You are here:
Accessing bulk predicted QSAR data via batch search functionality in the CompTox Chemicals Dashboard (QSAR 2021)
Citation:
Williams, A., T. Martin, Chris Grulke, AND K. Mansouri. Accessing bulk predicted QSAR data via batch search functionality in the CompTox Chemicals Dashboard (QSAR 2021). QSAR 2021 International Workshop on QSAR in Environmental and Health Sciences, Virtual, NC, June 07 - 10, 2021. https://doi.org/10.23645/epacomptox.15074892
Impact/Purpose:
Poster to be presented to the QSAR 2021 International Workshop on QSAR in Environmental and Health Sciences June 2021. Robust QSAR models, using a set of best practices for modeling and dataset collection, provide an automated method for the estimation of all types of chemical safety relevant endpoints for data poor chemicals. Robust QSAR models will be developed for endpoints with known value to the Agency in its chemical safety efforts including the prediction of toxicities, bioactivities, and environmental fate and physicochemical properties to support exposure modeling. Prediction models are a key aspect of delivering support to our partners. These include QSAR models, SAR, QSUR etc. This product will deliver access to the suite of prediction models delivered out of other CSS areas and will include single and batch structure input (via the CompTox Chemicals Dashboard), reporting, results delivery via a web interface and as web services, and a manuscript defining the prediction model delivery. These efforts support program and regional offices as well as the greater scientific community.
Description:
There are a myriad of public free access chemistry databases now accessible to the community to source various types of data to support, for example, drug discovery, environmental chemistry and materials research. The US EPA CompTox Chemicals Dashboard is a web-based application providing access to ~900,000 chemical substances and diverse data types including physicochemical property, toxicity and bioactivity data. While the application supports users with the expected single chemical search (based on CASRN, chemical name, InChI Key etc) one of the most powerful pieces of functionality is the batch search that allows a user to search of thousands of chemicals at a time. Batch searching using each of, or a combination of chemical names, CAS RNs, InChIs, masses or formulae as inputs facilitates downloads of data en masse into either Excel spreadsheet, comma or tab-separated value files, or into an SDF file containing thousands of chemicals. Data that can be exported includes data from QSAR prediction models, specifically TEST (Toxicity Estimation Software Tools) and OPERA models. This poster presents an overview of the batch search capability in the dashboard and the rich data streams that are made accessible by this functionality and available for exchange with other systems. It will also review the Open data that has been made available for download from the site so that it can be reused and repurposed in other systems. This abstract does not necessarily represent the views or policies of the U.S. Environmental Protection Agency.
URLs/Downloads:
DOI: Accessing bulk predicted QSAR data via batch search functionality in the CompTox Chemicals Dashboard (QSAR 2021)
QSAR2021_POSTER#240_BULK_QSAR_PREDICTIONS_AWILLIAMS_V2.PDF (PDF, NA pp, 1471.303 KB, about PDF)