PIPE

a protein-protein interaction passage extraction module for BioCreative challenge

Yung Chun Chang, Chun Han Chu, Yu Chen Su, Chien Chin Chen, Wen Lian Hsu

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Identifying the interactions between proteins mentioned in biomedical literatures is one of the frequently discussed topics of text mining in the life science field. In this article, we propose PIPE, an interaction pattern generation module used in the Collaborative Biocurator Assistant Task at BioCreative V (http://www.biocreative.org/) to capture frequent protein-protein interaction (PPI) patterns within text. We also present an interaction pattern tree (IPT) kernel method that integrates the PPI patterns with convolution tree kernel (CTK) to extract PPIs. Methods were evaluated on LLL, IEPA, HPRD50, AIMed and BioInfer corpora using cross-validation, cross-learning and cross-corpus evaluation. Empirical evaluations demonstrate that our method is effective and outperforms several well-known PPI extraction methods. DATABASE URL.

Original languageEnglish
JournalDatabase : the journal of biological databases and curation
Volume2016
DOIs
Publication statusPublished - Jan 1 2016
Externally publishedYes

Fingerprint

protein-protein interactions
Proteins
seeds
methodology
learning
Data Mining
Biological Science Disciplines
Convolution
extracts
Websites
Learning
proteins

ASJC Scopus subject areas

  • Information Systems
  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences(all)

Cite this

PIPE : a protein-protein interaction passage extraction module for BioCreative challenge. / Chang, Yung Chun; Chu, Chun Han; Su, Yu Chen; Chen, Chien Chin; Hsu, Wen Lian.

In: Database : the journal of biological databases and curation, Vol. 2016, 01.01.2016.

Research output: Contribution to journalArticle

@article{9c2853ecfd674414bf833ee3eb6a14fd,
title = "PIPE: a protein-protein interaction passage extraction module for BioCreative challenge",
abstract = "Identifying the interactions between proteins mentioned in biomedical literatures is one of the frequently discussed topics of text mining in the life science field. In this article, we propose PIPE, an interaction pattern generation module used in the Collaborative Biocurator Assistant Task at BioCreative V (http://www.biocreative.org/) to capture frequent protein-protein interaction (PPI) patterns within text. We also present an interaction pattern tree (IPT) kernel method that integrates the PPI patterns with convolution tree kernel (CTK) to extract PPIs. Methods were evaluated on LLL, IEPA, HPRD50, AIMed and BioInfer corpora using cross-validation, cross-learning and cross-corpus evaluation. Empirical evaluations demonstrate that our method is effective and outperforms several well-known PPI extraction methods. DATABASE URL.",
author = "Chang, {Yung Chun} and Chu, {Chun Han} and Su, {Yu Chen} and Chen, {Chien Chin} and Hsu, {Wen Lian}",
year = "2016",
month = "1",
day = "1",
doi = "10.1093/database/baw101",
language = "English",
volume = "2016",
journal = "Database : the journal of biological databases and curation",
issn = "1758-0463",
publisher = "Oxford University Press",

}

TY - JOUR

T1 - PIPE

T2 - a protein-protein interaction passage extraction module for BioCreative challenge

AU - Chang, Yung Chun

AU - Chu, Chun Han

AU - Su, Yu Chen

AU - Chen, Chien Chin

AU - Hsu, Wen Lian

PY - 2016/1/1

Y1 - 2016/1/1

N2 - Identifying the interactions between proteins mentioned in biomedical literatures is one of the frequently discussed topics of text mining in the life science field. In this article, we propose PIPE, an interaction pattern generation module used in the Collaborative Biocurator Assistant Task at BioCreative V (http://www.biocreative.org/) to capture frequent protein-protein interaction (PPI) patterns within text. We also present an interaction pattern tree (IPT) kernel method that integrates the PPI patterns with convolution tree kernel (CTK) to extract PPIs. Methods were evaluated on LLL, IEPA, HPRD50, AIMed and BioInfer corpora using cross-validation, cross-learning and cross-corpus evaluation. Empirical evaluations demonstrate that our method is effective and outperforms several well-known PPI extraction methods. DATABASE URL.

AB - Identifying the interactions between proteins mentioned in biomedical literatures is one of the frequently discussed topics of text mining in the life science field. In this article, we propose PIPE, an interaction pattern generation module used in the Collaborative Biocurator Assistant Task at BioCreative V (http://www.biocreative.org/) to capture frequent protein-protein interaction (PPI) patterns within text. We also present an interaction pattern tree (IPT) kernel method that integrates the PPI patterns with convolution tree kernel (CTK) to extract PPIs. Methods were evaluated on LLL, IEPA, HPRD50, AIMed and BioInfer corpora using cross-validation, cross-learning and cross-corpus evaluation. Empirical evaluations demonstrate that our method is effective and outperforms several well-known PPI extraction methods. DATABASE URL.

UR - http://www.scopus.com/inward/record.url?scp=85032923304&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85032923304&partnerID=8YFLogxK

U2 - 10.1093/database/baw101

DO - 10.1093/database/baw101

M3 - Article

VL - 2016

JO - Database : the journal of biological databases and curation

JF - Database : the journal of biological databases and curation

SN - 1758-0463

ER -