{"id":"https://openalex.org/W2107862878","doi":"https://doi.org/10.1093/bioinformatics/btu004","title":"Allerdictor: fast allergen prediction using text classification techniques","display_name":"Allerdictor: fast allergen prediction using text classification techniques","publication_year":2014,"publication_date":"2014-01-07","ids":{"openalex":"https://openalex.org/W2107862878","doi":"https://doi.org/10.1093/bioinformatics/btu004","mag":"2107862878","pmid":"https://pubmed.ncbi.nlm.nih.gov/24403538","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/3982160"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btu004","doi":"https://doi.org/10.1093/bioinformatics/btu004","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btu004","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/30/8/1120/17143548/btu004.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,"listed_in":["abdc-a","anvur-class-a","anvur-scientific","ccf-a","cwts-core","doaj","dongbi-b","doyens","jufo-3","ki-jl-2","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"parent_works":[],"lineage":["https://openalex.org/W2107862878"],"child_works_count":0,"type":"article","is_traditional":true,"indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/30/8/1120/17143548/btu004.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076346004","display_name":"Ha X. Dang","orcid":"https://orcid.org/0000-0002-9342-9249","observed_orcids":["https://orcid.org/0000-0002-9342-9249"]},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ha X. Dang","raw_affiliation_strings":["1 Virginia Bioinformatics Institute and 2Department of Biological Sciences, Virginia Tech, Blacksburg, VA 24061, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Virginia Bioinformatics Institute and 2Department of Biological Sciences, Virginia Tech, Blacksburg, VA 24061, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006678497","display_name":"Christopher B. Lawrence","orcid":"https://orcid.org/0009-0008-9972-5306","observed_orcids":["https://orcid.org/0009-0008-9972-5306"]},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Christopher B. Lawrence","raw_affiliation_strings":["1 Virginia Bioinformatics Institute and 2Department of Biological Sciences, Virginia Tech, Blacksburg, VA 24061, USA","Virginia Bioinformatics Institute and Department of Biological Sciences, Virginia Tech, Blacksburg, VA 24061, USA Virginia Bioinformatics Institute and Department of Biological Sciences, Virginia Tech, Blacksburg, VA 24061, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Virginia Bioinformatics Institute and 2Department of Biological Sciences, Virginia Tech, Blacksburg, VA 24061, USA","institution_ids":["https://openalex.org/I859038795"]},{"raw_affiliation_string":"Virginia Bioinformatics Institute and Department of Biological Sciences, Virginia Tech, Blacksburg, VA 24061, USA Virginia Bioinformatics Institute and Department of Biological Sciences, Virginia Tech, Blacksburg, VA 24061, USA","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5006678497"],"corresponding_institution_ids":["https://openalex.org/I859038795"],"apc_list":{"value":3989,"currency":"USD","value_usd":3989},"apc_paid":{"value":3989,"currency":"USD","value_usd":3989},"fwci":2.0825,"has_fulltext":true,"cited_by_count":64,"citation_normalized_percentile":{"value":0.87632943,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":"30","issue":"8","first_page":"1120","last_page":"1128"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9320999979972839,"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":0.9320999979972839,"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":0.022600000724196434,"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/T10634","display_name":"Food Allergy and Anaphylaxis Research","score":0.01810000091791153,"subfield":{"id":"https://openalex.org/subfields/2723","display_name":"Immunology and Allergy"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/allergenicity-prediction","display_name":"allergenicity prediction","score":0.9959999918937683},{"id":"https://openalex.org/keywords/text-classification","display_name":"text classification","score":0.6809999942779541},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"support vector machine","score":0.7870000004768372},{"id":"https://openalex.org/keywords/class-imbalance","display_name":"class