Seattle Structural Genomics Center for Infectious Disease


Virulence-associated target selection tool

This software suite was developed by Dr. Eithon Cadag for the purpose of predicting whether a protein sequence is associated with virulence, using a statistical classifier which has been first trained on virulent and non-virulent proteins [Cadag E., Tarczy-Horoch P. & Myler P.J., BMC Bioinformatics (2012) 13:321] The tool collects annotations from various public repositories, such as EntrezProtein, UniProt, KEGG, PDB and InterPro, and produces a network of inter-related data about the protein of interest. Subsequently, the annotations are weighed and resulting scores are submitted as input to a statistical classifier based on the PyML framework for machine learning [Ben-Hur A., 2008]. This strategy resulted in the selection of 876 targets for the SSGCID pipeline from eight bacterial and one eukaryotic genomes (Internal Target Batch_09).

SSGCID is committed to ensure that all electronic and information technology (EIT) products and services developed, acquired, maintained, or used under this contract comply with Section 508 of the Rehabilitation Act of 1973 (29 U.S.C. 794d), as amended by the Workforce Investment Act of 1998, and with the Electronic and Information Technology Accessibility Provisions in 36 CFR part 1194 set forth by the Architectural and Transportation Barriers Compliance Board. For inquiries and suggestions regarding Section 508 compliance of this website, please contact .