{"id":"https://openalex.org/W2170484170","doi":"https://doi.org/10.1186/1471-2105-13-s17-s9","title":"ChemEx: information extraction system for chemical data curation","display_name":"ChemEx: information extraction system for chemical data curation","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W2170484170","doi":"https://doi.org/10.1186/1471-2105-13-s17-s9","mag":"2170484170","pmid":"https://pubmed.ncbi.nlm.nih.gov/23282330"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-13-s17-s9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-13-s17-s9","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-13-S17-S9","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","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-13-S17-S9","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072024597","display_name":"Atima Tharatipyakul","orcid":"https://orcid.org/0000-0002-2513-6372"},"institutions":[{"id":"https://openalex.org/I902798049","display_name":"National Center for Genetic Engineering and Biotechnology","ror":"https://ror.org/047aswc67","country_code":"TH","type":"facility","lineage":["https://openalex.org/I1332092204","https://openalex.org/I902798049"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Atima Tharatipyakul","raw_affiliation_strings":["Information Systems Laboratory, National Center for Genetic Engineering and Biotechnology (BIOTEC), 113 Thailand Science Park, Phaholyothin Road, Klong 1, Klong Luang, Pathumthani, Thailand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Systems Laboratory, National Center for Genetic Engineering and Biotechnology (BIOTEC), 113 Thailand Science Park, Phaholyothin Road, Klong 1, Klong Luang, Pathumthani, Thailand","institution_ids":["https://openalex.org/I902798049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086527435","display_name":"Somrak Numnark","orcid":null},"institutions":[{"id":"https://openalex.org/I902798049","display_name":"National Center for Genetic Engineering and Biotechnology","ror":"https://ror.org/047aswc67","country_code":"TH","type":"facility","lineage":["https://openalex.org/I1332092204","https://openalex.org/I902798049"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Somrak Numnark","raw_affiliation_strings":["Information Systems Laboratory, National Center for Genetic Engineering and Biotechnology (BIOTEC), 113 Thailand Science Park, Phaholyothin Road, Klong 1, Klong Luang, Pathumthani, Thailand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Systems Laboratory, National Center for Genetic Engineering and Biotechnology (BIOTEC), 113 Thailand Science Park, Phaholyothin Road, Klong 1, Klong Luang, Pathumthani, Thailand","institution_ids":["https://openalex.org/I902798049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035554261","display_name":"Duangdao Wichadakul","orcid":"https://orcid.org/0000-0002-8802-2524"},"institutions":[{"id":"https://openalex.org/I902798049","display_name":"National Center for Genetic Engineering and Biotechnology","ror":"https://ror.org/047aswc67","country_code":"TH","type":"facility","lineage":["https://openalex.org/I1332092204","https://openalex.org/I902798049"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Duangdao Wichadakul","raw_affiliation_strings":["Information Systems Laboratory, National Center for Genetic Engineering and Biotechnology (BIOTEC), 113 Thailand Science Park, Phaholyothin Road, Klong 1, Klong Luang, Pathumthani, Thailand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Systems Laboratory, National Center for Genetic Engineering and Biotechnology (BIOTEC), 113 Thailand Science Park, Phaholyothin Road, Klong 1, Klong Luang, Pathumthani, Thailand","institution_ids":["https://openalex.org/I902798049"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090289533","display_name":"Supawadee Ingsriswang","orcid":"https://orcid.org/0000-0002-3183-5997"},"institutions":[{"id":"https://openalex.org/I902798049","display_name":"National Center for Genetic Engineering and Biotechnology","ror":"https://ror.org/047aswc67","country_code":"TH","type":"facility","lineage":["https://openalex.org/I1332092204","https://openalex.org/I902798049"]}],"countries":["TH"],"is_corresponding":true,"raw_author_name":"Supawadee Ingsriswang","raw_affiliation_strings":["Information Systems Laboratory, National Center for Genetic Engineering and Biotechnology (BIOTEC), 113 Thailand Science Park, Phaholyothin Road, Klong 1, Klong Luang, Pathumthani, Thailand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Systems Laboratory, National Center for Genetic Engineering and Biotechnology (BIOTEC), 113 Thailand Science Park, Phaholyothin Road, Klong 1, Klong Luang, Pathumthani, Thailand","institution_ids":["https://openalex.org/I902798049"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5090289533"],"corresponding_institution_ids":["https://openalex.org/I902798049"],"apc_list":{"value":2790,"currency":"USD","value_usd":2790},"apc_paid":{"value":2790,"currency":"USD","value_usd":2790},"fwci":0.4909,"has_fulltext":true,"cited_by_count":34,"citation_normalized_percentile":{"value":0.63704969,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"13","issue":"S17","first_page":"S9","last_page":"S9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.590499997138977,"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":0.590499997138977,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.08919999748468399,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12859","display_name":"Cell Image Analysis Techniques","score":0.045499999076128006,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"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":0.8113583326339722},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.6359931230545044},{"id":"https://openalex.org/keywords/data-curation","display_name":"Data curation","score":0.630551815032959},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6019500494003296},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5895622372627258},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.49312493205070496},{"id":"https://openalex.org/keywords/raster-graphics","display_name":"Raster