Challenges in adapting text mining for full text articles to assist pathway curation

K. E. Ravikumar; K. B. Wagholikar; Hongfang Liu

doi:10.1145/2649387.2649444

Challenges in adapting text mining for full text articles to assist pathway curation

K. E. Ravikumar, K. B. Wagholikar, Hongfang Liu

Health Sciences Research

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

3 Scopus citations

Abstract

Annotation of biological pathway databases is largely driven by manual effort with little assistance from text mining. It is a great challenge to the pathway curators to keep up with the pace of ever-growing literature. There have been recent efforts to fill this gap through text mining by identifying the relevant papers and the textual evidence pertaining to pathway information. In the current work, we evaluated the performance of a text mining system that extracts events describing molecular pathways from full text articles and its potential role in assisting manual curation of pathway databases. We specifically investigated the merits of mining full text articles for extracting pathway events by comparing the performance of our system on both full text articles and biomedical abstracts. From the preliminary results, we observed that by processing full text articles the performance of the system improved by nearly 22% against a small drop of 5% in the precision in comparison against the extractions from PubMed abstracts. Preliminary analysis of the text mining results for selected pathways from PharmGKB suggest that the pathway curators do use their biological knowledge to infer new information that go beyond what is often expressed in either the full text articles or abstracts. This study is an attempt to identify the magnitude of gaps that exist between the text mining deliverables and the demands of pathway curation.

Original language	English (US)
Title of host publication	ACM BCB 2014 - 5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics
Publisher	Association for Computing Machinery, Inc
Pages	551-558
Number of pages	8
ISBN (Electronic)	9781450328944
DOIs	https://doi.org/10.1145/2649387.2649444
State	Published - Sep 20 2014
Event	5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics, ACM BCB 2014 - Newport Beach Duration: Sep 20 2014 → Sep 23 2014

Publication series

Name	ACM BCB 2014 - 5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics

Other

Other	5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics, ACM BCB 2014
City	Newport Beach
Period	9/20/14 → 9/23/14

Keywords

Pathway curation
Pathway extraction
PharmGKB
Text mining

ASJC Scopus subject areas

Health Informatics
Computer Science Applications
Software
Biomedical Engineering

Access to Document

10.1145/2649387.2649444

Fingerprint Dive into the research topics of 'Challenges in adapting text mining for full text articles to assist pathway curation'. Together they form a unique fingerprint.

Cite this

Ravikumar, K. E., Wagholikar, K. B., & Liu, H. (2014). Challenges in adapting text mining for full text articles to assist pathway curation. In ACM BCB 2014 - 5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics (pp. 551-558). (ACM BCB 2014 - 5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics). Association for Computing Machinery, Inc. https://doi.org/10.1145/2649387.2649444

Challenges in adapting text mining for full text articles to assist pathway curation. / Ravikumar, K. E.; Wagholikar, K. B.; Liu, Hongfang.

ACM BCB 2014 - 5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics. Association for Computing Machinery, Inc, 2014. p. 551-558 (ACM BCB 2014 - 5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Ravikumar, KE, Wagholikar, KB & Liu, H 2014, Challenges in adapting text mining for full text articles to assist pathway curation. in ACM BCB 2014 - 5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics. ACM BCB 2014 - 5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics, Association for Computing Machinery, Inc, pp. 551-558, 5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics, ACM BCB 2014, Newport Beach, 9/20/14. https://doi.org/10.1145/2649387.2649444

Ravikumar KE, Wagholikar KB, Liu H. Challenges in adapting text mining for full text articles to assist pathway curation. In ACM BCB 2014 - 5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics. Association for Computing Machinery, Inc. 2014. p. 551-558. (ACM BCB 2014 - 5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics). https://doi.org/10.1145/2649387.2649444

Ravikumar, K. E. ; Wagholikar, K. B. ; Liu, Hongfang. / Challenges in adapting text mining for full text articles to assist pathway curation. ACM BCB 2014 - 5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics. Association for Computing Machinery, Inc, 2014. pp. 551-558 (ACM BCB 2014 - 5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics).

