Detects splice site via a convolutional neural network (CNNs)-based end-to-end learning approach. SpliceRover facilitates automatic feature extraction and classification of genomic sequences as true or pseudo splice sites. This software processes by taking account genomic sequences as one-hot vectors and produces probabilities for a positive and negative classification. This prediction tool can be used for donor and acceptor splice site prediction.
Center for Biotech Data Science, Ghent University Global Campus, Songdo, Incheon, South Korea; IDLab, Ghent University - imec, ELIS, Ghent, Belgium; Department of Biomedical Molecular Biology, Ghent University, Ghent, Belgium; Data Mining and Modeling for Biomedicine, VIB Inflammation Research Center, Ghent, Belgium; Department of Applied Mathematics, Computer Science and Statistics, Ghent University, Ghent, Belgium
SpliceRover funding source(s)
Supported by Ghent University Global Campus, Ghent University, imec, Flanders Innovation & Entrepreneurship (VLAIO), the Fund for Scientific Research-Flanders (FWO-Flanders), and the EU.