imbalance","score":0.6370000243186951},{"id":"https://openalex.org/keywords/biotechnology-products","display_name":"biotechnology products","score":0.8259999752044678},{"id":"https://openalex.org/keywords/swiss-prot","display_name":"Swiss-Prot","score":0.7049999833106995},{"id":"https://openalex.org/keywords/allergen-elimination","display_name":"allergen removal","score":0.35199999809265137}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6868315935134888},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.676242470741272},{"id":"https://openalex.org/C2780510475","wikidata":"https://www.wikidata.org/wiki/Q186752","display_name":"Allergen","level":3,"score":0.5418999195098877},{"id":"https://openalex.org/C2989486834","wikidata":"https://www.wikidata.org/wiki/Q3808900","display_name":"True positive rate","level":2,"score":0.5141018033027649},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.48121002316474915},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.43931907415390015},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.43784862756729126},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3899341821670532},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.328533411026001},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32757776975631714},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.14754271507263184},{"id":"https://openalex.org/C207480886","wikidata":"https://www.wikidata.org/wiki/Q42982","display_name":"Allergy","level":2,"score":0.10374000668525696},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C203014093","wikidata":"https://www.wikidata.org/wiki/Q101929","display_name":"Immunology","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000485","descriptor_name":"Allergens","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":true},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/btu004","doi":"https://doi.org/10.1093/bioinformatics/btu004","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btu004","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/30/8/1120/17143548/btu004.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,"listed_in":["abdc-a","anvur-class-a","anvur-scientific","ccf-a","cwts-core","doaj","dongbi-b","doyens","jufo-3","ki-jl-2","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmh:oai:europepmc.org:3358966","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3982160","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"Text"},{"id":"pmid:24403538","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/24403538","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,"listed_in":[],"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":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:3982160","doi":null,"is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC3982160/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btu004","doi":"https://doi.org/10.1093/bioinformatics/btu004","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btu004","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/30/8/1120/17143548/btu004.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,"listed_in":["abdc-a","anvur-class-a","anvur-scientific","ccf-a","cwts-core","doaj","dongbi-b","doyens","jufo-3","ki-jl-2","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3","score":0.5683000087738037}],"study_designs":[],"awards":[{"id":"https://openalex.org/G7858137230","display_name":"The Role of the Major Alternaria Allergen Alt_a_1 in Airway Inflammation","funder_award_id":"R21AI094071","funder_id":"https://openalex.org/F4320337355","funder_display_name":"National Institute of Allergy and Infectious Diseases"}],"funders":[{"id":"https://openalex.org/F4320337355","display_name":"National Institute of Allergy and Infectious Diseases","ror":"https://ror.org/043z4tv69"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2107862878.pdf","grobid_xml":"https://content.openalex.org/works/W2107862878.