No Cover Image

Journal article 96 views 19 downloads

TLGP: a flexible transfer learning algorithm for gene prioritization based on heterogeneous source domain

Yan Wang, Zuheng Xia, JINGJING DENG, Xianghua Xie Orcid Logo, Maoguo Gong, Xiaoke Ma

BMC Bioinformatics, Volume: 22, Issue: S9

Swansea University Authors: JINGJING DENG, Xianghua Xie Orcid Logo

  • s12859-021-04190-9.pdf

    PDF | Version of Record

    © The Author(s) 2021. This article is licensed under a Creative Commons Attribution 4.0 International License

    Download (1.26MB)

Abstract

BackgroundGene prioritization (gene ranking) aims to obtain the centrality of genes, which is critical for cancer diagnosis and therapy since keys genes correspond to the biomarkers or targets of drugs. Great efforts have been devoted to the gene ranking problem by exploring the similarity between c...

Full description

Published in: BMC Bioinformatics
ISSN: 1471-2105
Published: Springer Science and Business Media LLC 2021
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa57704
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2021-08-29T17:44:00Z
last_indexed 2022-01-08T04:25:37Z
id cronfa57704
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2022-01-07T15:25:30.4578213</datestamp><bib-version>v2</bib-version><id>57704</id><entry>2021-08-29</entry><title>TLGP: a flexible transfer learning algorithm for gene prioritization based on heterogeneous source domain</title><swanseaauthors><author><sid>e4218e3d46c58fcc78db2ada87eacf63</sid><firstname>JINGJING</firstname><surname>DENG</surname><name>JINGJING DENG</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>b334d40963c7a2f435f06d2c26c74e11</sid><ORCID>0000-0002-2701-8660</ORCID><firstname>Xianghua</firstname><surname>Xie</surname><name>Xianghua Xie</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2021-08-29</date><abstract>BackgroundGene prioritization (gene ranking) aims to obtain the centrality of genes, which is critical for cancer diagnosis and therapy since keys genes correspond to the biomarkers or targets of drugs. Great efforts have been devoted to the gene ranking problem by exploring the similarity between candidate and known disease-causing genes. However, when the number of disease-causing genes is limited, they are not applicable largely due to the low accuracy. Actually, the number of disease-causing genes for cancers, particularly for these rare cancers, are really limited. Therefore, there is a critical needed to design effective and efficient algorithms for gene ranking with limited prior disease-causing genes.ResultsIn this study, we propose a transfer learning based algorithm for gene prioritization (called TLGP) in the cancer (target domain) without disease-causing genes by transferring knowledge from other cancers (source domain). The underlying assumption is that knowledge shared by similar cancers improves the accuracy of gene prioritization. Specifically, TLGP first quantifies the similarity between the target and source domain by calculating the affinity matrix for genes. Then, TLGP automatically learns a fusion network for the target cancer by fusing affinity matrix, pathogenic genes and genomic data of source cancers. Finally, genes in the target cancer are prioritized. The experimental results indicate that the learnt fusion network is more reliable than gene co-expression network, implying that transferring knowledge from other cancers improves the accuracy of network construction. Moreover, TLGP outperforms state-of-the-art approaches in terms of accuracy, improving at least 5%.ConclusionThe proposed model and method provide an effective and efficient strategy for gene ranking by integrating genomic data from various cancers.