{"id":"https://openalex.org/W2136794542","doi":"https://doi.org/10.1186/1758-2946-7-s1-s5","title":"LeadMine: a grammar and dictionary driven approach to entity recognition","display_name":"LeadMine: a grammar and dictionary driven approach to entity recognition","publication_year":2015,"publication_date":"2015-01-19","ids":{"openalex":"https://openalex.org/W2136794542","doi":"https://doi.org/10.1186/1758-2946-7-s1-s5","mag":"2136794542","pmid":"https://pubmed.ncbi.nlm.nih.gov/25810776"},"language":"en","primary_location":{"id":"doi:10.1186/1758-2946-7-s1-s5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1758-2946-7-s1-s5","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/1758-2946-7-S1-S5","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/10.1186/1758-2946-7-S1-S5","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021129795","display_name":"Daniel M. Lowe","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel M Lowe","raw_affiliation_strings":["NextMove Software Ltd, Innovation Centre, Unit 23, Science Park, Milton Road, Cambridge, UK","NextMove Software Ltd, Innovation Centre, Unit 23, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NextMove Software Ltd, Innovation Centre, Unit 23, Science Park, Milton Road, Cambridge, UK","institution_ids":[]},{"raw_affiliation_string":"NextMove Software Ltd, Innovation Centre, Unit 23, Cambridge, UK","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064515321","display_name":"Roger A. Sayle","orcid":"https://orcid.org/0000-0003-0188-471X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Roger A Sayle","raw_affiliation_strings":["NextMove Software Ltd, Innovation Centre, Unit 23, Science Park, Milton Road, Cambridge, UK","NextMove Software Ltd, Innovation Centre, Unit 23, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NextMove Software Ltd, Innovation Centre, Unit 23, Science Park, Milton Road, Cambridge, UK","institution_ids":[]},{"raw_affiliation_string":"NextMove Software Ltd, Innovation Centre, Unit 23, Cambridge, UK","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5064515321"],"corresponding_institution_ids":[],"apc_list":{"value":2190,"currency":"USD","value_usd":2190},"apc_paid":{"value":2190,"currency":"USD","value_usd":2190},"fwci":2.8922,"has_fulltext":true,"cited_by_count":72,"citation_normalized_percentile":{"value":0.91540845,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"7","issue":"S1","first_page":"S5","last_page":"S5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.8546000123023987,"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":0.8546000123023987,"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":0.052299998700618744,"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/T11719","display_name":"Data Quality and Management","score":0.01209999993443489,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"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":0.8608179092407227},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7326271533966064},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6798239946365356},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.6493456363677979},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.5243611335754395},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.4959469735622406},{"id":"https://openalex.org/keywords/rule-based-machine-translation","display_name":"Rule-based machine translation","score":0.47496792674064636},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4691188633441925},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.45050978660583496},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.4310377538204193},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.35963642597198486},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.20706889033317566}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8608179092407227},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7326271533966064},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6798239946365356},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.6493456363677979},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.5243611335754395},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.4959469735622406},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.47496792674064636},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4691188633441925},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.45050978660583496},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.4310377538204193},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35963642597198486},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.20706889033317566},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1186/1758-2946-7-s1-s5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1758-2946-7-s1-s5","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/1758-2946-7-S1-S5","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:25810776","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/25810776","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:3334612","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4331695","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:10.1186/1758-2946-7-s1-s5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1758-2946-7-s1-s5","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/1758-2946-7-S1-S5","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/4","display_name":"Quality