Predicts alternative polyadenylation patterns from transcript sequences. Polyadenylation Code is a versatile model that can be generalized to multiple tasks that it was not trained on. It can also classify variants near polyadenylation site (PAS) and can be used for PAS discovery. It provides analysis of what sequences increase and decrease the strength of a PAS, and identifies features that are associated with tissue-specific and constitutive PAS.
Department of Electrical and Computer Engineering, University of Toronto, Toronto, ON, Canada; Banting and Best Department of Medical Research, University of Toronto, Toronto, ON, Canada; Deep Genomics, MaRS Centre, Heritage Building, Toronto, ON, Canada
Polyadenylation Code funding source(s)
Supported by the Natural Science and Engineering Research Council Canada.