{"id":"https://openalex.org/W4386884238","doi":"https://doi.org/10.1021/acs.jcim.3c00422","title":"ReactionDataExtractor 2.0: A Deep Learning Approach for Data Extraction from Chemical Reaction Schemes","display_name":"ReactionDataExtractor 2.0: A Deep Learning Approach for Data Extraction from Chemical Reaction Schemes","publication_year":2023,"publication_date":"2023-09-20","ids":{"openalex":"https://openalex.org/W4386884238","doi":"https://doi.org/10.1021/acs.jcim.3c00422","pmid":"https://pubmed.ncbi.nlm.nih.gov/37729111"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.3c00422","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.3c00422","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"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 Chemical Information and Modeling","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","datacite","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1021/acs.jcim.3c00422","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026250520","display_name":"Damian M. Wilary","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]},{"id":"https://openalex.org/I4210096386","display_name":"Bridge University","ror":"https://ror.org/00cbm0437","country_code":"SS","type":"education","lineage":["https://openalex.org/I4210096386"]}],"countries":["GB","SS"],"is_corresponding":false,"raw_author_name":"Damian M. Wilary","raw_affiliation_strings":["Cavendish Laboratory, Department of Physics, University of Cambridge, J. J. Thomson Avenue, Cambridge, CB3 0HE, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cavendish Laboratory, Department of Physics, University of Cambridge, J. J. Thomson Avenue, Cambridge, CB3 0HE, U.K","institution_ids":["https://openalex.org/I4210096386","https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068607578","display_name":"Jacqueline M. Cole","orcid":"https://orcid.org/0000-0002-1552-8743"},"institutions":[{"id":"https://openalex.org/I1286704778","display_name":"Rutherford Appleton Laboratory","ror":"https://ror.org/03gq8fr08","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1286704778","https://openalex.org/I162524378","https://openalex.org/I4210087105"]},{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]},{"id":"https://openalex.org/I4210096386","display_name":"Bridge University","ror":"https://ror.org/00cbm0437","country_code":"SS","type":"education","lineage":["https://openalex.org/I4210096386"]}],"countries":["GB","SS"],"is_corresponding":true,"raw_author_name":"Jacqueline M. Cole","raw_affiliation_strings":["Cavendish Laboratory, Department of Physics, University of Cambridge, J. J. Thomson Avenue, Cambridge, CB3 0HE, U.K","ISIS Neutron and Muon Source, STFC Rutherford Appleton Laboratory, Harwell Science and Innovation Campus, Didcot, Oxfordshire OX11 0QX, U.K"],"raw_orcid":"https://orcid.org/0000-0002-1552-8743","affiliations":[{"raw_affiliation_string":"Cavendish Laboratory, Department of Physics, University of Cambridge, J. J. Thomson Avenue, Cambridge, CB3 0HE, U.K","institution_ids":["https://openalex.org/I4210096386","https://openalex.org/I241749"]},{"raw_affiliation_string":"ISIS Neutron and Muon Source, STFC Rutherford Appleton Laboratory, Harwell Science and Innovation Campus, Didcot, Oxfordshire OX11 0QX, U.K","institution_ids":["https://openalex.org/I1286704778"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5068607578"],"corresponding_institution_ids":["https://openalex.org/I1286704778","https://openalex.org/I241749","https://openalex.org/I4210096386"],"apc_list":null,"apc_paid":null,"fwci":2.646,"has_fulltext":true,"cited_by_count":29,"citation_normalized_percentile":{"value":0.90894796,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"63","issue":"19","first_page":"6053","last_page":"6067"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9977999925613403,"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"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9977999925613403,"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/T11667","display_name":"Advanced Chemical Sensor