HOME > Polymer Genome

Polymer Genome

Polymer Genome is a web-based polymer informatics platform designed to predict the properties of polymers near-instantaneously using machine learning (ML) models. Unlike traditional static databases, it functions as a prediction engine where the underlying models are trained on large datasets generated through Density Functional Theory (DFT) calculations and experimental measurements. The platform is capable of predicting a wide range of properties, including band gaps, dielectric constants, refractive indices, glass transition temperatures, densities, and solubility parameters, aiming to accelerate the discovery and design of next-generation polymer materials.

Information
Case / Article
Learning Content
Review
Developer’s Voice

Information

Official site	https://polymergenome.org/
Openness	★★★
Manual	https://polymergenome.org/guide
License	The platform operates as a free-to-use online prediction tool for the community. While specific software licenses for the web engine are not explicitly listed, the underlying data and associated code are typically protected by copyright and intended for non-commercial academic use. Open-source tools and datasets from the group (often hosted on Khazana) may have specific open licenses.
Core Developers	Polymer Genome is primarily developed and maintained by the Ramprasad Research Group at the Georgia Institute of Technology. The project originated at the University of Connecticut before moving with the team to Georgia Tech. Key contributors include Prof. Rampi Ramprasad (The School of Materials Science and Engineering, Georgia Institute of Technology) and other team members such as Dr. Chiho Kim (Research Engineer II, The School of Materials Science and Engineering, Georgia Institute of Technology) Dr. Anand Chandrasekaran (PD 2016-2019, The School of Materials Science and Engineering, Georgia Institute of Technology) (Presently at: Materials Science team at Schrödinger, LLC) Dr. Huan Tran (Research Scientist II, The School of Materials Science and Engineering, Georgia Institute of Technology)
Availability	As a web-based platform, the primary requirement is a modern web browser and an internet connection.
Related Papers	Key papers include Tran, H. D., Kim, C., Chen, L., et al. “Machine-learning predictions of polymer properties with Polymer Genome.” J. Appl. Phys. 128, 171104 (2020). (URL: https://doi.org/10.1063/5.0023759) Kim, C., Chandrasekaran, A., Huan, T. D., Das, D., & Ramprasad, R. “Polymer Genome: A Data-Powered Polymer Informatics Platform for Property Predictions.” J. Phys. Chem. C 122, 31, 17575–17585 (2018). (URL: https://pubs.acs.org/doi/10.1021/acs.jpcc.8b02913) Huan, T. D., Mannodi-Kanakkithodi, A., Kim, C., et al. “A polymer dataset for accelerated property prediction and design.” Scientific Data 3, 160012 (2016). (URL: https://doi.org/10.1038/sdata.2016.12) Kuenneth, C., Schertzer, W., & Ramprasad, R. “Copolymer informatics with multitask deep neural networks.” Macromolecules, 54(13), 5957-5961 (2021). (URL: https://doi.org/10.1021/acs.macromol.1c00728) Kuenneth, C., Rajan, A. C., Tran, H., Chen, L., Kim, C., & Ramprasad, R. “Polymer informatics with multi-task learning.” Patterns, 2(4) (2021). (URL: https://doi.org/10.1016/j.patter.2021.100238) Chen, L., Kern, J., Lightstone, J. P., & Ramprasad, R. “Data-assisted polymer retrosynthesis planning.” Applied Physics Reviews, 8(3), 031405 (2021). (URL: https://doi.org/10.1063/5.0052962) Other related papers are listed on https://polymergenome.org/reference.
Related Sites	Khazana: A materials informatics repository hosted by the Ramprasad Group that stores computational data and machine learning tools closely related to Polymer Genome. Some underlying datasets of Polymer Genome are available through this repository.