{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T16:13:29Z","timestamp":1775664809162,"version":"3.50.1"},"reference-count":50,"publisher":"Oxford University Press (OUP)","issue":"12","license":[{"start":{"date-parts":[[2018,11,8]],"date-time":"2018-11-08T00:00:00Z","timestamp":1541635200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["21803045"],"award-info":[{"award-number":["21803045"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,6,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Various bacterial pathogens can deliver their secreted substrates also called effectors through Type III secretion systems (T3SSs) into host cells and cause diseases. Since T3SS secreted effectors (T3SEs) play important roles in pathogen\u2013host interactions, identifying them is crucial to our understanding of the pathogenic mechanisms of T3SSs. However, the effectors display high level of sequence diversity, therefore making the identification a difficult process. There is a need to develop a novel and effective method to screen and select putative novel effectors from bacterial genomes that can be validated by a smaller number of key experiments.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We develop a deep convolution neural network to directly classify any protein sequence into T3SEs or non-T3SEs, which is useful for both effector prediction and the study of sequence-function relationship. Different from traditional machine learning-based methods, our method automatically extracts T3SE-related features from a protein N-terminal sequence of 100 residues and maps it to the T3SEs space. We train and test our method on the datasets curated from 16 species, yielding an average classification accuracy of 83.7% in the 5-fold cross-validation and an accuracy of 92.6% for the test set. Moreover, when comparing with known state-of-the-art prediction methods, the accuracy of our method is 6.31\u201320.73% higher than previous methods on a common independent dataset. Besides, we visualize the convolutional kernels and successfully identify the key features of T3SEs, which contain important signal information for secretion. Finally, some effectors reported in the literature are used to further demonstrate the application of DeepT3.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>DeepT3 is freely available at: https:\/\/github.com\/lje00006\/DeepT3.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Supplementary information<\/jats:title>\n                  <jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/bty931","type":"journal-article","created":{"date-parts":[[2018,11,7]],"date-time":"2018-11-07T12:09:36Z","timestamp":1541592576000},"page":"2051-2057","source":"Crossref","is-referenced-by-count":44,"title":["DeepT3: deep convolutional neural networks accurately identify Gram-negative bacterial type III secreted effectors using the N-terminal sequence"],"prefix":"10.1093","volume":"35","author":[{"given":"Li","family":"Xue","sequence":"first","affiliation":[{"name":"School of Public Health, Southwest Medical University, Luzhou, Sichuan, PR, China"}]},{"given":"Bin","family":"Tang","sequence":"additional","affiliation":[{"name":"Basic Medical College of Southwest Medical University, Luzhou, Sichuan, PR, China"}]},{"given":"Wei","family":"Chen","sequence":"additional","affiliation":[{"name":"Integrative Genomics Core, City of Hope National Medical Center, Duarte, CA, USA"}]},{"given":"Jiesi","family":"Luo","sequence":"additional","affiliation":[{"name":"Key Laboratory for Aging and Regenerative Medicine, Department of Pharmacology, School of Pharmacy, Southwest Medical University, Luzhou, Sichuan, China"}]}],"member":"286","published-online":{"date-parts":[[2018,11,8]]},"reference":[{"key":"2023012713074924600_bty931-B1","doi-asserted-by":"crossref","first-page":"831","DOI":"10.1038\/nbt.3300","article-title":"Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning","volume":"33","author":"Alipanahi","year":"2015","journal-title":"Nat. Biotechnol"},{"key":"2023012713074924600_bty931-B2","doi-asserted-by":"crossref","first-page":"3387","DOI":"10.1093\/bioinformatics\/btx431","article-title":"DeepLoc: