{"id":"https://openalex.org/W4407360799","doi":"https://doi.org/10.1109/tcbbio.2025.3540588","title":"TP-ML: A Machine-Learning-Based Tool to Identify Threonine Proteases Using Sequence-Derived Optimal Features","display_name":"TP-ML: A Machine-Learning-Based Tool to Identify Threonine Proteases Using Sequence-Derived Optimal Features","publication_year":2025,"publication_date":"2025-02-11","ids":{"openalex":"https://openalex.org/W4407360799","doi":"https://doi.org/10.1109/tcbbio.2025.3540588","pmid":"https://pubmed.ncbi.nlm.nih.gov/40811363"},"language":"en","primary_location":{"id":"doi:10.1109/tcbbio.2025.3540588","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbbio.2025.3540588","pdf_url":null,"source":{"id":"https://openalex.org/S5407042751","display_name":"IEEE Transactions on Computational Biology and Bioinformatics","issn_l":"2998-4165","issn":["2998-4165"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042895656","display_name":"Ahmad Firoz","orcid":"https://orcid.org/0000-0003-3395-8015"},"institutions":[{"id":"https://openalex.org/I185163786","display_name":"King Abdulaziz University","ror":"https://ror.org/02ma4wv74","country_code":"SA","type":"education","lineage":["https://openalex.org/I185163786"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Ahmad Firoz","raw_affiliation_strings":["Department of Biological Sciences, Faculty of Science, King Abdulaziz University, Jeddah, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0003-3395-8015","affiliations":[{"raw_affiliation_string":"Department of Biological Sciences, Faculty of Science, King Abdulaziz University, Jeddah, Saudi Arabia","institution_ids":["https://openalex.org/I185163786"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042243661","display_name":"Adeel Malik","orcid":"https://orcid.org/0000-0002-3453-6001"},"institutions":[{"id":"https://openalex.org/I157264075","display_name":"Sangmyung University","ror":"https://ror.org/01x4whx42","country_code":"KR","type":"education","lineage":["https://openalex.org/I157264075"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Adeel Malik","raw_affiliation_strings":["Institute of Intelligence Informatics Technology, Sangmyung University, Seoul, South Korea","Institute of Intelligence Informatics Technology, Sangmyung University, Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Intelligence Informatics Technology, Sangmyung University, Seoul, South Korea","institution_ids":["https://openalex.org/I157264075"]},{"raw_affiliation_string":"Institute of Intelligence Informatics Technology, Sangmyung University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I157264075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081227888","display_name":"Nitin Mahajan","orcid":"https://orcid.org/0000-0002-0907-6410"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nitin Mahajan","raw_affiliation_strings":["Wugen, St. Louis, MO, USA"],"raw_orcid":"https://orcid.org/0000-0002-0907-6410","affiliations":[{"raw_affiliation_string":"Wugen, St. Louis, MO, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042484831","display_name":"Le Thi Phan","orcid":null},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Le Thi Phan","raw_affiliation_strings":["Computational Biology and Bioinformatics Laboratory, College of Biotechnology and Bioengineering, Department of Integrative Biotechnology, Sungkyunkwan University, Suwon, South Korea","Computational Biology and Bioinformatics Laboratory, Department of Integrative Biotechnology, College of Biotechnology and Bioengineering, Sungkyunkwan University, Suwon, Gyeonggi-do, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0003-4654-1024","affiliations":[{"raw_affiliation_string":"Computational Biology and Bioinformatics Laboratory, College of Biotechnology and Bioengineering, Department of Integrative Biotechnology, Sungkyunkwan University, Suwon, South Korea","institution_ids":["https://openalex.org/I848706"]},{"raw_affiliation_string":"Computational Biology and Bioinformatics Laboratory, Department of Integrative Biotechnology, College of Biotechnology and Bioengineering, Sungkyunkwan University, Suwon, Gyeonggi-do, Republic of Korea","institution_ids":["https://openalex.org/I848706"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104028966","display_name":"Hani S. H. Mohammed Ali","orcid":"https://orcid.org/0000-0003-0649-2635"},"institutions":[{"id":"https://openalex.org/I185163786","display_name":"King Abdulaziz University","ror":"https://ror.org/02ma4wv74","country_code":"SA","type":"education","lineage":["https://openalex.org/I185163786"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Hani S. H. Mohammed Ali","raw_affiliation_strings":["Department of Biological Sciences, Faculty of Science, King Abdulaziz University, Jeddah, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biological Sciences, Faculty of Science, King Abdulaziz University, Jeddah, Saudi Arabia","institution_ids":["https://openalex.org/I185163786"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073339942","display_name":"Chang\u2010Bae Kim","orcid":"https://orcid.org/0000-0002-1040-7600"},"institutions":[{"id":"https://openalex.org/I157264075","display_name":"Sangmyung University","ror":"https://ror.org/01x4whx42","country_code":"KR","type":"education","lineage":["https://openalex.org/I157264075"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chang-Bae