{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T06:14:00Z","timestamp":1772172840409,"version":"3.50.1"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1008898","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2021,4,15]],"date-time":"2021-04-15T00:00:00Z","timestamp":1618444800000}}],"reference-count":58,"publisher":"Public Library of Science (PLoS)","issue":"4","license":[{"start":{"date-parts":[[2021,4,5]],"date-time":"2021-04-05T00:00:00Z","timestamp":1617580800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004063","name":"Knut och Alice Wallenbergs Stiftelse","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004063","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002835","name":"Chalmers Tekniska H\u00f6gskola","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002835","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>\n                    Deregulation of the protein secretory pathway (PSP) is linked to many hallmarks of cancer, such as promoting tissue invasion and modulating cell-cell signaling. The collection of secreted proteins processed by the PSP, known as the secretome, is often studied due to its potential as a reservoir of tumor biomarkers. However, there has been less focus on the protein components of the secretory machinery itself. We therefore investigated the expression changes in secretory pathway components across many different cancer types. Specifically, we implemented a dual approach involving differential expression analysis and machine learning to identify PSP genes whose expression was associated with key tumor characteristics: mutation of p53, cancer status, and tumor stage. Eight different machine learning algorithms were included in the analysis to enable comparison between methods and to focus on signals that were robust to algorithm type. The machine learning approach was validated by identifying PSP genes known to be regulated by p53, and even outperformed the differential expression analysis approach. Among the different analysis methods and cancer types, the kinesin family members\n                    <jats:italic>KIF20A<\/jats:italic>\n                    and\n                    <jats:italic>KIF23<\/jats:italic>\n                    were consistently among the top genes associated with malignant transformation or tumor stage. However, unlike most cancer types which exhibited elevated\n                    <jats:italic>KIF20A<\/jats:italic>\n                    expression that remained relatively constant across tumor stages, renal carcinomas displayed a more gradual increase that continued with increasing disease severity. Collectively, our study demonstrates the complementary nature of a combined differential expression and machine learning approach for analyzing gene expression data, and highlights key PSP components relevant to features of tumor pathophysiology that may constitute potential therapeutic targets.\n                  <\/jats:p>","DOI":"10.1371\/journal.pcbi.1008898","type":"journal-article","created":{"date-parts":[[2021,4,5]],"date-time":"2021-04-05T13:37:29Z","timestamp":1617629849000},"page":"e1008898","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":11,"title":["Machine learning-based investigation of the cancer protein secretory pathway"],"prefix":"10.1371","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0956-039X","authenticated-orcid":true,"given":"Rasool","family":"Saghaleyni","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6037-7019","authenticated-orcid":true,"given":"Azam","family":"Sheikh Muhammad","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5308-7061","authenticated-orcid":true,"given":"Pramod","family":"Bangalore","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9955-6003","authenticated-orcid":true,"given":"Jens","family":"Nielsen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8567-5960","authenticated-orcid":true,"given":"Jonathan L.","family":"Robinson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2021,4,5]]},"reference":[{"key":"pcbi.1008898.ref001","doi-asserted-by":"crossref","first-page":"846","DOI":"10.1038\/nm.3915","article-title":"Toward understanding and exploiting tumor heterogeneity","volume":"21","author":"AA