{"id":"https://openalex.org/W2147140458","doi":"https://doi.org/10.1186/1471-2105-11-s5-o1","title":"The PPI affix dictionary (PPIAD) and BioMethod Lexicon: importance of affixes and tags for recognition of entity mentions and experimental protein interactions","display_name":"The PPI affix dictionary (PPIAD) and BioMethod Lexicon: importance of affixes and tags for recognition of entity mentions and experimental protein interactions","publication_year":2010,"publication_date":"2010-10-01","ids":{"openalex":"https://openalex.org/W2147140458","doi":"https://doi.org/10.1186/1471-2105-11-s5-o1","mag":"2147140458"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-11-s5-o1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-11-s5-o1","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/1471-2105-11-S5-O1","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/1471-2105-11-S5-O1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007203127","display_name":"Martin Krallinger","orcid":"https://orcid.org/0000-0002-2646-8782"},"institutions":[{"id":"https://openalex.org/I4210089594","display_name":"Spanish National Cancer Research Centre","ror":"https://ror.org/00bvhmc43","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4210089594"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Martin Krallinger","raw_affiliation_strings":["Structural Biology and BioComputing Programme, Spanish National Cancer Research Centre, Madrid, Spain"],"affiliations":[{"raw_affiliation_string":"Structural Biology and BioComputing Programme, Spanish National Cancer Research Centre, Madrid, Spain","institution_ids":["https://openalex.org/I4210089594"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048099130","display_name":"Ashish V. Tendulkar","orcid":null},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ashish V Tendulkar","raw_affiliation_strings":["Department of Computer Science and Engineering, Indian Institute of Technology, Madras, India","[Department of Computer Science and Engineering, Indian Institute of Technology Madras, India]"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology, Madras, India","institution_ids":["https://openalex.org/I24676775"]},{"raw_affiliation_string":"[Department of Computer Science and Engineering, Indian Institute of Technology Madras, India]","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018678007","display_name":"Florian Leitner","orcid":"https://orcid.org/0000-0003-4458-504X"},"institutions":[{"id":"https://openalex.org/I4210089594","display_name":"Spanish National Cancer Research Centre","ror":"https://ror.org/00bvhmc43","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4210089594"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Florian Leitner","raw_affiliation_strings":["Structural Biology and BioComputing Programme, Spanish National Cancer Research Centre, Madrid, Spain"],"affiliations":[{"raw_affiliation_string":"Structural Biology and BioComputing Programme, Spanish National Cancer Research Centre, Madrid, Spain","institution_ids":["https://openalex.org/I4210089594"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088383521","display_name":"Andrew Chatr\u2010aryamontri","orcid":"https://orcid.org/0000-0002-1589-9982"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]},{"id":"https://openalex.org/I4210134627","display_name":"Wellcome Centre for Cell Biology","ror":"https://ror.org/03xbccz06","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210134627","https://openalex.org/I87048295","https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andrew Chatr-aryamontri","raw_affiliation_strings":["Wellcome Trust Centre for Cell Biology, School of Biological Sciences, University of Edinburgh, Mayfield Road, Edinburgh, EH9 3JR, UK","Wellcome Trust Centre for Cell Biology School of Biological Sciences University of Edinburgh Edinburgh UK"],"affiliations":[{"raw_affiliation_string":"Wellcome Trust Centre for Cell Biology, School of Biological Sciences, University of Edinburgh, Mayfield Road, Edinburgh, EH9 3JR, UK","institution_ids":["https://openalex.org/I4210134627","https://openalex.org/I98677209"]},{"raw_affiliation_string":"Wellcome Trust Centre for Cell Biology School of Biological Sciences University of Edinburgh Edinburgh UK","institution_ids":["https://openalex.org/I4210134627","https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015217651","display_name":"Alfonso Valencia","orcid":"https://orcid.org/0000-0002-8937-6789"},"institutions":[{"id":"https://openalex.org/I4210089594","display_name":"Spanish National Cancer Research Centre","ror":"https://ror.org/00bvhmc43","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4210089594"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Alfonso Valencia","raw_affiliation_strings":["Structural Biology and BioComputing Programme, Spanish National Cancer Research