Inferring protein-protein interaction networks from protein complex data

Authors:
Shawn Martin;Zisu Mao;Linda S. Chan;Suraiya Rasheed
Affiliations:
Department of Computational Biology,Sandia National Laboratories, Albuquerque, NM 87185-1316, USA.;Laboratory of Viral Oncology and Proteomics Research, Department of Pathology, University of Southern California, Los Angeles, CA 90032-3626, USA.;Department of Pediatrics, Keck School of Medicine, University of Southern California, Los Angeles, CA 90032-3626, USA.;Laboratory of Viral Oncology and Proteomics Research, Department of Pathology, University of Southern California, Los Angeles, CA 90032-3626, USA
Venue:
International Journal of Bioinformatics Research and Applications
Year:
2007

Citing 6
Cited 0

Making large-scale support vector machine learning practical

Advances in kernel methods
An introduction to support Vector Machines: and other kernel-based learning methods

An introduction to support Vector Machines: and other kernel-based learning methods
Support vector machines: hype or hallelujah?

ACM SIGKDD Explorations Newsletter - Special issue on “Scalable data mining algorithms”
A Tutorial on Support Vector Machines for Pattern Recognition

Data Mining and Knowledge Discovery
Kernel methods for predicting protein--protein interactions

Bioinformatics
Predicting protein--protein interactions using signature products

Bioinformatics

Quantified Score

Hi-index	0.00

Visualization

Abstract

Present day approaches for the determination of protein-proteininteraction networks are usually based on two hybrid experimentalmeasurements. Here we consider a computational method that usesanother type of experimental data: instead of direct informationabout protein-protein interactions, we consider data in the form ofprotein complexes. We propose a method for using these complexes toprovide predictions of protein-protein interactions. When appliedto a dataset obtained from a cat melanoma cell line we find that weare able to predict when a protein pair belongs to a complex with∼96% accuracy. Further, we are able to extrapolate theexperimentally identified interaction pairs to the entire catproteome.