{"id":"https://openalex.org/W2133287192","doi":"https://doi.org/10.1186/1758-2946-4-s1-p19","title":"Large scale chemical patent mining with UIMA and UNICORE","display_name":"Large scale chemical patent mining with UIMA and UNICORE","publication_year":2012,"publication_date":"2012-05-01","ids":{"openalex":"https://openalex.org/W2133287192","doi":"https://doi.org/10.1186/1758-2946-4-s1-p19","mag":"2133287192"},"language":"en","primary_location":{"id":"doi:10.1186/1758-2946-4-s1-p19","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1758-2946-4-s1-p19","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/1758-2946-4-S1-P19","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"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":"Journal of Cheminformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/1758-2946-4-S1-P19","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001018442","display_name":"Alexander Klenner","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098248","display_name":"Fraunhofer Institute for Algorithms and Scientific Computing","ror":"https://ror.org/00trw9c49","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210098248","https://openalex.org/I4923324"]},{"id":"https://openalex.org/I4923324","display_name":"Fraunhofer-Gesellschaft","ror":"https://ror.org/05hkkdn48","country_code":"DE","type":"government","lineage":["https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Alexander Klenner","raw_affiliation_strings":["Fraunhofer-Institute for Algorithms and Scientific Computing (SCAI), Sankt Augustin, 53754, Germany","Fraunhofer\u2010Institute for Algorithms and Scientific Computing (SCAI), Sankt Augustin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer-Institute for Algorithms and Scientific Computing (SCAI), Sankt Augustin, 53754, Germany","institution_ids":["https://openalex.org/I4210098248"]},{"raw_affiliation_string":"Fraunhofer\u2010Institute for Algorithms and Scientific Computing (SCAI), Sankt Augustin, Germany","institution_ids":["https://openalex.org/I4923324"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021117163","display_name":"Sandra Bergmann","orcid":null},"institutions":[{"id":"https://openalex.org/I171892758","display_name":"Forschungszentrum J\u00fclich","ror":"https://ror.org/02nv7yv05","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I171892758"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sandra Bergmann","raw_affiliation_strings":["Forschungszentrum Juelich GmbH, Juelich, 52425, Germany","Forschungszentrum Juelich GmbH, Juelich  Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Forschungszentrum Juelich GmbH, Juelich, 52425, Germany","institution_ids":["https://openalex.org/I171892758"]},{"raw_affiliation_string":"Forschungszentrum Juelich GmbH, Juelich  Germany","institution_ids":["https://openalex.org/I171892758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108754338","display_name":"Marc Zimmermann","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098248","display_name":"Fraunhofer Institute for Algorithms and Scientific Computing","ror":"https://ror.org/00trw9c49","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210098248","https://openalex.org/I4923324"]},{"id":"https://openalex.org/I4923324","display_name":"Fraunhofer-Gesellschaft","ror":"https://ror.org/05hkkdn48","country_code":"DE","type":"government","lineage":["https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Marc Zimmermann","raw_affiliation_strings":["Fraunhofer-Institute for Algorithms and Scientific Computing (SCAI), Sankt Augustin, 53754, Germany","Fraunhofer\u2010Institute for Algorithms and Scientific Computing (SCAI), Sankt Augustin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer-Institute for Algorithms and Scientific Computing (SCAI), Sankt Augustin, 53754, Germany","institution_ids":["https://openalex.org/I4210098248"]},{"raw_affiliation_string":"Fraunhofer\u2010Institute for Algorithms and Scientific Computing (SCAI), Sankt Augustin, Germany","institution_ids":["https://openalex.org/I4923324"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040046189","display_name":"Mathilde Romberg","orcid":"https://orcid.org/0000-0002-6135-3817"},"institutions":[{"id":"https://openalex.org/I171892758","display_name":"Forschungszentrum J\u00fclich","ror":"https://ror.org/02nv7yv05","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I171892758"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mathilde Romberg","raw_affiliation_strings":["Forschungszentrum Juelich GmbH, Juelich, 52425, Germany","Forschungszentrum Juelich GmbH, Juelich  Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Forschungszentrum Juelich GmbH, Juelich, 52425, Germany","institution_ids":["https://openalex.org/I171892758"]},{"raw_affiliation_string":"Forschungszentrum Juelich GmbH, Juelich  Germany","institution_ids":["https://openalex.org/I171892758"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5001018442"],"corresponding_institution_ids":["https://openalex.org/I4210098248","https://openalex.org/I4923324"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":0.2687,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.59123017,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"4","issue":"S1","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":0.9625999927520752,"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":0.9625999927520752,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9473000168800354,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8254404067993164},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.8049513697624207},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6639735102653503},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5689737200737},{"id":"https://openalex.org/keywords/graphical-user-interface","display_name":"Graphical user