{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T20:38:07Z","timestamp":1783629487922,"version":"3.55.0"},"reference-count":28,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2024,4,11]],"date-time":"2024-04-11T00:00:00Z","timestamp":1712793600000},"content-version":"vor","delay-in-days":13,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Shenzhen Science and Technology Program","award":["20220814183301001"],"award-info":[{"award-number":["20220814183301001"]}]},{"name":"Strategic Interdisciplinary Research","award":["7020005"],"award-info":[{"award-number":["7020005"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,3,29]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Genome sequencing technologies reveal a huge amount of genomic sequences. Neural network-based methods can be prime candidates for retrieving insights from these sequences because of their applicability to large and diverse datasets. However, the highly variable lengths of genome sequences severely impair the presentation of sequences as input to the neural network. Genetic variations further complicate tasks that involve sequence comparison or alignment.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>Inspired by the theory and applications of \u201cspaced seeds,\u201d we propose a graph representation of genome sequences called \u201cgapped pattern graph.\u201d These graphs can be transformed through a Graph Convolutional Network to form lower-dimensional embeddings for downstream tasks. On the basis of the gapped pattern graphs, we implemented a neural network model and demonstrated its performance on diverse tasks involving microbe and mammalian genome data. Our method consistently outperformed all the other state-of-the-art methods across various metrics on all tasks, especially for the sequences with limited homology to the training data. In addition, our model was able to identify distinct gapped pattern signatures from the sequences.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>The framework is available at https:\/\/github.com\/deepomicslab\/GCNFrame.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btae188","type":"journal-article","created":{"date-parts":[[2024,4,11]],"date-time":"2024-04-11T19:37:14Z","timestamp":1712864234000},"source":"Crossref","is-referenced-by-count":5,"title":["Coding genomes with gapped pattern graph convolutional network"],"prefix":"10.1093","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2327-2888","authenticated-orcid":false,"given":"Ruo Han","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong Shenzhen Research Institute , Shen Zhen, 518063, China"},{"name":"Department of Computer Science, City University of Hong Kong , Hong Kong, 999077, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yen Kaow","family":"Ng","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong Shenzhen Research Institute , Shen Zhen, 518063, China"},{"name":"Department of Computer Science, City University of Hong Kong , Hong Kong, 999077, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4946-4880","authenticated-orcid":false,"given":"Xianglilan","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Pathogen and Biosecurity, Beijing Institute of Microbiology and Epidemiology , Beijing, 100071, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianping","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong Shenzhen Research Institute , Shen Zhen, 518063, China"},{"name":"Department of Computer Science, City University of Hong Kong , Hong Kong, 999077, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6246-6349","authenticated-orcid":false,"given":"Shuai Cheng","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong Shenzhen Research Institute , Shen Zhen, 518063, China"},{"name":"Department of Computer Science, City University of Hong Kong , Hong Kong, 999077, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2024,4,11]]},"reference":[{"key":"2024042222154761200_btae188-B1","doi-asserted-by":"crossref","first-page":"2834","DOI":"10.1093\/bioinformatics\/btab203","article-title":"STREME: accurate and versatile sequence motif discovery","volume":"37","author":"Bailey","year":"2021","journal-title":"Bioinformatics"},{"key":"2024042222154761200_btae188-B2","doi-asserted-by":"crossref","first-page":"D571","DOI":"10.1093\/nar\/gku1207","article-title":"NCBI viral genomes resource","volume":"43","author":"Brister","year":"2015","journal-title":"Nucleic Acids Res"},{"key":"2024042222154761200_btae188-B3","doi-asserted-by":"crossref","first-page":"D621","DOI":"10.1093\/nar\/gkr846","article-title":"ICEberg: a web-based resource for integrative and conjugative elements found in bacteria","volume":"40","author":"Bi","year":"2012","journal-title":"Nucleic Acids Res"},{"key":"2024042222154761200_btae188-B4","doi-asserted-by":"crossref","first-page":"1098","DOI":"10.1016\/j.cell.2021.01.029","article-title":"Massive expansion of human gut bacteriophage diversity","volume":"184","author":"Camarillo-Guerrero","year":"2021","journal-title":"Cell"},{"key":"2024042222154761200_btae188-B5","author":"Dalla-Torre"},{"key":"2024042222154761200_btae188-B6","doi-asserted-by":"crossref","first-page":"3113","DOI":"10.1093\/bioinformatics\/btx383","article-title":"WIsH: who is the host? Predicting prokaryotic hosts from metagenomic phage contigs","volume":"33","author":"Galiez","year":"2017","journal-title":"Bioinformatics"},{"key":"2024042222154761200_btae188-B7","first-page":"458","author":"Guo","year":"2021"},{"key":"2024042222154761200_btae188-B8","doi-asserted-by":"crossref","first-page":"R24","DOI":"10.1186\/gb-2007-8-2-r24","article-title":"Quantifying