Identification of Splice Junctions Across Species Using BLSTM Model

Abstract

Deep learning models like convolutional neural networks (CNN) and recurrent neural networks (RNN) have been used to identify splice sites from genome sequences. Most deep learning applications identify splice sites from a single species. Furthermore, the models generally identify and interpret only the canonical splice sites. However, a model capable of identifying both canonical and non-canonical splice sites from multiple species with comparable accuracy is more generalizable and robust. We analyze the performance of a BLSTM model for the first time across various species. We compare this RNN-based model with state-of-the-art splice site prediction models for identifying novel canonical and non-canonical splice sites in homo sapiens, mus musculus, and drosophila melanogaster.