{"id":"https://openalex.org/W2117055814","doi":"https://doi.org/10.1186/1758-2946-5-20","title":"Extracting and connecting chemical structures from text sources using chemicalize.org","display_name":"Extracting and connecting chemical structures from text sources using chemicalize.org","publication_year":2013,"publication_date":"2013-04-23","ids":{"openalex":"https://openalex.org/W2117055814","doi":"https://doi.org/10.1186/1758-2946-5-20","mag":"2117055814","pmid":"https://pubmed.ncbi.nlm.nih.gov/23618056"},"language":"en","primary_location":{"id":"doi:10.1186/1758-2946-5-20","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1758-2946-5-20","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/1758-2946-5-20","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","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/1758-2946-5-20","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039959378","display_name":"Christopher Southan","orcid":"https://orcid.org/0000-0001-9580-0446"},"institutions":[{"id":"https://openalex.org/I3025081897","display_name":"G\u00f6teborgs Stads","ror":"https://ror.org/03nd75281","country_code":"SE","type":"other","lineage":["https://openalex.org/I3025081897"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Christopher Southan","raw_affiliation_strings":["TW2Informatics Ltd, G\u00f6teborg, 42166, Sweden. cdsouthan@hotmail.com","TW2Informatics Ltd, G\u00f6teborg, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TW2Informatics Ltd, G\u00f6teborg, 42166, Sweden. cdsouthan@hotmail.com","institution_ids":["https://openalex.org/I3025081897"]},{"raw_affiliation_string":"TW2Informatics Ltd, G\u00f6teborg, Sweden","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091097543","display_name":"Andras Stracz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andras Stracz","raw_affiliation_strings":["ChemAxon Kft, Budapest, 1031, Hungary","ChemAxon Kft, Budapest, Hungary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ChemAxon Kft, Budapest, 1031, Hungary","institution_ids":[]},{"raw_affiliation_string":"ChemAxon Kft, Budapest, Hungary","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5039959378"],"corresponding_institution_ids":["https://openalex.org/I3025081897"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":1.9445,"has_fulltext":true,"cited_by_count":46,"citation_normalized_percentile":{"value":0.86195584,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"5","issue":"1","first_page":"20","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.8281999826431274,"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":0.8281999826431274,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.08349999785423279,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.007400000002235174,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pubchem","display_name":"PubChem","score":0.9451665878295898},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6991246342658997},{"id":"https://openalex.org/keywords/upload","display_name":"Upload","score":0.6316384077072144},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.569340169429779},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.49334731698036194},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.45875003933906555},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.361517071723938},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.31066662073135376},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.21232914924621582},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1624000072479248},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.09587520360946655}],"concepts":[{"id":"https://openalex.org/C158180186","wikidata":"https://www.wikidata.org/wiki/Q278487","display_name":"PubChem","level":2,"score":0.9451665878295898},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6991246342658997},{"id":"https://openalex.org/C71901391","wikidata":"https://www.wikidata.org/wiki/Q7126699","display_name":"Upload","level":2,"score":0.6316384077072144},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.569340169429779},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.49334731698036194},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.45875003933906555},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.361517071723938},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31066662073135376},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.21232914924621582},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1624000072479248},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.09587520360946655}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1186/1758-2946-5-20","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1758-2946-5-20","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/1758-2946-5-20","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":"pmid:23618056","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/23618056","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 cheminformatics","raw_type":null},{"id":"pmh:oai:europepmc.org:2646677","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3648358","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:10.1186/1758-2946-5-20","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1758-2946-5-20","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/1758-2946-5-20","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":[{"score":0.44999998807907104,"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2117055814.pdf","grobid_xml":"https://content.openalex.org/works/W2117055814.