DCiPatho: deep cross-fusion networks for genome scale identification of pathogens

Gaofei Jiang; Jiaxuan Zhang; Yaozhong Zhang; Xinrun Yang; Tingting Li; Ningqi Wang; Xingjian Chen; Fang-Jie Zhao; Zhong Wei; Yangchun Xu; Qirong Shen; Wei Xue

doi:10.1093/bib/bbad194

DCiPatho: deep cross-fusion networks for genome scale identification of pathogens

Gaofei Jiang
, Jiaxuan Zhang
, Yaozhong Zhang
, Xinrun Yang
, Tingting Li
, Ningqi Wang
, Xingjian Chen
, Fang-Jie Zhao
, Zhong Wei^*
, Yangchun Xu
, Qirong Shen
, Wei Xue^*

^*Corresponding author for this work

Department of Computer Science

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

26 Citations (Scopus)

44 Downloads (CityUHK Scholars)

Abstract

Pathogen detection from biological and environmental samples is important for global disease control. Despite advances in pathogen detection using deep learning, current algorithms have limitations in processing long genomic sequences. Through the deep cross fusion of cross, residual and deep neural networks, we developed DCiPatho for accurate pathogen detection based on the integrated frequency features of 3-to-7 k-mers. Compared with the existing state-of-the-art algorithms, DCiPatho can be used to accurately identify distinct pathogenic bacteria infecting humans, animals and plants. We evaluated DCiPatho on both learned and unlearned pathogen species using both genomics and metagenomics datasets. DCiPatho is an effective tool for the genomic-scale identification of pathogens by integrating the frequency of k-mers into deep cross-fusion networks. The source code is publicly available at https://github.com/ LorMeBioAI/DCiPatho. © The Author(s) 2023. Published by Oxford University Press.

Original language	English
Article number	bbad194
Journal	Briefings in Bioinformatics
Volume	24
Issue number	4
Online published	30 May 2023
DOIs	https://doi.org/10.1093/bib/bbad194
Publication status	Published - Jul 2023

Bibliographical note

Full text of this publication does not contain sufficient affiliation information. With consent from the author(s) concerned, the Research Unit(s) information for this record is based on the existing academic department affiliation of the author(s).

Research Keywords

pathogen identification
K-mer frequency
metagenomics
deep cross-fusion networks
NEURAL-NETWORK

Publisher's Copyright Statement

This full text is made available under CC-BY-NC 4.0. https://creativecommons.org/licenses/by-nc/4.0/

Policy Impact

Cited in Policy Documents

Access Output

10.1093/bib/bbad194

157867398.pdfFinal Published version, 1.13 MBLicence: CC BY-NC

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{2b8d6afd6d8846f0a61c338ee5aa8685,

title = "DCiPatho: deep cross-fusion networks for genome scale identification of pathogens",

abstract = "Pathogen detection from biological and environmental samples is important for global disease control. Despite advances in pathogen detection using deep learning, current algorithms have limitations in processing long genomic sequences. Through the deep cross fusion of cross, residual and deep neural networks, we developed DCiPatho for accurate pathogen detection based on the integrated frequency features of 3-to-7 k-mers. Compared with the existing state-of-the-art algorithms, DCiPatho can be used to accurately identify distinct pathogenic bacteria infecting humans, animals and plants. We evaluated DCiPatho on both learned and unlearned pathogen species using both genomics and metagenomics datasets. DCiPatho is an effective tool for the genomic-scale identification of pathogens by integrating the frequency of k-mers into deep cross-fusion networks. The source code is publicly available at https://github.com/ LorMeBioAI/DCiPatho. {\textcopyright} The Author(s) 2023. Published by Oxford University Press.",

keywords = "pathogen identification, K-mer frequency, metagenomics, deep cross-fusion networks, NEURAL-NETWORK",

author = "Gaofei Jiang and Jiaxuan Zhang and Yaozhong Zhang and Xinrun Yang and Tingting Li and Ningqi Wang and Xingjian Chen and Fang-Jie Zhao and Zhong Wei and Yangchun Xu and Qirong Shen and Wei Xue",

