{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T09:13:45Z","timestamp":1789982025349,"version":"4.0.1"},"reference-count":58,"publisher":"Public Library of Science (PLoS)","issue":"9","license":[{"start":{"date-parts":[[2017,9,14]],"date-time":"2017-09-14T00:00:00Z","timestamp":1505347200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000054","name":"National Cancer Institute","doi-asserted-by":"publisher","award":["R15CA203605"],"award-info":[{"award-number":["R15CA203605"]}],"id":[{"id":"10.13039\/100000054","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"DOI":"10.1371\/journal.pone.0184370","type":"journal-article","created":{"date-parts":[[2017,9,14]],"date-time":"2017-09-14T17:36:13Z","timestamp":1505410573000},"page":"e0184370","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":40,"title":["Application of unsupervised analysis techniques to lung cancer patient data"],"prefix":"10.1371","volume":"12","author":[{"given":"Chip M.","family":"Lynch","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Victor H.","family":"van Berkel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5959-4286","authenticated-orcid":true,"given":"Hermann B.","family":"Frieboes","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2017,9,14]]},"reference":[{"key":"ref1","unstructured":"NCI_SEER_Training_Lung_Cancer_Stats. Introduction to Lung Cancer: SEER training modules\u2014National Cancer Institute; [2015]. Available from: <ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"http:\/\/training.seer.cancer.gov\/lung\/\" xlink:type=\"simple\">http:\/\/training.seer.cancer.gov\/lung\/<\/ext-link>."},{"key":"ref2","unstructured":"NCI_SEER_Overview. Overview of the SEER program. Surveillance Epidemiology and End Results [2015]. Available from: <ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"http:\/\/seer.cancer.gov\/about\/\" xlink:type=\"simple\">http:\/\/seer.cancer.gov\/about\/<\/ext-link>"},{"key":"ref3","unstructured":"SEER_Program. Surveillance, Epidemiology, and End Results (SEER) Program (<ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"http:\/\/www.seer.cancer.gov\" xlink:type=\"simple\">www.seer.cancer.gov<\/ext-link>) Research Data (1973\u20132009), National Cancer Institute, DCCPS, Surveillance Research Program, Surveillance Systems Branch, released April 2012, based on the November 2011 submission."},{"key":"ref4","unstructured":"NCI_Lung_Cancer_Info. What You Need To Know About Lung Cancer: National Cancer Institute; [2015]. Available from: <ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"http:\/\/www.cancer.gov\/publications\/patient-education\/wyntk-lung-cancer\" xlink:type=\"simple\">http:\/\/www.cancer.gov\/publications\/patient-education\/wyntk-lung-cancer<\/ext-link>."},{"issue":"2","key":"ref5","doi-asserted-by":"crossref","first-page":"651","DOI":"10.1200\/JCO.1998.16.2.651","article-title":"Lung cancer in young patients: analysis of a Surveillance, Epidemiology, and End Results database","volume":"16","author":"S Ramalingam","year":"1998","journal-title":"Journal of clinical oncology"},{"issue":"35","key":"ref6","doi-asserted-by":"crossref","first-page":"5570","DOI":"10.1200\/JCO.2007.12.5435","article-title":"Lung cancer in elderly patients: an analysis of the surveillance, epidemiology, and end results database","volume":"25","author":"TK Owonikoko","year":"2007","journal-title":"Journal of clinical oncology"},{"issue":"1","key":"ref7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.jss.2009.12.030","article-title":"Analysis of second primary lung cancers in the SEER database","volume":"162","author":"A Bhaskarla","year":"2010","journal-title":"Journal of Surgical Research"},{"issue":"1","key":"ref8","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1634\/theoncologist.12-1-20","article-title":"Cancer statistics, trends, and multiple primary cancer analyses from the Surveillance, Epidemiology, and End Results (SEER) Program","volume":"12","author":"MJ Hayat","year":"2007","journal-title":"The Oncologist"},{"issue":"9","key":"ref9","doi-asserted-by":"crossref","first-page":"e185","DOI":"10.1371\/journal.pmed.0050185","article-title":"Lung cancer occurrence in never-smokers: an analysis of 13 cohorts and 22 cancer registry studies","volume":"5","author":"MJ Thun","year":"2008","journal-title":"PLOS medicine"},{"issue":"3","key":"ref10","doi-asserted-by":"crossref","first-page":"768","DOI":"10.1378\/chest.127.3.768","article-title":"Lung Cancer in Women: Analysis of the National Surveillance, Epidemiology, and End Results