{"id":"https://openalex.org/W7224891544","doi":"https://doi.org/10.5281/zenodo.23803806","title":"BChemXtract: Automated Extraction and FAIRification of Chemical Structures from Scientific Publications","display_name":"BChemXtract: Automated Extraction and FAIRification of Chemical Structures from Scientific Publications","publication_year":2026,"publication_date":"2026-10-30","ids":{"openalex":"https://openalex.org/W7224891544","doi":"https://doi.org/10.5281/zenodo.23803806"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.23803806","doi":"https://doi.org/10.5281/zenodo.23803806","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23803806","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.23803806","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051423642","display_name":"Felix B\u00e4nsch","orcid":"https://orcid.org/0000-0001-8973-8463","observed_orcids":["https://orcid.org/0000-0001-8973-8463"]},"institutions":[{"id":"https://openalex.org/I2801587414","display_name":"Beilstein-Institut","ror":"https://ror.org/05jdrrw50","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I2801587414"]},{"id":"https://openalex.org/I76198965","display_name":"Friedrich Schiller University Jena","ror":"https://ror.org/05qpz1x62","country_code":"DE","type":"education","lineage":["https://openalex.org/I76198965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"B\u00e4nsch, Felix","raw_affiliation_strings":["Beilstein-Institut","Friedrich Schiller University Jena"],"raw_orcid":"https://orcid.org/0000-0001-8973-8463","affiliations":[{"raw_affiliation_string":"Beilstein-Institut","institution_ids":["https://openalex.org/I2801587414"]},{"raw_affiliation_string":"Friedrich Schiller University Jena","institution_ids":["https://openalex.org/I76198965"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017832889","display_name":"Kohulan Rajan","orcid":"https://orcid.org/0000-0003-1066-7792","observed_orcids":["https://orcid.org/0000-0003-1066-7792"]},"institutions":[{"id":"https://openalex.org/I2801587414","display_name":"Beilstein-Institut","ror":"https://ror.org/05jdrrw50","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I2801587414"]},{"id":"https://openalex.org/I76198965","display_name":"Friedrich Schiller University Jena","ror":"https://ror.org/05qpz1x62","country_code":"DE","type":"education","lineage":["https://openalex.org/I76198965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Rajan, Kohulan","raw_affiliation_strings":["Beilstein-Institut","Friedrich Schiller University Jena"],"raw_orcid":"https://orcid.org/0000-0003-1066-7792","affiliations":[{"raw_affiliation_string":"Beilstein-Institut","institution_ids":["https://openalex.org/I2801587414"]},{"raw_affiliation_string":"Friedrich Schiller University Jena","institution_ids":["https://openalex.org/I76198965"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081315189","display_name":"Markus Nietfeld","orcid":"https://orcid.org/0000-0001-7786-3005","observed_orcids":["https://orcid.org/0000-0001-7786-3005"]},"institutions":[{"id":"https://openalex.org/I2801587414","display_name":"Beilstein-Institut","ror":"https://ror.org/05jdrrw50","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I2801587414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Nietfeld, Markus","raw_affiliation_strings":["Beilstein-Institut"],"raw_orcid":"https://orcid.org/0000-0001-7786-3005","affiliations":[{"raw_affiliation_string":"Beilstein-Institut","institution_ids":["https://openalex.org/I2801587414"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.89044077,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T11937","display_name":"Research Data Management Practices","score":0.1525000035762787,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11937","display_name":"Research Data Management Practices","score":0.1525000035762787,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10215","display_name":"Semantic Web and Ontologies","score":0.08810000121593475,"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"}},{"id":"https://openalex.org/T14330","display_name":"Library Science and Information Systems","score":0.07259999960660934,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/inchi","display_name":"InChI","score":0.5659999847412109},{"id":"https://openalex.org/keywords/fair-data","display_name":"FAIR data","score":0.7839999794960022},{"id":"https://openalex.org/keywords/chemical-information-extraction","display_name":"chemical information