{"id":"https://openalex.org/W3032308670","doi":"https://doi.org/10.1186/s12859-020-03542-1","title":"Extracting chemical reactions from text using Snorkel","display_name":"Extracting chemical reactions from text using Snorkel","publication_year":2020,"publication_date":"2020-05-27","ids":{"openalex":"https://openalex.org/W3032308670","doi":"https://doi.org/10.1186/s12859-020-03542-1","mag":"3032308670","pmid":"https://pubmed.ncbi.nlm.nih.gov/32460703"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-020-03542-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-020-03542-1","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-020-03542-1","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"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":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-020-03542-1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015530758","display_name":"Emily K. Mallory","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Emily K. Mallory","raw_affiliation_strings":["Biomedical Informatics Training Program, Stanford University, Stanford, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biomedical Informatics Training Program, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054291087","display_name":"Matthieu de Rochemonteix","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthieu de Rochemonteix","raw_affiliation_strings":["Department of Statistics, Stanford University, Stanford, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067607533","display_name":"Alex Ratner","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alex Ratner","raw_affiliation_strings":["Department of Computer Science, Stanford University, Stanford, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038028728","display_name":"Ambika Acharya","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ambika Acharya","raw_affiliation_strings":["Department of Computer Science, Stanford University, Stanford, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103148807","display_name":"Chris R\u00e9","orcid":"https://orcid.org/0000-0002-4109-0108"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chris Re","raw_affiliation_strings":["Department of Computer Science, Stanford University, Stanford, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020524467","display_name":"Roselie A. Bright","orcid":"https://orcid.org/0000-0002-7565-1284"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Roselie A. Bright","raw_affiliation_strings":["Office of Health Informatics, Office of the Chief Scientist, Office of the Commissioner, Food and Drug Administration, Silver Spring, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Office of Health Informatics, Office of the Chief Scientist, Office of the Commissioner, Food and Drug Administration, Silver Spring, MD, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084043782","display_name":"Russ B. Altman","orcid":"https://orcid.org/0000-0003-3859-2905"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Russ B. Altman","raw_affiliation_strings":["Departments of Medicine, Genetics, Bioengineering, and Biomedical Data Science, Stanford University, Stanford, CA, USA. russ.altman@stanford.edu","Departments of Medicine, Genetics, Bioengineering, and Biomedical Data Science, Stanford University, Stanford, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-3859-2905","affiliations":[{"raw_affiliation_string":"Departments of Medicine, Genetics, Bioengineering, and Biomedical Data Science, Stanford University, Stanford, CA, USA. russ.altman@stanford.edu","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Departments of Medicine, Genetics, Bioengineering, and Biomedical Data Science, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5084043782"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":0.9173,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.72993271,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"21","issue":"1","first_page":"217","last_page":"217"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9767000079154968,"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":0.9767000079154968,"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/T10028","display_name":"Topic Modeling","score":0.0034000000450760126,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.002300000051036477,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6859321594238281},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5451800227165222},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4844051003456116},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4754188656806946},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4226677715778351},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3912869095802307},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2850103974342346}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6859321594238281},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5451800227165222},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4844051003456116},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4754188656806946},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4226677715778351},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3912869095802307},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2850103974342346},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D001669","descriptor_name":"Biochemical Phenomena","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001669","descriptor_name":"Biochemical