prediction of protein subcellular localization using deep learning","volume":"33","author":"Almagro Armenteros","year":"2017","journal-title":"Bioinformatics"},{"key":"2023012713074924600_bty931-B3","doi-asserted-by":"crossref","first-page":"878.","DOI":"10.15252\/msb.20156651","article-title":"Deep learning for computational biology","volume":"12","author":"Angermueller","year":"2016","journal-title":"Mol. Syst. Biol"},{"key":"2023012713074924600_bty931-B4","doi-asserted-by":"crossref","first-page":"e1000376.","DOI":"10.1371\/journal.ppat.1000376","article-title":"Sequence-based prediction of type III secreted proteins","volume":"5","author":"Arnold","year":"2009","journal-title":"PLoS Pathog"},{"key":"2023012713074924600_bty931-B5","doi-asserted-by":"crossref","first-page":"e1002132","DOI":"10.1371\/journal.ppat.1002132","article-title":"Dynamic evolution of pathogenicity revealed by sequencing and comparative genomics of 19 Pseudomonas syringae isolates","volume":"7","author":"Baltrus","year":"2011","journal-title":"PLoS Pathog"},{"key":"2023012713074924600_bty931-B6","doi-asserted-by":"crossref","first-page":"349","DOI":"10.1093\/protein\/gzh037","article-title":"Feature-based prediction of non-classical and leaderless protein secretion","volume":"17","author":"Bendtsen","year":"2004","journal-title":"Protein Eng., Des. Sel"},{"key":"2023012713074924600_bty931-B7","doi-asserted-by":"crossref","first-page":"1649","DOI":"10.1016\/j.bbamcr.2014.01.035","article-title":"Assembly and structure of the T3SS","volume":"1843","author":"Burkinshaw","year":"2014","journal-title":"Biochim. Biophys. Acta"},{"key":"2023012713074924600_bty931-B8","doi-asserted-by":"crossref","first-page":"8336","DOI":"10.1073\/pnas.122220299","article-title":"Direct biochemical evidence for type III secretion-dependent translocation of the AvrBs2 effector protein into plant cells","volume":"99","author":"Casper-Lindley","year":"2002","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023012713074924600_bty931-B9","doi-asserted-by":"crossref","first-page":"811","DOI":"10.1038\/nrmicro1526","article-title":"The type III secretion injectisome","volume":"4","author":"Cornelis","year":"2006","journal-title":"Nat. Rev. Microbiol"},{"key":"2023012713074924600_bty931-B10","doi-asserted-by":"crossref","DOI":"10.1128\/mBio.00243-11","article-title":"A new means to identify type 3 secreted effectors: functionally interchangeable class IB chaperones recognize a conserved sequence","volume":"3","author":"Costa","year":"2012","journal-title":"mBio"},{"key":"2023012713074924600_bty931-B11","doi-asserted-by":"crossref","first-page":"855","DOI":"10.1046\/j.1365-2958.2002.03214.x","article-title":"The N-terminus of enteropathogenic Escherichia coli (EPEC) Tir mediates transport across bacterial and eukaryotic cell membranes","volume":"46","author":"Crawford","year":"2002","journal-title":"Mol. Microbiol"},{"key":"2023012713074924600_bty931-B12","doi-asserted-by":"crossref","first-page":"692","DOI":"10.1074\/mcp.M111.013672","article-title":"Quantitative proteomic analysis of type III secretome of enteropathogenic Escherichia coli reveals an expanded effector repertoire for attaching\/effacing bacterial pathogens","volume":"11","author":"Deng","year":"2012","journal-title":"Mol. Cell. Proteomics"},{"key":"2023012713074924600_bty931-B13","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1016\/j.tim.2009.01.004","article-title":"Secretion and subcellular localizations of bacterial proteins: a semantic awareness issue","volume":"17","author":"Desvaux","year":"2009","journal-title":"Trends Microbiol"},{"key":"2023012713074924600_bty931-B14","doi-asserted-by":"crossref","first-page":"bav064.","DOI":"10.1093\/database\/bav064","article-title":"BEAN 2.0: an integrated web resource for