0

I am trying to run spectral biclustering (using the biclust package on R) on a correlation matrix I generated from protein concentration and lifestyle traits. When I run the code, however, I get different results for each time I call the function.

For instance, one run had cluster one with 255 rows paired with 14 columns, and the second run had cluster one with 346 rows paired with 28 columns. Is this supposed to happen or am I dooing something wrong? If I am doing something wrong, how can I fix this problem.

SpectralBiclusters = spectral(transpose_res2,numberOfEigenvalues=6,minr=2, minc=2, withinVar=1, n_clusters = NULL, n_best = 3)

Also for reference, transpose_res2 is the correlation matrix with the proteins as the rows and the traits as the columns.

JOSHUA MANICKAM
  • 1
  • Also if any additional information is necessary please let me know. – JOSHUA MANICKAM Jun 06 '22 at 05:43
  • Yes, please add a piece of your data that reproduces the problem. You can use the function `dput()`. That will output the data in a format that makes it as easy as possible for others to read it in their own environment. That increases your chances to find someone who can help you. – Jan Jun 06 '22 at 07:18

0 Answers0