Digerati - A multipath parallel hybrid deep learning framework for the identification of mycobacterial PE/PPE proteins

Fuyi Li; Xudong Guo; Yue Bi; Runchang Jia; Miranda E Pitt; Shirui Pan; Shuqin Li; Robin B Gasser; Lachlan Jm Coin; Jiangning Song

doi:10.1016/j.compbiomed.2023.107155

Digerati - A multipath parallel hybrid deep learning framework for the identification of mycobacterial PE/PPE proteins

Comput Biol Med. 2023 Sep:163:107155. doi: 10.1016/j.compbiomed.2023.107155. Epub 2023 Jun 21.

Authors

Fuyi Li¹, Xudong Guo², Yue Bi³, Runchang Jia², Miranda E Pitt⁴, Shirui Pan⁵, Shuqin Li², Robin B Gasser⁶, Lachlan Jm Coin⁷, Jiangning Song⁸

Affiliations

¹ College of Information Engineering, Northwest A&F University, Yangling, 712100, China; Department of Microbiology and Immunology, The Peter Doherty Institute for Infection and Immunity, The University of Melbourne, 792 Elizabeth Street, Melbourne, Victoria, 3000, Australia. Electronic address: fuyi.li@nwafu.edu.cn.
² College of Information Engineering, Northwest A&F University, Yangling, 712100, China.
³ Biomedicine Discovery Institute and Department of Biochemistry and Molecular Biology, Monash University, Melbourne, Victoria, 3800, Australia.
⁴ Department of Microbiology and Immunology, The Peter Doherty Institute for Infection and Immunity, The University of Melbourne, 792 Elizabeth Street, Melbourne, Victoria, 3000, Australia.
⁵ School of Information and Communication Technology, Griffith University, QLD, 4222, Australia.
⁶ Melbourne Veterinary School, Faculty of Science, The University of Melbourne, VIC, 3010, Australia.
⁷ Department of Microbiology and Immunology, The Peter Doherty Institute for Infection and Immunity, The University of Melbourne, 792 Elizabeth Street, Melbourne, Victoria, 3000, Australia. Electronic address: lachlan.coin@unimelb.edu.au.
⁸ Biomedicine Discovery Institute and Department of Biochemistry and Molecular Biology, Monash University, Melbourne, Victoria, 3800, Australia. Electronic address: jiangning.song@monash.edu.

PMID: 37356289
DOI: 10.1016/j.compbiomed.2023.107155

Abstract

The genome of Mycobacterium tuberculosis contains a relatively high percentage (10%) of genes that are poorly characterised because of their highly repetitive nature and high GC content. Some of these genes encode proteins of the PE/PPE family, which are thought to be involved in host-pathogen interactions, virulence, and disease pathogenicity. Members of this family are genetically divergent and challenging to both identify and classify using conventional computational tools. Thus, advanced in silico methods are needed to identify proteins of this family for subsequent functional annotation efficiently. In this study, we developed the first deep learning-based approach, termed Digerati, for the rapid and accurate identification of PE and PPE family proteins. Digerati was built upon a multipath parallel hybrid deep learning framework, which equips multi-layer convolutional neural networks with bidirectional, long short-term memory, equipped with a self-attention module to effectively learn the higher-order feature representations of PE/PPE proteins. Empirical studies demonstrated that Digerati achieved a significantly better performance (∼18-20%) than alignment-based approaches, including BLASTP, PHMMER, and HHsuite, in both prediction accuracy and speed. Digerati is anticipated to facilitate community-wide efforts to conduct high-throughput identification and analysis of PE/PPE family members. The webserver and source codes of Digerati are publicly available at http://web.unimelb-bioinfortools.cloud.edu.au/Digerati/.

Keywords: Bioinformatics; Deep learning; Mycobacterial; PE/PPE protein; Sequence analysis.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Bacterial Proteins / genetics
Deep Learning*
Mycobacterium tuberculosis* / genetics
Mycobacterium tuberculosis* / metabolism
Virulence / genetics

Substances

Bacterial Proteins