Inferring hidden relationships from biological literature with multi-level context terms

Sejoon Lee, Jaejoon Choi, Kyunghyun Park, Min Song, Doheon Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The Swanson's ABC model is powerful to infer hidden relationships buried in biological literatures. However, the model is inadequate to infer the relations with context information. In addition, the model generates very large amount of candidates from biological text, and it is the semi-automatic, labor intensive technique requiring human expert's input. In this paper, we propose a novel interaction inference technique that incorporates context term vectors into the ABC model to discover meaningful, hidden relationships. Our hypothesis is that the context-based relation extraction between AB interactions and BC interactions is more effective and efficient than the original ABC model without considering the context information. We evaluated our hypothesis with the datasets of the "Alzheimer's disease" related 77,711 PubMed abstracts. As golden standards, PharmGKB and CTD databases were used. The results indicate that context-based interaction extraction achieved better precision than the basic ABC model approach. The literature analysis also shows that interactions inferred by the context-based approach are more meaningful than interactions by the basic ABC model.

Original languageEnglish
Title of host publicationCIKM 2011 Glasgow
Subtitle of host publicationDTMBIO'11 - Proceedings of the ACM 5th International Workshop on Data and Text Mining in Biomedical Informatics
Pages27-34
Number of pages8
DOIs
Publication statusPublished - 2011 Dec 15
EventACM 5th International Workshop on Data and Text Mining in Biomedical Informatics, DTMBIO'11, in Conjunction with the 20th ACM International Conference on Information and Knowledge Management, CIKM'11 - Glasgow, United Kingdom
Duration: 2011 Oct 242011 Oct 24

Publication series

NameInternational Conference on Information and Knowledge Management, Proceedings

Other

OtherACM 5th International Workshop on Data and Text Mining in Biomedical Informatics, DTMBIO'11, in Conjunction with the 20th ACM International Conference on Information and Knowledge Management, CIKM'11
CountryUnited Kingdom
CityGlasgow
Period11/10/2411/10/24

Fingerprint

Interaction
Data base
Inference
Alzheimer's disease
Labor

All Science Journal Classification (ASJC) codes

  • Decision Sciences(all)
  • Business, Management and Accounting(all)

Cite this

Lee, S., Choi, J., Park, K., Song, M., & Lee, D. (2011). Inferring hidden relationships from biological literature with multi-level context terms. In CIKM 2011 Glasgow: DTMBIO'11 - Proceedings of the ACM 5th International Workshop on Data and Text Mining in Biomedical Informatics (pp. 27-34). (International Conference on Information and Knowledge Management, Proceedings). https://doi.org/10.1145/2064696.2064704
Lee, Sejoon ; Choi, Jaejoon ; Park, Kyunghyun ; Song, Min ; Lee, Doheon. / Inferring hidden relationships from biological literature with multi-level context terms. CIKM 2011 Glasgow: DTMBIO'11 - Proceedings of the ACM 5th International Workshop on Data and Text Mining in Biomedical Informatics. 2011. pp. 27-34 (International Conference on Information and Knowledge Management, Proceedings).
@inproceedings{f3ad267ed9e64991945ef526b9b9d13a,
title = "Inferring hidden relationships from biological literature with multi-level context terms",
abstract = "The Swanson's ABC model is powerful to infer hidden relationships buried in biological literatures. However, the model is inadequate to infer the relations with context information. In addition, the model generates very large amount of candidates from biological text, and it is the semi-automatic, labor intensive technique requiring human expert's input. In this paper, we propose a novel interaction inference technique that incorporates context term vectors into the ABC model to discover meaningful, hidden relationships. Our hypothesis is that the context-based relation extraction between AB interactions and BC interactions is more effective and efficient than the original ABC model without considering the context information. We evaluated our hypothesis with the datasets of the {"}Alzheimer's disease{"} related 77,711 PubMed abstracts. As golden standards, PharmGKB and CTD databases were used. The results indicate that context-based interaction extraction achieved better precision than the basic ABC model approach. The literature analysis also shows that interactions inferred by the context-based approach are more meaningful than interactions by the basic ABC model.",
author = "Sejoon Lee and Jaejoon Choi and Kyunghyun Park and Min Song and Doheon Lee",
year = "2011",
month = "12",
day = "15",
doi = "10.1145/2064696.2064704",
language = "English",
isbn = "9781450309608",
series = "International Conference on Information and Knowledge Management, Proceedings",
pages = "27--34",
booktitle = "CIKM 2011 Glasgow",