@inproceedings{562fcb1e4bd140869e9ec1f3c39813d8,

title = "Challenges in adapting text mining for full text articles to assist pathway curation",

abstract = "Annotation of biological pathway databases is largely driven by manual effort with little assistance from text mining. It is a great challenge to the pathway curators to keep up with the pace of ever-growing literature. There have been recent efforts to fill this gap through text mining by identifying the relevant papers and the textual evidence pertaining to pathway information. In the current work, we evaluated the performance of a text mining system that extracts events describing molecular pathways from full text articles and its potential role in assisting manual curation of pathway databases. We specifically investigated the merits of mining full text articles for extracting pathway events by comparing the performance of our system on both full text articles and biomedical abstracts. From the preliminary results, we observed that by processing full text articles the performance of the system improved by nearly 22% against a small drop of 5% in the precision in comparison against the extractions from PubMed abstracts. Preliminary analysis of the text mining results for selected pathways from PharmGKB suggest that the pathway curators do use their biological knowledge to infer new information that go beyond what is often expressed in either the full text articles or abstracts. This study is an attempt to identify the magnitude of gaps that exist between the text mining deliverables and the demands of pathway curation.",

keywords = "Pathway curation, Pathway extraction, PharmGKB, Text mining",

author = "Ravikumar, {K. E.} and Wagholikar, {K. B.} and Hongfang Liu",

note = "Publisher Copyright: Copyright {\textcopyright} 2014 ACM. Copyright: Copyright 2015 Elsevier B.V., All rights reserved.; 5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics, ACM BCB 2014 ; Conference date: 20-09-2014 Through 23-09-2014",

year = "2014",

month = sep,

day = "20",

doi = "10.1145/2649387.2649444",

language = "English (US)",

series = "ACM BCB 2014 - 5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics",

publisher = "Association for Computing Machinery, Inc",

pages = "551--558",

booktitle = "ACM BCB 2014 - 5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics",

}

TY - GEN

T1 - Challenges in adapting text mining for full text articles to assist pathway curation

AU - Ravikumar, K. E.

AU - Wagholikar, K. B.

AU - Liu, Hongfang

PY - 2014/9/20

Y1 - 2014/9/20

N2 - Annotation of biological pathway databases is largely driven by manual effort with little assistance from text mining. It is a great challenge to the pathway curators to keep up with the pace of ever-growing literature. There have been recent efforts to fill this gap through text mining by identifying the relevant papers and the textual evidence pertaining to pathway information. In the current work, we evaluated the performance of a text mining system that extracts events describing molecular pathways from full text articles and its potential role in assisting manual curation of pathway databases. We specifically investigated the merits of mining full text articles for extracting pathway events by comparing the performance of our system on both full text articles and biomedical abstracts. From the preliminary results, we observed that by processing full text articles the performance of the system improved by nearly 22% against a small drop of 5% in the precision in comparison against the extractions from PubMed abstracts. Preliminary analysis of the text mining results for selected pathways from PharmGKB suggest that the pathway curators do use their biological knowledge to infer new information that go beyond what is often expressed in either the full text articles or abstracts. This study is an attempt to identify the magnitude of gaps that exist between the text mining deliverables and the demands of pathway curation.

AB - Annotation of biological pathway databases is largely driven by manual effort with little assistance from text mining. It is a great challenge to the pathway curators to keep up with the pace of ever-growing literature. There have been recent efforts to fill this gap through text mining by identifying the relevant papers and the textual evidence pertaining to pathway information. In the current work, we evaluated the performance of a text mining system that extracts events describing molecular pathways from full text articles and its potential role in assisting manual curation of pathway databases. We specifically investigated the merits of mining full text articles for extracting pathway events by comparing the performance of our system on both full text articles and biomedical abstracts. From the preliminary results, we observed that by processing full text articles the performance of the system improved by nearly 22% against a small drop of 5% in the precision in comparison against the extractions from PubMed abstracts. Preliminary analysis of the text mining results for selected pathways from PharmGKB suggest that the pathway curators do use their biological knowledge to infer new information that go beyond what is often expressed in either the full text articles or abstracts. This study is an attempt to identify the magnitude of gaps that exist between the text mining deliverables and the demands of pathway curation.

KW - Pathway curation

KW - Pathway extraction

KW - PharmGKB

KW - Text mining

UR - http://www.scopus.com/inward/record.url?scp=84920724226&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84920724226&partnerID=8YFLogxK

U2 - 10.1145/2649387.2649444

DO - 10.1145/2649387.2649444

M3 - Conference contribution

AN - SCOPUS:84920724226

T3 - ACM BCB 2014 - 5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics

SP - 551

EP - 558

BT - ACM BCB 2014 - 5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics

PB - Association for Computing Machinery, Inc

T2 - 5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics, ACM BCB 2014

Y2 - 20 September 2014 through 23 September 2014

ER -