Literature DB >> 26224335

Extracting relations from traditional Chinese medicine literature via heterogeneous entity networks.

Huaiyu Wan1, Marie-Francine Moens2, Walter Luyten3, Xuezhong Zhou4, Qiaozhu Mei5, Lu Liu6, Jie Tang7.   

Abstract

OBJECTIVE: Traditional Chinese medicine (TCM) is a unique and complex medical system that has developed over thousands of years. This article studies the problem of automatically extracting meaningful relations of entities from TCM literature, for the purposes of assisting clinical treatment or poly-pharmacology research and promoting the understanding of TCM in Western countries.
METHODS: Instead of separately extracting each relation from a single sentence or document, we propose to collectively and globally extract multiple types of relations (eg, herb-syndrome, herb-disease, formula-syndrome, formula-disease, and syndrome-disease relations) from the entire corpus of TCM literature, from the perspective of network mining. In our analysis, we first constructed heterogeneous entity networks from the TCM literature, in which each edge is a candidate relation, then used a heterogeneous factor graph model (HFGM) to simultaneously infer the existence of all the edges. We also employed a semi-supervised learning algorithm estimate the model's parameters.
RESULTS: We performed our method to extract relations from a large dataset consisting of more than 100,000 TCM article abstracts. Our results show that the performance of the HFGM at extracting all types of relations from TCM literature was significantly better than a traditional support vector machine (SVM) classifier (increasing the average precision by 11.09%, the recall by 13.83%, and the F1-measure by 12.47% for different types of relations, compared with a traditional SVM classifier).
CONCLUSION: This study exploits the power of collective inference and proposes an HFGM based on heterogeneous entity networks, which significantly improved our ability to extract relations from TCM literature.
© The Author 2015. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For Permissions, please email: journals.permissions@oup.com.

Entities:  

Keywords:  collective inference; factor graph model; heterogeneous entity networks; relation extraction; traditional Chinese medicine

Mesh:

Year:  2015        PMID: 26224335      PMCID: PMC7784314          DOI: 10.1093/jamia/ocv092

Source DB:  PubMed          Journal:  J Am Med Inform Assoc        ISSN: 1067-5027            Impact factor:   4.497


  18 in total

1.  Extraction of regulatory gene/protein networks from Medline.

Authors:  Jasmin Saric; Lars Juhl Jensen; Rossitza Ouzounova; Isabel Rojas; Peer Bork
Journal:  Bioinformatics       Date:  2005-07-26       Impact factor: 6.937

2.  RelEx--relation extraction using dependency parse trees.

Authors:  Katrin Fundel; Robert Küffner; Ralf Zimmer
Journal:  Bioinformatics       Date:  2006-12-01       Impact factor: 6.937

3.  Traditional medicine: a culture in the balance.

Authors:  Jane Qiu
Journal:  Nature       Date:  2007-07-12       Impact factor: 49.962

4.  Kernel approaches for genic interaction extraction.

Authors:  Seonho Kim; Juntae Yoon; Jihoon Yang
Journal:  Bioinformatics       Date:  2007-11-14       Impact factor: 6.937

5.  Protein-protein interaction extraction by leveraging multiple kernels and parsers.

Authors:  Makoto Miwa; Rune Saetre; Yusuke Miyao; Jun'ichi Tsujii
Journal:  Int J Med Inform       Date:  2009-06-04       Impact factor: 4.046

6.  Extraction of semantic biomedical relations from text using conditional random fields.

Authors:  Markus Bundschus; Mathaeus Dejori; Martin Stetter; Volker Tresp; Hans-Peter Kriegel
Journal:  BMC Bioinformatics       Date:  2008-04-23       Impact factor: 3.169

7.  Automated acquisition of disease drug knowledge from biomedical and clinical documents: an initial study.

Authors:  Elizabeth S Chen; George Hripcsak; Hua Xu; Marianthi Markatou; Carol Friedman
Journal:  J Am Med Inform Assoc       Date:  2007-10-18       Impact factor: 4.497

8.  Consolidating the set of known human protein-protein interactions in preparation for large-scale mapping of the human interactome.

Authors:  Arun K Ramani; Razvan C Bunescu; Raymond J Mooney; Edward M Marcotte
Journal:  Genome Biol       Date:  2005-04-15       Impact factor: 13.583

9.  TCMID: Traditional Chinese Medicine integrative database for herb molecular mechanism analysis.

Authors:  Ruichao Xue; Zhao Fang; Meixia Zhang; Zhenghui Yi; Chengping Wen; Tieliu Shi
Journal:  Nucleic Acids Res       Date:  2012-11-29       Impact factor: 16.971

10.  All-paths graph kernel for protein-protein interaction extraction with evaluation of cross-corpus learning.

Authors:  Antti Airola; Sampo Pyysalo; Jari Björne; Tapio Pahikkala; Filip Ginter; Tapio Salakoski
Journal:  BMC Bioinformatics       Date:  2008-11-19       Impact factor: 3.169

View more
  7 in total

1.  A general approach for improving deep learning-based medical relation extraction using a pre-trained model and fine-tuning.

Authors:  Tao Chen; Mingfen Wu; Hexi Li
Journal:  Database (Oxford)       Date:  2019-01-01       Impact factor: 3.451

Review 2.  Information Extraction from the Text Data on Traditional Chinese Medicine: A Review on Tasks, Challenges, and Methods from 2010 to 2021.

Authors:  Tingting Zhang; Zonghai Huang; Yaqiang Wang; Chuanbiao Wen; Yangzhi Peng; Ying Ye
Journal:  Evid Based Complement Alternat Med       Date:  2022-05-13       Impact factor: 2.650

3.  Collaborative relation annotation and quality analysis in Markyt environment.

Authors:  Martín Pérez-Pérez; Gael Pérez-Rodríguez; Florentino Fdez-Riverola; Anália Lourenço
Journal:  Database (Oxford)       Date:  2017-01-01       Impact factor: 3.451

4.  A corpus of plant-disease relations in the biomedical domain.

Authors:  Baeksoo Kim; Wonjun Choi; Hyunju Lee
Journal:  PLoS One       Date:  2019-08-28       Impact factor: 3.240

5.  Constructing fine-grained entity recognition corpora based on clinical records of traditional Chinese medicine.

Authors:  Tingting Zhang; Yaqiang Wang; Xiaofeng Wang; Yafei Yang; Ying Ye
Journal:  BMC Med Inform Decis Mak       Date:  2020-04-06       Impact factor: 2.796

6.  Decision-Making System for the Diagnosis of Syndrome Based on Traditional Chinese Medicine Knowledge Graph.

Authors:  Rui Yang; Qing Ye; Chunlei Cheng; Suhua Zhang; Yong Lan; Jing Zou
Journal:  Evid Based Complement Alternat Med       Date:  2022-02-10       Impact factor: 2.629

7.  Antimicrobial, Anthelmintic, and Antiviral Activity of Plants Traditionally Used for Treating Infectious Disease in the Similipal Biosphere Reserve, Odisha, India.

Authors:  Sujogya K Panda; Laxmipriya Padhi; Pieter Leyssen; Maoxuan Liu; Johan Neyts; Walter Luyten
Journal:  Front Pharmacol       Date:  2017-10-23       Impact factor: 5.810

  7 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.