HOME > Polymer Property Predictor and Database

Polymer Property Predictor and Database

Polymer Property Predictor and Database is a data resource developed to
support polymer informatics by providing a large dataset of polymer properties
automatically extracted from the scientific literature. The project utilizes
well-known theories and machine learning models to explore polymer–polymer and
polymer–solvent systems, recovering properties such as Flory–Huggins chi
parameters and related graphs, glass transition temperature Tg, and critical
solubility cloud points. The database accelerates polymer informatics and
automated extraction of polymer data from the literature, and serves as a
testbed for developing new data mining and machine learning pipelines. It is a
collaborative effort between Center for Hierarchical Materials Design (CHiMaD),
National Institute of Standards and Technology (NIST), and Air Force Research
Laboratory (AFRL).

Information
Case / Article
Learning Content
Review
Developer’s Voice

Information

Official site	https://pppdb.uchicago.edu/
Openness	★★★
Manual	https://pppdb.uchicago.edu/howto
License	Juan J. de Pablo (Pritzker School of Molecular Engineering, The University of Chicago) Jeffrey G. Ethier (Air Force Research Laboratory), mainly for the machine-learning-trained model used for prediction
Core Developers	The PPPdb project is developed by the Center for Hierarchical Materials Design (CHiMaD), a consortium including the University of Chicago, Northwestern University, and Argonne National Laboratory, in collaboration with the National Institute of Standards and Technology (NIST). The database is mainly developed by the de Pablo Group at the Pritzker School of Molecular Engineering, The University of Chicago. Key contributors include: Juan J. de Pablo (Pritzker School of Molecular Engineering, The University of Chicago) Jeffrey G. Ethier (Air Force Research Laboratory), mainly for the machine-learning-trained model used for prediction
Availability	Accessible via any modern web browser (e.g., Chrome, Firefox, Safari).
Related Papers	Automatic extraction of glass transition temperature data from literature. R. B. Tchoua et al., “Towards a Hybrid Human-Computer Scientific Information Extraction Pipeline,” 2017 IEEE 13th International Conference on e-Science (e-Science), Auckland, New Zealand, 2017, pp. 109–118, doi:10.1109/eScience.2017.23 Artificial neural networks trained to estimate cloud point temperatures. Ethier, Jeffrey G. et al., “Deep Learning of Binary Solution Phase Behavior of Polystyrene,” ACS Macro Letters 2021, 10, 749–754, doi:10.1021/acsmacrolett.1c00117 Ethier, Jeffrey G. et al., “Predicting Phase Behavior of Linear Polymers in Solution Using Machine Learning,” Macromolecules 2022, 55 (7), 2691–2702, doi:10.1021/acs.macromol.2c00245