Technologies","score":0.9814000129699707,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9725000262260437,"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":0.7944585084915161},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5664848685264587},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5356271862983704},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.5316869020462036},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4991724491119385},{"id":"https://openalex.org/keywords/cheminformatics","display_name":"Cheminformatics","score":0.46201056241989136},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4503253996372223},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4369988441467285},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.4331549406051636},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36231565475463867},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.1157720685005188}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7944585084915161},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5664848685264587},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5356271862983704},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5316869020462036},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4991724491119385},{"id":"https://openalex.org/C68762167","wikidata":"https://www.wikidata.org/wiki/Q910164","display_name":"Cheminformatics","level":2,"score":0.46201056241989136},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4503253996372223},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4369988441467285},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.4331549406051636},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36231565475463867},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.1157720685005188},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C147597530","wikidata":"https://www.wikidata.org/wiki/Q369472","display_name":"Computational chemistry","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},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":7,"locations":[{"id":"doi:10.1021/acs.jcim.3c00422","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.3c00422","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"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 Chemical Information and Modeling","raw_type":"journal-article"},{"id":"pmid:37729111","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37729111","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":"Journal of chemical information and modeling","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:10565829","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10565829","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10565829/pdf/ci3c00422.pdf","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 Chem Inf Model","raw_type":"Text"},{"id":"pmh:oai:www.repository.cam.ac.uk:1810/355852","is_oa":true,"landing_page_url":"https://www.repository.cam.ac.uk/handle/1810/355852","pdf_url":"https://www.repository.cam.ac.uk/bitstreams/524f6435-55a8-4559-9a4a-31ac42bbab91/download","source":{"id":"https://openalex.org/S4306401777","display_name":"Apollo (University of Cambridge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I241749","host_organization_name":"University of Cambridge","host_organization_lineage":["https://openalex.org/I241749"],"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":"Article"},{"id":"pmh:oai:www.repository.cam.ac.uk:1810/358086","is_oa":true,"landing_page_url":"https://www.repository.cam.ac.uk/handle/1810/358086","pdf_url":"https://www.repository.cam.ac.uk/bitstreams/c43b0026-99ce-4f00-b4ba-9ef089279722/download","source":{"id":"https://openalex.org/S4306401777","display_name":"Apollo (University of Cambridge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I241749","host_organization_name":"University of Cambridge","host_organization_lineage":["https://openalex.org/I241749"],"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":"Article"},{"id":"pmh:oai:purl.org/net/epubs:work/55304218","is_oa":true,"landing_page_url":"https://epubs.stfc.ac.uk/work/55304218","pdf_url":null,"source":{"id":"https://openalex.org/S4306400600","display_name":"ePubs (Science and Technology Facilities Council, Research Councils UK)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I162524378","host_organization_name":"Science and Technology Facilities Council","host_organization_lineage":["https://openalex.org/I162524378"],"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":"","raw_type":"Text"},{"id":"doi:10.17863/cam.100690","is_oa":true,"landing_page_url":"https://doi.org/10.17863/cam.100690","pdf_url":null,"source":{"id":"https://openalex.org/S7407050737","display_name":"Apollo","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.1021/acs.jcim.3c00422","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.3c00422","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"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 Chemical Information and Modeling","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1531024995","display_name":null,"funder_award_id":"RCSRF1819\\7\\10","funder_id":"https://openalex.org/F4320320005","funder_display_name":"Royal