Alizadeh","year":"2015","journal-title":"Nat Med"},{"key":"pcbi.1008898.ref002","doi-asserted-by":"crossref","first-page":"646","DOI":"10.1016\/j.cell.2011.02.013","article-title":"Hallmarks of cancer: the next generation","volume":"144","author":"D Hanahan","year":"2011","journal-title":"Cell"},{"key":"pcbi.1008898.ref003","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1016\/j.ccr.2012.02.022","article-title":"Accessories to the crime: functions of cells recruited to the tumor microenvironment","volume":"21","author":"D Hanahan","year":"2012","journal-title":"Cancer Cell"},{"key":"pcbi.1008898.ref004","doi-asserted-by":"crossref","first-page":"643","DOI":"10.1016\/j.trecan.2017.07.002","article-title":"The Unfolded Protein Response in Immunogenic Cell Death and Cancer Immunotherapy.","volume":"3","author":"N Rufo","year":"2017","journal-title":"Trends Cancer Res"},{"key":"pcbi.1008898.ref005","first-page":"12","author":"M Uhl\u00e9n","year":"2019","journal-title":"The human secretome. Sci Signal"},{"key":"pcbi.1008898.ref006","doi-asserted-by":"crossref","first-page":"299","DOI":"10.3389\/fcell.2019.00299","article-title":"Comprehensive Identification and Characterization of Human Secretome Based on Integrative Proteomic and Transcriptomic Data.","volume":"7","author":"G Chen","year":"2019","journal-title":"Front Cell Dev Biol"},{"key":"pcbi.1008898.ref007","doi-asserted-by":"crossref","first-page":"2622","DOI":"10.1016\/j.celrep.2019.02.025","article-title":"A Systematic Investigation of the Malignant Functions and Diagnostic Potential of the Cancer Secretome.","volume":"26","author":"JL Robinson","year":"2019","journal-title":"Cell Rep"},{"key":"pcbi.1008898.ref008","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1038\/s41540-017-0021-4","article-title":"Human protein secretory pathway genes are expressed in a tissue-specific pattern to match processing demands of the secretome","volume":"3","author":"A Feizi","year":"2017","journal-title":"NPJ Syst Biol Appl"},{"key":"pcbi.1008898.ref009","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1038\/s41467-019-13867-y","article-title":"Genome-scale reconstructions of the mammalian secretory pathway predict metabolic costs and limitations of protein secretion","volume":"11","author":"JM Gutierrez","year":"2020","journal-title":"Nat Commun."},{"key":"pcbi.1008898.ref010","doi-asserted-by":"crossref","first-page":"43238","DOI":"10.1038\/srep43238","article-title":"A multi-component classifier for nonalcoholic fatty liver disease (NAFLD) based on genomic, proteomic, and phenomic data domains","volume":"7","author":"GC Wood","year":"2017","journal-title":"Sci Rep"},{"key":"pcbi.1008898.ref011","doi-asserted-by":"crossref","first-page":"e1006826","DOI":"10.1371\/journal.pcbi.1006826","article-title":"Machine learning analysis of gene expression data reveals novel diagnostic and prognostic biomarkers and identifies therapeutic targets for soft tissue sarcomas","volume":"15","author":"DGP van IJzendoorn","year":"2019","journal-title":"PLoS Comput Biol"},{"key":"pcbi.1008898.ref012","doi-asserted-by":"crossref","first-page":"18119","DOI":"10.1073\/pnas.1813645116","article-title":"Identification of the expressome by machine learning on omics data","volume":"116","author":"RC Sartor","year":"2019","journal-title":"Proc Natl Acad Sci U S A"},{"key":"pcbi.1008898.ref013","first-page":"41","article-title":"Applications of Support Vector Machine (SVM) Learning in Cancer Genomics.","volume":"15","author":"S Huang","year":"2018","journal-title":"Cancer Genomics Proteomics"},{"key":"pcbi.1008898.ref014","first-page":"15","article-title":"Opportunities and obstacles for deep learning in biology and medicine","author":"T Ching","year":"2018","journal-title":"J R Soc Interface"},{"key":"pcbi.1008898.ref015","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1186\/s12859-018-2035-3","article-title":"Ensemble of rankers for efficient gene signature extraction in smoke exposure classification","volume":"19","author":"M Giordano","year":"2018","journal-title":"BMC Bioinformatics"},{"key":"pcbi.1008898.ref016","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1016\/j.cmpb.2019.04.007","article-title":"MLSeq: Machine learning interface for RNA-sequencing data","volume":"175","author":"D Goksuluk","year":"2019","journal-title":"Comput Methods Programs Biomed"},{"key":"pcbi.1008898.ref017","doi-asserted-by":"crossref","first-page":"e63284","DOI":"10.1371\/journal.pone.0063284","article-title":"Genome-scale modeling of the protein secretory machinery in yeast","volume":"8","author":"A Feizi","year":"2013","journal-title":"PLoS One"},{"key":"pcbi.1008898.ref018","article-title":"Random decision forests.","author":"TK Ho","journal-title":"Proceedings of 3rd International Conference on Document Analysis and Recognition."