Extraction of pharmacokinetic evidence of drug-drug interactions from the literature
Autor(a) principal: | |
---|---|
Data de Publicação: | 2015 |
Outros Autores: | , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/1822/35793 |
Resumo: | Drug-drug interaction (DDI) is a major cause of morbidity and mortality and a subject of intense scientific interest. Biomedical literature mining can aid DDI research by extracting evidence for large numbers of potential interactions from published literature and clinical databases. Though DDI is investigated in domains ranging in scale from intracellular biochemistry to human populations, literature mining has not been used to extract specific types of experimental evidence, which are reported differently for distinct experimental goals. We focus on pharmacokinetic evidence for DDI, essential for identifying causal mechanisms of putative interactions and as input for further pharmacological and pharmacoepidemiology investigations. We used manually curated corpora of PubMed abstracts and annotated sentences to evaluate the efficacy of literature mining on two tasks: first, identifying PubMed abstracts containing pharmacokinetic evidence of DDIs; second, extracting sentences containing such evidence from abstracts. We implemented a text mining pipeline and evaluated it using several linear classifiers and a variety of feature transforms. The most important textual features in the abstract and sentence classification tasks were analyzed. We also investigated the performance benefits of using features derived from PubMed metadata fields, various publicly available named entity recognizers, and pharmacokinetic dictionaries. Several classifiers performed very well in distinguishing relevant and irrelevant abstracts (reaching F10.93, MCC0.74, iAUC0.99) and sentences (F10.76, MCC0.65, iAUC0.83). We found that word bigram features were important for achieving optimal classifier performance and that features derived from Medical Subject Headings (MeSH) terms significantly improved abstract classification. We also found that some drug-related named entity recognition tools and dictionaries led to slight but significant improvements, especially in classification of evidence sentences. Based on our thorough analysis of classifiers and feature transforms and the high classification performance achieved, we demonstrate that literature mining can aid DDI discovery by supporting automatic extraction of specific types of experimental evidence. |
id |
RCAP_67ea072c43b831e8d9d7eb04500112b9 |
---|---|
oai_identifier_str |
oai:repositorium.sdum.uminho.pt:1822/35793 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Extraction of pharmacokinetic evidence of drug-drug interactions from the literatureCiências Naturais::Ciências da Computação e da InformaçãoScience & TechnologyDrug-drug interaction (DDI) is a major cause of morbidity and mortality and a subject of intense scientific interest. Biomedical literature mining can aid DDI research by extracting evidence for large numbers of potential interactions from published literature and clinical databases. Though DDI is investigated in domains ranging in scale from intracellular biochemistry to human populations, literature mining has not been used to extract specific types of experimental evidence, which are reported differently for distinct experimental goals. We focus on pharmacokinetic evidence for DDI, essential for identifying causal mechanisms of putative interactions and as input for further pharmacological and pharmacoepidemiology investigations. We used manually curated corpora of PubMed abstracts and annotated sentences to evaluate the efficacy of literature mining on two tasks: first, identifying PubMed abstracts containing pharmacokinetic evidence of DDIs; second, extracting sentences containing such evidence from abstracts. We implemented a text mining pipeline and evaluated it using several linear classifiers and a variety of feature transforms. The most important textual features in the abstract and sentence classification tasks were analyzed. We also investigated the performance benefits of using features derived from PubMed metadata fields, various publicly available named entity recognizers, and pharmacokinetic dictionaries. Several classifiers performed very well in distinguishing relevant and irrelevant abstracts (reaching F10.93, MCC0.74, iAUC0.99) and sentences (F10.76, MCC0.65, iAUC0.83). We found that word bigram features were important for achieving optimal classifier performance and that features derived from Medical Subject Headings (MeSH) terms significantly improved abstract classification. We also found that some drug-related named entity recognition tools and dictionaries led to slight but significant improvements, especially in classification of evidence sentences. Based on our thorough analysis of classifiers and feature transforms and the high classification performance achieved, we demonstrate that literature mining can aid DDI discovery by supporting automatic extraction of specific types of experimental evidence.National Institutes of Health, National Library of Medicine Program, grant 01LM011945-01 "BLR: Evidence-based Drug-Interaction Discovery: In-Vivo, In-Vitro and Clinical," a grant from the Indiana University Collaborative Research Program 2013, "Drug-Drug Interaction Prediction from Large-scale Mining of Literature and Patient Records," as well as a grant from the joint