Cargando…
Extracting chemical–protein relations with ensembles of SVM and deep learning models
Mining relations between chemicals and proteins from the biomedical literature is an increasingly important task. The CHEMPROT track at BioCreative VI aims to promote the development and evaluation of systems that can automatically detect the chemical–protein relations in running text (PubMed abstra...
Autores principales: | , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Oxford University Press
2018
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6051439/ https://www.ncbi.nlm.nih.gov/pubmed/30020437 http://dx.doi.org/10.1093/database/bay073 |
_version_ | 1783340524816564224 |
---|---|
author | Peng, Yifan Rios, Anthony Kavuluru, Ramakanth Lu, Zhiyong |
author_facet | Peng, Yifan Rios, Anthony Kavuluru, Ramakanth Lu, Zhiyong |
author_sort | Peng, Yifan |
collection | PubMed |
description | Mining relations between chemicals and proteins from the biomedical literature is an increasingly important task. The CHEMPROT track at BioCreative VI aims to promote the development and evaluation of systems that can automatically detect the chemical–protein relations in running text (PubMed abstracts). This work describes our CHEMPROT track entry, which is an ensemble of three systems, including a support vector machine, a convolutional neural network, and a recurrent neural network. Their output is combined using majority voting or stacking for final predictions. Our CHEMPROT system obtained 0.7266 in precision and 0.5735 in recall for an F-score of 0.6410 during the challenge, demonstrating the effectiveness of machine learning-based approaches for automatic relation extraction from biomedical literature and achieving the highest performance in the task during the 2017 challenge. Database URL: http://www.biocreative.org/tasks/biocreative-vi/track-5/ |
format | Online Article Text |
id | pubmed-6051439 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2018 |
publisher | Oxford University Press |
record_format | MEDLINE/PubMed |
spelling | pubmed-60514392018-07-23 Extracting chemical–protein relations with ensembles of SVM and deep learning models Peng, Yifan Rios, Anthony Kavuluru, Ramakanth Lu, Zhiyong Database (Oxford) Original Article Mining relations between chemicals and proteins from the biomedical literature is an increasingly important task. The CHEMPROT track at BioCreative VI aims to promote the development and evaluation of systems that can automatically detect the chemical–protein relations in running text (PubMed abstracts). This work describes our CHEMPROT track entry, which is an ensemble of three systems, including a support vector machine, a convolutional neural network, and a recurrent neural network. Their output is combined using majority voting or stacking for final predictions. Our CHEMPROT system obtained 0.7266 in precision and 0.5735 in recall for an F-score of 0.6410 during the challenge, demonstrating the effectiveness of machine learning-based approaches for automatic relation extraction from biomedical literature and achieving the highest performance in the task during the 2017 challenge. Database URL: http://www.biocreative.org/tasks/biocreative-vi/track-5/ Oxford University Press 2018-07-17 /pmc/articles/PMC6051439/ /pubmed/30020437 http://dx.doi.org/10.1093/database/bay073 Text en Published by Oxford University Press 2018. This work is written by US Government employees and is in the public domain in the US. https://academic.oup.com/journals/pages/about_us/legal/notices This article is published and distributed under the terms of the Oxford University Press, Standard Journals Publication Model (https://academic.oup.com/journals/pages/about_us/legal/notices) |
spellingShingle | Original Article Peng, Yifan Rios, Anthony Kavuluru, Ramakanth Lu, Zhiyong Extracting chemical–protein relations with ensembles of SVM and deep learning models |
title | Extracting chemical–protein relations with ensembles of SVM and deep learning models |
title_full | Extracting chemical–protein relations with ensembles of SVM and deep learning models |
title_fullStr | Extracting chemical–protein relations with ensembles of SVM and deep learning models |
title_full_unstemmed | Extracting chemical–protein relations with ensembles of SVM and deep learning models |
title_short | Extracting chemical–protein relations with ensembles of SVM and deep learning models |
title_sort | extracting chemical–protein relations with ensembles of svm and deep learning models |
topic | Original Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6051439/ https://www.ncbi.nlm.nih.gov/pubmed/30020437 http://dx.doi.org/10.1093/database/bay073 |
work_keys_str_mv | AT pengyifan extractingchemicalproteinrelationswithensemblesofsvmanddeeplearningmodels AT riosanthony extractingchemicalproteinrelationswithensemblesofsvmanddeeplearningmodels AT kavulururamakanth extractingchemicalproteinrelationswithensemblesofsvmanddeeplearningmodels AT luzhiyong extractingchemicalproteinrelationswithensemblesofsvmanddeeplearningmodels |