Affordable Access

Access to the full text

Identifying genomic islands with deep neural networks

Authors
  • Assaf, Rida1
  • Xia, Fangfang2, 3
  • Stevens, Rick2, 4
  • 1 Department of Computer Science, University of Chicago, S. Ellis Ave., Chicago, 60637, USA , Chicago (United States)
  • 2 Computing Environment and Life Sciences Division, Argonne National Laboratory, S. Cass Ave., Lemont, 60439, USA , Lemont (United States)
  • 3 Data Science and Learning Division, Argonne National Laboratory, S. Cass Ave., Lemont, 60439, USA , Lemont (United States)
  • 4 The University of Chicago Consortium for Advanced Science and Engineering, University of Chicago, S. Ellis Ave., Chicago, 60637, USA , Chicago (United States)
Type
Published Article
Journal
BMC Genomics
Publisher
Springer (Biomed Central Ltd.)
Publication Date
Jun 02, 2021
Volume
22
Issue
Suppl 3
Identifiers
DOI: 10.1186/s12864-021-07575-5
Source
Springer Nature
Keywords
License
Green

Abstract

BackgroundHorizontal gene transfer is the main source of adaptability for bacteria, through which genes are obtained from different sources including bacteria, archaea, viruses, and eukaryotes. This process promotes the rapid spread of genetic information across lineages, typically in the form of clusters of genes referred to as genomic islands (GIs). Different types of GIs exist, and are often classified by the content of their cargo genes or their means of integration and mobility. While various computational methods have been devised to detect different types of GIs, no single method is capable of detecting all types.ResultsWe propose a method, which we call Shutter Island, that uses a deep learning model (Inception V3, widely used in computer vision) to detect genomic islands. The intrinsic value of deep learning methods lies in their ability to generalize. Via a technique called transfer learning, the model is pre-trained on a large generic dataset and then re-trained on images that we generate to represent genomic fragments. We demonstrate that this image-based approach generalizes better than the existing tools.ConclusionsWe used a deep neural network and an image-based approach to detect the most out of the correct GI predictions made by other tools, in addition to making novel GI predictions. The fact that the deep neural network was re-trained on only a limited number of GI datasets and then successfully generalized indicates that this approach could be applied to other problems in the field where data is still lacking or hard to curate.

Report this publication

Statistics

Seen <100 times