the identification and functional analysis of type III secreted effectors","volume":"2015","author":"Dong","year":"2015","journal-title":"Database"},{"key":"2023012713074924600_bty931-B15","doi-asserted-by":"crossref","first-page":"e56632","DOI":"10.1371\/journal.pone.0056632","article-title":"Using weakly conserved motifs hidden in secretion signals to identify type-III effectors from bacterial pathogen genomes","volume":"8","author":"Dong","year":"2013","journal-title":"PLoS One"},{"key":"2023012713074924600_bty931-B16","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1016\/j.mib.2008.12.007","article-title":"Role of Pseudomonas aeruginosa type III effectors in disease","volume":"12","author":"Engel","year":"2009","journal-title":"Curr. Opin. Microbiol"},{"key":"2023012713074924600_bty931-B17","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":"2023012713074924600_bty931-B18","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1016\/j.bbamcr.2004.03.011","article-title":"Type III protein secretion mechanism in mammalian and plant pathogens","volume":"1694","author":"He","year":"2004","journal-title":"Biochim. Biophys. Acta"},{"key":"2023012713074924600_bty931-B19","doi-asserted-by":"crossref","first-page":"2842","DOI":"10.1093\/bioinformatics\/btx218","article-title":"Capturing non-local interactions by long short-term memory bidirectional recurrent neural networks for improving prediction of protein secondary structure, backbone angles, contact numbers and solvent accessibility","volume":"33","author":"Heffernan","year":"2017","journal-title":"Bioinformatics"},{"key":"2023012713074924600_bty931-B20","doi-asserted-by":"crossref","first-page":"3879","DOI":"10.1111\/1462-2920.13755","article-title":"A global survey of bacterial type III secretion systems and their effectors","volume":"19","author":"Hu","year":"2017","journal-title":"Environ. Microbiol"},{"key":"2023012713074924600_bty931-B21","doi-asserted-by":"crossref","first-page":"680","DOI":"10.1093\/bioinformatics\/btq003","article-title":"CD-HIT Suite: a web server for clustering and comparing biological sequences","volume":"26","author":"Huang","year":"2010","journal-title":"Bioinformatics"},{"key":"2023012713074924600_bty931-B22","doi-asserted-by":"crossref","first-page":"3685","DOI":"10.1093\/bioinformatics\/btx531","article-title":"An introduction to deep learning on biological sequence data: examples and solutions","volume":"33","author":"Jurtz","year":"2017","journal-title":"Bioinformatics"},{"key":"2023012713074924600_bty931-B23","doi-asserted-by":"crossref","first-page":"990","DOI":"10.1101\/gr.200535.115","article-title":"Basset: learning the regulatory code of the accessible genome with deep convolutional neural networks","volume":"26","author":"Kelley","year":"2016","journal-title":"Genome Res"},{"key":"2023012713074924600_bty931-B24","doi-asserted-by":"crossref","first-page":"7279","DOI":"10.1128\/JB.185.24.7279-7284.2003","article-title":"InvB is a type III secretion-associated chaperone for the Salmonella enterica effector protein SopE","volume":"185","author":"Lee","year":"2003","journal-title":"J. Bacteriol"},{"key":"2023012713074924600_bty931-B25","doi-asserted-by":"crossref","first-page":"732","DOI":"10.1093\/bioinformatics\/btx679","article-title":"Chromatin accessibility prediction via a hybrid deep convolutional neural network","volume":"34","author":"Liu","year":"2018","journal-title":"Bioinformatics"},{"key":"2023012713074924600_bty931-B26","doi-asserted-by":"crossref","first-page":"e5917.","DOI":"10.1371\/journal.pone.0005917","article-title":"Prediction of type III secretion signals in genomes of gram-negative bacteria","volume":"4","author":"Lower","year":"2009","journal-title":"PLoS One"},{"key":"2023012713074924600_bty931-B27","doi-asserted-by":"crossref","first-page":"3048","DOI":"10.1039\/C5AN00311C","article-title":"A sequence-based two-level method for the prediction of type I secreted RTX