Cargando…

Leveraging prior knowledge for protein–protein interaction extraction with memory network

Automatically extracting protein–protein interactions (PPIs) from biomedical literature provides additional support for precision medicine efforts. This paper proposes a novel memory network-based model (MNM) for PPI extraction, which leverages prior knowledge about protein–protein pairs with memory...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhou, Huiwei, Liu, Zhuang, Ning, Shixian, Yang, Yunlong, Lang, Chengkun, Lin, Yingyu, Ma, Kun
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Oxford University Press 2018
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6047414/
https://www.ncbi.nlm.nih.gov/pubmed/30010731
http://dx.doi.org/10.1093/database/bay071
_version_ 1783339940976787456
author Zhou, Huiwei
Liu, Zhuang
Ning, Shixian
Yang, Yunlong
Lang, Chengkun
Lin, Yingyu
Ma, Kun
author_facet Zhou, Huiwei
Liu, Zhuang
Ning, Shixian
Yang, Yunlong
Lang, Chengkun
Lin, Yingyu
Ma, Kun
author_sort Zhou, Huiwei
collection PubMed
description Automatically extracting protein–protein interactions (PPIs) from biomedical literature provides additional support for precision medicine efforts. This paper proposes a novel memory network-based model (MNM) for PPI extraction, which leverages prior knowledge about protein–protein pairs with memory networks. The proposed MNM captures important context clues related to knowledge representations learned from knowledge bases. Both entity embeddings and relation embeddings of prior knowledge are effective in improving the PPI extraction model, leading to a new state-of-the-art performance on the BioCreative VI PPI dataset. The paper also shows that multiple computational layers over an external memory are superior to long short-term memory networks with the local memories. Database URL: http://www.biocreative.org/tasks/biocreative-vi/track-4/
format Online
Article
Text
id pubmed-6047414
institution National Center for Biotechnology Information
language English
publishDate 2018
publisher Oxford University Press
record_format MEDLINE/PubMed
spelling pubmed-60474142018-07-19 Leveraging prior knowledge for protein–protein interaction extraction with memory network Zhou, Huiwei Liu, Zhuang Ning, Shixian Yang, Yunlong Lang, Chengkun Lin, Yingyu Ma, Kun Database (Oxford) Original Article Automatically extracting protein–protein interactions (PPIs) from biomedical literature provides additional support for precision medicine efforts. This paper proposes a novel memory network-based model (MNM) for PPI extraction, which leverages prior knowledge about protein–protein pairs with memory networks. The proposed MNM captures important context clues related to knowledge representations learned from knowledge bases. Both entity embeddings and relation embeddings of prior knowledge are effective in improving the PPI extraction model, leading to a new state-of-the-art performance on the BioCreative VI PPI dataset. The paper also shows that multiple computational layers over an external memory are superior to long short-term memory networks with the local memories. Database URL: http://www.biocreative.org/tasks/biocreative-vi/track-4/ Oxford University Press 2018-07-13 /pmc/articles/PMC6047414/ /pubmed/30010731 http://dx.doi.org/10.1093/database/bay071 Text en © The Author(s) 2018. Published by Oxford University Press. http://creativecommons.org/licenses/by/4.0/ This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted reuse, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Original Article
Zhou, Huiwei
Liu, Zhuang
Ning, Shixian
Yang, Yunlong
Lang, Chengkun
Lin, Yingyu
Ma, Kun
Leveraging prior knowledge for protein–protein interaction extraction with memory network
title Leveraging prior knowledge for protein–protein interaction extraction with memory network
title_full Leveraging prior knowledge for protein–protein interaction extraction with memory network
title_fullStr Leveraging prior knowledge for protein–protein interaction extraction with memory network
title_full_unstemmed Leveraging prior knowledge for protein–protein interaction extraction with memory network
title_short Leveraging prior knowledge for protein–protein interaction extraction with memory network
title_sort leveraging prior knowledge for protein–protein interaction extraction with memory network
topic Original Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6047414/
https://www.ncbi.nlm.nih.gov/pubmed/30010731
http://dx.doi.org/10.1093/database/bay071
work_keys_str_mv AT zhouhuiwei leveragingpriorknowledgeforproteinproteininteractionextractionwithmemorynetwork
AT liuzhuang leveragingpriorknowledgeforproteinproteininteractionextractionwithmemorynetwork
AT ningshixian leveragingpriorknowledgeforproteinproteininteractionextractionwithmemorynetwork
AT yangyunlong leveragingpriorknowledgeforproteinproteininteractionextractionwithmemorynetwork
AT langchengkun leveragingpriorknowledgeforproteinproteininteractionextractionwithmemorynetwork
AT linyingyu leveragingpriorknowledgeforproteinproteininteractionextractionwithmemorynetwork
AT makun leveragingpriorknowledgeforproteinproteininteractionextractionwithmemorynetwork