Multistage Gene Normalization and SVM-Based Ranking for Protein Interactor Extraction in Full-Text Articles

The interactor normalization task (INT) is to identify genes that play the interactor role in protein-protein interactions (PPIs), to map these genes to unique IDs, and to rank them according to their normalized confidence. INT has two subtasks: gene normalization (GN) and interactor ranking. The ma...

Full description

Saved in:
Bibliographic Details
Published in:IEEE/ACM transactions on computational biology and bioinformatics 2010-07, Vol.7 (3), p.412-420
Main Authors: Hong-Jie Dai, Po-Ting Lai, Tsai, Richard Tzong-Han
Format: Article
Language:English
Subjects:
Abstracting and Indexing as Topic
Abstracts
Algorithms
Artificial Intelligence
Centralized control
Data mining
Data Mining - methods
Databases, Genetic
feature evaluation and selection
Genes
Humans
Information Storage and Retrieval
Intrusion detection
mining methods and algorithms
Natural Language Processing
Periodicals as Topic
Protein Interaction Mapping - methods
Proteins
scientific databases
Signal processing
Spatial databases
System performance
Text mining
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The interactor normalization task (INT) is to identify genes that play the interactor role in protein-protein interactions (PPIs), to map these genes to unique IDs, and to rank them according to their normalized confidence. INT has two subtasks: gene normalization (GN) and interactor ranking. The main difficulties of INT GN are identifying genes across species and using full papers instead of abstracts. To tackle these problems, we developed a multistage GN algorithm and a ranking method, which exploit information in different parts of a paper. Our system achieved a promising AUC of 0.43471. Using the multistage GN algorithm, we have been able to improve system performance (AUC) by 1.719 percent compared to a one-stage GN algorithm. Our experimental results also show that with full text, versus abstract only, INT AUC performance was 22.6 percent higher.
ISSN:1545-5963
1557-9964
DOI:10.1109/TCBB.2010.45