proteins","volume":"140","author":"Luo","year":"2015","journal-title":"Analyst"},{"key":"2023012713074924600_bty931-B28","doi-asserted-by":"crossref","first-page":"412","DOI":"10.1016\/j.pbi.2008.05.001","article-title":"Evolution of prokaryotic and eukaryotic virulence effectors","volume":"11","author":"Ma","year":"2008","journal-title":"Curr. Opin. Plant Biol"},{"key":"2023012713074924600_bty931-B29","first-page":"851","article-title":"Deep learning in bioinformatics","volume":"18","author":"Min","year":"2017","journal-title":"Brief. Bioinform"},{"key":"2023012713074924600_bty931-B30","article-title":"Deep learning for healthcare: review, opportunities and challenges","author":"Miotto","year":"2017","journal-title":"Brief. Bioinform"},{"key":"2023012713074924600_bty931-B31","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.1365-2958.2005.04823.x","article-title":"A genome-wide screen identifies a Bordetella type III secretion effector and candidate effectors in other species","volume":"58","author":"Panina","year":"2005","journal-title":"Mol. Microbiol"},{"key":"2023012713074924600_bty931-B32","first-page":"2825","article-title":"Scikit-learn: machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res"},{"key":"2023012713074924600_bty931-B33","doi-asserted-by":"crossref","first-page":"7652","DOI":"10.1073\/pnas.112183899","article-title":"Genomewide identification of proteins secreted by the Hrp type III protein secretion system of Pseudomonas syringae pv. tomato DC3000","volume":"99","author":"Petnicki-Ocwieja","year":"2002","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023012713074924600_bty931-B34","doi-asserted-by":"crossref","first-page":"e1000375.","DOI":"10.1371\/journal.ppat.1000375","article-title":"Accurate prediction of secreted substrates and identification of a conserved putative secretion signal for type III secretion systems","volume":"5","author":"Samudrala","year":"2009","journal-title":"PLoS Pathog"},{"key":"2023012713074924600_bty931-B35","doi-asserted-by":"crossref","first-page":"442.","DOI":"10.1186\/1471-2105-12-442","article-title":"Meta-analytic approach to the accurate prediction of secreted virulence effectors in gram-negative bacteria","volume":"12","author":"Sato","year":"2011","journal-title":"BMC Bioinformatics"},{"key":"2023012713074924600_bty931-B36","doi-asserted-by":"crossref","first-page":"7227","DOI":"10.1128\/jb.178.24.7227-7233.1996","article-title":"Delineation and mutational analysis of the Yersinia pseudotuberculosis YopE domains which mediate translocation across bacterial and eukaryotic cellular membranes","volume":"178","author":"Schesser","year":"1996","journal-title":"J. Bacteriol"},{"key":"2023012713074924600_bty931-B37","doi-asserted-by":"crossref","first-page":"134","DOI":"10.1128\/CMR.00032-07","article-title":"Molecular pathogenesis of Shigella spp.: controlling host cell signaling, invasion, and death by type III secretion","volume":"21","author":"Schroeder","year":"2008","journal-title":"Clin. Microbiol. Rev"},{"key":"2023012713074924600_bty931-B38","doi-asserted-by":"crossref","first-page":"i639","DOI":"10.1093\/bioinformatics\/btw427","article-title":"DeepChrome: deep-learning for predicting gene expression from histone modifications","volume":"32","author":"Singh","year":"2016","journal-title":"Bioinformatics"},{"key":"2023012713074924600_bty931-B39","doi-asserted-by":"crossref","first-page":"11998","DOI":"10.1073\/pnas.92.26.11998","article-title":"Identification of the YopE and YopH domains required for secretion and internalization into the cytosol of macrophages, using the cyaA gene fusion approach","volume":"92","author":"Sory","year":"1995","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023012713074924600_bty931-B40","doi-asserted-by":"crossref","first-page":"2487","DOI":"10.1093\/bioinformatics\/bty116","article-title":"SECLAF: a webserver and deep neural network design tool for hierarchical biological sequence