Difference between tokenizing anndata vs loom
#351
by
alandenadel
- opened
Tokenizing anndata adds cells
tokenized_cells += [
rank_genes(X_norm[i].data, coding_miRNA_tokens[X_norm[i].indices])
for i in range(X_norm.shape[0])
]
while tokenizing loom adds cells like this:
tokenized_cells += [
tokenize_cell(subview_norm_array[:, i], coding_miRNA_tokens)
for i in range(subview_norm_array.shape[1])
]
Can someone explain why anndata needs rank_genes and loom does not?
Thank you for your question. If you look in the code for tokenize_cell, it calls rank_genes, so they both use it.
ctheodoris
changed discussion status to
closed