{"id":"https://openalex.org/W2137125475","doi":"https://doi.org/10.1093/bioinformatics/btn099","title":"A nearest neighbor approach for automated transporter prediction and categorization from protein sequences","display_name":"A nearest neighbor approach for automated transporter prediction and categorization from protein sequences","publication_year":2008,"publication_date":"2008-03-12","ids":{"openalex":"https://openalex.org/W2137125475","doi":"https://doi.org/10.1093/bioinformatics/btn099","mag":"2137125475","pmid":"https://pubmed.ncbi.nlm.nih.gov/18337257"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btn099","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btn099","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/24/9/1129/49046230/bioinformatics_24_9_1129.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/24/9/1129/49046230/bioinformatics_24_9_1129.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066737474","display_name":"Haiquan Li","orcid":"https://orcid.org/0000-0002-8049-0278"},"institutions":[{"id":"https://openalex.org/I4210126540","display_name":"Noble Research Institute","ror":"https://ror.org/02zta5505","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210126540"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Haiquan Li","raw_affiliation_strings":["Bioinformatics Lab, Plant Biology Division, The Samuel Roberts Noble Foundation, Inc., 2510 Sam Noble Parkway, Ardmore, OK 73401, USA"],"affiliations":[{"raw_affiliation_string":"Bioinformatics Lab, Plant Biology Division, The Samuel Roberts Noble Foundation, Inc., 2510 Sam Noble Parkway, Ardmore, OK 73401, USA","institution_ids":["https://openalex.org/I4210126540"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103136502","display_name":"Xinbin Dai","orcid":"https://orcid.org/0000-0001-8886-9875"},"institutions":[{"id":"https://openalex.org/I4210126540","display_name":"Noble Research Institute","ror":"https://ror.org/02zta5505","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210126540"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinbin Dai","raw_affiliation_strings":["Bioinformatics Lab, Plant Biology Division, The Samuel Roberts Noble Foundation, Inc., 2510 Sam Noble Parkway, Ardmore, OK 73401, USA"],"affiliations":[{"raw_affiliation_string":"Bioinformatics Lab, Plant Biology Division, The Samuel Roberts Noble Foundation, Inc., 2510 Sam Noble Parkway, Ardmore, OK 73401, USA","institution_ids":["https://openalex.org/I4210126540"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103560194","display_name":"Xuechun Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126540","display_name":"Noble Research Institute","ror":"https://ror.org/02zta5505","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210126540"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuechun Zhao","raw_affiliation_strings":["Bioinformatics Lab, Plant Biology Division, The Samuel Roberts Noble Foundation, Inc., 2510 Sam Noble Parkway, Ardmore, OK 73401, USA"],"affiliations":[{"raw_affiliation_string":"Bioinformatics Lab, Plant Biology Division, The Samuel Roberts Noble Foundation, Inc., 2510 Sam Noble Parkway, Ardmore, OK 73401, USA","institution_ids":["https://openalex.org/I4210126540"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5066737474"],"corresponding_institution_ids":["https://openalex.org/I4210126540"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":2.3512,"has_fulltext":true,"cited_by_count":43,"citation_normalized_percentile":{"value":0.88617624,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"24","issue":"9","first_page":"1129","last_page":"1136"},"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9988999962806702,"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":0.9940999746322632,"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/categorization","display_name":"Categorization","score":0.7304357886314392},{"id":"https://openalex.org/keywords/transporter","display_name":"Transporter","score":0.6869191527366638},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5826740264892578},{"id":"https://openalex.org/keywords/k-nearest-neighbors-algorithm","display_name":"k-nearest neighbors algorithm","score":0.5616985559463501},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.531417191028595},{"id":"https://openalex.org/keywords/membrane-transport-protein","display_name":"Membrane transport protein","score":0.4152929186820984},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3816491365432739},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3489570617675781},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32138118147850037},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.26872265338897705},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.18706205487251282},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.142170250415802}],"concepts":[{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.7304357886314392},{"id":"https://openalex.org/C149011108","wikidata":"https://www.wikidata.org/wiki/Q652985","display_name":"Transporter","level":3,"score":0.6869191527366638},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5826740264892578},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.5616985559463501},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.531417191028595},{"id":"https://openalex.org/C115335371","wikidata":"https://www.wikidata.org/wiki/Q142943","display_name":"Membrane