 March 2019) |
| 6 | PI1M | computational | virtual polymers; physical, thermal, electrical properties | https://github.com/RUIMINMA1996/PI1M (accessed on 11 December 2020) |
| 7 | Dortmund database | computational | physical properties, phase equilibrium data | https://ddbst.com/ (accessed on 7 October 2020) |
| 8 | AI plus Polymers | empirical/computational | thermoset, thermoplastic; physical, mechanical, thermal, electrical properties | https://polymergenome.ecust.edu.cn/ (accessed on 23 March 2019) |
Compilation Table of Polymer (Homopolymer/Copolymer) - Related Datasets
| Dataset Name | Core Content & Application Field | Availability | Access Link | Notes |
|---|---|---|---|---|
| PoLyInfo: Polymer Database for Polymeric Materials Design | Provides experimental property data of homopolymers and copolymers, applied in polymeric materials design | Requires registration | https://ieeexplore.ieee.org/document/6076416?utm_source=acs&getft_integrator=acs | - |
| Polymer Genome: A Data-Powered Polymer Informatics Platform for Property Predictions | A data-driven polymer informatics platform for property prediction of homopolymers and copolymers | Requires registration; application submitted 1 year ago but not approved yet | https://www.polymergenome.org/copg | - |
| Copolymer Informatics with Multitask Deep Neural Networks | Data/tools related to copolymer informatics based on multitask deep neural networks | Not available | https://github.com/Ramprasad-Group/copolymer_informatics | - |
| Khazana Polymer Dataset | Contains a large amount of polymer property data, focusing on properties of homopolymers and copolymers | Publicly available | https://khazana.gatech.edu/dataset/ | Mainly developed by the Ramprasad Research Group |
| CopDDB: a descriptor database for copolymers and its applications to machine learning | A copolymer descriptor database for machine learning applications, capable of predicting reactivity ratio r1 (k11/k12) | Available; published in 2025 | https://github.com/hatanaka-lab/CopDDB/tree/main | Core function: prediction of reactivity ratio r1 |
| CoPolDB: a copolymerization database for radical polymerization | A copolymer database for radical polymerization, focusing on data of r1/F1 copolymerization systems | Available | https://www.copoldb.jp/copolym/ | Specifically designed for radical polymerization scenarios |
| Enabling data-driven design of block copolymer self-assembly | Supports data-driven design of block copolymer self-assembly, providing Scanning Electron Microscopy (SEM) image data | Available; published in 2025 | https://zenodo.org/records/13927939 | Core data type: SEM images |
| Multi-objective Bayesian Optimization for Experimental Design in Copolymerization and Revealing Chemical Mechanism of Pareto Fronts | Tools/data for Multi-Objective Bayesian Optimization (MOBO), applied to optimize the copolymerization conditions of Styrene-Methyl Methacrylate (ST-MMA) | Available; published in 2025 | https://github.com/MI-Lab-NAIST/Multi-objective_Bayesian_optimization_for_experimental_design_in_copolymerization | Focuses on the optimization of ST-MMA copolymerization conditions |
| Universal Phase Identification of Block Copolymers From Physics-Informed Machine Learning | Data related to universal phase identification of block copolymers based on physics-informed machine learning, including Small-Angle X-Ray Scattering (SAXS) data of block copolymer phases | Available; published in 2025 | https://github.com/UncertaintyQuantification/automated_polymer_phase_identification/tree/main/data | Core data type: SAXS data of block copolymer phases |
| High-Throughput Generation of Block Copolymer Libraries via Click Chemistry and Automated Chromatography | Data of block copolymer libraries generated via high-throughput methods using click chemistry and automated chromatography, including automated chromatography data of di-block and tri-block polymers | Available; published in 2025 | https://datadryad.org/search?utf8=%E2%9C%93&q=Block+Copolymer+Libraries | Data type: automated chromatography data; covers di-block and tri-block polymers |
| Machine Learning Prediction of Antibacterial Activity of Block Copolymers | Dataset for predicting the antibacterial activity of block copolymers using machine learning | Available; published in 2024 | https://github.com/varunkundi/polymerML/blob/main/dataset_ML_Polymer.xlsx | Data format: Excel spreadsheet; focuses on antibacterial activity prediction |
| Interpretable Machine Learning Models for Phase Prediction in Polymerization-Induced Self-Assembly (PISA) | Data related to interpretable machine learning models for phase prediction in Polymerization-Induced Self-Assembly (PISA) | Available | https://github.com/marioboley/PISA_ML | Specifically designed for phase prediction in PISA processes |
| Sequence-Based Computational Design of High-Affinity Amphiphilic Copolymers for Protein Targeting | Data related to sequence-based computational design of high-affinity amphiphilic copolymers (for protein targeting) | Available; published in 2025 | https://pubs.acs.org/doi/suppl/10.1021/acs.macromol.5c01112/suppl_file/ma5c01112_si_002.zip | Data provided as supplementary files (ZIP format); focuses on the design of protein-targeting copolymers |
| Predicting homopolymer and copolymer solubility through machine learning | Dataset for predicting the solubility of homopolymers and copolymers using machine learning | Available; published in 2025 | https://github.com/cstubb/PolySol/tree/main/data/csvs | Data format: CSV files; core application: solubility prediction |
| An artificial neural network to predict reactivity ratios in radical copolymerization | Data/tools related to artificial neural networks for predicting reactivity ratios in radical copolymerization | Not available | https://polymatai.pythonanywhere.com/search | Specifically designed for predicting reactivity ratios in radical copolymerization |