Centre, Madrid, Spain"],"affiliations":[{"raw_affiliation_string":"Structural Biology and BioComputing Programme, Spanish National Cancer Research Centre, Madrid, Spain","institution_ids":["https://openalex.org/I4210089594"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5007203127"],"corresponding_institution_ids":["https://openalex.org/I4210089594"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":0.4066,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.63978661,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"11","issue":"S5","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9997000098228455,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9997000098228455,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9602000117301941,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9541000127792358,"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/affix","display_name":"Affix","score":0.9625644683837891},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.7507236003875732},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6440696716308594},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5519751310348511},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4617704451084137},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4227045476436615},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.37056344747543335},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.30421626567840576}],"concepts":[{"id":"https://openalex.org/C2778428490","wikidata":"https://www.wikidata.org/wiki/Q62155","display_name":"Affix","level":2,"score":0.9625644683837891},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.7507236003875732},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6440696716308594},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5519751310348511},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4617704451084137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4227045476436615},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.37056344747543335},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.30421626567840576},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1186/1471-2105-11-s5-o1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-11-s5-o1","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/1471-2105-11-S5-O1","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:b073e4ae64bc4ae6853794b05871d40d","is_oa":true,"landing_page_url":"https://doaj.org/article/b073e4ae64bc4ae6853794b05871d40d","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 11, Iss Suppl 5, p O1 (2010)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:2956388","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/2956388","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-11-s5-o1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-11-s5-o1","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/1471-2105-11-S5-O1","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4000000059604645,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1209016659","display_name":null,"funder_award_id":"BIO2007-66855","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n"},{"id":"https://openalex.org/G2240538154","display_name":null,"funder_award_id":"LSHG-CT-2005-518254","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320322930","display_name":"Ministerio de Ciencia e Innovaci\u00f3n","ror":"https://ror.org/034900433"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2147140458.pdf","grobid_xml":"https://content.openalex.org/works/W2147140458.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W2064030835","https://openalex.org/W2078017455","https://openalex.org/W2104965688","https://openalex.org/W2154142897","https://openalex.org/W2168091548"],"related_works":["https://openalex.org/W3107474891","https://openalex.org/W1554149234","https://openalex.org/W3027466640","https://openalex.org/W1529136209","https://openalex.org/W1595294003","https://openalex.org/W2765593440","https://openalex.org/W2921012827","https://openalex.org/W2578226461","https://openalex.org/W2046564421","https://openalex.org/W3129647673"],"abstract_inverted_index":{"Substantial":[0],"text":[1,45,115,166],"mining":[2,116],"efforts":[3],"are":[4,97],"being":[5],"devoted":[6],"to":[7,90,127,160,184,192,198,285,307,423],"detect":[8,91,193],"protein":[9,54,83,162,179,351],"mentions":[10,55,163,201],"and":[11,87,92,135,197,234,250,328,353,357,405,434,442,448,455,465],"protein-protein":[12],"interaction":[13,60,144,204,217,227,309,352,372,382,395,406,424],"(PPI)":[14],"relations":[15],"from":[16],"scientific":[17],"articles":[18,46,196],"[1,2].":[19],"In":[20,270],"this":[21],"context,":[22],"the":[23,28,32,57,103,107,154,214,259,266,271,320,325,335,340,417,483,486],"BioCreative":[24],"challenge":[25],"showed":[26,420],"that":[27,236,387,414],"correct":[29],"identification":[30],"of":[31,51,53,59,102,111,122,132,156,210,213,225,