{"id":"https://openalex.org/W4378176367","doi":"https://doi.org/10.3390/a16060263","title":"DrugFinder: Druggable Protein Identification Model Based on Pre-Trained Models and Evolutionary Information","display_name":"DrugFinder: Druggable Protein Identification Model Based on Pre-Trained Models and Evolutionary Information","publication_year":2023,"publication_date":"2023-05-25","ids":{"openalex":"https://openalex.org/W4378176367","doi":"https://doi.org/10.3390/a16060263"},"language":"en","primary_location":{"id":"doi:10.3390/a16060263","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a16060263","pdf_url":"https://www.mdpi.com/1999-4893/16/6/263/pdf?version=1684999164","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1999-4893/16/6/263/pdf?version=1684999164","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100695048","display_name":"Mu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I44675526","display_name":"Shanghai Ocean University","ror":"https://ror.org/04n40zv07","country_code":"CN","type":"education","lineage":["https://openalex.org/I44675526"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mu Zhang","raw_affiliation_strings":["College of Information Technology, Shanghai Ocean University, Shanghai 201306, China","College of Information Technology, Shanghai Ocean University, Shanghai 201306, China;"],"affiliations":[{"raw_affiliation_string":"College of Information Technology, Shanghai Ocean University, Shanghai 201306, China","institution_ids":["https://openalex.org/I44675526"]},{"raw_affiliation_string":"College of Information Technology, Shanghai Ocean University, Shanghai 201306, China;","institution_ids":["https://openalex.org/I44675526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114236921","display_name":"Fengqiang Wan","orcid":null},"institutions":[{"id":"https://openalex.org/I44675526","display_name":"Shanghai Ocean University","ror":"https://ror.org/04n40zv07","country_code":"CN","type":"education","lineage":["https://openalex.org/I44675526"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengqiang Wan","raw_affiliation_strings":["College of Information Technology, Shanghai Ocean University, Shanghai 201306, China","College of Information Technology, Shanghai Ocean University, Shanghai 201306, China;"],"affiliations":[{"raw_affiliation_string":"College of Information Technology, Shanghai Ocean University, Shanghai 201306, China","institution_ids":["https://openalex.org/I44675526"]},{"raw_affiliation_string":"College of Information Technology, Shanghai Ocean University, Shanghai 201306, China;","institution_ids":["https://openalex.org/I44675526"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011641116","display_name":"Taigang Liu","orcid":"https://orcid.org/0000-0002-8449-9667"},"institutions":[{"id":"https://openalex.org/I44675526","display_name":"Shanghai Ocean University","ror":"https://ror.org/04n40zv07","country_code":"CN","type":"education","lineage":["https://openalex.org/I44675526"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Taigang Liu","raw_affiliation_strings":["College of Information Technology, Shanghai Ocean University, Shanghai 201306, China","College of Information Technology, Shanghai Ocean University, Shanghai 201306, China;"],"affiliations":[{"raw_affiliation_string":"College of Information Technology, Shanghai Ocean University, Shanghai 201306, China","institution_ids":["https://openalex.org/I44675526"]},{"raw_affiliation_string":"College of Information Technology, Shanghai Ocean University, Shanghai 201306, China;","institution_ids":["https://openalex.org/I44675526"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5011641116"],"corresponding_institution_ids":["https://openalex.org/I44675526"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":1.0644,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.77059742,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"16","issue":"6","first_page":"263","last_page":"263"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12576","display_name":"vaccines and immunoinformatics approaches","score":0.991599977016449,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/druggability","display_name":"Druggability","score":0.8783485889434814},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.7545763850212097},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.7490606904029846},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7015653252601624},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6875689029693604},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.629524827003479},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6243570446968079},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.5989910960197449},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5125513076782227},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.45004802942276},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36953192949295044},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15640321373939514},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.08904018998146057}],"concepts":[{"id":"https://openalex.org/C10679952","wikidata":"https://www.wikidata.org/wiki/Q5308937","display_name":"Druggability","level":3,"score":0.8783485889434814},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.7545763850212097},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.7490606904029846},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7015653252601624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6875689029693604},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.629524827003479},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6243570446968079},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.5989910960197449},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5125513076782227},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.45004802942276},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36953192949295044},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15640321373939514},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.08904018998146057},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/a16060263","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a16060263","pdf_url":"https://www.mdpi.com/1999-4893/16/6/263/pdf?version=1684999164","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:c4028fa1596b4992803f86e7aa1465bb","is_oa":true,"landing_page_url":"https://doaj.org/article/c4028fa1596b4992803f86e7aa1465bb","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Algorithms, Vol 