Database","volume":"127","author":"JB Fu","year":"2005","journal-title":"CHEST Journal"},{"issue":"7","key":"ref11","doi-asserted-by":"crossref","first-page":"1215","DOI":"10.1158\/1055-9965.1215.13.7","article-title":"Comparative Analysis of Incidence Rates Subcommittee, Data Evaluation and Publication Committee, North American Association of Central Cancer Registries. Subsite-specific colorectal cancer incidence rates and stage distributions among Asians and Pacific Islanders in the United States, 1995 to 1999","volume":"13","author":"X Wu","year":"2004","journal-title":"Cancer Epidemiol Biomarkers Prev"},{"issue":"3","key":"ref12","first-page":"84","article-title":"Conditional survival in rectal cancer: a SEER database analysis","volume":"1","author":"SJ Wang","year":"2007","journal-title":"Gastrointestinal cancer research: GCR"},{"issue":"2","key":"ref13","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1016\/j.lungcan.2008.08.010","article-title":"Trends in the outcomes for patients with limited stage small cell lung cancer: An analysis of the Surveillance, Epidemiology, and End Results database","volume":"64","author":"BE Lally","year":"2009","journal-title":"Lung Cancer"},{"key":"ref14","doi-asserted-by":"crossref","unstructured":"Agrawal A, Choudhary A, editors. Identifying hotspots in lung cancer data using association rule mining. 11th International Conference on Data Mining Workshops (ICDMW); 2011: IEEE.","DOI":"10.1109\/ICDMW.2011.93"},{"issue":"2","key":"ref15","doi-asserted-by":"crossref","first-page":"34","DOI":"10.4018\/jkdb.2011040103","article-title":"Association Rule Mining Based HotSpot Analysis on SEER Lung Cancer Data","volume":"2","author":"A Agrawal","year":"2011","journal-title":"International Journal of Knowledge Discovery in Bioinformatics (IJKDB)"},{"key":"ref16","doi-asserted-by":"crossref","unstructured":"Agrawal A, Misra S, Narayanan R, Polepeddi L, Choudhary A, editors. A lung cancer outcome calculator using ensemble data mining on SEER data. Proceedings of the Tenth International Workshop on Data Mining in Bioinformatics; 2011: ACM.","DOI":"10.1145\/2003351.2003356"},{"issue":"6","key":"ref17","doi-asserted-by":"crossref","first-page":"657","DOI":"10.1002\/jso.23883","article-title":"The quest for population-level cancer recurrence data; current deficiencies and targets for improvement","volume":"111","author":"H In","year":"2015","journal-title":"J Surg Oncol"},{"issue":"3","key":"ref18","doi-asserted-by":"crossref","first-page":"S545","DOI":"10.1016\/j.ijrobp.2012.07.1453","article-title":"Patterns of Practice and Outcomes for Stage I Non-small Cell Lung Cancer (NSCLC): Analysis of SEER-17 Data, 1999\u20132008","volume":"84","author":"N Kapadia","year":"2012","journal-title":"International Journal of Radiation Oncology* Biology* Physics"},{"key":"ref19","first-page":"11","article-title":"Advances in Computational Biology","author":"Z Liu","year":"2010"},{"key":"ref20","doi-asserted-by":"crossref","unstructured":"Skrypnyk I, editor Finding Survival Groups in SEER Lung Cancer Data. Machine Learning and Applications (ICMLA), 2012 11th International Conference on; 2012: IEEE.","DOI":"10.1109\/ICMLA.2012.191"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1155\/2012\/920245","article-title":"Lung cancer survival prediction using ensemble data mining on SEER data","volume":"20","author":"A Agrawal","year":"2012","journal-title":"Scientific Programming"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"632786","DOI":"10.1155\/2009\/632786","article-title":"Developing prognostic systems of cancer patients by ensemble clustering","volume":"2009","author":"D Chen","year":"2009","journal-title":"J Biomed Biotechnol"},{"issue":"8","key":"ref23","first-page":"1","article-title":"Comparison of the C4.5 and a Naive Bayes Classifier for the Prediction of Lung Cancer Survivability","volume":"4","author":"G Dimitoglu","year":"2012","journal-title":"Journal of Computing"},{"key":"ref24","unstructured":"Fradkin D. Machine learning methods in the analysis of lung cancer survival data. February 2006."