{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T19:04:39Z","timestamp":1791313479901,"version":"4.3.1"},"reference-count":44,"publisher":"Wiley","issue":"3","license":[{"start":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T00:00:00Z","timestamp":1778112000000},"content-version":"vor","delay-in-days":6,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Proteomics Clinical Apps"],"published-print":{"date-parts":[[2026,5]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>Over the years, several proteins and peptides with diverse therapeutic properties such as anticancer, antimicrobial, antihypertensive effects have been discovered. However, only a few hundred proteins are considered druggable with US FDA approval, while most of them failed during clinical trials.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Experimental Design<\/jats:title>\n                    <jats:p>This study systematically investigates the compositional and physicochemical properties of FDA\u2010approved proteins to develop predictive models for identifying druggable proteins. Our main dataset comprises of 356 FDA approved proteins as positive dataset and equal number of randomly selected proteins as negative dataset. We used 80% data as training set and 20% as independent validation data, with no protein in validation dataset having more than 40% similarity with any protein in training dataset.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Result<\/jats:title>\n                    <jats:p>Random forest\u2010based model developed using SVC\u2010L1 selected features obtained maximum performance AUC of 0.80 with MCC 0.61 on validation data. In addition to this, we performed MERCI\u2010based motif analysis to find exclusive motifs\/ patterns in druggable proteins. Finally, we proposed an ensemble\u2010based method combining best performing machine learning model with exclusive motifs and achieved AUC 0.92 with MCC 0.83 on independent validation dataset.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion and Clinical Relevance<\/jats:title>\n                    <jats:p>\n                      In order to serve the scientific community, web server and standalone package of \u201cThPPred\u201d facilitating prediction and designing of druggable proteins is proposed (\n                      <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/webs.iiitd.edu.in\/raghava\/thppred\/\">https:\/\/webs.iiitd.edu.in\/raghava\/thppred\/<\/jats:ext-link>\n                      ).\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/prca.70046","type":"journal-article","created":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T11:11:59Z","timestamp":1778152319000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["An Ensemble Method for Predicting and Designing of Druggable Proteins"],"prefix":"10.1002","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7045-5188","authenticated-orcid":false,"given":"Shipra","family":"Jain","sequence":"first","affiliation":[{"name":"Department of Computational Biology Indraprastha Institute of Information Technology  New Delhi India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Srijanee","family":"Gupta","sequence":"additional","affiliation":[{"name":"Department of Computational Biology Indraprastha Institute of Information Technology  New Delhi India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8902-2876","authenticated-orcid":false,"given":"Gajendra P. S.","family":"Raghava","sequence":"additional","affiliation":[{"name":"Department of Computational Biology Indraprastha Institute of Information Technology  New Delhi India"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,5,7]]},"reference":[{"key":"e_1_2_14_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/J.DRUDIS.2024.104047"},{"key":"e_1_2_14_3_1","doi-asserted-by":"publisher","DOI":"10.1371\/JOURNAL.PONE.0181748"},{"key":"e_1_2_14_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/J.DRUDIS.2022.103464"},{"key":"e_1_2_14_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/J.DRUDIS.2009.10.009"},{"key":"e_1_2_14_6_1","doi-asserted-by":"publisher","DOI":"10.1038\/S41392\u2010022\u201000904\u20104"},{"key":"e_1_2_14_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/J.DRUDIS.2014.10.003"},{"key":"e_1_2_14_8_1","doi-asserted-by":"publisher","DOI":"10.1093\/BIB\/BBAA367"},{"key":"e_1_2_14_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978\u20101\u201061779\u2010921\u20101_1\/COVER"},{"key":"e_1_2_14_10_1","doi-asserted-by":"publisher","DOI":"10.1021\/ACS.JMEDCHEM.3C01835"},{"key":"e_1_2_14_11_1","doi-asserted-by":"publisher","DOI":"10.1038\/S41573\u2010019\u20100053\u20100"},{"key":"e_1_2_14_12_1","