Identifying Genomic Islands with Deep Neural Networks

Horizontal Gene Transfer(HGT) is the main source of adaptability for bacteria, allowing it to obtain genes from different sources like bacteria, archaea, viruses, and eukaryotes. This promotes the rapid spread of genetic information across lineages, typically in the form of clusters of genes referred to as genomic islands(GIs). There are different types of GIs, often classified by the content of their cargo genes or their means of integration and mobility. Different computational methods have been devised to detect different types of GIs, but there is no single method that is capable of detecting all GIs. The intrinsic value of machine learning methods lies in their ability to generalize. We propose a method(we call it Shutter Island ) that uses deep learning, or more specifically, the Inception V3 model, to detect Genomic Islands in bacterial genomes. We show that using this approach, it is possible to generalize better than the existing tools, detecting more of their correct results than other tools, while making novel GI predictions.