},{"issue":"1","key":"ref25","first-page":"39","article-title":"Diagnosis of Lung Cancer Prediction System Using Data Mining Classification Techniques","volume":"4","author":"V Krishnaiah","year":"2013","journal-title":"International Journal of Computer Science and Information Technologies"},{"key":"ref26","first-page":"125","article-title":"Missing dataimputationonthe5-yearsurvivalpredictionofbreast cancer patientswithunknowndiscretevalues","volume":"59","author":"PJ Garc\u00eda-Laencina","year":"2015","journal-title":"ComputersinBiologyandMedicine"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1016\/j.jbi.2015.09.012","article-title":"A new cluster-based oversampling method for improving survival prediction of hepatocellular carcinoma patients","volume":"58","author":"MS Santos","year":"2015","journal-title":"Journal of Biomedical Informatics"},{"issue":"6","key":"ref28","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1038\/nrg3920","article-title":"Machine learning applications in genetics and genomics","volume":"16","author":"MW Libbrecht","year":"2015","journal-title":"Nat Rev Genet"},{"issue":"12","key":"ref29","doi-asserted-by":"crossref","first-page":"595","DOI":"10.1089\/omi.2013.0017","article-title":"Application of machine learning to proteomics data: classification and biomarker identification in postgenomics biology","volume":"17","author":"AL Swan","year":"2013","journal-title":"OMICS"},{"issue":"11","key":"ref30","doi-asserted-by":"crossref","first-page":"923","DOI":"10.1038\/nmeth1113","article-title":"Semi-supervised learning for peptide identification from shotgun proteomics datasets","volume":"4","author":"L Kall","year":"2007","journal-title":"Nat Methods"},{"issue":"W1","key":"ref31","doi-asserted-by":"crossref","first-page":"W65","DOI":"10.1093\/nar\/gkv458","article-title":"Pse-in-One: a web server for generating various modes of pseudo components of DNA, RNA, and protein sequences","volume":"43","author":"B Liu","year":"2015","journal-title":"Nucleic Acids Res"},{"issue":"6","key":"ref32","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1016\/j.ygeno.2012.04.003","article-title":"Random forests for genomic data analysis","volume":"99","author":"X Chen","year":"2012","journal-title":"Genomics"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1186\/1471-2105-7-3","article-title":"Gene selection and classification of microarray data using random forest","volume":"7","author":"R Diaz-Uriarte","year":"2006","journal-title":"BMC Bioinformatics"},{"issue":"3","key":"ref34","doi-asserted-by":"crossref","first-page":"142","DOI":"10.6026\/97320630007142","article-title":"Random forest for gene selection and microarray data classification","volume":"7","author":"K Moorthy","year":"2011","journal-title":"Bioinformation"},{"key":"ref35","first-page":"564","article-title":"The spectrum kernel: a string kernel for SVM protein classification","author":"C Leslie","year":"2002","journal-title":"Pac Symp Biocomput"},{"key":"ref36","doi-asserted-by":"crossref","unstructured":"Sonnenburg S, R\u00e3tsch G, Sch\u00f6lkopf B, editors. Large scale genomic sequence SVM classifiers. Proceedings of the 22nd International Conference on Machine Learning; 2005: ACM Press.","DOI":"10.1145\/1102351.1102458"},{"issue":"9","key":"ref37","doi-asserted-by":"crossref","first-page":"e106691","DOI":"10.1371\/journal.pone.0106691","article-title":"iDNA-Prot|dis: identifying DNA-binding proteins by incorporating amino acid distance-pairs and reduced alphabet profile into the general pseudo amino acid composition","volume":"9","author":"B Liu","year":"2014","journal-title":"PLoS One"},{"key":"ref38","doi-asserted-by":"crossref","unstructured":"Abreu PH, Amaro H, Silva DC, Machado P, Abreu MH, editors. Personalizing Breast Cancer Patients with Heterogeneous Data. The International Conference on Health Informatics; 2014.","DOI":"10.1007\/978-3-319-03005-0_11"},{"key":"ref39","doi-asserted-by":"crossref","unstructured":"Abreu PH, Amaro H, Silva DC, Machado P, Abreu MH, Afonso N, et al., editors. Overall Survival Prediction for Women Breast Cancer Using Ensemble Methods and Incomplete Clinical Data. XIII Mediterranean Conference on Medical and Biological Engineering and Computing; 2013: Springer International Publishing.","DOI":"10.1007\/978-3-319-00846-2_338"},{"key":"ref40","unstructured":"NCI_SEER_AJCC_Cancer_Staging. AJCC Cancer Staging."