A Topic-modeling Based Framework for Drug-drug Interaction Classification from Biomedical Text

Dingcheng Li, Sijia Liu, Majid Rastegar-Mojarad, Yanshan Wang, Vipin Chaudhary, Terry M Therneau, Hongfang D Liu

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Classification of drug-drug interaction (DDI) from medical literatures is significant in preventing medication-related errors. Most of the existing machine learning approaches are based on supervised learning methods. However, the dynamic nature of drug knowledge, combined with the enormity and rapidly growing of the biomedical literatures make supervised DDI classification methods easily overfit the corpora and may not meet the needs of real-world applications. In this paper, we proposed a relation classification framework based on topic modeling (RelTM) augmented with distant supervision for the task of DDI from biomedical text. The uniqueness of RelTM lies in its two-level sampling from both DDI and drug entities. Through this design, RelTM take both relation features and drug mention features into considerations. An efficient inference algorithm for the model using Gibbs sampling is also proposed. Compared to the previous supervised models, our approach does not require human efforts such as annotation and labeling, which is its advantage in trending big data applications. Meanwhile, the distant supervision combination allows RelTM to incorporate rich existing knowledge resources provided by domain experts. The experimental results on the 2013 DDI challenge corpus reach 48% in F1 score, showing the effectiveness of RelTM.

Original languageEnglish (US)
Pages (from-to)789-798
Number of pages10
JournalAMIA ... Annual Symposium proceedings. AMIA Symposium
Volume2016
StatePublished - 2016
Externally publishedYes

Fingerprint

Drug Interactions
Pharmaceutical Preparations
Medication Errors
Learning

ASJC Scopus subject areas

  • Medicine(all)

Cite this

A Topic-modeling Based Framework for Drug-drug Interaction Classification from Biomedical Text. / Li, Dingcheng; Liu, Sijia; Rastegar-Mojarad, Majid; Wang, Yanshan; Chaudhary, Vipin; Therneau, Terry M; Liu, Hongfang D.

In: AMIA ... Annual Symposium proceedings. AMIA Symposium, Vol. 2016, 2016, p. 789-798.

Research output: Contribution to journalArticle

Li, Dingcheng ; Liu, Sijia ; Rastegar-Mojarad, Majid ; Wang, Yanshan ; Chaudhary, Vipin ; Therneau, Terry M ; Liu, Hongfang D. / A Topic-modeling Based Framework for Drug-drug Interaction Classification from Biomedical Text. In: AMIA ... Annual Symposium proceedings. AMIA Symposium. 2016 ; Vol. 2016. pp. 789-798.
@article{70716d769afc406cb1ebf181293f0cb4,
title = "A Topic-modeling Based Framework for Drug-drug Interaction Classification from Biomedical Text",
abstract = "Classification of drug-drug interaction (DDI) from medical literatures is significant in preventing medication-related errors. Most of the existing machine learning approaches are based on supervised learning methods. However, the dynamic nature of drug knowledge, combined with the enormity and rapidly growing of the biomedical literatures make supervised DDI classification methods easily overfit the corpora and may not meet the needs of real-world applications. In this paper, we proposed a relation classification framework based on topic modeling (RelTM) augmented with distant supervision for the task of DDI from biomedical text. The uniqueness of RelTM lies in its two-level sampling from both DDI and drug entities. Through this design, RelTM take both relation features and drug mention features into considerations. An efficient inference algorithm for the model using Gibbs sampling is also proposed. Compared to the previous supervised models, our approach does not require human efforts such as annotation and labeling, which is its advantage in trending big data applications. Meanwhile, the distant supervision combination allows RelTM to incorporate rich existing knowledge resources provided by domain experts. The experimental results on the 2013 DDI challenge corpus reach 48{\%} in F1 score, showing the effectiveness of RelTM.",
author = "Dingcheng Li and Sijia Liu and Majid Rastegar-Mojarad and Yanshan Wang and Vipin Chaudhary and Therneau, {Terry M} and Liu, {Hongfang D}",
year = "2016",
language = "English (US)",
volume = "2016",
pages = "789--798",
journal = "AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium",
issn = "1559-4076",
publisher = "American Medical Informatics Association",

}

TY - JOUR

T1 - A Topic-modeling Based Framework for Drug-drug Interaction Classification from Biomedical Text

AU - Li, Dingcheng

AU - Liu, Sijia

AU - Rastegar-Mojarad, Majid

AU - Wang, Yanshan

AU - Chaudhary, Vipin

AU - Therneau, Terry M

AU - Liu, Hongfang D

PY - 2016

Y1 - 2016

N2 - Classification of drug-drug interaction (DDI) from medical literatures is significant in preventing medication-related errors. Most of the existing machine learning approaches are based on supervised learning methods. However, the dynamic nature of drug knowledge, combined with the enormity and rapidly growing of the biomedical literatures make supervised DDI classification methods easily overfit the corpora and may not meet the needs of real-world applications. In this paper, we proposed a relation classification framework based on topic modeling (RelTM) augmented with distant supervision for the task of DDI from biomedical text. The uniqueness of RelTM lies in its two-level sampling from both DDI and drug entities. Through this design, RelTM take both relation features and drug mention features into considerations. An efficient inference algorithm for the model using Gibbs sampling is also proposed. Compared to the previous supervised models, our approach does not require human efforts such as annotation and labeling, which is its advantage in trending big data applications. Meanwhile, the distant supervision combination allows RelTM to incorporate rich existing knowledge resources provided by domain experts. The experimental results on the 2013 DDI challenge corpus reach 48% in F1 score, showing the effectiveness of RelTM.

AB - Classification of drug-drug interaction (DDI) from medical literatures is significant in preventing medication-related errors. Most of the existing machine learning approaches are based on supervised learning methods. However, the dynamic nature of drug knowledge, combined with the enormity and rapidly growing of the biomedical literatures make supervised DDI classification methods easily overfit the corpora and may not meet the needs of real-world applications. In this paper, we proposed a relation classification framework based on topic modeling (RelTM) augmented with distant supervision for the task of DDI from biomedical text. The uniqueness of RelTM lies in its two-level sampling from both DDI and drug entities. Through this design, RelTM take both relation features and drug mention features into considerations. An efficient inference algorithm for the model using Gibbs sampling is also proposed. Compared to the previous supervised models, our approach does not require human efforts such as annotation and labeling, which is its advantage in trending big data applications. Meanwhile, the distant supervision combination allows RelTM to incorporate rich existing knowledge resources provided by domain experts. The experimental results on the 2013 DDI challenge corpus reach 48% in F1 score, showing the effectiveness of RelTM.

UR - http://www.scopus.com/inward/record.url?scp=85027488840&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85027488840&partnerID=8YFLogxK

M3 - Article

C2 - 28269875

AN - SCOPUS:85027488840

VL - 2016

SP - 789

EP - 798

JO - AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium

JF - AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium

SN - 1559-4076

ER -