</abstract><type>Journal Article</type><journal>BMC Bioinformatics</journal><volume>22</volume><journalNumber>S9</journalNumber><paginationStart/><paginationEnd/><publisher>Springer Science and Business Media LLC</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic>1471-2105</issnElectronic><keywords>Gene prioritizatio, Transfer learning, Gene co-expression network, Integrative analysis</keywords><publishedDay>25</publishedDay><publishedMonth>8</publishedMonth><publishedYear>2021</publishedYear><publishedDate>2021-08-25</publishedDate><doi>10.1186/s12859-021-04190-9</doi><url/><notes/><college>COLLEGE NANME</college><CollegeCode>COLLEGE CODE</CollegeCode><institution>Swansea University</institution><apcterm>Another institution paid the OA fee</apcterm><funders>This work was supported by the National Natural Science Foundation of China with No. 61772394 (XM) and Scientifc Research Foundation for the Returned Overseas Chinese Scholars of Shaanxi Province with No. 2018003 (XM). Publication costs are founded by National Natural Science Foundation of China (No. 61772394)</funders><lastEdited>2022-01-07T15:25:30.4578213</lastEdited><Created>2021-08-29T18:41:49.9271161</Created><path><level id="1">College of Science</level><level id="2">Computer Science</level></path><authors><author><firstname>Yan</firstname><surname>Wang</surname><order>1</order></author><author><firstname>Zuheng</firstname><surname>Xia</surname><order>2</order></author><author><firstname>JINGJING</firstname><surname>DENG</surname><order>3</order></author><author><firstname>Xianghua</firstname><surname>Xie</surname><orcid>0000-0002-2701-8660</orcid><order>4</order></author><author><firstname>Maoguo</firstname><surname>Gong</surname><order>5</order></author><author><firstname>Xiaoke</firstname><surname>Ma</surname><order>6</order></author></authors><documents><document><filename>57704__20712__3ca1e183fba1499c934711668de7814f.pdf</filename><originalFilename>s12859-021-04190-9.pdf</originalFilename><uploaded>2021-08-29T18:43:34.4302066</uploaded><type>Output</type><contentLength>1319713</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>&#xA9; The Author(s) 2021. This article is licensed under a Creative Commons Attribution 4.0 International License</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling 2022-01-07T15:25:30.4578213 v2 57704 2021-08-29 TLGP: a flexible transfer learning algorithm for gene prioritization based on heterogeneous source domain e4218e3d46c58fcc78db2ada87eacf63 JINGJING DENG JINGJING DENG true false b334d40963c7a2f435f06d2c26c74e11 0000-0002-2701-8660 Xianghua Xie Xianghua Xie true false 2021-08-29 BackgroundGene prioritization (gene ranking) aims to obtain the centrality of genes, which is critical for cancer diagnosis and therapy since keys genes correspond to the biomarkers or targets of drugs. Great efforts have been devoted to the gene ranking problem by exploring the similarity between candidate and known disease-causing genes. However, when the number of disease-causing genes is limited, they are not applicable largely due to the low accuracy. Actually, the number of disease-causing genes for cancers, particularly for these rare cancers, are really limited. Therefore, there is a critical needed to design effective and efficient algorithms for gene ranking with limited prior disease-causing genes.ResultsIn this study, we propose a transfer learning based algorithm for gene prioritization (called TLGP) in the cancer (target domain) without disease-causing genes by transferring knowledge from other cancers (source domain). The underlying assumption is that knowledge shared by similar cancers improves the accuracy of gene prioritization. Specifically, TLGP first quantifies the similarity between the target and source domain by calculating the affinity matrix for genes. Then, TLGP automatically learns a fusion network for the target cancer by fusing affinity matrix, pathogenic genes and genomic data of source cancers. Finally, genes in the target cancer are prioritized. The experimental results indicate that the learnt fusion network is more reliable than gene co-expression network, implying that transferring knowledge from other cancers improves the accuracy of network construction. Moreover, TLGP outperforms state-of-the-art approaches in terms of accuracy, improving at least 5%.ConclusionThe proposed model and method provide an effective and efficient strategy for gene ranking by integrating genomic data from various cancers. Journal Article BMC Bioinformatics 22 S9 Springer Science and Business Media LLC 1471-2105 Gene prioritizatio, Transfer learning, Gene co-expression network, Integrative analysis 25 8 2021 2021-08-25 10.1186/s12859-021-04190-9 COLLEGE NANME COLLEGE CODE Swansea University Another institution paid the OA fee This work was supported by the National Natural Science Foundation of China with No. 61772394 (XM) and Scientifc Research Foundation for the Returned Overseas Chinese