Extracting causal relations on HIV drug resistance from literature

<p>Abstract</p> <p>Background</p> <p>In HIV treatment it is critical to have up-to-date resistance data of applicable drugs since HIV has a very high rate of mutation. These data are made available through scientific publications and must be extracted manually by expert...

Full description

Bibliographic Details
Main Authors: Boucher Charles A, Nualláin Breanndán Ó, Bui Quoc-Chinh, Sloot Peter MA
Format: Article
Language:English
Published: BMC 2010-02-01
Series:BMC Bioinformatics
Online Access:http://www.biomedcentral.com/1471-2105/11/101
_version_ 1818114484241170432
author Boucher Charles A
Nualláin Breanndán Ó
Bui Quoc-Chinh
Sloot Peter MA
author_facet Boucher Charles A
Nualláin Breanndán Ó
Bui Quoc-Chinh
Sloot Peter MA
author_sort Boucher Charles A
collection DOAJ
description <p>Abstract</p> <p>Background</p> <p>In HIV treatment it is critical to have up-to-date resistance data of applicable drugs since HIV has a very high rate of mutation. These data are made available through scientific publications and must be extracted manually by experts in order to be used by virologists and medical doctors. Therefore there is an urgent need for a tool that partially automates this process and is able to retrieve relations between drugs and virus mutations from literature.</p> <p>Results</p> <p>In this work we present a novel method to extract and combine relationships between HIV drugs and mutations in viral genomes. Our extraction method is based on natural language processing (NLP) which produces grammatical relations and applies a set of rules to these relations. We applied our method to a relevant set of PubMed abstracts and obtained 2,434 extracted relations with an estimated performance of 84% for F-score. We then combined the extracted relations using logistic regression to generate resistance values for each <drug, mutation> pair. The results of this relation combination show more than 85% agreement with the Stanford HIVDB for the ten most frequently occurring mutations. The system is used in 5 hospitals from the Virolab project <url>http://www.virolab.org</url> to preselect the most relevant novel resistance data from literature and present those to virologists and medical doctors for further evaluation.</p> <p>Conclusions</p> <p>The proposed relation extraction and combination method has a good performance on extracting HIV drug resistance data. It can be used in large-scale relation extraction experiments. The developed methods can also be applied to extract other type of relations such as gene-protein, gene-disease, and disease-mutation.</p>
first_indexed 2024-12-11T03:51:27Z
format Article
id doaj.art-eb384805ae1c491a963ec94c673aa100
institution Directory Open Access Journal
issn 1471-2105
language English
last_indexed 2024-12-11T03:51:27Z
publishDate 2010-02-01
publisher BMC
record_format Article
series BMC Bioinformatics
spelling doaj.art-eb384805ae1c491a963ec94c673aa1002022-12-22T01:21:53ZengBMCBMC Bioinformatics1471-21052010-02-0111110110.1186/1471-2105-11-101Extracting causal relations on HIV drug resistance from literatureBoucher Charles ANualláin Breanndán ÓBui Quoc-ChinhSloot Peter MA<p>Abstract</p> <p>Background</p> <p>In HIV treatment it is critical to have up-to-date resistance data of applicable drugs since HIV has a very high rate of mutation. These data are made available through scientific publications and must be extracted manually by experts in order to be used by virologists and medical doctors. Therefore there is an urgent need for a tool that partially automates this process and is able to retrieve relations between drugs and virus mutations from literature.</p> <p>Results</p> <p>In this work we present a novel method to extract and combine relationships between HIV drugs and mutations in viral genomes. Our extraction method is based on natural language processing (NLP) which produces grammatical relations and applies a set of rules to these relations. We applied our method to a relevant set of PubMed abstracts and obtained 2,434 extracted relations with an estimated performance of 84% for F-score. We then combined the extracted relations using logistic regression to generate resistance values for each <drug, mutation> pair. The results of this relation combination show more than 85% agreement with the Stanford HIVDB for the ten most frequently occurring mutations. The system is used in 5 hospitals from the Virolab project <url>http://www.virolab.org</url> to preselect the most relevant novel resistance data from literature and present those to virologists and medical doctors for further evaluation.</p> <p>Conclusions</p> <p>The proposed relation extraction and combination method has a good performance on extracting HIV drug resistance data. It can be used in large-scale relation extraction experiments. The developed methods can also be applied to extract other type of relations such as gene-protein, gene-disease, and disease-mutation.</p>http://www.biomedcentral.com/1471-2105/11/101
spellingShingle Boucher Charles A
Nualláin Breanndán Ó
Bui Quoc-Chinh
Sloot Peter MA
Extracting causal relations on HIV drug resistance from literature
BMC Bioinformatics
title Extracting causal relations on HIV drug resistance from literature
title_full Extracting causal relations on HIV drug resistance from literature
title_fullStr Extracting causal relations on HIV drug resistance from literature
title_full_unstemmed Extracting causal relations on HIV drug resistance from literature
title_short Extracting causal relations on HIV drug resistance from literature
title_sort extracting causal relations on hiv drug resistance from literature
url http://www.biomedcentral.com/1471-2105/11/101
work_keys_str_mv AT bouchercharlesa extractingcausalrelationsonhivdrugresistancefromliterature
AT nuallainbreanndano extractingcausalrelationsonhivdrugresistancefromliterature
AT buiquocchinh extractingcausalrelationsonhivdrugresistancefromliterature
AT slootpeterma extractingcausalrelationsonhivdrugresistancefromliterature