Education","score":0.8299999833106995}],"awards":[],"funders":[{"id":"https://openalex.org/F4320307770","display_name":"AstraZeneca","ror":"https://ror.org/04r9x1a08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2136794542.pdf","grobid_xml":"https://content.openalex.org/works/W2136794542.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W1601495365","https://openalex.org/W1991154713","https://openalex.org/W2009660063","https://openalex.org/W2033377040","https://openalex.org/W2095596879","https://openalex.org/W2101553882","https://openalex.org/W2121244856","https://openalex.org/W2133527736","https://openalex.org/W2135505477","https://openalex.org/W2149369282","https://openalex.org/W2165671627"],"related_works":["https://openalex.org/W2280422768","https://openalex.org/W3143197806","https://openalex.org/W4252555497","https://openalex.org/W3121175838","https://openalex.org/W3016293053","https://openalex.org/W1690653314","https://openalex.org/W2401723157","https://openalex.org/W2065055572","https://openalex.org/W2017988763","https://openalex.org/W2118045671"],"abstract_inverted_index":{"BACKGROUND:":[0],"Chemical":[1],"entity":[2,46,53,89,264],"recognition":[3,63],"has":[4,23],"traditionally":[5],"been":[6],"performed":[7],"by":[8,66],"machine":[9,222,226],"learning":[10,223,227],"approaches.":[11,224],"Here":[12],"we":[13],"describe":[14],"an":[15,45,52,88],"approach":[16,22,238,251],"using":[17],"grammars":[18,113],"and":[19,114,164,177,192,204,248],"dictionaries.":[20],"This":[21],"the":[24,27,42,95,128,147,160,198,215,219,241,245],"advantage":[25],"that":[26,127],"entities":[28,163,243],"found":[29],"can":[30,75,207,261],"be":[31,48,60,76],"directly":[32,239],"related":[33],"to":[34,47,86,102,131,158,165,172,244],"a":[35,91,108,142],"given":[36],"grammar":[37],"or":[38],"dictionary,":[39],"which":[40,57,260],"allows":[41,253],"type":[43],"of":[44,97,110,135,162,218,232,255],"known":[49],"and,":[50],"if":[51,70],"is":[54,64,68,81],"misannotated,":[55],"indicates":[56],"resource":[58],"should":[59],"corrected.":[61,77],"As":[62],"driven":[65],"what":[67],"expected,":[69],"spelling":[71],"errors":[72,80,256],"occur,":[73],"they":[74],"Correcting":[78],"such":[79],"highly":[82],"useful":[83],"when":[84],"attempting":[85],"lookup":[87],"in":[90,94,221,257],"database":[92],"or,":[93],"case":[96],"chemical":[98,137],"names,":[99],"converting":[100],"them":[101],"structures.":[103],"RESULTS:":[104],"Our":[105,152,181,250],"system":[106,154],"uses":[107],"mixture":[109],"expertly":[111],"curated":[112],"dictionaries,":[115],"as":[116,118,212,214,233],"well":[117],"dictionaries":[119,247],"automatically":[120],"derived":[121],"from":[122],"public":[123],"resources.":[124],"We":[125],"show":[126],"heuristics":[129],"developed":[130],"filter":[132],"our":[133,237],"dictionary":[134,145,205],"trivial":[136],"names":[138],"(from":[139],"PubChem)":[140],"yields":[141],"better":[143],"performing":[144],"than":[146],"previously":[148],"published":[149],"Jochem":[150],"dictionary.":[151],"final":[153],"performs":[155],"post-processing":[156],"steps":[157,169],"modify":[159],"boundaries":[161],"detect":[166],"abbreviations.":[167],"These":[168],"are":[170,229],"shown":[171],"significantly":[173],"improve":[174],"performance":[175],"(2.6%":[176],"4.0%":[178],"F1-score":[179],"respectively).":[180],"complete":[182],"system,":[183],"with":[184,263],"incremental":[185],"post-BioCreative":[186],"workshop":[187],"improvements,":[188],"achieves":[189],"89.9%":[190],"precision":[191],"85.4%":[193],"recall":[194],"(87.6%":[195],"F1-score)":[196],"on":[197],"CHEMDNER":[199],"test":[200],"set.":[201],"CONCLUSIONS:":[202],"Grammar":[203],"approaches":[206,228],"produce":[208],"results":[209],"at":[210],"least":[211],"good":[213],"current":[216],"state":[217],"art":[220],"While":[225],"commonly":[230],"thought":[231],"\"black":[234],"box\"":[235],"systems,":[236],"links":[240],"output":[242],"input":[246],"grammars.":[249],"also":[252],"correction":[254],"detected":[258],"entities,":[259],"assist":[262],"resolution.":[265]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":17},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}