classification","author":"Szalkai","year":"2018","journal-title":"Bioinformatics"},{"key":"2023012713074924600_bty931-B41","doi-asserted-by":"crossref","first-page":"S4","DOI":"10.1186\/1471-2105-11-S7-S4","article-title":"T3SEdb: data warehousing of virulence effectors secreted by the bacterial Type III Secretion System","volume":"11 (Suppl 7)","author":"Tay","year":"2010","journal-title":"BMC Bioinformatics"},{"key":"2023012713074924600_bty931-B42","doi-asserted-by":"crossref","first-page":"1464","DOI":"10.1111\/mmi.12069","article-title":"A translocator-specific export signal establishes the translocator-effector secretion hierarchy that is important for type III secretion system function","volume":"86","author":"Tomalka","year":"2012","journal-title":"Mol. Microbiol"},{"key":"2023012713074924600_bty931-B43","first-page":"D190","article-title":"The universal protein resource (UniProt)","volume":"36","author":"UniProt","year":"2008","journal-title":"Nucleic Acids Res"},{"key":"2023012713074924600_bty931-B44","doi-asserted-by":"crossref","first-page":"1536","DOI":"10.1093\/bioinformatics\/btl151","article-title":"Two Sample Logo: a graphical representation of the differences between two sets of sequence alignments","volume":"22","author":"Vacic","year":"2006","journal-title":"Bioinformatics"},{"key":"2023012713074924600_bty931-B45","doi-asserted-by":"crossref","first-page":"2740","DOI":"10.1093\/bioinformatics\/bty179","article-title":"Deep learning improves antimicrobial peptide recognition","author":"Veltri","year":"2018","journal-title":"Bioinformatics"},{"key":"2023012713074924600_bty931-B46","doi-asserted-by":"crossref","first-page":"e69","DOI":"10.1093\/nar\/gky215","article-title":"DeFine: deep convolutional neural networks accurately quantify intensities of transcription factor-DNA binding and facilitate evaluation of functional non-coding variants","volume":"46","author":"Wang","year":"2018","journal-title":"Nucleic Acids Res"},{"key":"2023012713074924600_bty931-B47","doi-asserted-by":"crossref","first-page":"i672","DOI":"10.1093\/bioinformatics\/btw446","article-title":"AUCpreD: proteome-level protein disorder prediction by AUC-maximized deep convolutional neural fields","volume":"32","author":"Wang","year":"2016","journal-title":"Bioinformatics"},{"key":"2023012713074924600_bty931-B48","doi-asserted-by":"crossref","first-page":"777","DOI":"10.1093\/bioinformatics\/btr021","article-title":"High-accuracy prediction of bacterial type III secreted effectors based on position-specific amino acid composition profiles","volume":"27","author":"Wang","year":"2011","journal-title":"Bioinformatics"},{"key":"2023012713074924600_bty931-B49","doi-asserted-by":"crossref","first-page":"e84439","DOI":"10.1371\/journal.pone.0084439","article-title":"Effective identification of gram-negative bacterial type III secreted effectors using position-specific residue conservation profiles","volume":"8","author":"Yang","year":"2013","journal-title":"PLoS One"},{"key":"2023012713074924600_bty931-B50","doi-asserted-by":"crossref","first-page":"S47.","DOI":"10.1186\/1471-2105-11-S1-S47","article-title":"Computational prediction of type III secreted proteins from gram-negative bacteria","volume":"11 (Suppl 1)","author":"Yang","year":"2010","journal-title":"BMC Bioinformatics"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/35\/12\/2051\/48935120\/bioinformatics_35_12_2051.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/35\/12\/2051\/48935120\/bioinformatics_35_12_2051.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T14:13:21Z","timestamp":1674828801000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/35\/12\/2051\/5165378"}},"subtitle":[],"editor":[{"given":"John","family":"Hancock","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2018,11,8]]},"references-count":50,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2019,6,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/bty931","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2019,6]]},"published":{"date-parts":[[2018,11,8]]}}}