extraction","score":0.34200000762939453},{"id":"https://openalex.org/keywords/pubchem","display_name":"PubChem","score":0.7350000143051147},{"id":"https://openalex.org/keywords/chemical-abbreviations","display_name":"chemical abbreviations","score":0.4860000014305115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.717199981212616},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.527400016784668},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5205000042915344},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.4507000148296356},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.4311000108718872},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.4255000054836273},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40450000762939453},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.4016000032424927},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.3815999925136566},{"id":"https://openalex.org/C125832229","wikidata":"https://www.wikidata.org/wiki/Q6503924","display_name":"Chemical nomenclature","level":2,"score":0.37220001220703125},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.29499998688697815},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2924000024795532},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.2757999897003174},{"id":"https://openalex.org/C68476402","wikidata":"https://www.wikidata.org/wiki/Q1456936","display_name":"Table of contents","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.2578999996185303}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.23803806","doi":"https://doi.org/10.5281/zenodo.23803806","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23803806","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},{"id":"doi:10.5281/zenodo.23803807","doi":"https://doi.org/10.5281/zenodo.23803807","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23803807","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.5281/zenodo.23803806","doi":"https://doi.org/10.5281/zenodo.23803806","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23803806","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W7168138616","https://openalex.org/W7202381636"],"related_works":["https://openalex.org/W7221519280","https://openalex.org/W2117055814","https://openalex.org/W4386001223","https://openalex.org/W3130247384","https://openalex.org/W7095155926","https://openalex.org/W2160592517","https://openalex.org/W2170484170","https://openalex.org/W7100061033","https://openalex.org/W6931264825","https://openalex.org/W2974323528"],"abstract_inverted_index":{"Chemical":[0],"structures":[1,39,67,82,115],"are":[2,83],"published":[3],"as":[4,92],"images,":[5],"which":[6],"makes":[7],"them":[8,21],"inappropriate":[9],"for":[10],"database":[11],"indexing,":[12],"structure":[13],"search":[14],"and":[15,24,45,64,95,111,145],"computational":[16],"reuse.":[17],"Recognition":[18],"tools":[19],"recover":[20],"after":[22],"publication":[23],"cannot":[25],"restore":[26],"what":[27],"the":[28,42,66,69,77,80,89,102,146],"rendering":[29],"discarded.":[30],"BChemXtract":[31],"is":[32],"an":[33],"open-source":[34],"Java":[35],"library":[36],"that":[37],"extracts":[38],"directly":[40],"from":[41,55,59],"ChemDraw":[43],"CDX":[44],"CDXML":[46],"files":[47],"authors":[48],"already":[49],"submit.":[50],"It":[51],"separates":[52],"chemical":[53],"fragments":[54],"annotations,":[56],"expands":[57],"abbreviations":[58],"a":[60,123,131,142],"curated":[61],"lookup":[62],"table":[63],"converts":[65],"with":[68,116,136,141],"Chemistry":[70,107],"Development":[71],"Kit":[72],"into":[73],"standard":[74],"identifiers.":[75],"In":[76],"Beilstein":[78,103],"Journals":[79],"extracted":[81],"validated":[84],"by":[85],"hand,":[86],"embedded":[87],"in":[88,97,118],"article":[90],"metadata":[91],"Schema.org":[93],"JSON-LD":[94],"deposited":[96],"PubChem.":[98],"Volume":[99],"20":[100],"of":[101,105,127],"Journal":[104],"Organic":[106],"(BJOC),":[108],"2993":[109],"figures":[110],"schemes,":[112],"yielded":[113],"23,320":[114],"InChIs":[117],"under":[119],"two":[120],"minutes.":[121],"On":[122],"225-file":[124],"benchmark":[125,147],"98.2%":[126],"unique":[128],"substances":[129],"got":[130],"valid":[132],"InChI,":[133],"against":[134],"14.2%":[135],"Open":[137],"Babel.":[138],"MIT":[139],"licence,":[140],"web":[143],"application":[144],"corpus.":[148],"Library:":[149],"github.com/beilstein-institut/bchemxtractWeb":[150],"application:":[151],"cheminfo.beilstein.org/bchemxtract":[152]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-10-31T00:00:00"}
