Datasets For Practical Model Selection For Prospective Virtual Screening

This repository contains datasets for the manuscript "Practical model selection for prospective virtual screening": <strong>pria_rmi_cv.tar.gz</strong>: A compressed directory containing chemical screening data for the <strong>PriA-SSB AS</strong>, <strong>PriA-SSB FP</strong>, and <strong>RMI-FANCM FP</strong> binary datasets. The files also contain the associated continuous % inhibition values and chemical features represented as SMILES and ECFP4 fingerprints. The dataset has been split into five folds for cross validation. <strong>pria_rmi_pcba_cv.tar.gz</strong>: A compressed directory containing chemical screening data for the <strong>PriA-SSB AS</strong>, <strong>PriA-SSB FP</strong>, and <strong>RMI-FANCM FP</strong> binary datasets as well as public PubChem BioAssay datasets. The files also contain the PriA-SSB and RMI-FANCM continuous % inhibition values and chemical features represented as SMILES and ECFP4 fingerprints. The dataset has been split into five folds for cross validation. Missing values are left blank. <strong>pria_prospective.csv.gz</strong>: A compressed file containing chemical screening data for the binary dataset <strong>PriA-SSB prospective</strong>. The file also contains the continuous % inhibition values and chemical features represented as SMILES and ECFP4 fingerprints. If you use this data in a publication, please cite: Shengchao Liu⁺, Moayad Alnammi⁺, Spencer S. Ericksen, Andrew F. Voter, James L. Keck, F. Michael Hoffmann, Scott A. Wildman, Anthony Gitter. Practical model selection for prospective virtual screening. <em>bioRxiv</em> 2018. doi:10.1101/337956 PubChem data were provided by the PubChem database. Follow the PubChem citation guidelines if you use the PubChem data. Version 1.0.1 updates pria_prospective.csv.gz. The file contents did not change, but the file format was modified to avoid a problem opening the file on macOS.