program between the Fundação Luso-Americana para o Desenvolvimento (Portugal) and National Science Foundation (USA), 2012-2014, "Network Mining For Gene Regulation And Biochemical Signaling."Public Library of ScienceUniversidade do MinhoKolchinsky, ArtemyLourenço, AnáliaWu, Heng-YiLi, LangRocha, Luís M.2015-052015-05-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/1822/35793engKolchinsky, Artemy; Lourenço, Anália; Wu, Heng-Yi; Li, Lang; Rocha, Luis M., Extraction of pharmacokinetic evidence of drugdrug interactions from the literature. PLoS One, 10(5), e0122199, 20151932-62031932-620310.1371/journal.pone.012219925961290http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0122199info:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-07-21T12:00:24Zoai:repositorium.sdum.uminho.pt:1822/35793Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T18:50:17.428646Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
Extraction of pharmacokinetic evidence of drug-drug interactions from the literature |
title |
Extraction of pharmacokinetic evidence of drug-drug interactions from the literature |
spellingShingle |
Extraction of pharmacokinetic evidence of drug-drug interactions from the literature Kolchinsky, Artemy Ciências Naturais::Ciências da Computação e da Informação Science & Technology |
title_short |
Extraction of pharmacokinetic evidence of drug-drug interactions from the literature |
title_full |
Extraction of pharmacokinetic evidence of drug-drug interactions from the literature |
title_fullStr |
Extraction of pharmacokinetic evidence of drug-drug interactions from the literature |
title_full_unstemmed |
Extraction of pharmacokinetic evidence of drug-drug interactions from the literature |
title_sort |
Extraction of pharmacokinetic evidence of drug-drug interactions from the literature |
author |
Kolchinsky, Artemy |
author_facet |
Kolchinsky, Artemy Lourenço, Anália Wu, Heng-Yi Li, Lang Rocha, Luís M. |
author_role |
author |
author2 |
Lourenço, Anália Wu, Heng-Yi Li, Lang Rocha, Luís M. |
author2_role |
author author author author |
dc.contributor.none.fl_str_mv |
Universidade do Minho |
dc.contributor.author.fl_str_mv |
Kolchinsky, Artemy Lourenço, Anália Wu, Heng-Yi Li, Lang Rocha, Luís M. |
dc.subject.por.fl_str_mv |
Ciências Naturais::Ciências da Computação e da Informação Science & Technology |
topic |
Ciências Naturais::Ciências da Computação e da Informação Science & Technology |
description |
Drug-drug interaction (DDI) is a major cause of morbidity and mortality and a subject of intense scientific interest. Biomedical literature mining can aid DDI research by extracting evidence for large numbers of potential interactions from published literature and clinical databases. Though DDI is investigated in domains ranging in scale from intracellular biochemistry to human populations, literature mining has not been used to extract specific types of experimental evidence, which are reported differently for distinct experimental goals. We focus on pharmacokinetic evidence for DDI, essential for identifying causal mechanisms of putative interactions and as input for further pharmacological and pharmacoepidemiology investigations. We used manually curated corpora of PubMed abstracts and annotated sentences to evaluate the efficacy of literature mining on two tasks: first, identifying PubMed abstracts containing pharmacokinetic evidence of DDIs; second, extracting sentences containing such evidence from abstracts. We implemented a text mining pipeline and evaluated it using several linear classifiers and a variety of feature transforms. The most important textual features in the abstract and sentence classification tasks were analyzed. We also investigated the performance benefits of using features derived from PubMed metadata fields, various publicly available named entity recognizers, and pharmacokinetic dictionaries. Several classifiers performed very well in distinguishing relevant and irrelevant abstracts (reaching F10.93, MCC0.74, iAUC0.99) and sentences (F10.76, MCC0.65, iAUC0.83). We found that word bigram features were important for achieving optimal classifier performance and that features derived from Medical Subject Headings (MeSH) terms significantly improved abstract classification. We also found that some drug-related named entity recognition tools and dictionaries led to slight but significant improvements, especially in classification of evidence sentences. Based on our thorough analysis of classifiers and feature transforms and the high classification performance achieved, we demonstrate that literature mining can aid DDI discovery by supporting automatic extraction of specific types of experimental evidence. |
publishDate |
2015 |
dc.date.none.fl_str_mv |
2015-05 2015-05-01T00:00:00Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/1822/35793 |
url |
http://hdl.handle.net/1822/35793 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Kolchinsky, Artemy; Lourenço, Anália; Wu, Heng-Yi; Li, Lang; Rocha, Luis M., Extraction of pharmacokinetic evidence of drugdrug interactions from the literature. PLoS One, 10(5), e0122199, 2015 1932-6203 1932-6203 10.1371/journal.pone.0122199 25961290 http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0122199 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Public Library of Science |
publisher.none.fl_str_mv |
Public Library of Science |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799132270594883584 |