Integrating semantic information into multiple kernels for protein-protein interaction extraction from biomedical literatures.

Protein-Protein Interaction (PPI) extraction is an important task in the biomedical information extraction. Presently, many machine learning methods for PPI extraction have achieved promising results. However, the performance is still not satisfactory. One reason is that the semantic resources were...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Lishuang Li, Panpan Zhang, Tianfu Zheng, Hongying Zhang, Zhenchao Jiang, Degen Huang
Formato:	article
Lenguaje:	EN
Publicado:	Public Library of Science (PLoS) 2014
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/2ed299407ca24f2cacdffaca53b3d8c3
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:2ed299407ca24f2cacdffaca53b3d8c3
record_format	dspace
spelling	oai:doaj.org-article:2ed299407ca24f2cacdffaca53b3d8c32021-11-18T08:28:22ZIntegrating semantic information into multiple kernels for protein-protein interaction extraction from biomedical literatures.1932-620310.1371/journal.pone.0091898https://doaj.org/article/2ed299407ca24f2cacdffaca53b3d8c32014-01-01T00:00:00Zhttps://www.ncbi.nlm.nih.gov/pmc/articles/pmid/24622773/?tool=EBIhttps://doaj.org/toc/1932-6203Protein-Protein Interaction (PPI) extraction is an important task in the biomedical information extraction. Presently, many machine learning methods for PPI extraction have achieved promising results. However, the performance is still not satisfactory. One reason is that the semantic resources were basically ignored. In this paper, we propose a multiple-kernel learning-based approach to extract PPIs, combining the feature-based kernel, tree kernel and semantic kernel. Particularly, we extend the shortest path-enclosed tree kernel (SPT) by a dynamic extended strategy to retrieve the richer syntactic information. Our semantic kernel calculates the protein-protein pair similarity and the context similarity based on two semantic resources: WordNet and Medical Subject Heading (MeSH). We evaluate our method with Support Vector Machine (SVM) and achieve an F-score of 69.40% and an AUC of 92.00%, which show that our method outperforms most of the state-of-the-art systems by integrating semantic information.Lishuang LiPanpan ZhangTianfu ZhengHongying ZhangZhenchao JiangDegen HuangPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 9, Iss 3, p e91898 (2014)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Lishuang Li Panpan Zhang Tianfu Zheng Hongying Zhang Zhenchao Jiang Degen Huang Integrating semantic information into multiple kernels for protein-protein interaction extraction from biomedical literatures.
description	Protein-Protein Interaction (PPI) extraction is an important task in the biomedical information extraction. Presently, many machine learning methods for PPI extraction have achieved promising results. However, the performance is still not satisfactory. One reason is that the semantic resources were basically ignored. In this paper, we propose a multiple-kernel learning-based approach to extract PPIs, combining the feature-based kernel, tree kernel and semantic kernel. Particularly, we extend the shortest path-enclosed tree kernel (SPT) by a dynamic extended strategy to retrieve the richer syntactic information. Our semantic kernel calculates the protein-protein pair similarity and the context similarity based on two semantic resources: WordNet and Medical Subject Heading (MeSH). We evaluate our method with Support Vector Machine (SVM) and achieve an F-score of 69.40% and an AUC of 92.00%, which show that our method outperforms most of the state-of-the-art systems by integrating semantic information.
format	article
author	Lishuang Li Panpan Zhang Tianfu Zheng Hongying Zhang Zhenchao Jiang Degen Huang
author_facet	Lishuang Li Panpan Zhang Tianfu Zheng Hongying Zhang Zhenchao Jiang Degen Huang
author_sort	Lishuang Li
title	Integrating semantic information into multiple kernels for protein-protein interaction extraction from biomedical literatures.
title_short	Integrating semantic information into multiple kernels for protein-protein interaction extraction from biomedical literatures.
title_full	Integrating semantic information into multiple kernels for protein-protein interaction extraction from biomedical literatures.
title_fullStr	Integrating semantic information into multiple kernels for protein-protein interaction extraction from biomedical literatures.
title_full_unstemmed	Integrating semantic information into multiple kernels for protein-protein interaction extraction from biomedical literatures.
title_sort	integrating semantic information into multiple kernels for protein-protein interaction extraction from biomedical literatures.
publisher	Public Library of Science (PLoS)
publishDate	2014
url	https://doaj.org/article/2ed299407ca24f2cacdffaca53b3d8c3
work_keys_str_mv	AT lishuangli integratingsemanticinformationintomultiplekernelsforproteinproteininteractionextractionfrombiomedicalliteratures AT panpanzhang integratingsemanticinformationintomultiplekernelsforproteinproteininteractionextractionfrombiomedicalliteratures AT tianfuzheng integratingsemanticinformationintomultiplekernelsforproteinproteininteractionextractionfrombiomedicalliteratures AT hongyingzhang integratingsemanticinformationintomultiplekernelsforproteinproteininteractionextractionfrombiomedicalliteratures AT zhenchaojiang integratingsemanticinformationintomultiplekernelsforproteinproteininteractionextractionfrombiomedicalliteratures AT degenhuang integratingsemanticinformationintomultiplekernelsforproteinproteininteractionextractionfrombiomedicalliteratures
_version_	1718421731239002112

Integrating semantic information into multiple kernels for protein-protein interaction extraction from biomedical literatures.

Ejemplares similares