{"id":"https://openalex.org/W2912891621","doi":"https://doi.org/10.1109/bibm.2018.8621241","title":"Toward data-driven identification of kingdom-specific protein sequence motifs","display_name":"Toward data-driven identification of kingdom-specific protein sequence motifs","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2912891621","doi":"https://doi.org/10.1109/bibm.2018.8621241","mag":"2912891621"},"language":"en","primary_location":{"id":"doi:10.1109/bibm.2018.8621241","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm.2018.8621241","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5072663707","display_name":"Corrine F. Elliott","orcid":"https://orcid.org/0000-0001-7935-9945"},"institutions":[{"id":"https://openalex.org/I143302722","display_name":"University of Kentucky","ror":"https://ror.org/02k3smh20","country_code":"US","type":"education","lineage":["https://openalex.org/I143302722"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Corrine F. Elliott","raw_affiliation_strings":["Computer Science Statistics University of Kentucky, Lexington, KY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Statistics University of Kentucky, Lexington, KY, USA","institution_ids":["https://openalex.org/I143302722"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020748360","display_name":"Kristin B. Linscott","orcid":null},"institutions":[{"id":"https://openalex.org/I143302722","display_name":"University of Kentucky","ror":"https://ror.org/02k3smh20","country_code":"US","type":"education","lineage":["https://openalex.org/I143302722"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kristin Linscott","raw_affiliation_strings":["Molec. and Cellular Biol. University of Kentucky, Lexington, KY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Molec. and Cellular Biol. University of Kentucky, Lexington, KY, USA","institution_ids":["https://openalex.org/I143302722"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006604219","display_name":"Satrio Husodo","orcid":null},"institutions":[{"id":"https://openalex.org/I143302722","display_name":"University of Kentucky","ror":"https://ror.org/02k3smh20","country_code":"US","type":"education","lineage":["https://openalex.org/I143302722"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Satrio Husodo","raw_affiliation_strings":["Computer Science University of Kentucky, Lexington, KY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science University of Kentucky, Lexington, KY, USA","institution_ids":["https://openalex.org/I143302722"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109875165","display_name":"Joseph Chappell","orcid":null},"institutions":[{"id":"https://openalex.org/I143302722","display_name":"University of Kentucky","ror":"https://ror.org/02k3smh20","country_code":"US","type":"education","lineage":["https://openalex.org/I143302722"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joseph Chappell","raw_affiliation_strings":["Molec. and Cellular Biol. Pharmaceutical Sciences University of Kentucky, Lexington, KY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Molec. and Cellular Biol. Pharmaceutical Sciences University of Kentucky, Lexington, KY, USA","institution_ids":["https://openalex.org/I143302722"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102842945","display_name":"Jinze Liu","orcid":"https://orcid.org/0000-0003-0555-9412"},"institutions":[{"id":"https://openalex.org/I143302722","display_name":"University of Kentucky","ror":"https://ror.org/02k3smh20","country_code":"US","type":"education","lineage":["https://openalex.org/I143302722"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinze Liu","raw_affiliation_strings":["Computer Science University of Kentucky, Lexington, KY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science University of Kentucky, Lexington, KY, USA","institution_ids":["https://openalex.org/I143302722"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I143302722"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1344659,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"7","issue":null,"first_page":"2221","last_page":"2228"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","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/T10015","display_name":"Genomics and Phylogenetic Studies","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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9990000128746033,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9984999895095825,"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/identification","display_name":"Identification (biology)","score":0.6514678597450256},{"id":"https://openalex.org/keywords/scope","display_name":"Scope (computer science)","score":0.6411817073822021},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5787362456321716},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5704699158668518},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.5150282382965088},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5107717514038086},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.48911792039871216},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4853995740413666},{"id":"https://openalex.org/keywords/protein-function","display_name":"Protein function","score":0.4838891923427582},{"id":"https://openalex.org/keywords/protein-domain","display_name":"Protein domain","score":0.4369127154350281},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.31364044547080994},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.25901123881340027},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.1665745973587036},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.08065754175186157}],"concepts":[{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6514678597450256},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.6411817073822021},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5787362456321716},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5704699158668518},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.5150282382965088},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5107717514038086},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.48911792039871216},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4853995740413666},{"id":"https://openalex.org/C2986374874","wikidata":"https://www.wikidata.org/wiki/Q8054","display_name":"Protein function","level":3,"score":0.4838891923427582},{"id":"https://openalex.org/C144292202","wikidata":"https://www.wikidata.org/wiki/Q898273","display_name":"Protein domain","level":3,"score":0.4369127154350281},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.31364044547080994},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.25901123881340027},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.1665745973587036},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.08065754175186157},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm.2018.8621241","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm.2018.8621241","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1995875735","https://openalex.org/W2033561922","https://openalex.org/W2085292202","https://openalex.org/W2106882534","https://openalex.org/W2120866529","https://openalex.org/W2127322768","https://openalex.org/W2127774996","https://openalex.org/W2132926880","https://openalex.org/W2140872496","https://openalex.org/W2144362290","https://openalex.org/W2426147716","https://openalex.org/W2468255124","https://openalex.org/W6671976145"],"related_works":["https://openalex.org/W2095784700","https://openalex.org/W3165639034","https://openalex.org/W2135470984","https://openalex.org/W2096697992","https://openalex.org/W2159663778","https://openalex.org/W2374348541","https://openalex.org/W2015809665","https://openalex.org/W4402253264","https://openalex.org/W2065993463","https://openalex.org/W2935275081"],"abstract_inverted_index":{"Biological":[0],"researchers":[1],"have":[2],"proposed":[3],"the":[4,36,79],"existence":[5],"of":[6,14,31,38,51],"protein":[7,58,71,91,97],"domains":[8,59],"specific":[9],"to":[10,28,56,83,88],"individual":[11],"taxonomic":[12],"kingdoms":[13],"organism":[15],"that":[16],"do":[17],"not":[18],"participate":[19],"directly":[20],"in":[21],"catalytic":[22],"activity":[23],"and":[24,43,77,93],"yet":[25],"are":[26],"essential":[27],"genetic":[29],"complementation":[30],"loss-of-function":[32],"mutations":[33],"[1].":[34],"Under":[35],"scope":[37],"this":[39,65],"project,":[40],"we":[41],"design":[42],"implement":[44],"a":[45,70,89],"computational":[46],"algorithm":[47,66],"for":[48,69],"unsupervised":[49],"identification":[50],"new":[52],"kingdom-specific":[53,75],"sequence":[54],"motifs":[55],"distinguish":[57],"warranting":[60],"empirical":[61],"investigation.":[62],"We":[63],"execute":[64],"on":[67],"sequences":[68],"with":[72,81],"empirically":[73],"documented":[74],"domain,":[76],"validate":[78],"results":[80],"respect":[82],"biological":[84],"realism":[85],"by":[86],"mapping":[87],"3-D":[90],"structure":[92],"comparing":[94],"against":[95],"existing":[96],"annotations.":[98]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
