Introduction

Protein Complexes Mining from Protein Interaction Network

Introduction

While recent technological advances have made available large datasets of experimentally- detected pairwise protein-protein interactions, there is still a lack of experimentally-determined protein complex data. To make up for this lack of protein complex data, we explore the mining of existing protein interaction graphs for protein complexes. We propose a novel graph mining algorithm to detect the dense neighborhoods (highly connected regions) in an interaction graph which may correspond to protein complexes. We present experimental results with yeast protein interaction data to demonstrate the effectiveness of our proposed method. Compared with other existing techniques, our predicted complexes can match or overlap significantly better with the known protein complexes in the MIPS benchmark database. Novel protein complexes were also predicted to help biologists in their search for new protein complexes.

Algorithms

In this project, we proposed two algorithms:

1. LCMA (Local Cliques Merging Algorithm), the paper Interaction Graph Mining for Protein Complexes Using Local Clique Merging , Won Best PAPER Award in the 16th International Conference on Genome Informatics (GIW 2005), Japan GIW 2005

2. DECAFF (Dense-neighborhood Extraction using Connectivity and conFidence Features), which improves the LCMA algorithm significatly. This paper has been published in CSB 2007.

All complexes listed in this website were predicted using DECAFF .