doi-asserted-by":"publisher","DOI":"10.3389\/FIMMU.2024.1328145"},{"key":"e_1_2_14_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecl.2004.11.006"},{"key":"e_1_2_14_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/J.JCONREL.2022.09.066"},{"key":"e_1_2_14_15_1","doi-asserted-by":"publisher","DOI":"10.1186\/S12859\u2010019\u20103006\u2010Z"},{"key":"e_1_2_14_16_1","doi-asserted-by":"publisher","DOI":"10.1371\/JOURNAL.PCBI.1010511"},{"key":"e_1_2_14_17_1","doi-asserted-by":"publisher","DOI":"10.1093\/BIOINFORMATICS\/BTAC200"},{"key":"e_1_2_14_18_1","doi-asserted-by":"publisher","DOI":"10.1186\/S12915\u2010023\u201001740\u2010W"},{"key":"e_1_2_14_19_1","doi-asserted-by":"publisher","DOI":"10.1093\/BIOINFORMATICS\/BTAD125"},{"key":"e_1_2_14_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/J.CHEMOLAB.2022.104490"},{"key":"e_1_2_14_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCBB.2022.3183018"},{"key":"e_1_2_14_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/J.JBI.2017.09.011"},{"key":"e_1_2_14_23_1","doi-asserted-by":"publisher","DOI":"10.2174\/1574893617666211220153429"},{"key":"e_1_2_14_24_1","doi-asserted-by":"publisher","DOI":"10.1093\/BIOINFORMATICS\/BTAA275"},{"key":"e_1_2_14_25_1","doi-asserted-by":"publisher","DOI":"10.1093\/BIOINFORMATICS\/BTZ246"},{"key":"e_1_2_14_26_1","doi-asserted-by":"publisher","DOI":"10.1093\/BIB\/BBAB358"},{"key":"e_1_2_14_27_1","doi-asserted-by":"publisher","DOI":"10.3389\/FIMMU.2020.00071"},{"key":"e_1_2_14_28_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btl158"},{"key":"e_1_2_14_29_1","doi-asserted-by":"publisher","DOI":"10.1093\/BIB\/BBAC174"},{"key":"e_1_2_14_30_1","doi-asserted-by":"publisher","DOI":"10.1093\/BIB\/BBAA294"},{"key":"e_1_2_14_31_1","doi-asserted-by":"publisher","DOI":"10.1093\/BIOINFORMATICS\/BTL158"},{"key":"e_1_2_14_32_1","doi-asserted-by":"publisher","DOI":"10.1093\/BIB\/BBAA259"},{"key":"e_1_2_14_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/S10994\u2010006\u20106226\u20101\/METRICS"},{"key":"e_1_2_14_34_1","doi-asserted-by":"publisher","DOI":"10.1002\/CEM.873"},{"key":"e_1_2_14_35_1","doi-asserted-by":"publisher","DOI":"10.1001\/JAMA.2016.7653"},{"key":"e_1_2_14_36_1","doi-asserted-by":"crossref","unstructured":"T.ChenandC.Guestrin \u201cXGBoost: A Scalable Tree Boosting System \u201d inProceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 13\u201017\u2010August\u20102016(2016) 785\u2013794 https:\/\/doi.org\/10.1145\/2939672.2939785\/SUPPL_FILE\/KDD2016_CHEN_BOOSTING_SYSTEM_01\u2010ACM.MP4.","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_2_14_37_1","doi-asserted-by":"crossref","unstructured":"A.Mucherino P. J.Papajorgji andP. M.Pardalos \u201ck\u2010Nearest Neighbor Classification \u201d (2009):83\u2013106 https:\/\/doi.org\/10.1007\/978\u20100\u2010387\u201088615\u20102_4.","DOI":"10.1007\/978-0-387-88615-2_4"},{"key":"e_1_2_14_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/J.PROCS.2013.05.137"},{"key":"e_1_2_14_39_1","doi-asserted-by":"publisher","DOI":"10.1093\/BIB\/BBAA153"},{"key":"e_1_2_14_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/J.COMPBIOMED.2023.106929"},{"key":"e_1_2_14_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/J.COMPBIOMED.2022.105297"},{"key":"e_1_2_14_42_1","doi-asserted-by":"publisher","DOI":"10.1089\/CMB.2023.0040"},{"key":"e_1_2_14_43_1","doi-asserted-by":"publisher","DOI":"10.1038\/srep20678"},{"key":"e_1_2_14_44_1","doi-asserted-by":"publisher","DOI":"10.1002\/PMIC.202400004"},{"key":"e_1_2_14_45_1","doi-asserted-by":"publisher","DOI":"10.1093\/BIOINFORMATICS\/BTR110"}],"container-title":["PROTEOMICS \u2013 Clinical Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/prca.70046","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/prca.70046","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/prca.70046","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T16:40:21Z","timestamp":1783010421000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/prca.70046"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":44,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,5]]}},"alternative-id":["10.1002\/prca.70046"],"URL":"https:\/\/doi.org\/10.1002\/prca.70046","archive":["Portico"],"relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2024.10.17.618792","asserted-by":"object"}]},"ISSN":["1862-8346","1862-8354"],"issn-type":[{"value":"1862-8346","type":"print"},{"value":"1862-8354","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]},"assertion":[{"value":"2025-06-14","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-21","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-05-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70046"}}