{"id":"https://openalex.org/W3159789740","doi":"https://doi.org/10.1186/s13321-021-00538-8","title":"DECIMER 1.0: deep learning for chemical image recognition using transformers","display_name":"DECIMER 1.0: deep learning for chemical image recognition using transformers","publication_year":2021,"publication_date":"2021-08-17","ids":{"openalex":"https://openalex.org/W3159789740","doi":"https://doi.org/10.1186/s13321-021-00538-8","mag":"3159789740","pmid":"https://pubmed.ncbi.nlm.nih.gov/34404468"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-021-00538-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-021-00538-8","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-021-00538-8","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/track/pdf/10.1186/s13321-021-00538-8","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017832889","display_name":"Kohulan Rajan","orcid":"https://orcid.org/0000-0003-1066-7792"},"institutions":[{"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":"Kohulan Rajan","raw_affiliation_strings":["Institute for Inorganic and Analytical Chemistry, Friedrich-Schiller-University Jena, Lessingstr. 8, 07743, Jena, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Inorganic and Analytical Chemistry, Friedrich-Schiller-University Jena, Lessingstr. 8, 07743, Jena, Germany","institution_ids":["https://openalex.org/I76198965"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089744377","display_name":"Achim Zielesny","orcid":"https://orcid.org/0000-0003-0722-4229"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Achim Zielesny","raw_affiliation_strings":["Institute for Bioinformatics and Chemoinformatics, Westphalian University of Applied Sciences, August-Schmidt-Ring 10, 45665, Recklinghausen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Bioinformatics and Chemoinformatics, Westphalian University of Applied Sciences, August-Schmidt-Ring 10, 45665, Recklinghausen, Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040194803","display_name":"Christoph Steinbeck","orcid":"https://orcid.org/0000-0001-6966-0814"},"institutions":[{"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":true,"raw_author_name":"Christoph Steinbeck","raw_affiliation_strings":["Institute for Inorganic and Analytical Chemistry, Friedrich-Schiller-University Jena, Lessingstr. 8, 07743, Jena, Germany. christoph.steinbeck@uni-jena.de","Institute for Inorganic and Analytical Chemistry, Friedrich-Schiller-University Jena, Lessingstr. 8, 07743, Jena, Germany"],"raw_orcid":"https://orcid.org/0000-0001-6966-0814","affiliations":[{"raw_affiliation_string":"Institute for Inorganic and Analytical Chemistry, Friedrich-Schiller-University Jena, Lessingstr. 8, 07743, Jena, Germany. christoph.steinbeck@uni-jena.de","institution_ids":["https://openalex.org/I76198965"]},{"raw_affiliation_string":"Institute for Inorganic and Analytical Chemistry, Friedrich-Schiller-University Jena, Lessingstr. 8, 07743, Jena, Germany","institution_ids":["https://openalex.org/I76198965"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5040194803"],"corresponding_institution_ids":["https://openalex.org/I76198965"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1606,"currency":"EUR","value_usd":1732},"fwci":4.0525,"has_fulltext":true,"cited_by_count":70,"citation_normalized_percentile":{"value":0.95159327,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"13","issue":"1","first_page":"61","last_page":"61"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9940000176429749,"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":0.9940000176429749,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.9779000282287598,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.964900016784668,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7068548202514648},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5151130557060242},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.493552565574646},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.46361833810806274},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4042956829071045},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32961905002593994},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12090590596199036},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.11780276894569397}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7068548202514648},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5151130557060242},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.493552565574646},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.46361833810806274},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4042956829071045},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32961905002593994},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12090590596199036},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.11780276894569397},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1186/s13321-021-00538-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-021-00538-8","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-021-00538-8","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:34404468","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34404468","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:doaj.org/article:c7830eb23e624b3a9de9aaf72f75ed14","is_oa":true,"landing_page_url":"https://doaj.org/article/c7830eb23e624b3a9de9aaf72f75ed14","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 13, Iss 1, Pp 1-16 (2021)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:8369700","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8369700","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"},{"id":"pmh:oai:www.db-thueringen.de:dbt_mods_00056071","is_oa":true,"landing_page_url":"https://www.db-thueringen.de/receive/dbt_mods_00056071","pdf_url":null,"source":{"id":"https://openalex.org/S4306400120","display_name":"Common Library Network (Der Gemeinsame Bibliotheksverbund)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210149878","host_organization_name":"Verbundzentrale des GBV","host_organization_lineage":["https://openalex.org/I4210149878"],"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":"article"}],"best_oa_location":{"id":"doi:10.1186/s13321-021-00538-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-021-00538-8","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-021-00538-8","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320313941","display_name":"Friedrich-Schiller-Universit\u00e4t Jena","ror":"https://ror.org/05qpz1x62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3159789740.pdf","grobid_xml":"https://content.openalex.org/works/W3159789740.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W1508604947","https://openalex.org/W1522301498","https://openalex.org/W1966456689","https://openalex.org/W1975147762","https://openalex.org/W2031942128","https://openalex.org/W2042126044","https://openalex.org/W2108598243","https://openalex.org/W2114704115","https://openalex.org/W2133564696","https://openalex.org/W2136623753","https://openalex.org/W2145870108","https://openalex.org/W2148797284","https://openalex.org/W2172216479","https://openalex.org/W2183341477","https://openalex.org/W2271840356","https://openalex.org/W2416943854","https://openalex.org/W2523785361","https://openalex.org/W2610394652","https://openalex.org/W2626778328","https://openalex.org/W2766447205","https://openalex.org/W2895677720","https://openalex.org/W2899070097","https://openalex.org/W2950178297","https://openalex.org/W2955425717","https://openalex.org/W2963734039","https://openalex.org/W3007750971","https://openalex.org/W3009321976","https://openalex.org/W3013318641","https://openalex.org/W3035160371","https://openalex.org/W3045928028","https://openalex.org/W3085821739","https://openalex.org/W3092396754","https://openalex.org/W3094640617","https://openalex.org/W3097598035","https://openalex.org/W3103383152","https://openalex.org/W3127736057","https://openalex.org/W3130247384","https://openalex.org/W3133325765","https://openalex.org/W3138074128","https://openalex.org/W3203895579","https://openalex.org/W3204820152","https://openalex.org/W4232500930"],"related_works":["https://openalex.org/W2731899572","https://openalex.org/W2961085424","https://openalex.org/W3215138031","https://openalex.org/W4306674287","https://openalex.org/W3009238340","https://openalex.org/W4360585206","https://openalex.org/W4321369474","https://openalex.org/W4285208911","https://openalex.org/W3046775127","https://openalex.org/W3082895349"],"abstract_inverted_index":{"The":[0,33,90],"amount":[1],"of":[2,37,142,149,160,186],"data":[3,38],"available":[4,26],"on":[5],"chemical":[6,63,150,187],"structures":[7,188],"and":[8,35,56,66,192],"their":[9],"properties":[10],"has":[11],"increased":[12],"steadily":[13],"over":[14],"the":[15,23,82,103,107,132,140,167],"past":[16],"decades.":[17],"In":[18,59,134,164],"particular,":[19],"articles":[20,41],"published":[21],"before":[22],"mid-1990":[24],"are":[25,47,87],"only":[27],"in":[28,42],"printed":[29],"or":[30],"scanned":[31],"form.":[32],"extraction":[34],"storage":[36],"from":[39,184],"those":[40],"a":[43,54,70,128,135,158,173],"publicly":[44],"accessible":[45],"database":[46],"desirable,":[48],"but":[49],"doing":[50],"this":[51,165],"manually":[52],"is":[53,171],"slow":[55],"error-prone":[57],"process.":[58],"order":[60],"to":[61,101,112,126,131,145],"extract":[62],"structure":[64,151],"depictions":[65,152,185,197],"convert":[67],"them":[68],"into":[69],"computer-readable":[71],"format,":[72],"Optical":[73],"Chemical":[74,95],"Structure":[75],"Recognition":[76],"(OCSR)":[77],"tools":[78,86],"were":[79,124],"developed":[80],"where":[81],"best":[83],"performing":[84],"OCSR":[85,104],"mostly":[88],"rule-based.":[89],"DECIMER":[91,169],"(Deep":[92],"lEarning":[93],"for":[94,196],"ImagE":[96],"Recognition)":[97],"project":[98],"was":[99],"launched":[100],"address":[102],"problem":[105],"with":[106,153,180,198],"latest":[108],"computational":[109],"intelligence":[110],"methods":[111],"provide":[113],"an":[114],"automated":[115],"open-source":[116],"software":[117],"solution.":[118],"Various":[119],"current":[120],"deep":[121],"learning":[122],"approaches":[123],"explored":[125],"seek":[127],"best-fitting":[129],"solution":[130],"problem.":[133],"preliminary":[136],"communication,":[137],"we":[138],"outlined":[139],"prospect":[141],"being":[143],"able":[144],"predict":[146,178],"SMILES":[147,179],"encodings":[148],"about":[154],"90%":[155],"accuracy":[156,183,195],"using":[157],"dataset":[159],"50-100":[161],"million":[162],"molecules.":[163],"article,":[166],"new":[168],"model":[170],"presented,":[172],"transformer-based":[174],"network,":[175],"which":[176],"can":[177],"above":[181,193],"96%":[182],"without":[189],"stereochemical":[190,199],"information":[191],"89%":[194],"information.":[200]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":21},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":14}],"updated_date":"2026-07-04T07:58:01.006859","created_date":"2025-10-10T00:00:00"}