Phenomena","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001669","descriptor_name":"Biochemical Phenomena","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001669","descriptor_name":"Biochemical Phenomena","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011642","descriptor_name":"Publications","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011642","descriptor_name":"Publications","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011642","descriptor_name":"Publications","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011642","descriptor_name":"Publications","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1186/s12859-020-03542-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-020-03542-1","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-020-03542-1","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"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":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:32460703","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/32460703","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:9cb4eacf8100417aadbb541d13cecffd","is_oa":true,"landing_page_url":"https://doaj.org/article/9cb4eacf8100417aadbb541d13cecffd","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":"BMC Bioinformatics, Vol 21, Iss 1, Pp 1-15 (2020)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:7251675","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7251675","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":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s12859-020-03542-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-020-03542-1","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-020-03542-1","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"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":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7400000095367432}],"awards":[{"id":"https://openalex.org/G1325793420","display_name":null,"funder_award_id":"R01 LM005652","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"},{"id":"https://openalex.org/G1394151085","display_name":null,"funder_award_id":"NRSA F31","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G1914228612","display_name":null,"funder_award_id":"R01 GM102365","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G2433402685","display_name":null,"funder_award_id":"LM012354","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G2589055757","display_name":null,"funder_award_id":"N000141712266","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G2825852195","display_name":null,"funder_award_id":"ACI-1429830","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2935333310","display_name":null,"funder_award_id":"N000141712266","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G3213469825","display_name":"MRI: Acquisition of an Extreme GPU Cluster for Interdisciplinary Research","funder_award_id":"1429830","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G324214434","display_name":null,"funder_award_id":"CCF1763315","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3897007235","display_name":null,"funder_award_id":"U01 FD005978","funder_id":"https://openalex.org/F4320332163","funder_display_name":"U.S. Food and Drug Administration"},{"id":"https://openalex.org/G4130961295","display_name":null,"funder_award_id":"DGE-114747","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G421559017","display_name":null,"funder_award_id":"F31 LM012354","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"},{"id":"https://openalex.org/G4292887491","display_name":null,"funder_award_id":"CCF1563078","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G4475131919","display_name":null,"funder_award_id":"114747","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5097059376","display_name":null,"funder_award_id":"DGE-114747","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G538509161","display_name":null,"funder_award_id":"FA86501827865","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G5593774952","display_name":null,"funder_award_id":"GM102365","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G5925649794","display_name":null,"funder_award_id":"CCF1763315","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G6065575299","display_name":null,"funder_award_id":"FA87501720095","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G6411790401","display_name":null,"funder_award_id":"LM05652","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G6610709059","display_name":null,"funder_award_id":"U01FD004979","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G7108608281","display_name":null,"funder_award_id":"U01FD004979","funder_id":"https://openalex.org/F4320332163","funder_display_name":"U.S. Food and Drug Administration"},{"id":"https://openalex.org/G8203307141","display_name":null,"funder_award_id":"CCF1563078","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8203850527","display_name":null,"funder_award_id":"U01 FD004979","funder_id":"https://openalex.org/F4320332163","funder_display_name":"U.S. Food and Drug Administration"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306085","display_name":"U.S. Department of Health and Human Services","ror":"https://ror.org/033jnv181"},{"id":"https://openalex.org/F4320306202","display_name":"Gordon and Betty Moore Foundation","ror":"https://ror.org/006wxqw41"},{"id":"https://openalex.org/F4320307894","display_name":"Accenture","ror":"https://ror.org/013g16z83"},{"id":"https://openalex.org/F4320316785","display_name":"VMware","ror":null},{"id":"https://openalex.org/F4320322617","display_name":"Okawa