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1966456689","https://openalex.org/W1975767684","https://openalex.org/W1992251613","https://openalex.org/W1999488408","https://openalex.org/W2012833682","https://openalex.org/W2034354062","https://openalex.org/W2039063816","https://openalex.org/W2070347480","https://openalex.org/W2085398335","https://openalex.org/W2096541451","https://openalex.org/W2107931279","https://openalex.org/W2110455859","https://openalex.org/W2135505477","https://openalex.org/W2138010103","https://openalex.org/W2138922592","https://openalex.org/W2139007180","https://openalex.org/W2750911671","https://openalex.org/W4235440435"],"related_works":["https://openalex.org/W2104366126","https://openalex.org/W2547231910","https://openalex.org/W2235675062","https://openalex.org/W2177317049","https://openalex.org/W4293208996","https://openalex.org/W2169546341","https://openalex.org/W2127553917","https://openalex.org/W2013068027","https://openalex.org/W1505362105","https://openalex.org/W4211227887"],"abstract_inverted_index":{"BACKGROUND:":[0],"Exploring":[1],"bioactive":[2,337],"chemistry":[3,55,172,206,338],"requires":[4],"navigating":[5],"between":[6,261,281],"structures":[7,24,100,135,178,199,218,234],"and":[8,34,72,86,103,140,159,177,242,263,283,294,318,335],"data":[9,201],"from":[10,27,75,136,164,204,222,305],"a":[11,115,137,223],"variety":[12],"of":[13,31,118,132,143,225,272,277],"text-based":[14],"sources.":[15],"While":[16],"PubChem":[17,153],"currently":[18],"includes":[19],"approximately":[20],"16":[21],"million":[22,26],"document-extracted":[23],"(15":[25],"patents)":[28],"the":[29,130,141,150,182,270,275,295,300,319],"extent":[30],"public":[32],"inter-document":[33],"document-to-database":[35],"links":[36],"is":[37,56,321],"still":[38],"well":[39,187],"below":[40],"any":[41,306],"estimated":[42],"total,":[43],"especially":[44],"for":[45,94,214,258,274],"journal":[46],"articles.":[47],"A":[48,169],"major":[49],"expansion":[50],"in":[51,101,251,288,292,330],"access":[52],"to":[53,81,98,152,157,181,190,229,302],"text-entombed":[54],"enabled":[57],"by":[58,207],"chemicalize.org.":[59],"This":[60,267],"on-line":[61],"resource":[62],"can":[63],"process":[64],"IUPAC":[65,247],"names,":[66],"SMILES,":[67],"InChI":[68],"strings,":[69],"CAS":[70],"numbers":[71],"drug":[73,233],"names":[74,248],"pasted":[76],"text,":[77],"PDFs":[78,213],"or":[79,309],"URLs":[80],"generate":[82],"structures,":[83],"calculate":[84],"properties":[85],"launch":[87],"searches.":[88],"Here,":[89],"we":[90],"explore":[91],"its":[92],"utility":[93,271],"answering":[95],"questions":[96],"related":[97,228],"chemical":[99,278,333],"documents":[102,192,262,282],"where":[104],"these":[105],"overlap":[106],"with":[107,146,200,314],"database":[108],"records.":[109],"These":[110],"aspects":[111],"are":[112],"illustrated":[113],"using":[114],"common":[116,205],"theme":[117],"Dipeptidyl":[119],"Peptidase":[120],"4":[121],"(DPPIV)":[122],"inhibitors.":[123],"RESULTS:":[124],"Full-text":[125],"open":[126,316],"URL":[127],"sources":[128],"facilitated":[129],"download":[131],"over":[133],"1400":[134],"DPPIV":[138,170,230],"patent":[139],"alignment":[142],"specific":[144],"examples":[145],"IC50":[147],"data.":[148],"Uploading":[149],"SMILES":[151],"revealed":[154],"extensive":[155],"linking":[156],"patents":[158],"papers,":[160],"including":[161,285],"prior":[162],"submissions":[163],"chemicalize.org":[165,273,296],"as":[166,186,188],"submitting":[167],"source.":[168,311],"medicinal":[171,331],"paper":[173],"was":[174],"completely":[175],"extracted":[176,221],"were":[179,202,219],"aligned":[180],"activity":[183],"results":[184],"table,":[185],"linked":[189,250],"other":[191,315,336],"via":[193],"PubChem.":[194,252],"In":[195],"both":[196],"cases,":[197],"key":[198],"partitioned":[203],"dividing":[208],"them":[209],"into":[210],"individual":[211],"new":[212],"conversion.":[215],"Over":[216],"500":[217],"also":[220],"batch":[224],"PubMed":[226],"abstracts":[227],"inhibition.":[231],"The":[232],"could":[235],"be":[236],"stepped":[237],"through":[238],"each":[239],"text":[240,304],"occurrence":[241],"included":[243],"some":[244],"converted":[245],"MeSH-only":[246],"not":[249],"Performing":[253],"set":[254],"intersections":[255],"proved":[256],"effective":[257],"detecting":[259],"compounds-in-common":[260],"merged":[264],"extractions.":[265],"CONCLUSION:":[266],"work":[268],"demonstrates":[269],"exploration":[276],"structure":[279,286],"connectivity":[280],"databases,":[284],"searches":[287,291],"PubChem,":[289],"InChIKey":[290],"Google":[293],"archive.":[297],"It":[298,312,325],"has":[299],"flexibility":[301],"extract":[303],"internal,":[307],"external":[308],"Web":[310],"synergizes":[313],"tools":[317],"application":[320],"undergoing":[322],"continued":[323],"development.":[324],"should":[326],"thus":[327],"facilitate":[328],"progress":[329],"chemistry,":[332],"biology":[334],"domains.":[339]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2025-10-10T00:00:00"}