}

Lee, S, Choi, J, Park, K, Song, M & Lee, D 2011, Inferring hidden relationships from biological literature with multi-level context terms. in CIKM 2011 Glasgow: DTMBIO'11 - Proceedings of the ACM 5th International Workshop on Data and Text Mining in Biomedical Informatics. International Conference on Information and Knowledge Management, Proceedings, pp. 27-34, ACM 5th International Workshop on Data and Text Mining in Biomedical Informatics, DTMBIO'11, in Conjunction with the 20th ACM International Conference on Information and Knowledge Management, CIKM'11, Glasgow, United Kingdom, 11/10/24. https://doi.org/10.1145/2064696.2064704

Inferring hidden relationships from biological literature with multi-level context terms. / Lee, Sejoon; Choi, Jaejoon; Park, Kyunghyun; Song, Min; Lee, Doheon.

CIKM 2011 Glasgow: DTMBIO'11 - Proceedings of the ACM 5th International Workshop on Data and Text Mining in Biomedical Informatics. 2011. p. 27-34 (International Conference on Information and Knowledge Management, Proceedings).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Inferring hidden relationships from biological literature with multi-level context terms

AU - Lee, Sejoon

AU - Choi, Jaejoon

AU - Park, Kyunghyun

AU - Song, Min

AU - Lee, Doheon

PY - 2011/12/15

Y1 - 2011/12/15

N2 - The Swanson's ABC model is powerful to infer hidden relationships buried in biological literatures. However, the model is inadequate to infer the relations with context information. In addition, the model generates very large amount of candidates from biological text, and it is the semi-automatic, labor intensive technique requiring human expert's input. In this paper, we propose a novel interaction inference technique that incorporates context term vectors into the ABC model to discover meaningful, hidden relationships. Our hypothesis is that the context-based relation extraction between AB interactions and BC interactions is more effective and efficient than the original ABC model without considering the context information. We evaluated our hypothesis with the datasets of the "Alzheimer's disease" related 77,711 PubMed abstracts. As golden standards, PharmGKB and CTD databases were used. The results indicate that context-based interaction extraction achieved better precision than the basic ABC model approach. The literature analysis also shows that interactions inferred by the context-based approach are more meaningful than interactions by the basic ABC model.

AB - The Swanson's ABC model is powerful to infer hidden relationships buried in biological literatures. However, the model is inadequate to infer the relations with context information. In addition, the model generates very large amount of candidates from biological text, and it is the semi-automatic, labor intensive technique requiring human expert's input. In this paper, we propose a novel interaction inference technique that incorporates context term vectors into the ABC model to discover meaningful, hidden relationships. Our hypothesis is that the context-based relation extraction between AB interactions and BC interactions is more effective and efficient than the original ABC model without considering the context information. We evaluated our hypothesis with the datasets of the "Alzheimer's disease" related 77,711 PubMed abstracts. As golden standards, PharmGKB and CTD databases were used. The results indicate that context-based interaction extraction achieved better precision than the basic ABC model approach. The literature analysis also shows that interactions inferred by the context-based approach are more meaningful than interactions by the basic ABC model.

UR - http://www.scopus.com/inward/record.url?scp=83255184425&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=83255184425&partnerID=8YFLogxK

U2 - 10.1145/2064696.2064704

DO - 10.1145/2064696.2064704

M3 - Conference contribution

SN - 9781450309608

T3 - International Conference on Information and Knowledge Management, Proceedings

SP - 27

EP - 34

BT - CIKM 2011 Glasgow

ER -

Lee S, Choi J, Park K, Song M, Lee D. Inferring hidden relationships from biological literature with multi-level context terms. In CIKM 2011 Glasgow: DTMBIO'11 - Proceedings of the ACM 5th International Workshop on Data and Text Mining in Biomedical Informatics. 2011. p. 27-34. (International Conference on Information and Knowledge Management, Proceedings). https://doi.org/10.1145/2064696.2064704