{"id":"https://openalex.org/W2160091014","doi":"https://doi.org/10.1186/1758-2946-7-s1-s7","title":"A document processing pipeline for annotating chemical entities in scientific documents","display_name":"A document processing pipeline for annotating chemical entities in scientific documents","publication_year":2015,"publication_date":"2015-01-19","ids":{"openalex":"https://openalex.org/W2160091014","doi":"https://doi.org/10.1186/1758-2946-7-s1-s7","mag":"2160091014","pmid":"https://pubmed.ncbi.nlm.nih.gov/25810778"},"language":"en","primary_location":{"id":"doi:10.1186/1758-2946-7-s1-s7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1758-2946-7-s1-s7","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/1758-2946-7-S1-S7","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-S7","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072967999","display_name":"David Campos","orcid":"https://orcid.org/0000-0002-3448-2111"},"institutions":[{"id":"https://openalex.org/I2802805223","display_name":"Calouste Gulbenkian Foundation","ror":"https://ror.org/04yxemn98","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I2802805223"]}],"countries":["PT"],"is_corresponding":true,"raw_author_name":"David Campos","raw_affiliation_strings":["BMD Software, Lda., Rua Calouste Gulbenkian, 1, 3810-074 Aveiro, Portugal","BMD Software, Lda, Rua Calouste Gulbenkian, 1, 3810-074, Aveiro, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BMD Software, Lda., Rua Calouste Gulbenkian, 1, 3810-074 Aveiro, Portugal","institution_ids":["https://openalex.org/I2802805223"]},{"raw_affiliation_string":"BMD Software, Lda, Rua Calouste Gulbenkian, 1, 3810-074, Aveiro, Portugal","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073280030","display_name":"S\u00e9rgio Matos","orcid":"https://orcid.org/0000-0003-1941-3983"},"institutions":[{"id":"https://openalex.org/I60858718","display_name":"University of Aveiro","ror":"https://ror.org/00nt41z93","country_code":"PT","type":"education","lineage":["https://openalex.org/I60858718"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"S\u00e9rgio Matos","raw_affiliation_strings":["DETI/IEETA, Universidade de Aveiro, Campus Universit\u00b4ario de Santiago, 3810-193 Aveiro, Portugal","DETI/IEETA, Universidade de Aveiro, Campus Universit\u00b4ario de Santiago, 3810-193, Aveiro, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DETI/IEETA, Universidade de Aveiro, Campus Universit\u00b4ario de Santiago, 3810-193 Aveiro, Portugal","institution_ids":["https://openalex.org/I60858718"]},{"raw_affiliation_string":"DETI/IEETA, Universidade de Aveiro, Campus Universit\u00b4ario de Santiago, 3810-193, Aveiro, Portugal","institution_ids":["https://openalex.org/I60858718"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040524956","display_name":"Jos\u00e9 Lu\u00eds Oliveira","orcid":"https://orcid.org/0000-0002-6672-6176"},"institutions":[{"id":"https://openalex.org/I60858718","display_name":"University of Aveiro","ror":"https://ror.org/00nt41z93","country_code":"PT","type":"education","lineage":["https://openalex.org/I60858718"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 L Oliveira","raw_affiliation_strings":["DETI/IEETA, Universidade de Aveiro, Campus Universit\u00b4ario de Santiago, 3810-193 Aveiro, Portugal","DETI/IEETA, Universidade de Aveiro, Campus Universit\u00b4ario de Santiago, 3810-193, Aveiro, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DETI/IEETA, Universidade de Aveiro, Campus Universit\u00b4ario de Santiago, 3810-193 Aveiro, Portugal","institution_ids":["https://openalex.org/I60858718"]},{"raw_affiliation_string":"DETI/IEETA, Universidade de Aveiro, Campus Universit\u00b4ario de Santiago, 3810-193, Aveiro, Portugal","institution_ids":["https://openalex.org/I60858718"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5072967999"],"corresponding_institution_ids":["https://openalex.org/I2802805223"],"apc_list":{"value":1290,"currency":"GBP","value_usd":2190},"apc_paid":{"value":1290,"currency":"GBP","value_usd":2190},"fwci":1.5152,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.82405255,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"7","issue":"S1","first_page":"S7","last_page":"S7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9369000196456909,"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":0.9369000196456909,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.01899999938905239,"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/T10028","display_name":"Topic Modeling","score":0.015200000256299973,"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/computer-science","display_name":"Computer science","score":0.84145188331604},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.7734044790267944},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.6789981126785278},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6580489277839661},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6464305520057678},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6173627972602844},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5901346206665039},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.573616623878479},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5637204051017761},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5378602743148804},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5270581245422363},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5190354585647583},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5024707317352295},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.480033278465271},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4184149205684662}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.84145188331604},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.7734044790267944},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.6789981126785278},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6580489277839661},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6464305520057678},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6173627972602844},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5901346206665039},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.573616623878479},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5637204051017761},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5378602743148