How to determine the k value about liger HOT 1 CLOSED

In the PBMC walkthrough it actually specifies several non-default options with which to run suggestK, whereas this figure looks like it was produced with only the default options. I would recommend one change from the current walkthrough command, which is to run multiple iterations of NMF at each value of k by setting nrep; this might allow you to more easily identify an inflection point in the curve. For example, here is the result from running with the following options:

k.suggest <- suggestK(a.pbmc, num.cores = 5, gen.new = T, return.data = T, plot.log2 = F, 
nrep = 5)

While this variation does take longer to run, I think it's more clear the inflection point is somewhere between k=15 and k=25. As the walkthrough states, we selected k=22 (after some inspection of downstream results), but you can try other values of k for similar results. For the supplementary figure in the paper, we set nrep=20 (though I would not recommend this for most analyses as it takes over an hour to run). We'll update the walkthrough with this recommended change; feel free to look at the paper supplement and methods for a more detailed explanation of this heuristic.

from liger.