},{"key":"ref41","article-title":"Non-Small Cell Lung Cancer Stages","year":"2017"},{"issue":"10","key":"ref42","doi-asserted-by":"crossref","first-page":"977","DOI":"10.1093\/bioinformatics\/17.10.977","article-title":"Model-based clustering and data transformations for gene expression data","volume":"17","author":"KY Yeung","year":"2001","journal-title":"Bioinformatics"},{"key":"ref43","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1007\/s00357-003-0015-3","article-title":"Enhanced Model-Based Clustering, Density Estimation, and Discriminant Analysis Software: MCLUST","volume":"20","author":"C Fraley","year":"2003","journal-title":"Journal of Classification"},{"issue":"7\u20138","key":"ref44","doi-asserted-by":"crossref","first-page":"853","DOI":"10.1002\/pmic.201300308","article-title":"Self-organizing maps: a versatile tool for the automatic analysis of untargeted imaging datasets","volume":"14","author":"P Franceschi","year":"2014","journal-title":"Proteomics"},{"issue":"1","key":"ref45","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1016\/j.mimet.2010.10.013","article-title":"Prediction of thermophilic proteins using feature selection technique","volume":"84","author":"H Lin","year":"2011","journal-title":"J Microbiol Methods"},{"issue":"4","key":"ref46","doi-asserted-by":"crossref","first-page":"1269","DOI":"10.1039\/C5MB00883B","article-title":"Identification of immunoglobulins using Chou&apos;s pseudo amino acid composition with feature selection technique","volume":"12","author":"H Tang","year":"2016","journal-title":"Mol Biosyst"},{"key":"ref47","doi-asserted-by":"crossref","first-page":"3267325","DOI":"10.1155\/2017\/3267325","article-title":"Predicting Presynaptic and Postsynaptic Neurotoxins by Developing Feature Selection Technique","volume":"2017","author":"H Tang","year":"2017","journal-title":"Biomed Res Int"},{"key":"ref48","article-title":"Fast prediction of protein methylation sites using a sequence-based feature selection technique","author":"L Wei","year":"2017","journal-title":"IEEE\/ACM Trans Comput Biol Bioinform"},{"key":"ref49","doi-asserted-by":"crossref","first-page":"34817","DOI":"10.1038\/srep34817","article-title":"Prediction of phosphothreonine sites in human proteins by fusing different features","volume":"6","author":"YW Zhao","year":"2016","journal-title":"Sci Rep"},{"key":"ref50","doi-asserted-by":"crossref","first-page":"367","DOI":"10.1186\/1471-2105-11-367","article-title":"A flexible R package for nonnegative matrix factorization","volume":"11","author":"R Gaujoux","year":"2010","journal-title":"BMC Bioinformatics"},{"key":"ref51","year":"2015"},{"issue":"3","key":"ref52","doi-asserted-by":"crossref","first-page":"467","DOI":"10.1093\/bioinformatics\/btw630","article-title":"Pro54DB: a database for experimentally verified sigma-54 promoters","volume":"33","author":"ZY Liang","year":"2017","journal-title":"Bioinformatics"},{"key":"ref53","article-title":"Identifying sigma70 promoters with novel pseudo nucleotide composition","author":"H Lin","year":"2017","journal-title":"IEEE\/ACM Trans Comput Biol Bioinform"},{"issue":"3","key":"ref54","doi-asserted-by":"crossref","first-page":"362","DOI":"10.1093\/bioinformatics\/btv604","article-title":"iEnhancer-2L: a two-layer predictor for identifying enhancers and their strength by pseudo k-tuple nucleotide composition","volume":"32","author":"B Liu","year":"2016","journal-title":"Bioinformatics"},{"issue":"43","key":"ref55","doi-asserted-by":"crossref","first-page":"69783","DOI":"10.18632\/oncotarget.11975","article-title":"iOri-Human: identify human origin of replication by incorporating dinucleotide physicochemical properties into pseudo nucleotide composition","volume":"7","author":"CJ Zhang","year":"2016","journal-title":"Oncotarget"},{"issue":"D1","key":"ref56","first-page":"D135","article-title":"RNALocate: a resource for RNA subcellular localizations","volume":"45","author":"T Zhang","year":"2017","journal-title":"Nucleic Acids Res"},{"issue":"3","key":"ref57","doi-asserted-by":"crossref","first-page":"683","DOI":"10.1080\/07391102.2016.1157761","article-title":"MethyRNA: a web server for identification of N6-methyladenosine sites","volume":"35","author":"W Chen","year":"2017","journal-title":"J Biomol Struct Dyn"},{"issue":"8","key":"ref58","doi-asserted-by":"crossref","first-page":"13338","DOI":"10.18632\/oncotarget.14524","article-title":"Pse-Analysis: a python package for DNA\/RNA and protein\/ peptide sequence analysis based on pseudo components and kernel methods","volume":"8","author":"B Liu","year":"2017","journal-title":"Oncotarget"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/dx.plos.org\/10.1371\/journal.pone.0184370","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,25]],"date-time":"2023-08-25T21:55:15Z","timestamp":1693000515000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0184370"}},"subtitle":[],"editor":[{"given":"Bin","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2017,9,14]]},"references-count":58,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2017,9,14]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0184370","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,9,14]]}}}