804},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5270581245422363},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5190354585647583},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5024707317352295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.480033278465271},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4184149205684662},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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-s7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1758-2946-7-s1-s7","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/1758-2946-7-S1-S7","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:25810778","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/25810778","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:3334614","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4331697","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-s7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1758-2946-7-s1-s7","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/1758-2946-7-S1-S7","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":0.6200000047683716,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G635961249","display_name":null,"funder_award_id":"PEst-OE/EEI/UI0127/2014","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G6382720711","display_name":null,"funder_award_id":"115372","funder_id":"https://openalex.org/F4320314178","funder_display_name":"European Federation of Pharmaceutical Industries and Associations"}],"funders":[{"id":"https://openalex.org/F4320314178","display_name":"European Federation of Pharmaceutical Industries and Associations","ror":"https://ror.org/00g1x4v36"},{"id":"https://openalex.org/F4320334779","display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","ror":"https://ror.org/00snfqn58"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2160091014.pdf","grobid_xml":"https://content.openalex.org/works/W2160091014.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W77347155","https://openalex.org/W1532940542","https://openalex.org/W1561467090","https://openalex.org/W1859283887","https://openalex.org/W1991154713","https://openalex.org/W1992593537","https://openalex.org/W2033377040","https://openalex.org/W2040298461","https://openalex.org/W2049240985","https://openalex.org/W2055032581","https://openalex.org/W2065963191","https://openalex.org/W2074640468","https://openalex.org/W2095596879","https://openalex.org/W2096777607","https://openalex.org/W2121244856","https://openalex.org/W2124772738","https://openalex.org/W2127239015","https://openalex.org/W2127553917","https://openalex.org/W2135505477","https://openalex.org/W2136640051","https://openalex.org/W2147880316","https://openalex.org/W2151428465","https://openalex.org/W2154142897","https://openalex.org/W2159620792","https://openalex.org/W2170146596","https://openalex.org/W2178441628","https://openalex.org/W2912832745","https://openalex.org/W4231056502"],"related_works":["https://openalex.org/W4250494529","https://openalex.org/W1964783010","https://openalex.org/W2399696375","https://openalex.org/W45206245","https://openalex.org/W2211396092","https://openalex.org/W2061834489","https://openalex.org/W3088215229","https://openalex.org/W2078793151","https://openalex.org/W3047727388","https://openalex.org/W2759598007"],"abstract_inverted_index":{"BACKGROUND:":[0],"The":[1,80,182,223],"recognition":[2,123,154,173],"of":[3,18,29,40,82,100,128,137,147,174],"drugs":[4,75],"and":[5,37,42,68,76,88,93,117,139,156,176,196,210,233],"chemical":[6,101,151,160,175],"entities":[7],"in":[8,26,104,149,158,179],"text":[9],"is":[10],"a":[11,90,119,126,134,140,167,186,229],"very":[12],"important":[13],"task":[14,113,155],"within":[15],"the":[16,23,27,38,98,109,150,159,220],"field":[17,132],"biomedical":[19],"information":[20,94],"extraction,":[21],"given":[22],"rapid":[24],"growth":[25],"amount":[28],"published":[30],"texts":[31],"(scientific":[32],"papers,":[33],"patents,":[34],"patient":[35],"records)":[36],"relevance":[39],"these":[41],"other":[43],"related":[44],"concepts.":[45],"If":[46],"done":[47],"effectively,":[48],"this":[49,83],"could":[50],"allow":[51],"exploiting":[52],"such":[53,63],"textual":[54],"resources":[55],"to":[56,86,115],"automatically":[57],"extract":[58],"or":[59,72],"infer":[60],"relevant":[61],"information,":[62],"as":[64,228],"drug":[65,78,177],"profiles,":[66],"relations":[67],"similarities":[69],"between":[70,74],"drugs,":[71],"associations":[73],"potential":[77],"targets.":[79],"objective":[81],"work":[84],"was":[85],"develop":[87],"validate":[89],"document":[91,161,230],"processing":[92],"extraction":[95],"pipeline":[96],"for":[97,171],"identification":[99],"entity":[102,122,152],"mentions":[103,213],"text.":[105],"RESULTS:":[106],"We":[107,165],"used":[108],"BioCreative":[110],"IV":[111],"CHEMDNER":[112],"data":[114],"train":[116],"evaluate":[118],"machine-learning":[120],"based":[121],"system.":[124],"Using":[125],"combination":[127],"two":[129],"conditional":[130],"random":[131],"models,":[133],"selected":[135],"set":[136],"features,":[138],"post-processing":[141],"stage,":[142],"we":[143],"achieved":[144],"F-measure":[145],"results":[146],"87.48%":[148],"mention":[153],"87.75%":[157],"indexing":[162],"task.":[163],"CONCLUSIONS:":[164],"present":[166],"machine":[168],"learning-based":[169],"solution":[170],"automatic":[172],"names":[178],"scientific":[180],"documents.":[181],"proposed":[183],"approach":[184],"applies":[185],"rich":[187],"feature":[188],"set,":[189],"including":[190],"linguistic,":[191],"orthographic,":[192],"morphological,":[193],"dictionary":[194],"matching":[195],"local":[197],"context":[198],"features.":[199],"Post-processing":[200],"modules":[201],"are":[202],"also":[203],"integrated,":[204],"performing":[205],"parentheses":[206],"correction,":[207],"abbreviation":[208],"resolution":[209],"filtering":[211],"erroneous":[212],"using":[214],"an":[215],"exclusion":[216],"list":[217],"derived":[218],"from":[219],"training":[221],"data.":[222],"developed":[224],"methods":[225],"were":[226],"implemented":[227],"annotation":[231],"tool":[232],"web":[234],"service,":[235],"freely":[236],"available":[237],"at":[238],"http://bioinformatics.ua.pt/becas-chemicals/.":[239]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":5},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}