Experimental Comparison of Classification Methods for Key Kinase Identification

摘要

Kinases play important roles in a developing neuron protruding neurites or an axon with their complex interactions. To elucidate the effect of each kinase on axon elongation and regeneration from a small set of experiments, we applied machine learning methods to a synthetic dataset based on a biologically feasible model. The result showed the ridged partial least squares (RPLS) algorithm performed better than other standard algorithms such as naive Bayes classifier, support vector machines and random forest classification. This suggests the effectiveness of dimension reduction done in RPLS.