Steven M. Muskal and Stephan C. Schurer
Scientific Tracks Abstracts: Drug Design
Large corpora of kinase small molecule inhibitor data are accessible to pubic sector research from thousands of journal article and patent publications. These data are generated employing a wide variety of assay methodologies and experimental procedures by numerous laboratories. We accessed this data of over 500,000 molecules from the Kinase Knowledge Base (KKB) and after rigorous aggregation and standardization generated over 180 diverse datasets covering all major groups of the human Kinome. To investigate how the data could be used to generate predictive models, which modeling technique(s) were best suited and applicable for virtual screening, and which characteristics of datasets were associated with the best predictors, we generated hundreds of classification and regression models. Their rigorous cross-validation and characterization demonstrated highly predictive classification and quantitative models for the majority of kinase targets if a minimum required number of active compounds or structure-activity data points, respectively, were available. Our results indicated that the publically accessible data are exceedingly valuable and well suited to develop highly accurate predictors employing different machine learning techniques with the potential for practical applications of virtual screening across the kinome.
Dr. Steven Muskal, founder of Sertanty, Inc. and Chief Executive Officer of Eidogen-Sertanty, has over 20 years of technology development and marketing experience in the biopharmaceutical community. Prior to establishing Sertanty, he served as Vice President of Informatics for Libraria, Inc., helping to secure financing while responsible for technology development and operational activity. Prior to joining Libraria, he served as Unit Director at the Affymax Research Institute and as a member of the Glaxo Wellcome Scientific Computing Board. At Affymax, he directed departments focusing on advanced technologies in parallel synthesis, lead optimization (ADME), and research computing. Previously, he was a Product Manager, Senior Scientist, and Applications Scientist at MDL Information Systems responsible for the design, development, and marketing of combinatorial chemistry software, and for a worldwide technical marketing network of product specialists. Dr. Muskal received his Doctorate in Biophysical Chemistry from the University of California, Berkeley and his B.Sc. in Engineering Chemistry and Computer Science from the Colorado School of Mines. He is triathlete, plays amateur baseball, and is the drummer for Raised on V inyl.