search

wgmao / DelayedPLIER

1 stars 2 forks source link

Error with sample data #2

Closed miltondp closed 2 months ago

miltondp commented 2 months ago

I followed the example in the README file and the training seems to finish, but it fails with this error:

> PLIER.res <- PLIER(data, priorMat, output_path = "output/")

Selecting common genes: 5485
Removing 0 pathways with too few genes
Computing SVD
Using rsvd
Done
k is set to 260
[1] 120.8525
[1] "L2 is set to 120.852491861614"
[1] "L1 is set to 60.426245930807"
errorY (SVD based:best possible) = 0.8011
New L3 is 0.000488095243523415
New L3 is 0.000626726698448458
New L3 is 0.000626726698448458
New L3 is 0.000626726698448458
New L3 is 0.000626726698448458
New L3 is 0.000626726698448458
New L3 is 0.000626726698448458
Bdiff is not decreasing
Bdiff is not decreasing
Bdiff is not decreasing
Bdiff is not decreasing
Bdiff is not decreasing
Bdiff is not decreasing
converged at  iteration 151 Bdiff is not decreasing
Error in if (class(mat) == "matrix") { : the condition has length > 1

The copyMat function seems to be used to compute the AUC for the LV/pathways.

msubirana commented 2 months ago

I've fixed the copyMat function, and it's now working correctly. I've submitted a pull request for review @wgmao

wgmao commented 2 months ago

Apologies for the delay in getting back to you. Thank you for your help in resolving this bug. Your contribution is greatly appreciated!