transport protein","level":4,"score":0.4152929186820984},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3816491365432739},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3489570617675781},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32138118147850037},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.26872265338897705},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.18706205487251282},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.142170250415802}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D026901","descriptor_name":"Membrane Transport Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D026901","descriptor_name":"Membrane Transport Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D026901","descriptor_name":"Membrane Transport Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btn099","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btn099","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/24/9/1129/49046230/bioinformatics_24_9_1129.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:18337257","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/18337257","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":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1020.649","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1020.649","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://bioinformatics.oxfordjournals.org/content/early/2008/03/12/bioinformatics.btn099.full.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btn099","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btn099","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/24/9/1129/49046230/bioinformatics_24_9_1129.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Life below water","id":"https://metadata.un.org/sdg/14"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2137125475.pdf","grobid_xml":"https://content.openalex.org/works/W2137125475.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W205578041","https://openalex.org/W606440866","https://openalex.org/W1528285574","https://openalex.org/W1912982817","https://openalex.org/W1968390147","https://openalex.org/W1992648037","https://openalex.org/W1998523455","https://openalex.org/W2005313213","https://openalex.org/W2022366078","https://openalex.org/W2035443825","https://openalex.org/W2055043387","https://openalex.org/W2059463006","https://openalex.org/W2064430200","https://openalex.org/W2067353791","https://openalex.org/W2080432979","https://openalex.org/W2087928503","https://openalex.org/W2090436685","https://openalex.org/W2096669041","https://openalex.org/W2097870001","https://openalex.org/W2102122585","https://openalex.org/W2103017472","https://openalex.org/W2105300849","https://openalex.org/W2107903949","https://openalex.org/W2109318635","https://openalex.org/W2109867978","https://openalex.org/W2111876537","https://openalex.org/W2117619142","https://openalex.org/W2118675686","https://openalex.org/W2122111042","https://openalex.org/W2129448726","https://openalex.org/W2129995544","https://openalex.org/W2135834023","https://openalex.org/W2144944670","https://openalex.org/W2154865259","https://openalex.org/W2158120166","https://openalex.org/W2159299078","https://openalex.org/W2162016003","https://openalex.org/W2181695842","https://openalex.org/W4229908240","https://openalex.org/W4230932396","https://openalex.org/W6666673903","https://openalex.org/W6683473195","https://openalex.org/W6685731813","https://openalex.org/W6812385203"],"related_works":["https://openalex.org/W2126864090","https://openalex.org/W3099434004","https://openalex.org/W2095056890","https://openalex.org/W2964790432","https://openalex.org/W1461515649","https://openalex.org/W2077714949","https://openalex.org/W3023758696","https://openalex.org/W2365259202","https://openalex.org/W4234286952","https://openalex.org/W2500411831"],"abstract_inverted_index":{"Our":[0],"approach":[1],"satisfactorily":[2],"distinguished":[3],"484":[4],"transporter":[5],"families":[6],"in":[7,40,79],"the":[8,23,64,76],"Transporter":[9],"Classification":[10],"Database,":[11],"a":[12,26],"curated":[13],"and":[14,43],"representative":[15],"database":[16,24],"for":[17],"transporters.":[18],"A":[19,53],"five-fold":[20],"cross-validation":[21],"on":[22,32,63],"achieved":[25],"positive":[27],"classification":[28],"rate":[29],"of":[30,60,69,75],"72.3%":[31],"average.":[33],"Furthermore,":[34],"this":[35],"method":[36],"successfully":[37],"detected":[38],"transporters":[39,78],"seven":[41],"model":[42],"four":[44],"non-model":[45],"organisms,":[46,66],"ranging":[47],"from":[48],"archaean":[49],"to":[50],"mammalian":[51],"species.":[52],"preliminary":[54],"literature-based":[55],"validation":[56],"has":[57],"cross-validated":[58],"65.8%":[59],"our":[61,70],"predictions":[62,71],"11":[65],"including":[67],"55.9%":[68],"overlapping":[72],"with":[73],"83.6%":[74],"predicted":[77],"TransportDB.":[80]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}