Errors with reloading EMBEDR, Simes' method, question about figures about embedr HOT 3 OPEN

Hello!

Sorry for the delay in responding!

1. I will look into finding and posting those figure-generating codes.
2. Can you tell me the initialization you used and the size of the data that generated this error?
3. This looks like a bug in the path-finding code... Again if you could send me the full script that generated this error I might be able to diagnose the issue better.
4. I was waiting for an update to UMAP before adding that example, but it appears to have been updated so I will generate and post that shortly!

from embedr.

Hi,

No worries, thanks for getting back to me!

R.e #3 I figured it out, was just an issue with how windows was handling slashes with '.split("/")[-1]', I just had to change it out to .split(os.sep)[-1] and have had no more problems there.

For #2, the error has occured with datasets from 1000 cells x 10PCs up to 3500 cells x 3700 genes. For the intialisation, i've tried:

embObj = EMBEDR(DRA=alg, #error occurs with t-SNE and UMAP
n_jobs=-1,
random_state=96, #have tried multiple
n_data_embed=5,
n_null_embed=5,
n_components=2,
perplexity=perp, #have tried multiple from 10 to 300
n_neighbors=n_neib, #have tried multiple from 31 to 999
pVal_type='simes',
verbose=3,
project_name=f'{alg}_{dat}',
project_dir=project_dir)

Im running Python 3.8.13 with Jupyter lab 3.3.4.

Thanks, and I saw on twitter you recently defended so congratulations!
Ebony

from embedr.

Also, I was wondering why you chose not to perform multiple testing adjustment of the p-values for the paper? This is why I originally wanted to see how using the Simes method changed the results. As I couldnt get it working I performed BH adjustment on the raw p-values before averaging across the embeddings instead, and saw a large difference for some datasets. Does the way the p-value is dervived make adjustment unnecessary?

Sorry for all the questions!
Ebony

from embedr.