261,263,265,303,319,331,345,370,394,400,416,477,485],"individual":[33],"interactor":[34,161],"proteins":[35,71,105,133],"is":[36,389,480],"still":[37],"a":[38,150,223,343,367,390],"challenging":[39],"task,":[40],"especially":[41],"when":[42],"using":[43],"full":[44,165],"[2].":[47],"A":[48],"systematic":[49],"analysis":[50,399],"particularities":[52],"in":[56,106,113,120,139,164,334],"context":[58],"descriptions":[61],"was":[62],"nonetheless":[63],"missing.":[64],"Experimental":[65],"biologists":[66],"often":[67,98],"use":[68],"specific":[69,187],"fusion":[70],"or":[72,81,253],"protein-tags":[73],"such":[74,426],"as":[75,100,172,427],"-GST,":[76],"-His,":[77],"-Myc,":[78],"FLAG-,":[79],"antibodies":[80],"fluorescent":[82],"(GFP,":[84],"YFP,":[85],"CFP":[86],"RFP)":[88],"tags":[89,96],"visualize":[93],"interactions.":[94,180],"These":[95],"mentioned":[99,378],"affixes":[101,112,158,188,229],"target":[104],"literature.":[108],"The":[109],"importance":[110],"biomedical":[114],"had":[117],"been":[118,282,314],"addressed":[119],"case":[121],"affixal":[123],"negation":[124],"expressions":[125],"[3],":[126],"consider":[128],"general":[129],"posttranslational":[130],"modifications":[131],"[4]":[134],"can":[136],"be":[137,190,238],"observed":[138],"trigger":[140],"verbs":[141],"used":[142],"for":[143,175,350],"extraction":[145],"[5].":[146],"We":[147],"carried":[148],"out":[149],"detailed":[151],"study":[152],"on":[153,208],"presence":[155],"common":[157,392],"belonging":[159],"sentences":[167],"considered":[168],"by":[169,289,295],"database":[170],"curators":[171],"evidential":[173],"support":[174],"experimentally":[176],"characterized":[177,358],"physical":[178],"Furthermore,":[181],"we":[182,220,338,412],"tried":[183],"determine":[185],"whether":[186],"might":[189],"useful":[191],"PPI":[194,273],"relevant":[195,228,383],"correlate":[199],"affix":[200,245,267,274,278,304,363,403,418],"with":[202,362],"particular":[203],"detection":[205,310,407],"methods.":[206],"Based":[207],"examination":[209],"over":[211],"3,000":[212],"previously":[215],"referred":[216],"evidence":[218,321,373],"passages":[219],"have":[221,313],"compiled":[222],"collection":[224,344],"277":[226],"(89":[230],"suffixes,":[231],"176":[232],"prefixes":[233],"12":[235],"could":[237],"both),":[239],"which":[240,385],"were":[241],"structured":[242],"into":[243],"36":[244],"tag":[246,268,279,305,364],"classes":[247,306,404,419],"(26":[248],"super-affix":[249],"10":[251],"combined":[252],"sub-affix":[254],"classes).":[255],"Figure":[256],"1A":[257],"shows":[258,386],"frequency":[260],"mention":[262],"each":[264,277],"classes.":[269,365],"resulting":[272],"dictionary":[275],"(PPIAD),":[276],"class":[280],"has":[281],"manually":[283],"linked":[284],"experimental":[286,346],"qualifiers":[287],"represented":[288],"associated":[290],"PSI-MI":[291,308,336],"ontology":[292,337],"[5]":[293],"concepts":[294,312],"considering":[296],"their":[297],"concept":[298],"definitions.":[299],"Additionally,":[300],"statistical":[301,398],"associations":[302,401,422],"method":[311,347,359,408],"derived":[315],"through":[316],"curator-based":[317],"annotations":[318,409],"passages.":[322],"To":[323],"overcome":[324],"limited":[326],"scope":[327],"lexical":[329],"coverage":[330],"terms":[332,348],"contained":[333],"build":[339],"BioMethod":[341],"Lexicon,":[342],"important":[349],"gene":[354],"regulation":[355],"relations,":[356],"term":[360],"co-mentions":[361],"Within":[366],"total":[368],"set":[369],"6,300":[371],"sentences,":[374],"1,946":[375],"(31":[376],"%)":[377],"at":[379,482],"least":[380],"one":[381],"affix,":[384],"it":[388],"relatively":[391],"feature":[393],"descriptions.":[396],"Using":[397],"between":[402],"(Chi-square":[410],"test)":[411],"discovered":[413],"some":[415],"strong":[421],"methods,":[425],"between:":[428],"MI:0096":[429],"AF_21":[430],"(MI:":[431],"pull":[432],"down":[433],"PPIAD:":[435],"gst_pull_down_tag),":[436],"MI:0676":[437],"AF_6":[438],"(tandem":[439],"affinity":[440],"purification":[441],"Tandem_Affinity_Purification_tag),":[443],"MI:0018":[444],"AF_10":[445],"(two":[446],"hybrid":[447],"Gal4_tag),":[449],"MI:0006":[450],"AF_4":[451],"(anti":[452],"bait":[453],"coimmunoprecipitation":[454],"Antibody_tag),":[456],"MI:0055":[457],"AF_15":[458],"(fluorescent":[459],"*":[460],"Correspondence:":[461],"mkrallinger@cnio.es":[462],"Structural":[463],"Biology":[464],"BioComputing":[466],"Programme,":[467],"Spanish":[468],"National":[469],"Cancer":[470],"Research":[471],"Centre,":[472],"Madrid,":[473],"Spain":[474],"Full":[475],"list":[476],"author":[478],"information":[479],"available":[481],"end":[484],"article":[487],"Krallinger":[488],"et":[489],"al.":[490],"BMC":[491],"Bioinformatics":[492],"2010,":[493],"11(Suppl":[494],"5):O1":[495],"http://www.biomedcentral.com/1471-2105/11/S5/O1":[496]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}