{"id":"https://openalex.org/W1204496755","doi":"https://doi.org/10.13097/archive-ouverte/unige:12936","title":"Modular text mining for protein-protein interactions extraction","display_name":"Modular text mining for protein-protein interactions extraction","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W1204496755","doi":"https://doi.org/10.13097/archive-ouverte/unige:12936","mag":"1204496755"},"language":"en","primary_location":{"id":"pmh:oai:unige.ch:unige:12936","is_oa":true,"landing_page_url":"https://archive-ouverte.unige.ch/unige:12936","pdf_url":"https://archive-ouverte.unige.ch/unige:12936","source":{"id":"https://openalex.org/S4306402259","display_name":"Archive ouverte UNIGE (University of Geneva)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114457229","host_organization_name":"University of Geneva","host_organization_lineage":["https://openalex.org/I114457229"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"type":"dissertation","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://archive-ouverte.unige.ch/unige:12936","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018379596","display_name":"Fr\u00e9d\u00e9ric Ehrler","orcid":"https://orcid.org/0000-0001-9734-3242"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ehrler, Fr\u00e9d\u00e9ric","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5018379596"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"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":0.972100019454956,"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":0.972100019454956,"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/computer-science","display_name":"Computer science","score":0.7178281545639038},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6564234495162964},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5873152017593384},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5198721885681152},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5176628232002258},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5085078477859497},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.48916199803352356},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4812181293964386},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.45687592029571533},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.43200886249542236},{"id":"https://openalex.org/keywords/protein\u2013protein-interaction","display_name":"Protein\u2013protein interaction","score":0.41922715306282043},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28926682472229004},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.16330036520957947},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1357649266719818}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7178281545639038},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6564234495162964},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5873152017593384},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5198721885681152},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5176628232002258},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5085078477859497},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.48916199803352356},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4812181293964386},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.45687592029571533},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.43200886249542236},{"id":"https://openalex.org/C11804247","wikidata":"https://www.wikidata.org/wiki/Q896177","display_name":"Protein\u2013protein interaction","level":2,"score":0.41922715306282043},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28926682472229004},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.16330036520957947},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1357649266719818},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:unige.ch:unige:12936","is_oa":true,"landing_page_url":"https://archive-ouverte.unige.ch/unige:12936","pdf_url":"https://archive-ouverte.unige.ch/unige:12936","source":{"id":"https://openalex.org/S4306402259","display_name":"Archive ouverte UNIGE (University of Geneva)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114457229","host_organization_name":"University of Geneva","host_organization_lineage":["https://openalex.org/I114457229"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"doi:10.13097/archive-ouverte/unige:12936","is_oa":true,"landing_page_url":"https://doi.org/10.13097/archive-ouverte/unige:12936","pdf_url":null,"source":{"id":"https://openalex.org/S7407051284","display_name":"Uni Genf","issn_l":null,"issn":[],"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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"thesis"}],"best_oa_location":{"id":"pmh:oai:unige.ch:unige:12936","is_oa":true,"landing_page_url":"https://archive-ouverte.unige.ch/unige:12936","pdf_url":"https://archive-ouverte.unige.ch/unige:12936","source":{"id":"https://openalex.org/S4306402259","display_name":"Archive ouverte UNIGE (University of Geneva)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114457229","host_organization_name":"University of Geneva","host_organization_lineage":["https://openalex.org/I114457229"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"score":0.699999988079071,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1204496755.pdf","grobid_xml":"https://content.openalex.org/works/W1204496755.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2052852434","https://openalex.org/W2205636404","https://openalex.org/W1589261038","https://openalex.org/W2048503857","https://openalex.org/W2146496657","https://openalex.org/W2604774594","https://openalex.org/W2414530477","https://openalex.org/W2593145382","https://openalex.org/W2033319677","https://openalex.org/W2589878794","https://openalex.org/W2024594931","https://openalex.org/W2210328290","https://openalex.org/W2343455533","https://openalex.org/W2468102681","https://openalex.org/W2148290194","https://openalex.org/W2465332210","https://openalex.org/W1519470527","https://openalex.org/W2004356755","https://openalex.org/W2624143718","https://openalex.org/W2112378479"],"abstract_inverted_index":{"Since":[0],"researchers":[1],"discovered":[2],"that":[3,172],"proteins":[4,111,119],"do":[5],"not":[6],"function":[7],"isolated":[8],"in":[9,14,114,160],"a":[10,106,161,179],"cell":[11],"but":[12],"act":[13],"multi-protein":[15],"complexes,":[16],"the":[17,47,61,74,78,87,90,94,101,110,115,127,149,153,157,169,185,192,197],"number":[18],"of":[19,31,49,63,80,82,93,103,145,152,156,196],"publications":[20],"about":[21],"protein-protein":[22,64],"interactions":[23,65,128],"(PPI)":[24],"has":[25],"increased":[26],"significantly.":[27],"This":[28],"large":[29],"amount":[30],"unstructured":[32],"textual":[33],"information":[34,48],"is":[35,54],"difficult":[36],"to":[37,45,56,59,136],"exploit":[38],"by":[39],"humans":[40],"as":[41],"these":[42],"have":[43],"trouble":[44],"localize":[46],"interest":[50],"efficiently.":[51],"Therefore,":[52],"it":[53,182],"necessary":[55],"develop":[57],"techniques":[58],"automate":[60],"extraction":[62,76,96],"from":[66,77],"free":[67],"text.":[68],"In":[69],"this":[70,146],"thesis,":[71],"we":[72],"explore":[73],"PPI":[75,95],"point":[79],"view":[81],"database":[83],"curators":[84],"and":[85,125,188,194],"study":[86,137],"dependencies":[88],"between":[89],"different":[91,132],"steps":[92,133,186],"process.":[97],"It":[98],"starts":[99],"with":[100],"recognition":[102],"articles":[104],"containing":[105],"PPI.":[107],"Once":[108],"done,":[109],"are":[112,129],"located":[113],"selected":[116],"documents.":[117],"These":[118,131],"must":[120],"then":[121],"be":[122],"unambiguously":[123],"identified,":[124],"finally":[126,189],"extracted.":[130],"allow":[134],"u":[135],"exhaustively":[138],"various":[139],"data":[140],"mining":[141],"techniques.":[142],"The":[143],"outcomes":[144],"thesis":[147],"confirm":[148],"crucial":[150],"importance":[151],"performance":[154],"consistency":[155],"tasks":[158],"involved":[159],"process":[162],"over":[163],"their":[164],"individual":[165],"performance.":[166],"More":[167],"specifically,":[168],"results":[170],"reveal":[171],"each":[173],"time":[174],"an":[175],"error":[176],"occurs":[177],"at":[178],"given":[180],"step,":[181],"influences":[183],"all":[184],"downstream":[187],"strongly":[190],"reduces":[191],"precision":[193],"recall":[195],"generated":[198],"interactions.":[199]},"counts_by_year":[],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}