Scholars of Shaanxi Province with No. 2018003 (XM). Publication costs are founded by National Natural Science Foundation of China (No. 61772394) 2022-01-07T15:25:30.4578213 2021-08-29T18:41:49.9271161 College of Science Computer Science Yan Wang 1 Zuheng Xia 2 JINGJING DENG 3 Xianghua Xie 0000-0002-2701-8660 4 Maoguo Gong 5 Xiaoke Ma 6 57704__20712__3ca1e183fba1499c934711668de7814f.pdf s12859-021-04190-9.pdf 2021-08-29T18:43:34.4302066 Output 1319713 application/pdf Version of Record true © The Author(s) 2021. This article is licensed under a Creative Commons Attribution 4.0 International License true eng http://creativecommons.org/licenses/by/4.0/
title TLGP: a flexible transfer learning algorithm for gene prioritization based on heterogeneous source domain
spellingShingle TLGP: a flexible transfer learning algorithm for gene prioritization based on heterogeneous source domain
JINGJING DENG
Xianghua Xie
title_short TLGP: a flexible transfer learning algorithm for gene prioritization based on heterogeneous source domain
title_full TLGP: a flexible transfer learning algorithm for gene prioritization based on heterogeneous source domain
title_fullStr TLGP: a flexible transfer learning algorithm for gene prioritization based on heterogeneous source domain
title_full_unstemmed TLGP: a flexible transfer learning algorithm for gene prioritization based on heterogeneous source domain
title_sort TLGP: a flexible transfer learning algorithm for gene prioritization based on heterogeneous source domain
author_id_str_mv e4218e3d46c58fcc78db2ada87eacf63
b334d40963c7a2f435f06d2c26c74e11
author_id_fullname_str_mv e4218e3d46c58fcc78db2ada87eacf63_***_JINGJING DENG
b334d40963c7a2f435f06d2c26c74e11_***_Xianghua Xie
author JINGJING DENG
Xianghua Xie
author2 Yan Wang
Zuheng Xia
JINGJING DENG
Xianghua Xie
Maoguo Gong
Xiaoke Ma
format Journal article
container_title BMC Bioinformatics
container_volume 22
container_issue S9
publishDate 2021
institution Swansea University
issn 1471-2105
doi_str_mv 10.1186/s12859-021-04190-9
publisher Springer Science and Business Media LLC
college_str College of Science
hierarchytype
hierarchy_top_id collegeofscience
hierarchy_top_title College of Science
hierarchy_parent_id collegeofscience
hierarchy_parent_title College of Science
department_str Computer Science{{{_:::_}}}College of Science{{{_:::_}}}Computer Science
document_store_str 1
active_str 0
description BackgroundGene prioritization (gene ranking) aims to obtain the centrality of genes, which is critical for cancer diagnosis and therapy since keys genes correspond to the biomarkers or targets of drugs. Great efforts have been devoted to the gene ranking problem by exploring the similarity between candidate and known disease-causing genes. However, when the number of disease-causing genes is limited, they are not applicable largely due to the low accuracy. Actually, the number of disease-causing genes for cancers, particularly for these rare cancers, are really limited. Therefore, there is a critical needed to design effective and efficient algorithms for gene ranking with limited prior disease-causing genes.ResultsIn this study, we propose a transfer learning based algorithm for gene prioritization (called TLGP) in the cancer (target domain) without disease-causing genes by transferring knowledge from other cancers (source domain). The underlying assumption is that knowledge shared by similar cancers improves the accuracy of gene prioritization. Specifically, TLGP first quantifies the similarity between the target and source domain by calculating the affinity matrix for genes. Then, TLGP automatically learns a fusion network for the target cancer by fusing affinity matrix, pathogenic genes and genomic data of source cancers. Finally, genes in the target cancer are prioritized. The experimental results indicate that the learnt fusion network is more reliable than gene co-expression network, implying that transferring knowledge from other cancers improves the accuracy of network construction. Moreover, TLGP outperforms state-of-the-art approaches in terms of accuracy, improving at least 5%.ConclusionThe proposed model and method provide an effective and efficient strategy for gene ranking by integrating genomic data from various cancers.
published_date 2021-08-25T04:13:59Z
_version_ 1737027841198915584
score 10.878401