},{"key":"pcbi.1008898.ref019","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/s10994-006-6226-1","article-title":"Extremely randomized trees","author":"P Geurts","year":"2006","journal-title":"Machine Learning"},{"key":"pcbi.1008898.ref020","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1006\/jcss.1997.1504","article-title":"A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting","author":"Y Freund","year":"1997","journal-title":"Journal of Computer and System Sciences"},{"key":"pcbi.1008898.ref021","doi-asserted-by":"crossref","first-page":"785","DOI":"10.1145\/2939672.2939785","volume-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"T Chen","year":"2016"},{"key":"pcbi.1008898.ref022","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","article-title":"Regression Shrinkage and Selection Via the Lasso","author":"R Tibshirani","year":"1996","journal-title":"Journal of the Royal Statistical Society: Series B (Methodological)."},{"key":"pcbi.1008898.ref023","doi-asserted-by":"crossref","DOI":"10.1145\/130385.130401","article-title":"A training algorithm for optimal margin classifiers","author":"BE Boser","year":"1992","journal-title":"Proceedings of the fifth annual workshop on Computational learning theory\u2014COLT \u201892"},{"key":"pcbi.1008898.ref024","doi-asserted-by":"crossref","first-page":"e116","DOI":"10.1371\/journal.pcbi.0030116","article-title":"Machine learning and its applications to biology","volume":"3","author":"AL Tarca","year":"2007","journal-title":"PLoS Comput Biol"},{"key":"pcbi.1008898.ref025","doi-asserted-by":"crossref","first-page":"5529","DOI":"10.1242\/jcs.123604","article-title":"Machine learning in cell biology\u2014teaching computers to recognize phenotypes","volume":"126","author":"C Sommer","year":"2013","journal-title":"J Cell Sci"},{"key":"pcbi.1008898.ref026","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1038\/ncb2641","article-title":"p53 mutations in cancer","volume":"15","author":"PAJ Muller","year":"2013","journal-title":"Nat Cell Biol"},{"key":"pcbi.1008898.ref027","doi-asserted-by":"crossref","first-page":"3943","DOI":"10.1038\/onc.2016.502","article-title":"Census and evaluation of p53 target genes","volume":"36","author":"M Fischer","year":"2017","journal-title":"Oncogene"},{"key":"pcbi.1008898.ref028","doi-asserted-by":"crossref","first-page":"e63187","DOI":"10.1371\/journal.pone.0063187","article-title":"p53 and cell cycle dependent transcription of kinesin family member 23 (KIF23) is controlled via a CHR promoter element bound by DREAM and MMB complexes","volume":"8","author":"M Fischer","year":"2013","journal-title":"PLoS One."},{"key":"pcbi.1008898.ref029","doi-asserted-by":"crossref","first-page":"1130","DOI":"10.1038\/cdd.2010.179","article-title":"Differential regulation of the proapoptotic multidomain protein Bak by p53 and p73 at the promoter level","volume":"18","author":"V Graupner","year":"2011","journal-title":"Cell Death Differ"},{"key":"pcbi.1008898.ref030","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1007\/978-94-017-9732-0_12","article-title":"The Kinesin-6 Members MKLP1, MKLP2 and MPP1","author":"RD Baron","year":"2015","journal-title":"Kinesins and Cancer"},{"key":"pcbi.1008898.ref031","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1016\/S0378-1119(00)00135-9","article-title":"cDNA cloning, expression pattern, genomic structure and chromosomal location of RAB6KIFL, a human kinesin-like gene","volume":"248","author":"F Lai","year":"2000","journal-title":"Gene"},{"key":"pcbi.1008898.ref032","doi-asserted-by":"crossref","first-page":"527","DOI":"10.1038\/nrc3310","article-title":"Kinesins