interface","score":0.5542525053024292},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5461075305938721},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5340190529823303},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.49677926301956177},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.44237253069877625},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.4101918041706085},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3853805363178253},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.17841801047325134},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14508932828903198},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10204681754112244}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8254404067993164},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.8049513697624207},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6639735102653503},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5689737200737},{"id":"https://openalex.org/C37789001","wikidata":"https://www.wikidata.org/wiki/Q782543","display_name":"Graphical user interface","level":2,"score":0.5542525053024292},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5461075305938721},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5340190529823303},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.49677926301956177},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.44237253069877625},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.4101918041706085},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3853805363178253},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17841801047325134},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14508932828903198},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10204681754112244},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1186/1758-2946-4-s1-p19","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1758-2946-4-s1-p19","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/1758-2946-4-S1-P19","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"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":"Journal of Cheminformatics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:9883d93167a94b09a5d7e0da82ac48df","is_oa":true,"landing_page_url":"https://doaj.org/article/9883d93167a94b09a5d7e0da82ac48df","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Cheminformatics, Vol 4, Iss Suppl 1, p P19 (2012)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:3341337","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3341337","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Cheminform","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/1758-2946-4-s1-p19","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1758-2946-4-s1-p19","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/1758-2946-4-S1-P19","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"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":"Journal of Cheminformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2133287192.pdf","grobid_xml":"https://content.openalex.org/works/W2133287192.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2358755282","https://openalex.org/W2625833328","https://openalex.org/W1533177136","https://openalex.org/W4380994516","https://openalex.org/W2295917292"],"abstract_inverted_index":{"Finding":[0],"information":[1,35],"about":[2],"annotated":[3,148,216],"chemical":[4,67],"reactions":[5],"for":[6,15,65,79,85,122,207],"drugs":[7],"and":[8,30,39,58,83,109,164,170,190,212],"small":[9],"compounds":[10],"is":[11,21,36,126,145,178,218],"a":[12,37,146],"crucial":[13],"step":[14],"pharmaceutical":[16],"industries.":[17],"This":[18],"data":[19],"often":[20],"presented":[22],"in":[23,180,210],"form":[24],"of":[25,33,52,106,139,185],"unstructured":[26],"documents":[27],"(especially":[28],"patents)":[29],"manual":[31],"extraction":[32],"this":[34,119],"time-":[38],"cost":[40],"inefficient":[41],"effort.\r\n\r\nIn":[42],"our":[43,186],"project":[44],"UIMA-HPC":[45],"[1],":[46],"we":[47],"describe":[48],"the":[49,93,98,107,129,173,202],"combined":[50],"usage":[51],"Unstructured":[53],"Information":[54],"Managment":[55],"Architecture":[56],"(UIMA)":[57],"Uniform":[59],"Interface":[60],"to":[61,113],"Computing":[62],"Recources":[63],"(UNICORE)":[64],"large-scale":[66],"patent":[68],"mining.":[69],"Our":[70],"approach":[71],"will":[72],"incorporate":[73],"existing":[74],"software":[75],"such":[76],"as":[77],"chemoCR":[78],"image":[80],"processing":[81],"(image-to-structure)":[82],"OCR":[84],"text":[86,211],"reconstruction.":[87],"All":[88],"components":[89,105],"are":[90,160,192,197],"wrapped":[91],"inside":[92],"UIMA":[94,99,141,187],"framework":[95,100,131],"pipeline.":[96],"Using":[97],"ensures":[101],"compatibility":[102],"between":[103],"different":[104],"pipeline":[108],"makes":[110],"it":[111],"possible":[112],"connect":[114],"arbitrary":[115],"annotation":[116],"modules":[117],"into":[118],"system.":[120],"Scale-out":[121],"large":[123],"document":[124],"collections":[125],"achieved":[127],"by":[128,162,172],"UNICORE":[130,203],"on":[132,199],"High":[133],"Performance":[134],"Clusters,":[135],"which":[136],"enables":[137],"parallelization":[138],"all":[140,152],"nodes.":[142],"The":[143],"aim":[144],"fully":[147],"pdf":[149],"collection":[150],"where":[151],"biomedical":[153],"entities":[154],"(compound":[155],"names,":[156],"reaction":[157],"schemes,":[158],"etc.)":[159],"connected":[161],"references":[163],"thus":[165],"can":[166],"be":[167],"easily":[168],"browsed":[169],"searched":[171],"user.":[174],"Planned":[175],"schematic":[176],"workflow":[177,184],"shown":[179],"Figure":[181],"\u200bFigure11.\r\n\r\n\r\n\r\nFigure":[182],"1\r\n\r\nPlanned":[183],"framework.":[188,204],"'Recognition'":[189],"'annotation'":[191],"CPU":[193],"intensive":[194],"parts":[195],"that":[196],"parallelized":[198],"demand":[200],"using":[201],"'Merging'":[205],"checks":[206],"cross-annotations":[208],"(entity":[209],"image).":[213],"Finally,":[214],"an":[215],"PDF":[217],"...":[219]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-19T15:47:20.252518","created_date":"2016-06-24T00:00:00"}
