Fast protein classification with multiple networks
1Max Planck Institute for Biological Cybernetics Spemannstrasse 38, 72076 Tübingen, Germany
2Computational Biology Research Center, National Institute of Advanced Industrial Science and Technology (AIST) 2-42 Aomi Koto-ku, Tokyo, Japan
3Friedrich Miescher Laboratory, Max Planck Society Spemannstrasse 37, 72076, Tübingen, Germany
*To whom correspondence should be addressed.
Motivation: Support vector machines (SVMs) have been successfully used to classify proteins into functional categories. Recently, to integrate multiple data sources, a semidefinite programming (SDP) based SVM method was introduced. In SDP/SVM, multiple kernel matrices corresponding to each of data sources are combined with weights obtained by solving an SDP. However, when trying to apply SDP/SVM to large problems, the computational cost can become prohibitive, since both converting the data to a kernel matrix for the SVM and solving the SDP are time and memory demanding. Another application-specific drawback arises when some of the data sources are protein networks. A common method of converting the network to a kernel matrix is the diffusion kernel method, which has time complexity of O(n3), and produces a dense matrix of size n x n.
Results: We propose an efficient method of protein classification using multiple protein networks. Available protein networks, such as a physical interaction network or a metabolic network, can be directly incorporated. Vectorial data can also be incorporated after conversion into a network by means of neighbor point connection. Similar to the SDP/SVM method, the combination weights are obtained by convex optimization. Due to the sparsity of network edges, the computation time is nearly linear in the number of edges of the combined network. Additionally, the combination weights provide information useful for discarding noisy or irrelevant networks. Experiments on function prediction of 3588 yeast proteins show promising results: the computation time is enormously reduced, while the accuracy is still comparable to the SDP/SVM method.
Availability: Software and data will be available on request.
Contact: shin{at}tuebingen.mpg.de
CiteULike 
Connotea 
Del.icio.us What's this?
This article has been cited by other articles:
|
|
 |
|
  Z. Tian, T. Hwang, and R. Kuang A hypergraph-based learning algorithm for classifying gene expression and arrayCGH data with prior knowledge Bioinformatics, November 1, 2009; 25(21): 2831 - 2838. [Abstract] [Full Text] [PDF]
|
|
|
|
|
|
T. Hwang, H. Sicotte, Z. Tian, B. Wu, J.-P. Kocher, D. A. Wigle, V. Kumar, and R. Kuang Robust and efficient identification of biomarkers by classifying features on graphs Bioinformatics, September 15, 2008; 24(18): 2023 - 2029. [Abstract] [Full Text] [PDF]
|
|
|
|
|
|
H. N. Chua, W.-K. Sung, and L. Wong An efficient strategy for extensive integration of diverse biological data for protein function prediction Bioinformatics, December 15, 2007; 23(24): 3364 - 3373. [Abstract] [Full Text] [PDF]
|
|