and cancer","volume":"12","author":"O Rath","year":"2012","journal-title":"Nat Rev Cancer"},{"key":"pcbi.1008898.ref033","doi-asserted-by":"crossref","first-page":"631","DOI":"10.1038\/nrm2002","article-title":"SNAREs\u2014engines for membrane fusion","author":"R Jahn","year":"2006","journal-title":"Nature Reviews Molecular Cell Biology"},{"key":"pcbi.1008898.ref034","first-page":"1","article-title":"Role of SNARE proteins in tumourigenesis and their potential as targets for novel anti-cancer therapeutics","volume":"1856","author":"J Meng","year":"2015","journal-title":"Biochim Biophys Acta"},{"key":"pcbi.1008898.ref035","doi-asserted-by":"crossref","first-page":"4129","DOI":"10.2147\/OTT.S201799","article-title":"Progression of the role of CRYAB in signaling pathways and cancers","volume":"12","author":"J Zhang","year":"2019","journal-title":"Onco Targets Ther"},{"key":"pcbi.1008898.ref036","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.pharmthera.2016.01.012","article-title":"\u03b1B-crystallin: Portrait of a malignant chaperone as a cancer therapeutic target","author":"D Malin","year":"2016","journal-title":"Pharmacology & Therapeutics"},{"key":"pcbi.1008898.ref037","doi-asserted-by":"crossref","first-page":"3709","DOI":"10.1038\/onc.2011.529","article-title":"Tumor suppressor Alpha B-crystallin (CRYAB) associates with the cadherin\/catenin adherens junction and impairs NPC progression-associated properties","author":"Z Huang","year":"2012","journal-title":"Oncogene"},{"key":"pcbi.1008898.ref038","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1379\/CSC-107R.1","article-title":"Differential expression of alphaB-crystallin and Hsp27-1 in anaplastic thyroid carcinomas because of tumor-specific alphaB-crystallin gene (CRYAB) silencing","volume":"10","author":"I Mineva","year":"2005","journal-title":"Cell Stress Chaperones"},{"key":"pcbi.1008898.ref039","doi-asserted-by":"crossref","DOI":"10.3390\/cancers12020259","article-title":"Rab GTPases: Emerging Oncogenes and Tumor Suppressive Regulators for the Editing of Survival Pathways in Cancer.","volume":"12","author":"PD Gopal Krishnan","year":"2020","journal-title":"Cancers"},{"key":"pcbi.1008898.ref040","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1186\/s12935-017-0411-0","article-title":"High expression of Rab25 contributes to malignant phenotypes and biochemical recurrence in patients with prostate cancer after radical prostatectomy","volume":"17","author":"C Hu","year":"2017","journal-title":"Cancer Cell Int"},{"key":"pcbi.1008898.ref041","doi-asserted-by":"crossref","first-page":"477","DOI":"10.1038\/nrd1751","article-title":"Glycans in cancer and inflammation\u2014potential for therapeutics and diagnostics","author":"DH Dube","year":"2005","journal-title":"Nature Reviews Drug Discovery"},{"key":"pcbi.1008898.ref042","doi-asserted-by":"crossref","first-page":"525","DOI":"10.1002\/pmic.201300387","article-title":"Cell surface protein glycosylation in cancer","author":"MN Christiansen","year":"2014","journal-title":"PROTEOMICS"},{"key":"pcbi.1008898.ref043","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.chembiol.2013.12.010","article-title":"The challenge and promise of glycomics","volume":"21","author":"RD Cummings","year":"2014","journal-title":"Chem Biol"},{"key":"pcbi.1008898.ref044","doi-asserted-by":"crossref","first-page":"D506","DOI":"10.1093\/nar\/gky1049","article-title":"UniProt: a worldwide hub of protein knowledge","volume":"47","author":"UniProt Consortium","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"pcbi.1008898.ref045","doi-asserted-by":"crossref","first-page":"4593","DOI":"10.1074\/jbc.R100039200","article-title":"Hyaluronan-Cell Interactions in Cancer and Vascular Disease","author":"BP Toole","year":"2002","journal-title":"Journal of Biological Chemistry"},{"key":"pcbi.1008898.ref046","doi-asserted-by":"crossref","first-page":"37R","DOI":"10.1093\/glycob\/12.3.37R","article-title":"Hyaluronan promotes the malignant phenotype","volume":"12","author":"BP Toole","year":"2002","journal-title":"Glycobiology"},{"key":"pcbi.1008898.ref047","doi-asserted-by":"crossref","first-page":"e0167449","DOI":"10.1371\/journal.pone.0167449","article-title":"High