graphics","score":0.47966766357421875},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35684165358543396},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33982548117637634},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3255348205566406},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1104535162448883}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8113583326339722},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.6359931230545044},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.630551815032959},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6019500494003296},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5895622372627258},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.49312493205070496},{"id":"https://openalex.org/C181844469","wikidata":"https://www.wikidata.org/wiki/Q182270","display_name":"Raster graphics","level":2,"score":0.47966766357421875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35684165358543396},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33982548117637634},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3255348205566406},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1104535162448883},{"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D007256","descriptor_name":"Information Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007256","descriptor_name":"Information Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007256","descriptor_name":"Information Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D054852","descriptor_name":"Small Molecule Libraries","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D054852","descriptor_name":"Small Molecule Libraries","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D054852","descriptor_name":"Small Molecule Libraries","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1186/1471-2105-13-s17-s9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-13-s17-s9","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-13-S17-S9","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":"pmid:23282330","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/23282330","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:fdc02dbef04b40d796c8b3b499cb2610","is_oa":false,"landing_page_url":"https://doaj.org/article/fdc02dbef04b40d796c8b3b499cb2610","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 13, Iss Suppl 17, p S9 (2012)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:2521683","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3521388","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-13-s17-s9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-13-s17-s9","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-13-S17-S9","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320326787","display_name":"National Center for Genetic Engineering and Biotechnology","ror":"https://ror.org/047aswc67"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2170484170.pdf","grobid_xml":"https://content.openalex.org/works/W2170484170.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W142136654","https://openalex.org/W1578560356","https://openalex.org/W1601495365","https://openalex.org/W1966456689","https://openalex.org/W2021662118","https://openalex.org/W2033377040","https://openalex.org/W2051554764","https://openalex.org/W2064030835","https://openalex.org/W2069719501","https://openalex.org/W2077991901","https://openalex.org/W2095596879","https://openalex.org/W2111044246","https://openalex.org/W2117441847","https://openalex.org/W2118832478","https://openalex.org/W2127239015","https://openalex.org/W2136796599","https://openalex.org/W2141474275","https://openalex.org/W2141869602","https://openalex.org/W2160592517","https://openalex.org/W2165671627","https://openalex.org/W2167992389","https://openalex.org/W2168905447","https://openalex.org/W2597377917","https://openalex.org/W4210483668","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2093392189","https://openalex.org/W2701062589","https://openalex.org/W2743147667","https://openalex.org/W2773877060","https://openalex.org/W4308914582","https://openalex.org/W2386874685","https://openalex.org/W2060977224","https://openalex.org/W2914128081","https://openalex.org/W2368651715","https://openalex.org/W4280620143"],"abstract_inverted_index":{"BACKGROUND:":[0],"Manual":[1],"chemical":[2,32,56,89,122],"data":[3,16,123],"curation":[4,124],"from":[5,79,131,144],"publications":[6],"is":[7,70],"error-prone,":[8],"time":[9],"consuming,":[10],"and":[11,46,64,76,113,119,129,139],"hard":[12],"to":[13,27,41,72,92],"maintain":[14],"up-to-date":[15],"sets.":[17],"Automatic":[18],"information":[19,38,57,105],"extraction":[20,39,58],"can":[21,98,141],"be":[22,142],"used":[23],"as":[24],"a":[25,55,132],"tool":[26],"reduce":[28],"these":[29],"problems.":[30],"Since":[31],"structures":[33],"usually":[34],"described":[35],"in":[36,66],"images,":[37],"needs":[40],"combine":[42],"structure":[43,83],"image":[44,84],"recognition":[45,85],"text":[47,63,80,101],"mining":[48],"together.":[49],"RESULTS:":[50],"We":[51],"have":[52],"developed":[53],"ChemEx,":[54],"system.":[59],"ChemEx":[60,117],"processes":[61],"both":[62],"images":[65,91],"publications.":[67,136],"Text":[68],"annotator":[69],"able":[71],"extract":[73],"compound,":[74],"organism,":[75],"assay":[77,114],"entities":[78],"content":[81],"while":[82],"enables":[86],"translation":[87],"of":[88,106,135],"raster":[90],"machine":[93],"readable":[94],"format.":[95],"A":[96],"user":[97],"view":[99],"annotated":[100],"along":[102],"with":[103],"summarized":[104],"compounds,":[107,112,127],"organism":[108],"that":[109],"produces":[110],"those":[111],"tests.":[115],"CONCLUSIONS:":[116],"facilitates":[118],"speeds":[120],"up":[121],"by":[125],"extracting":[126],"organisms,":[128],"assays":[130],"large":[133],"collection":[134],"The":[137],"software":[138],"corpus":[140],"downloaded":[143],"http://www.biotec.or.th/isl/ChemEx.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":4},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