Kim","raw_affiliation_strings":["Department of Biotechnology, Sangmyung University, Seoul, South Korea","Department of Biotechnology, Sangmyung University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-1040-7600","affiliations":[{"raw_affiliation_string":"Department of Biotechnology, Sangmyung University, Seoul, South Korea","institution_ids":["https://openalex.org/I157264075"]},{"raw_affiliation_string":"Department of Biotechnology, Sangmyung University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I157264075"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040180866","display_name":"Balachandran Manavalan","orcid":"https://orcid.org/0000-0003-0697-9419"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Balachandran Manavalan","raw_affiliation_strings":["Computational Biology and Bioinformatics Laboratory, College of Biotechnology and Bioengineering, Department of Integrative Biotechnology, Sungkyunkwan University, Suwon, South Korea","Computational Biology and Bioinformatics Laboratory, Department of Integrative Biotechnology, College of Biotechnology and Bioengineering, Sungkyunkwan University, Suwon, Gyeonggi-do, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0003-0697-9419","affiliations":[{"raw_affiliation_string":"Computational Biology and Bioinformatics Laboratory, College of Biotechnology and Bioengineering, Department of Integrative Biotechnology, Sungkyunkwan University, Suwon, South Korea","institution_ids":["https://openalex.org/I848706"]},{"raw_affiliation_string":"Computational Biology and Bioinformatics Laboratory, Department of Integrative Biotechnology, College of Biotechnology and Bioengineering, Sungkyunkwan University, Suwon, Gyeonggi-do, Republic of Korea","institution_ids":["https://openalex.org/I848706"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4868,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.59839854,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"22","issue":"3","first_page":"984","last_page":"996"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9998999834060669,"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":0.9998999834060669,"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/T12576","display_name":"vaccines and immunoinformatics approaches","score":0.9876999855041504,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9850000143051147,"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/proteases","display_name":"Proteases","score":0.7400677800178528},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5773056745529175},{"id":"https://openalex.org/keywords/threonine","display_name":"Threonine","score":0.5617504119873047},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5409835577011108},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5140982270240784},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41177135705947876},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37002795934677124},{"id":"https://openalex.org/keywords/serine","display_name":"Serine","score":0.2959133982658386},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.2932176887989044},{"id":"https://openalex.org/keywords/biochemistry","display_name":"Biochemistry","score":0.24385708570480347},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2401677370071411},{"id":"https://openalex.org/keywords/enzyme","display_name":"Enzyme","score":0.09536564350128174}],"concepts":[{"id":"https://openalex.org/C182220744","wikidata":"https://www.wikidata.org/wiki/Q7251226","display_name":"Proteases","level":3,"score":0.7400677800178528},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5773056745529175},{"id":"https://openalex.org/C2775880066","wikidata":"https://www.wikidata.org/wiki/Q186521","display_name":"Threonine","level":4,"score":0.5617504119873047},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5409835577011108},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5140982270240784},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41177135705947876},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37002795934677124},{"id":"https://openalex.org/C2776414213","wikidata":"https://www.wikidata.org/wiki/Q183290","display_name":"Serine","level":3,"score":0.2959133982658386},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.2932176887989044},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.24385708570480347},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2401677370071411},{"id":"https://openalex.org/C181199279","wikidata":"https://www.wikidata.org/wiki/Q8047","display_name":"Enzyme","level":2,"score":0.09536564350128174}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcbbio.2025.3540588","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbbio.2025.3540588","pdf_url":null,"source":{"id":"https://openalex.org/S5407042751","display_name":"IEEE Transactions on Computational Biology and Bioinformatics","issn_l":"2998-4165","issn":["2998-4165"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},{"id":"pmid:40811363","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40811363","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on computational biology and bioinformatics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Zero