similarity between motifs","volume":"8","author":"Gupta","year":"2007","journal-title":"Genome Biol"},{"key":"2024042222154761200_btae188-B9","first-page":"1025","volume-title":"Adv Neural Inf Process Syst","author":"Hamilton","year":"2017"},{"key":"2024042222154761200_btae188-B10","doi-asserted-by":"crossref","first-page":"e11396","DOI":"10.7717\/peerj.11396","article-title":"BACPHLIP: predicting bacteriophage lifestyle from conserved protein domains","volume":"9","author":"Hockenberry","year":"2021","journal-title":"PeerJ"},{"key":"2024042222154761200_btae188-B11","doi-asserted-by":"crossref","first-page":"2969","DOI":"10.1093\/bioinformatics\/btm422","article-title":"Multiple spaced seeds for homology search","volume":"23","author":"Ilie","year":"2007","journal-title":"Bioinformatics"},{"key":"2024042222154761200_btae188-B12","doi-asserted-by":"crossref","first-page":"2112","DOI":"10.1093\/bioinformatics\/btab083","article-title":"DNABERT: pre-trained bidirectional encoder representations from transformers model for DNA-language in genome","volume":"37","author":"Ji","year":"2021","journal-title":"Bioinformatics"},{"key":"2024042222154761200_btae188-B13","doi-asserted-by":"crossref","first-page":"e0223680","DOI":"10.1371\/journal.pone.0223680","article-title":"Comprehensive analysis of chromosomal mobile genetic elements in the gut microbiome reveals phylum-level niche-adaptive gene pools","volume":"14","author":"Jiang","year":"2019","journal-title":"PLoS One"},{"key":"2024042222154761200_btae188-B14","doi-asserted-by":"crossref","first-page":"431","DOI":"10.1186\/1471-2105-11-431","article-title":"Hidden Markov model speed heuristic and iterative HMM search procedure","volume":"11","author":"Johnson","year":"2010","journal-title":"BMC Bioinformatics"},{"key":"2024042222154761200_btae188-B15","doi-asserted-by":"crossref","first-page":"D156","DOI":"10.1093\/nar\/gkt1123","article-title":"CollecTF: a database of experimentally validated transcription factor-binding sites in bacteria","volume":"42","author":"K\u0131l\u0131\u00e7","year":"2014","journal-title":"Nucleic Acids Res"},{"key":"2024042222154761200_btae188-B16","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"2024042222154761200_btae188-B17","doi-asserted-by":"crossref","first-page":"bbac565","DOI":"10.1093\/bib\/bbac565","article-title":"GraphLncLoc: long non-coding RNA subcellular localization prediction using graph convolutional networks based on sequence to graph transformation","volume":"24","author":"Li","year":"2023","journal-title":"Brief Bioinform"},{"key":"2024042222154761200_btae188-B18","doi-asserted-by":"crossref","first-page":"440","DOI":"10.1093\/bioinformatics\/18.3.440","article-title":"PatternHunter: faster and more sensitive homology search","volume":"18","author":"Ma","year":"2002","journal-title":"Bioinformatics"},{"key":"2024042222154761200_btae188-B19","author":"Ma","year":"2019"},{"key":"2024042222154761200_btae188-B20","author":"McInnes","year":"2018"},{"key":"2024042222154761200_btae188-B21","first-page":"1","author":"Shekar","year":"2019"},{"key":"2024042222154761200_btae188-B22","author":"Tong","year":"2020"},{"key":"2024042222154761200_btae188-B23","doi-asserted-by":"crossref","first-page":"116","DOI":"10.3390\/v8050116","article-title":"HostPhinder: a phage host prediction tool","volume":"8","author":"Villarroel","year":"2016","journal-title":"Viruses"},{"key":"2024042222154761200_btae188-B24","doi-asserted-by":"crossref","first-page":"bbab385","DOI":"10.1093\/bib\/bbab385","article-title":"DeepHost: phage host prediction with convolutional neural network","volume":"23","author":"Wang","year":"2022","journal-title":"Brief Bioinform"},{"key":"2024042222154761200_btae188-B25","doi-asserted-by":"crossref","first-page":"giab056","DOI":"10.1093\/gigascience\/giab056","article-title":"DeePhage: distinguishing virulent and temperate phage-derived sequences in metavirome data with a deep learning approach","volume":"10","author":"Wu","year":"2021","journal-title":"Gigascience"},{"key":"2024042222154761200_btae188-B26","doi-asserted-by":"crossref","first-page":"8484","DOI":"10.1038\/s41598-019-44966-x","article-title":"Modeling in-vivo protein-DNA binding by combining multiple-instance learning with a hybrid deep neural network","volume":"9","author":"Zhang","year":"2019","journal-title":"Sci Rep"},{"key":"2024042222154761200_btae188-B27","author":"Zhang","year":"2021"},{"key":"2024042222154761200_btae188-B28","doi-asserted-by":"crossref","first-page":"186","DOI":"10.1186\/s13059-017-1319-7","article-title":"Alignment-free sequence comparison: benefits, applications, and tools","volume":"18","author":"Zielezinski","year":"2017","journal-title":"Genome Biol"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btae188\/57218147\/btae188.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/4\/btae188\/57303426\/btae188.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/4\/btae188\/57303426\/btae188.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,22]],"date-time":"2024-04-22T22:16:19Z","timestamp":1713824179000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btae188\/7644280"}},"subtitle":[],"editor":[{"given":"Alfonso","family":"Valencia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,3,29]]},"references-count":28,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,3,29]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btae188","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,4,1]]},"published":{"date-parts":[[2024,3,29]]},"article-number":"btae188"}}