Related Experiment Video
Updated: May 20, 2026

Genome-wide Protein-protein Interaction Screening by Protein-fragment Complementation Assay (PCA) in Living Cells
Published on: March 3, 2015
Improving protein-protein interaction pair ranking with an integrated global association score
1Department of Computer Science and Engineering, Yuan Ze University, No. 135, Far East Rd., 320 Chung-Li, Taiwan. thtsai@saturn.yzu.edu.tw
This study introduces a new method for ranking protein-protein interaction (PPI) pairs using a composite score. This approach improves the reliability of PPI database curation by considering global gene associations alongside pair associations.
Area of Science:
- Bioinformatics
- Computational Biology
- Text Mining
Background:
- Protein-protein interaction (PPI) database curation relies on text-mining for gene recognition and PPI pair extraction.
- Accurate ranking of PPI pairs is crucial for efficient manual curation.
- Current ranking methods primarily use pairwise gene association, which may not capture the full context.
Purpose of the Study:
- To develop a more reliable method for ranking protein-protein interaction (PPI) pairs extracted from scientific literature.
- To introduce a composite interaction score that incorporates both direct pair association and global gene associations within an article.
- To evaluate the effectiveness of different data fusion algorithms for estimating global gene association scores.
Main Methods:
- A composite interaction score was designed, combining pair association scores with global association scores.
- Three data fusion algorithms (two Borda-Fuse models, one Linear Combination Model - LCM) were tested to estimate global association scores.
- Performance was evaluated using the BioCreative II.5 Interaction Pair Task (IPT) dataset, measuring the area under the interpolated precision/recall curve (AUC iP/R).
Main Results:
- The Linear Combination Model (LCM) significantly improved the estimation of global association scores.
- Using LCM boosted the AUC iP/R score from 0.0175 to 0.2396.
- The proposed composite score and LCM outperformed the best system in the BioCreative II.5 IPT competition.
Conclusions:
- A novel composite interaction score enhances the ranking of protein-protein interaction pairs.
- Estimating global gene associations using LCM provides a more reliable ranking for PPI database curation.
- This approach offers a significant improvement over existing methods for automated PPI extraction and ranking.
More Related Videos
13:56A Comparative Approach to Characterize the Landscape of Host-Pathogen Protein-Protein Interactions
Published on: July 18, 2013
07:08Optimization of Synthetic Proteins: Identification of Interpositional Dependencies Indicating Structurally and/or Functionally Linked Residues
Published on: July 14, 2015
Related Concept Videos
Protein-protein Interfaces
Protein-Protein Interfaces
Protein Networks
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
Protein Networks
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
Conserved Binding Sites
Binding sites are often located in large pockets, and if their location on a protein’s surface is unknown, it can be predicted using various approaches. The energetic method computationally analyses the...
Protein Complexes with Interchangeable Parts
The SCF ubiquitin ligase is a protein complex of five individual proteins. This complex attaches ubiquitin to other target proteins to mark them for degradation. In order to...