论文信息 - Protein Classification Using Random Walk on Graph

Protein Classification Using Random Walk on Graph

Inspired by the label propagation based on random walk, a basic classifier is proposed for biological computation. We apply this model to predict the localization of proteins, specifically the yeast and gram-negative bacteria protein data. A series of evaluations and comparisons are conducted to prove its excellent performance as an effectively independent classifier.

[1] J. Lafferty,et al. Combining active learning and semi-supervised learning using Gaussian fields and harmonic functions , 2003, ICML 2003.

[2] Graham Cormode,et al. Node Classification in Social Networks , 2011, Social Network Data Analytics.

[3] Zhaolei Zhang,et al. Learned Random-Walk Kernels and Empirical-Map Kernels for Protein Sequence Classification , 2009, J. Comput. Biol..

[4] Tommi S. Jaakkola,et al. Partially labeled classification with Markov random walks , 2001, NIPS.

[5] Valerio Freschi,et al. Protein function prediction from interaction networks using a random walk ranking algorithm , 2007, 2007 IEEE 7th International Symposium on BioInformatics and BioEngineering.

[6] László Lovász,et al. Random Walks on Graphs: A Survey , 1993 .

[7] Zoubin Ghahramani,et al. Combining active learning and semi-supervised learning using Gaussian fields and harmonic functions , 2003, ICML 2003.