note = "Full text of this publication does not contain sufficient affiliation information. With consent from the author(s) concerned, the Research Unit(s) information for this record is based on the existing academic department affiliation of the author(s).",

year = "2023",

month = jul,

doi = "10.1093/bib/bbad194",

language = "English",

volume = "24",

journal = "Briefings in Bioinformatics",

issn = "1467-5463",

publisher = "Oxford University Press",

number = "4",

}

TY - JOUR

T1 - DCiPatho

T2 - deep cross-fusion networks for genome scale identification of pathogens

AU - Jiang, Gaofei

AU - Zhang, Jiaxuan

AU - Zhang, Yaozhong

AU - Yang, Xinrun

AU - Li, Tingting

AU - Wang, Ningqi

AU - Chen, Xingjian

AU - Zhao, Fang-Jie

AU - Wei, Zhong

AU - Xu, Yangchun

AU - Shen, Qirong

AU - Xue, Wei

N1 - Full text of this publication does not contain sufficient affiliation information. With consent from the author(s) concerned, the Research Unit(s) information for this record is based on the existing academic department affiliation of the author(s).

PY - 2023/7

Y1 - 2023/7

N2 - Pathogen detection from biological and environmental samples is important for global disease control. Despite advances in pathogen detection using deep learning, current algorithms have limitations in processing long genomic sequences. Through the deep cross fusion of cross, residual and deep neural networks, we developed DCiPatho for accurate pathogen detection based on the integrated frequency features of 3-to-7 k-mers. Compared with the existing state-of-the-art algorithms, DCiPatho can be used to accurately identify distinct pathogenic bacteria infecting humans, animals and plants. We evaluated DCiPatho on both learned and unlearned pathogen species using both genomics and metagenomics datasets. DCiPatho is an effective tool for the genomic-scale identification of pathogens by integrating the frequency of k-mers into deep cross-fusion networks. The source code is publicly available at https://github.com/ LorMeBioAI/DCiPatho. © The Author(s) 2023. Published by Oxford University Press.

AB - Pathogen detection from biological and environmental samples is important for global disease control. Despite advances in pathogen detection using deep learning, current algorithms have limitations in processing long genomic sequences. Through the deep cross fusion of cross, residual and deep neural networks, we developed DCiPatho for accurate pathogen detection based on the integrated frequency features of 3-to-7 k-mers. Compared with the existing state-of-the-art algorithms, DCiPatho can be used to accurately identify distinct pathogenic bacteria infecting humans, animals and plants. We evaluated DCiPatho on both learned and unlearned pathogen species using both genomics and metagenomics datasets. DCiPatho is an effective tool for the genomic-scale identification of pathogens by integrating the frequency of k-mers into deep cross-fusion networks. The source code is publicly available at https://github.com/ LorMeBioAI/DCiPatho. © The Author(s) 2023. Published by Oxford University Press.

KW - pathogen identification

KW - K-mer frequency

KW - metagenomics

KW - deep cross-fusion networks

KW - NEURAL-NETWORK

UR - http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=LinksAMR&SrcApp=PARTNER_APP&DestLinkType=FullRecord&DestApp=WOS&KeyUT=000999123100001

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85165521372&origin=recordpage

UR - https://www.scopus.com/pages/publications/85165521372

UR - https://app-overton-io.ezproxy.cityu.edu.hk/articles.php?query=10.1093/bib/bbad194

U2 - 10.1093/bib/bbad194

DO - 10.1093/bib/bbad194

M3 - RGC 21 - Publication in refereed journal

C2 - 37249547

SN - 1467-5463

VL - 24

JO - Briefings in Bioinformatics

JF - Briefings in Bioinformatics

IS - 4

M1 - bbad194

ER -

DCiPatho: deep cross-fusion networks for genome scale identification of pathogens

Abstract

Bibliographical note

Research Keywords

Publisher's Copyright Statement

Policy Impact

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this