The inconsistency of polymer indexing caused by the lack of uniformity in expression of polymer names is a major challenge for widespread use of polymer related data resources and informatics. This work develops a multi-algorithm-based mapping methodology entitled ChemProps that is optimized to solve the polymer indexing issue with easy-to-update design. RESTful API is enabled for lightweight data exchange and easy integration across data systems. The methodology uses weighting factors and a scoring approach in the optimization to identify the ground truth chemical name from all possible candidates. Ten-fold validation is utilized in the training and 100% test accuracy is obtained on the 54 test data points in the most recent runs. The weight factors continue to evolve as ChemProps grows with additional polymer names. ChemProps can be used by other polymer databases to remove duplicate entries or to enable a “search by SMILES” function. ChemProps is also an excellent tool for auto-populating polymer properties thanks to its easy-to-update design.
The ChemProps service is available at https://materialsmine.org/nm#/ChemProps. You can use the GUI for one-time searches or request a token for the API service there. Please refer to the paper for details of the project and instructions to the API service.
Active Researcher on the Project:
Relevant Publications
[1] Hu, B., Lin, A., & Brinson, L. C. (2021). ChemProps: A RESTful API enabled database for composite polymer name standardization. Journal of cheminformatics, 13(1), 1-13.