Combines subgroups of features into a network, allows different tissues to share feature subgroups. WASP uses hidden variables within a network architecture to model non-linear relationships between putative regulatory features and splicing changes. It can be applied to datasets profiling larger numbers of tissues, different species, and different types of alternative splicing. The tool was tested and achieves relative improvements of 52% in splicing code quality and up to 22% in classification error, compared with the state of the art.
Department of Electrical and Computer Engineering, University of Toronto, Toronto, Canada; Banting and Best Department of Medical Research, Centre of Cellular and Biomolecular Research, University of Toronto, Toronto, Canada
WASP funding source(s)
Supported by Canadian Institutes for Health Research Operating Grant MOP-106690; Genome Canada and Ontario Genomics Institute Grants; Natural Sciences and Engineering Research Council (NSERC) Grant SMFSU 379968-09; Canadian Foundation for Innovation and Ontario Research Fund Grant 203788 and by a Fellow of the Canadian Institute for Advanced Research and an NSERC E.W.R. Steacie Fellow.