Expression of KIF20A Is Associated with Poor Overall Survival and Tumor Progression in Early-Stage Cervical Squamous Cell Carcinoma.","volume":"11","author":"W Zhang","year":"2016","journal-title":"PLoS One"},{"key":"pcbi.1008898.ref048","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1016\/j.ajpath.2011.09.040","article-title":"KIF20A mRNA and Its Product MKlp2 Are Increased During Hepatocyte Proliferation and Hepatocarcinogenesis","author":"I Gasnereau","year":"2012","journal-title":"The American Journal of Pathology"},{"key":"pcbi.1008898.ref049","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1038\/ncb2383","article-title":"Defining human ERAD networks through an integrative mapping strategy","volume":"14","author":"JC Christianson","year":"2011","journal-title":"Nat Cell Biol"},{"key":"pcbi.1008898.ref050","doi-asserted-by":"crossref","first-page":"2953","DOI":"10.1039\/C6MB00476H","article-title":"Integrative analysis of human omics data using biomolecular networks","volume":"12","author":"JL Robinson","year":"2016","journal-title":"Mol Biosyst"},{"key":"pcbi.1008898.ref051","doi-asserted-by":"crossref","first-page":"399","DOI":"10.1038\/s41592-018-0019-x","article-title":"The curse(s) of dimensionality","volume":"15","author":"N Altman","year":"2018","journal-title":"Nat Methods"},{"key":"pcbi.1008898.ref052","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1016\/j.gdata.2017.10.006","article-title":"Co-expression network analysis identified six hub genes in association with progression and prognosis in human clear cell renal cell carcinoma (ccRCC).","author":"L Yuan","year":"2017","journal-title":"Genomics Data."},{"key":"pcbi.1008898.ref053","doi-asserted-by":"crossref","first-page":"e71","DOI":"10.1093\/nar\/gkv1507","article-title":"TCGAbiolinks: an R\/Bioconductor package for integrative analysis of TCGA data","author":"A Colaprico","year":"2016","journal-title":"Nucleic Acids Research"},{"key":"pcbi.1008898.ref054","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1038\/nbt.2514","article-title":"Sensitive detection of somatic point mutations in impure and heterogeneous cancer samples","volume":"31","author":"K Cibulskis","year":"2013","journal-title":"Nat Biotechnol"},{"key":"pcbi.1008898.ref055","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1093\/bioinformatics\/btp616","article-title":"edgeR: a Bioconductor package for differential expression analysis of digital gene expression data","volume":"26","author":"MD Robinson","year":"2010","journal-title":"Bioinformatics"},{"key":"pcbi.1008898.ref056","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","author":"F Pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"pcbi.1008898.ref057","doi-asserted-by":"crossref","first-page":"D607","DOI":"10.1093\/nar\/gky1131","article-title":"STRING v11: protein-protein association networks with increased coverage, supporting functional discovery in genome-wide experimental datasets","volume":"47","author":"D Szklarczyk","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"pcbi.1008898.ref058","doi-asserted-by":"crossref","first-page":"3037","DOI":"10.4161\/15384101.2014.949083","article-title":"The transcription factor p53: not a repressor, solely an activator","volume":"13","author":"M Fischer","year":"2014","journal-title":"Cell Cycle"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1008898","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2021,4,15]],"date-time":"2021-04-15T00:00:00Z","timestamp":1618444800000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1008898","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,27]],"date-time":"2024-08-27T12:04:59Z","timestamp":1724760299000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1008898"}},"subtitle":[],"editor":[{"given":"Vassily","family":"Hatzimanikatis","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2021,4,5]]},"references-count":58,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2021,4,5]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1008898","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2020.09.09.289413","asserted-by":"object"}]},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4,5]]}}}