Figure 10
From: Learning pair-wise gene functional similarity by multiplex gene expression maps
Cumulated weight of selected features on the restricted subset - Cellular Component. 1 - 42: wavelet features; 43 - 110: original voxels; 111: the correlation coefficient; 112: the p-value of the correlation coefficients; 113: the Euclidean distance between pair-wise gene maps; 114 - 284: average of neighbouring voxels; 285 - 455: absolute value of difference between neighbouring voxels.