The Materials Genome Initiative is transforming Materials Science into a data-rich discipline. These developments open exciting opportunities for knowledge discovery in materials databases using informatics approaches to inform the rational design of novel materials with the desired physical and chemical properties. Statistical and data mining approaches have been successfully employed in both chemistry and biology leading to the development of cheminformatics and bioinformatics, respectively. However, until recently their application in materials science has been limited due to the lack of sufficient body of data. In this work we showcase a pilot materials informatics applications capable of (i) instantaneously query and retrieve the necessary material information in the desired form, (ii) identify, visualize and study important data patterns, and (iii) generate experimentally-testable hypotheses by building predictive Machine Learning (ML) models based on materials’ characteristics. Specifically, we posit that materials with similar structural, topological, and electronic characteristics are expected to have similar physical chemical properties irrespective of their formal composition. To enable uniform comparison of materials by their intrinsic properties, we will represent all materials uniquely by multiple numerical descriptors, or fingerprints. This representation will enable the use of classical cheminformatics and ML approaches to mine, visualize, and model any set of materials as we demonstrated in our recent pioneering studies on Materials Cartography [1]. Reference: Isayev, O., Fourches, D., Muratov, E,N,. Oses, C., Rasch K.M., Tropsha, A., and Curtarolo, S. Chem, Mater, 2015, 27, 735–743. DOI: 10.1021/cm503507h

Data-driven chemistry: From small molecules to discovery of new functional materials

251st National Meeting (2016)

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.