Foundation for Information and Telecommunications","ror":"https://ror.org/01enbtr31"},{"id":"https://openalex.org/F4320330001","display_name":"Ant Financial Services Group","ror":null},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320332163","display_name":"U.S. Food and Drug Administration","ror":"https://ror.org/034xvzb47"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332622","display_name":"University of California, San Francisco","ror":"https://ror.org/043mz5j54"},{"id":"https://openalex.org/F4320334432","display_name":"Stanford Research Computing Center, Stanford University","ror":null},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"},{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3032308670.pdf","grobid_xml":"https://content.openalex.org/works/W3032308670.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1956506048","https://openalex.org/W1964670939","https://openalex.org/W1972380983","https://openalex.org/W1981276685","https://openalex.org/W2044018282","https://openalex.org/W2058190388","https://openalex.org/W2096951189","https://openalex.org/W2128601422","https://openalex.org/W2130502764","https://openalex.org/W2149369282","https://openalex.org/W2153579005","https://openalex.org/W2159482845","https://openalex.org/W2169491861","https://openalex.org/W2294346158","https://openalex.org/W2404161646","https://openalex.org/W2769041395","https://openalex.org/W2895604144","https://openalex.org/W2911489562","https://openalex.org/W2951576432","https://openalex.org/W2959716049","https://openalex.org/W2962915384","https://openalex.org/W2963341956","https://openalex.org/W4294216483"],"related_works":["https://openalex.org/W2389214306","https://openalex.org/W2965083567","https://openalex.org/W4235240664","https://openalex.org/W1838576100","https://openalex.org/W2757182831","https://openalex.org/W2095886385","https://openalex.org/W2089704382","https://openalex.org/W1983399550","https://openalex.org/W97075385","https://openalex.org/W3204019825"],"abstract_inverted_index":{"BACKGROUND:":[0],"Enzymatic":[1],"and":[2,44,50,69,78,123,146,173,220],"chemical":[3,16,96,109,116,119,132,211,241,260,291],"reactions":[4,17,292],"are":[5],"key":[6],"for":[7,73,94],"understanding":[8],"biological":[9],"processes":[10],"in":[11,194,248],"cells.":[12],"Curated":[13],"databases":[14,21],"of":[15,30,65,87,115,131,151,164,207,259,273,281,297],"exist":[18],"but":[19,55],"these":[20],"struggle":[22],"to":[23,40,118,180,187,196,233,293,300],"keep":[24],"up":[25],"with":[26,154,189,290],"the":[27,31,47,113,142,167,181,202,234,249,279],"exponential":[28],"growth":[29],"biomedical":[32,100],"literature.":[33],"Conventional":[34],"text":[35],"mining":[36],"pipelines":[37],"provide":[38],"tools":[39],"automatically":[41],"extract":[42],"entities":[43],"relationships":[45,98,134,213,243,262],"from":[46,99,135,141,244,263],"scientific":[48,266],"literature,":[49],"partially":[51],"replace":[52],"expert":[53],"curation,":[54],"such":[56],"machine":[57],"learning":[58,92],"frameworks":[59],"often":[60],"require":[61],"a":[62,89,108,147,162,191,222,257,269,294],"large":[63,270],"amount":[64],"labeled":[66,274],"training":[67,271],"data":[68],"thus":[70],"lack":[71],"scalability":[72],"both":[74],"larger":[75,223],"document":[76],"corpora":[77],"new":[79],"relationship":[80,111],"types.":[81],"RESULTS:":[82],"We":[83,121],"developed":[84],"an":[85],"application":[86,284],"Snorkel,":[88],"weakly":[90],"supervised":[91],"framework,":[93],"extracting":[95],"reaction":[97,110,133,212,242,261],"literature":[101],"abstracts.":[102],"For":[103,166],"this":[104,253],"work,":[105,254],"we":[106,169,238,255,277],"defined":[107],"as":[112,231],"transformation":[114],"A":[117],"B.":[120],"built":[122,256,285],"evaluated":[124],"our":[125,282],"system":[126],"on":[127,286],"small":[128],"annotated":[129,153],"sets":[130],"two":[136,205],"corpora:":[137],"curated":[138],"bacteria-related":[139],"abstracts":[140,152,267],"MetaCyc":[143,287],"database":[144,258],"(MetaCyc_Corpus)":[145],"more":[148,182,209],"general":[149,183,295],"set":[150,272,296],"MeSH":[155],"(Medical":[156],"Subject":[157],"Headings)":[158],"term":[159],"Bacteria":[160],"(Bacteria_Corpus;":[161],"superset":[163],"MetaCyc_Corpus).":[165],"MetaCyc_Corpus,":[168],"obtained":[170],"84%":[171],"precision":[172,186],"41%":[174],"recall":[175,195],"(55%":[176],"F1":[177,199],"score).":[178,200],"Extending":[179],"Bacteria_Corpus":[184,203],"decreased":[185],"62%":[188],"only":[190],"four-point":[192],"drop":[193],"37%":[197],"(46%":[198],"Overall,":[201],"contained":[204],"orders":[206],"magnitude":[208],"candidate":[210],"(nine":[214],"million":[215,246],"candidates":[216,247],"vs":[217,228],"68,0000":[218],"candidates)":[219],"had":[221],"class":[224],"imbalance":[225],"(2.5%":[226],"positives":[227],"5%":[229],"positives)":[230],"compared":[232],"MetaCyc_Corpus.":[235],"In":[236],"total,":[237],"extracted":[239],"6871":[240],"nine":[245],"Bacteria_Corpus.":[250],"CONCLUSIONS:":[251],"With":[252],"almost":[264],"900,000":[265],"without":[268],"annotations.":[275],"Further,":[276],"showed":[278],"generalizability":[280],"initial":[283],"documents":[288],"enriched":[289],"articles":[298],"related":[299],"bacteria.":[301]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4}],"updated_date":"2026-06-24T13:16:06.693445","created_date":"2025-10-10T00:00:00"}