hunger","score":0.7699999809265137,"id":"https://metadata.un.org/sdg/2"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":81,"referenced_works":["https://openalex.org/W607977164","https://openalex.org/W1831050183","https://openalex.org/W1883724926","https://openalex.org/W1969956377","https://openalex.org/W1980537409","https://openalex.org/W1982267716","https://openalex.org/W1984075743","https://openalex.org/W1993711987","https://openalex.org/W2019488416","https://openalex.org/W2025282821","https://openalex.org/W2034221489","https://openalex.org/W2037032199","https://openalex.org/W2042084565","https://openalex.org/W2043434733","https://openalex.org/W2046646461","https://openalex.org/W2047672715","https://openalex.org/W2075503331","https://openalex.org/W2095131443","https://openalex.org/W2110325001","https://openalex.org/W2122111042","https://openalex.org/W2122304792","https://openalex.org/W2132292391","https://openalex.org/W2142270082","https://openalex.org/W2145957695","https://openalex.org/W2148156110","https://openalex.org/W2156125289","https://openalex.org/W2156665896","https://openalex.org/W2163957306","https://openalex.org/W2170398003","https://openalex.org/W2171464043","https://openalex.org/W2209939573","https://openalex.org/W2284109062","https://openalex.org/W2295598076","https://openalex.org/W2322691988","https://openalex.org/W2323491683","https://openalex.org/W2342600311","https://openalex.org/W2557383173","https://openalex.org/W2565219567","https://openalex.org/W2620578360","https://openalex.org/W2769449671","https://openalex.org/W2799829423","https://openalex.org/W2800245053","https://openalex.org/W2884524796","https://openalex.org/W2910705748","https://openalex.org/W2950389803","https://openalex.org/W2971941127","https://openalex.org/W2974695603","https://openalex.org/W2988542995","https://openalex.org/W2993807644","https://openalex.org/W2994622524","https://openalex.org/W2997757919","https://openalex.org/W3011121236","https://openalex.org/W3015209591","https://openalex.org/W3020886002","https://openalex.org/W3022808455","https://openalex.org/W3023847102","https://openalex.org/W3108883807","https://openalex.org/W3118608107","https://openalex.org/W3128013506","https://openalex.org/W3144560185","https://openalex.org/W3153138486","https://openalex.org/W3177828909","https://openalex.org/W3199970975","https://openalex.org/W3203343200","https://openalex.org/W4200398711","https://openalex.org/W4200549490","https://openalex.org/W4220763302","https://openalex.org/W4225008496","https://openalex.org/W4251601076","https://openalex.org/W4254721730","https://openalex.org/W4255738047","https://openalex.org/W4283754817","https://openalex.org/W4285807029","https://openalex.org/W4293030651","https://openalex.org/W4307818652","https://openalex.org/W4308769190","https://openalex.org/W4313334552","https://openalex.org/W4320077880","https://openalex.org/W4400132061","https://openalex.org/W4400762160","https://openalex.org/W6684571960"],"related_works":["https://openalex.org/W2414472555","https://openalex.org/W2357602378","https://openalex.org/W2061945526","https://openalex.org/W3138728990","https://openalex.org/W2094734839","https://openalex.org/W2100844557","https://openalex.org/W2552013322","https://openalex.org/W2286775035","https://openalex.org/W2771318933","https://openalex.org/W1966737823"],"abstract_inverted_index":{"Threonine":[0],"proteases":[1],"(TPs)":[2],"are":[3,44],"enzymes":[4],"vital":[5],"for":[6,28,38,153],"several":[7],"biological":[8],"processes":[9],"and":[10,15,21,31,40,47,73,77,133,136,142,161],"diseases":[11],"including":[12],"Alzheimer's":[13],"disease":[14],"cancer.":[16],"Their":[17],"potential":[18],"to":[19,96,112,148],"target":[20],"degrade":[22],"proteins":[23],"intracellularly":[24],"makes":[25],"them":[26],"valuable":[27],"various":[29],"therapeutic":[30],"industrial":[32,162],"applications.":[33],"However,":[34],"traditional":[35],"experimental":[36,159],"methods":[37],"identifying":[39,154],"characterizing":[41],"novel":[42],"TPs":[43],"exhaustive,":[45],"time-consuming,":[46],"expensive.":[48],"To":[49],"address":[50],"this,":[51],"we":[52],"developed":[53],"TP-ML,":[54],"a":[55,70,86,150],"support":[56],"vector":[57],"machine-based":[58],"prediction":[59],"tool":[60,152],"that":[61],"can":[62],"differentiate":[63],"TP":[64],"from":[65,102],"non-TP":[66],"sequences.":[67,84],"We":[68,145],"generated":[69],"benchmark":[71],"dataset":[72],"calculated":[74],"the":[75,91,98,103,125],"physicochemical":[76],"compositional":[78],"features":[79,108],"using":[80],"primary":[81],"amino":[82],"acid":[83],"Subsequently,":[85],"comparison":[87],"was":[88,122],"made":[89],"between":[90],"two":[92],"feature":[93,100],"selection":[94],"approaches":[95],"identify":[97],"optimal":[99,107],"sets":[101],"original":[104],"encodings.":[105],"These":[106],"were":[109],"then":[110],"used":[111],"train":[113],"five":[114],"different":[115],"machine-learning":[116],"classifiers,":[117],"each":[118],"assessed":[119],"independently.":[120],"TP-ML":[121,147],"selected":[123],"as":[124],"best":[126],"model":[127],"showing":[128],"consistent":[129],"performance":[130],"during":[131],"cross-validation":[132],"independent":[134],"evaluation,":[135],"achieved":[137],"an":[138],"accuracy":[139],"of":[140],"0.934":[141],"0.888,":[143],"respectively.":[144],"anticipate":[146],"be":[149],"powerful":[151],"TPs,":[155],"aiding":[156],"in":[157],"their":[158],"characterization":[160],"application":[163],"exploration.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}