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W387031605","https://openalex.org/W1532325895","https://openalex.org/W1540550673","https://openalex.org/W1549656520","https://openalex.org/W1618905105","https://openalex.org/W1976526581","https://openalex.org/W1993940964","https://openalex.org/W2003451882","https://openalex.org/W2005604222","https://openalex.org/W2012037212","https://openalex.org/W2035265157","https://openalex.org/W2041258965","https://openalex.org/W2041267049","https://openalex.org/W2043990114","https://openalex.org/W2056983531","https://openalex.org/W2057051757","https://openalex.org/W2063345857","https://openalex.org/W2064580901","https://openalex.org/W2076096957","https://openalex.org/W2087347434","https://openalex.org/W2089000221","https://openalex.org/W2102023232","https://openalex.org/W2104863787","https://openalex.org/W2112874093","https://openalex.org/W2119152270","https://openalex.org/W2127314673","https://openalex.org/W2130253098","https://openalex.org/W2139091446","https://openalex.org/W2139212933","https://openalex.org/W2142763532","https://openalex.org/W2153544727","https://openalex.org/W2158714788","https://openalex.org/W2168518560","https://openalex.org/W2171196697","https://openalex.org/W4213009331","https://openalex.org/W4239510810","https://openalex.org/W4249435950","https://openalex.org/W4312960235"],"related_works":["https://openalex.org/W4304892064","https://openalex.org/W4399561131","https://openalex.org/W2142763532","https://openalex.org/W2119152270","https://openalex.org/W4292519143","https://openalex.org/W2003805630","https://openalex.org/W2063345857","https://openalex.org/W2015176909","https://openalex.org/W2005604222","https://openalex.org/W4403922588"],"abstract_inverted_index":{"MOTIVATION:":[0],"Accurately":[1],"identifying":[2],"and":[3,66,120,136,148,161,215,230,234],"eliminating":[4],"allergens":[5,25,183],"from":[6],"biotechnology-derived":[7],"products":[8],"are":[9,83,90,117,121,246],"important":[10,22],"for":[11,103,169],"human":[12],"health.":[13],"From":[14],"a":[15,57,146,201,207],"biomedical":[16],"research":[17],"perspective,":[18],"it":[19],"is":[20,226],"also":[21],"to":[23,51,75,99,205],"identify":[24],"in":[26,138,166,228],"sequenced":[27],"genomes.":[28],"Many":[29],"allergen":[30,53,104,114,133,151,170],"prediction":[31,115,152],"tools":[32,42,89,116],"have":[33,43],"been":[34],"developed":[35,144],"during":[36],"the":[37,76,80,86,112,123,139],"past":[38],"years.":[39],"Although":[40],"these":[41],"achieved":[44],"certain":[45],"levels":[46],"of":[47,79,111,125,211,218],"specificity,":[48],"when":[49],"applied":[50],"large-scale":[52,132],"discovery":[54,134],"(e.g.":[55],"at":[56,71,190,238,248],"whole-genome":[58],"scale),":[59],"they":[60,94],"still":[61],"yield":[62],"many":[63],"false":[64],"positives":[65],"thus":[67],"low":[68,72],"precision":[69,186],"(even":[70],"recall)":[73],"due":[74],"extreme":[77],"skewness":[78],"data":[81,245],"(allergens":[82],"rare).":[84],"Moreover,":[85],"most":[87],"accurate":[88,149],"relatively":[91],"slow":[92],"because":[93],"use":[95],"protein":[96,156],"sequence":[97],"alignment":[98],"build":[100],"feature":[101],"vectors":[102],"classifiers.":[105],"Additionally,":[106],"only":[107,196],"web":[108,235],"server":[109,236],"implementations":[110],"current":[113],"publicly":[118],"available":[119,231,247],"without":[122],"capability":[124],"large":[126],"batch":[127],"submission.":[128],"These":[129],"weaknesses":[130],"make":[131],"ineffective":[135],"inefficient":[137],"public":[140],"domain.":[141],"RESULTS:":[142],"We":[143],"Allerdictor,":[145],"fast":[147,191],"sequence-based":[150],"tool":[153],"that":[154,180],"models":[155],"sequences":[157,214],"as":[158,220,232],"text":[159,167],"documents":[160],"uses":[162],"support":[163],"vector":[164],"machine":[165],"classification":[168],"prediction.":[171],"Test":[172],"results":[173],"on":[174,200],"multiple":[175],"highly":[176],"skewed":[177],"datasets":[178],"demonstrated":[179],"Allerdictor":[181,195,225],"predicted":[182],"with":[184],"high":[185,188],"over":[187],"recall":[189],"speed.":[192],"For":[193],"example,":[194],"took":[197],"\u223c6":[198],"min":[199],"single":[202],"core":[203],"PC":[204],"scan":[206],"whole":[208],"Swiss-Prot":[209],"database":[210],"\u223c540":[212],"000":[213],"identified":[216],"<1%":[217],"them":[219],"allergens.":[221],"AVAILABILITY":[222],"AND":[223],"IMPLEMENTATION:":[224],"implemented":[227],"Python":[229],"standalone":[233],"versions":[237],"http://allerdictor.vbi.vt.edu":[239],"CONTACT:":[240],"lawrence@vbi.vt.edu":[241],"Supplementary":[242,244],"information:":[243],"Bioinformatics":[249],"online.":[250]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":1}],"updated_date":"2026-11-13T13:42:25.865203","created_date":"2016-06-24T00:00:00"}
