ChemProps: A RESTful API enabled database for composite polymer name standardization
Bingyin Hu, Anqi Lin, L. Catherine Brinson · 2021 · 20 citationsRead the paper
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 limits broad application of materials informatics for innovation in broad classes of polymer science and polymeric based materials. The current solution of using a variety of different chemical identifiers has proven insufficient to address the challenge and is not intuitive for researchers. This work proposes a multi-algorithm-based mapping methodology entitled ChemProps that is optimized to solve the polymer indexing issue with easy-to-update design both in depth and in width. RESTful API is enabled for lightweight data exchange and easy integration across data systems. A weight factor is assigned to each algorithm to generate scores for candidate chemical names and optimized to maximize the minimum value of the score difference between the ground truth chemical name and the other candidate chemical names. Ten-fold validation is utilized on the 160 training data points to prevent overfitting issues. The obtained set of weight factors achieves a 100% test accuracy on the 54 test data points. The weight factors will evolve as ChemProps grows. With ChemProps, other polymer databases can remove duplicate entries and enable a more accurate "search by SMILES" function by using ChemProps as a common name-to-SMILES translator through API calls. ChemProps is also an excellent tool for auto-populating polymer properties thanks to its easy-to-update design.
What the full text shows
Working prototype- The multi-algorithm mapping methodology achieved perfect accuracy on the test set. — 100% test accuracy (Tested on 54 unique searching packages (SPs))
- The system successfully mapped polymer names using a weighted voting system of 12 algorithms. — 12 algorithms (Optimized using 166 training SPs from NanoMine data)
- The core database was initialized with a set of unique polymer names. — 564 unique polymer names (Pulled from Polymer Genome and NanoMine)
- A subset of the database was fully indexed with SMILES, abbreviations, synonyms, trade names, and density. — 89 polymer names (Used for the current study's algorithm development)
- The system indexes common nano-fillers alongside polymers. — 54 fillers (Indexed with synonyms and density information)
- Setup
- Core database built on MongoDB with raw data stored in Google Spreadsheets; training set of 166 unique searching packages and a test set of 54 unique searching packages.
- How
- Developed a RESTful API-enabled database using a weighted voting system of 12 mapping algorithms (including Bag-of-Characters and relaxed Bag-of-Words) to standardize polymer names. Weights were optimized to maximize the minimum score difference between ground truth and candidate names, with ten-fold validation to prevent overfitting.
- Limitations
- Trade name algorithms currently have zero weight, indicating they are not yet important mapping features. · The current training/test sets from NanoMine did not contain SMILES strings, limiting the evolution of the SMILES-based algorithm weight. · The system relies on an external NIH Online SMILES Translator for uSMILES generation.
Summarized by Gemma 4 from the open-access full text · 8 Oct 2026. Read it