The Materials Genome Initiative is transforming Materials Science into a data-rich discipline. This evolution is drastically modifying the way researchers are accessing, querying, visualizing, and modeling large arrays of materials data. The volume and complexity of experimentally-measured and computationally-derived data have increased at a high speed making it extremely difficult to rely on classical data-analytical approaches and computational tools. In this work we proposed a convenient way to (i) instantaneously query and retrieve the necessary material information in the desired form, (ii) identify, visualize and study important data patterns (e.g., metal vs. insulator depending on material structure), and (iii) generate experimentally-testable hypotheses by building predictive Quantitative structure-activity relationship (QSPR) models based on materials’ characteristics. This data to knowledge progression would allow the discovery of novel materials with enhanced physical or biologically-relevant properties.

Cheminformatics-inspired approaches for big materials data

249th National Meeting (2015)

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