16, Iss 6, p 263 (2023)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1999-4893/16/6/263/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/a16060263","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Algorithms; Volume 16; Issue 6; Pages: 263","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/a16060263","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a16060263","pdf_url":"https://www.mdpi.com/1999-4893/16/6/263/pdf?version=1684999164","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4378176367.pdf"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W1875028359","https://openalex.org/W1975601078","https://openalex.org/W1978257492","https://openalex.org/W1986902688","https://openalex.org/W2044002635","https://openalex.org/W2045732402","https://openalex.org/W2055043387","https://openalex.org/W2057021995","https://openalex.org/W2064675550","https://openalex.org/W2076974281","https://openalex.org/W2087322782","https://openalex.org/W2101234009","https://openalex.org/W2116633922","https://openalex.org/W2122111042","https://openalex.org/W2139086914","https://openalex.org/W2158714788","https://openalex.org/W2252158617","https://openalex.org/W2500660203","https://openalex.org/W2612935389","https://openalex.org/W2734475733","https://openalex.org/W2765699853","https://openalex.org/W2767891136","https://openalex.org/W2781620754","https://openalex.org/W2781640664","https://openalex.org/W2896457183","https://openalex.org/W2902320908","https://openalex.org/W2911964244","https://openalex.org/W2952230511","https://openalex.org/W2952437275","https://openalex.org/W2963647449","https://openalex.org/W2979417040","https://openalex.org/W2995514860","https://openalex.org/W4207043639","https://openalex.org/W4220900187","https://openalex.org/W4225891318","https://openalex.org/W4239510810","https://openalex.org/W4281665783","https://openalex.org/W4288089799","https://openalex.org/W4312129273","https://openalex.org/W4320731502","https://openalex.org/W6675354045","https://openalex.org/W6683738474","https://openalex.org/W6739901393","https://openalex.org/W6769627184","https://openalex.org/W6910681941"],"related_works":["https://openalex.org/W4367336074","https://openalex.org/W4379620016","https://openalex.org/W3154045278","https://openalex.org/W3210764983","https://openalex.org/W3089416646","https://openalex.org/W4367335949","https://openalex.org/W4380048833","https://openalex.org/W4285162676","https://openalex.org/W3036529732","https://openalex.org/W4382052559"],"abstract_inverted_index":{"The":[0,49],"identification":[1,15,45,162],"of":[2,10,58,69,139,142,146,180,184,193],"druggable":[3,37,43],"proteins":[4],"has":[5],"always":[6],"been":[7],"the":[8,52,55,59,66,70,86,95,128,132,149,158,189,194],"core":[9],"drug":[11],"development.":[12],"Traditional":[13],"structure-based":[14],"methods":[16,34],"are":[17],"time-consuming":[18],"and":[19,25,65,80,94,100,121,144,182],"costly.":[20],"As":[21],"a":[22,41],"result,":[23],"more":[24,26],"researchers":[27],"have":[28],"shifted":[29],"their":[30],"attention":[31],"to":[32,76,91,175],"sequence-based":[33,42],"for":[35],"identifying":[36],"proteins.":[38],"We":[39],"propose":[40],"protein":[44,61],"model":[46,50,62,82,130,165],"called":[47],"DrugFinder.":[48],"extracts":[51],"features":[53,79,97],"from":[54,160],"embedding":[56],"output":[57],"pre-trained":[60],"Prot_T5_Xl_Uniref50":[63],"(T5)":[64],"evolutionary":[67],"information":[68],"position-specific":[71],"scoring":[72],"matrix":[73],"(PSSM).":[74],"Afterwards,":[75],"remove":[77],"redundant":[78],"improve":[81],"performance,":[83],"we":[84],"used":[85],"random":[87],"forest":[88],"(RF)":[89],"method":[90],"select":[92],"features,":[93],"selected":[96],"were":[98],"trained":[99],"tested":[101],"on":[102,148,169],"multiple":[103],"different":[104],"machine":[105],"learning":[106],"classifiers,":[107,127],"including":[108],"support":[109],"vector":[110],"machines":[111],"(SVM),":[112],"RF,":[113],"naive":[114],"Bayes":[115],"(NB),":[116],"extreme":[117],"gradient":[118],"boosting":[119],"(XGB),":[120],"k-nearest":[122],"neighbors":[123],"(KNN).":[124],"Among":[125],"these":[126],"XGB":[129],"achieved":[131],"best":[133],"results.":[134],"DrugFinder":[135],"reached":[136],"an":[137,178],"accuracy":[138,179],"94.98%,":[140],"sensitivity":[141],"96.33%":[143],"specificity":[145],"96.83%":[147],"independent":[150],"test":[151,172],"set,":[152],"which":[153],"is":[154],"much":[155],"better":[156],"than":[157],"results":[159],"existing":[161],"methods.":[163],"Our":[164],"also":[166],"performed":[167],"well":[168],"another":[170],"additional":[171],"set":[173],"related":[174],"tumors,":[176],"achieving":[177],"88.71%":[181],"precision":[183],"93.72%.":[185],"This":[186],"further":[187],"demonstrates":[188],"strong":[190],"generalization":[191],"capability":[192],"model.":[195]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-11T08:14:18.477133","created_date":"2023-05-26T00:00:00"}