Academy of Engineering"}],"funders":[{"id":"https://openalex.org/F4320320005","display_name":"Royal Academy of Engineering","ror":"https://ror.org/0526snb40"},{"id":"https://openalex.org/F4320332535","display_name":"BASF Corporation","ror":"https://ror.org/002yzpx87"},{"id":"https://openalex.org/F4320334632","display_name":"Science and Technology Facilities Council","ror":"https://ror.org/057g20z61"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1966456689","https://openalex.org/W1975147762","https://openalex.org/W2001642682","https://openalex.org/W2021662118","https://openalex.org/W2051554764","https://openalex.org/W2069719501","https://openalex.org/W2134164499","https://openalex.org/W2160592517","https://openalex.org/W2193145675","https://openalex.org/W2523785361","https://openalex.org/W2559924584","https://openalex.org/W2808304511","https://openalex.org/W2884561390","https://openalex.org/W2949650786","https://openalex.org/W2953106684","https://openalex.org/W2953328958","https://openalex.org/W2963734039","https://openalex.org/W2964332384","https://openalex.org/W3013318641","https://openalex.org/W3018757597","https://openalex.org/W3047398431","https://openalex.org/W3094502228","https://openalex.org/W3097598035","https://openalex.org/W3106250896","https://openalex.org/W3159481202","https://openalex.org/W3159789740","https://openalex.org/W3194700752","https://openalex.org/W3200122731","https://openalex.org/W3201277766","https://openalex.org/W3202406646","https://openalex.org/W4221146106","https://openalex.org/W4225409008","https://openalex.org/W4229443452","https://openalex.org/W4281617541","https://openalex.org/W4283074682","https://openalex.org/W4293377385","https://openalex.org/W4296836559","https://openalex.org/W4297775537","https://openalex.org/W4301076899","https://openalex.org/W4307139584","https://openalex.org/W4382198765"],"related_works":["https://openalex.org/W1573015311","https://openalex.org/W2889938001","https://openalex.org/W4386509167","https://openalex.org/W3165034028","https://openalex.org/W1570419641","https://openalex.org/W4293771607","https://openalex.org/W2296499206","https://openalex.org/W132037564","https://openalex.org/W3210319767","https://openalex.org/W2393746579"],"abstract_inverted_index":{"Knowledge":[0],"in":[1,56,67],"the":[2,57,79],"chemical":[3,10,17,30,151,190],"domain":[4],"is":[5,19,172],"often":[6],"disseminated":[7],"graphically":[8],"via":[9],"reaction":[11,24,118],"schemes.":[12],"The":[13,166],"task":[14],"of":[15,29,59,70,81,95,117,169],"describing":[16],"transformations":[18],"greatly":[20],"simplified":[21],"by":[22,37,50,143],"introducing":[23],"schemes":[25,119],"that":[26,120,158],"are":[27,46,65],"composed":[28,116],"diagrams":[31],"and":[32,72,98,127,134,180],"symbols.":[33],"While":[34],"intuitively":[35],"understood":[36,49],"any":[38],"chemist,":[39],"like":[40],"most":[41],"graphical":[42],"representations,":[43],"such":[44],"drawings":[45],"not":[47],"easily":[48],"machines;":[51],"this":[52,105],"poses":[53],"a":[54,86,93,113,149,155],"challenge":[55],"context":[58],"data":[60,82,191],"extraction.":[61,83,192],"Currently":[62],"available":[63],"tools":[64],"limited":[66],"their":[68],"scope":[69],"extraction":[71],"require":[73],"manual":[74],"preprocessing,":[75],"thus":[76],"slowing":[77],"down":[78],"speed":[80,179],"We":[84,107],"present":[85],"new":[87],"tool,":[88],"ReactionDataExtractor":[89],"v2.0,":[90],"which":[91,174],"uses":[92],"combination":[94],"neural":[96],"networks":[97],"symbolic":[99],"artificial":[100],"intelligence":[101],"to":[102,148,154,177,182],"effectively":[103],"remove":[104],"barrier.":[106],"have":[108,160],"evaluated":[109],"our":[110,145,170],"tool":[111,171],"on":[112],"test":[114],"set":[115],"were":[121],"taken":[122],"from":[123],"open-source":[124],"journal":[125],"articles":[126],"realized":[128],"F1":[129],"score":[130],"metrics":[131,138],"between":[132],"75":[133],"96%.":[135],"These":[136],"evaluation":[137],"can":[139],"be":[140],"further":[141],"improved":[142],"tuning":[144],"object-detection":[146],"models":[147],"specific":[150],"subdomain":[152],"thanks":[153],"data-driven":[156],"approach":[157],"we":[159],"adopted":[161],"with":[162],"synthetically":[163],"generated":[164],"data.":[165],"system":[167],"architecture":[168],"modular,":[173],"allows":[175],"it":[176],"balance":[178],"accuracy":[181],"afford":[183],"an":[184],"autonomous,":[185],"high-throughput":[186],"solution":[187],"for":[188],"image-based":[189]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":3}],"updated_date":"2026-05-19T08:33:51.333923","created_date":"2025-10-10T00:00:00"}