Deep6: Classification of Metatranscriptomic Sequences into Cellular Empires and Viral Realms Using Deep Learning Models

Jan F Finke; Colleen T E Kellogg; Curtis A Suttle

doi:10.1128/mra.01079-22

Deep6: Classification of Metatranscriptomic Sequences into Cellular Empires and Viral Realms Using Deep Learning Models

Microbiol Resour Announc. 2023 Feb 16;12(2):e0107922. doi: 10.1128/mra.01079-22. Epub 2023 Jan 18.

Authors

Jan F Finke^{1

2}, Colleen T E Kellogg¹, Curtis A Suttle^{2

3

4

5}

Affiliations

¹ Hakai Institute, Heriot Bay, British Columbia, Canada.
² Department of Earth, Ocean, and Atmospheric Sciences, The University of British Columbia, Vancouver, British Columbia, Canada.
³ Department of Microbiology and Immunology, The University of British Columbia, Vancouver, British Columbia, Canada.
⁴ Department of Botany, The University of British Columbia, Vancouver, British Columbia, Canada.
⁵ Institute for the Oceans and Fisheries, The University of British Columbia, Vancouver, British Columbia, Canada.

Abstract

Deep6 is a deep learning model that classifies metatranscriptomic sequences as short as 250 nucleotides into prokaryotes, eukaryotes, or one of the four viral realms, using a reference-independent and alignment-free approach. Average accuracies range from 0.87 to 0.97, depending on sequence length.

Abstract

Grants and funding