Weakly supervised learning of biomedical information extraction from curated data

Background Numerous publicly available biomedical databases derive data by curating from literatures. The curated data can be useful as training examples for information extraction, but curated data usually lack the exact mentions and their locations in the text required for supervised machine learn...

Full description

Saved in:
Bibliographic Details
Published in:BMC bioinformatics Vol. 17; no. Suppl 1; p. 1
Main Authors: Jain, Suvir, R., Kashyap, Kuo, Tsung-Ting, Bhargava, Shitij, Lin, Gordon, Hsu, Chun-Nan
Format: Journal Article
Language:English
Published: London BioMed Central 11.01.2016
BioMed Central Ltd
Subjects:
Abstracting and Indexing as Topic - methods
Algorithms
Bioinformatics
Biomedical and Life Sciences
Computational Biology/Bioinformatics
Computational linguistics
Computer Appl. in Life Sciences
Data Curation
Data mining
Data Mining - methods
Databases, Factual
Disease - genetics
Genetic Predisposition to Disease
Genome-Wide Association Study
Genomics
Humans
Language processing
Life Sciences
Machine learning
Microarrays
Natural language interfaces
Proceedings
Risk Assessment
New York
Biomedical text mining
Database curation
Natural language processing
Information extraction
Machine learning
ISSN:1471-2105, 1471-2105
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Background Numerous publicly available biomedical databases derive data by curating from literatures. The curated data can be useful as training examples for information extraction, but curated data usually lack the exact mentions and their locations in the text required for supervised machine learning. This paper describes a general approach to information extraction using curated data as training examples. The idea is to formulate the problem as cost-sensitive learning from noisy labels, where the cost is estimated by a committee of weak classifiers that consider both curated data and the text. Results We test the idea on two information extraction tasks of Genome-Wide Association Studies (GWAS). The first task is to extract target phenotypes (diseases or traits) of a study and the second is to extract ethnicity backgrounds of study subjects for different stages (initial or replication). Experimental results show that our approach can achieve 87 % of Precision-at-2 (P@2) for disease/trait extraction, and 0.83 of F1-Score for stage-ethnicity extraction, both outperforming their cost-insensitive baseline counterparts. Conclusions The results show that curated biomedical databases can potentially be reused as training examples to train information extractors without expert annotation or refinement, opening an unprecedented opportunity of using “big data” in biomedical text mining.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1471-2105
1471-2105
DOI:10.1186/s12859-015-0844-1