Tian Chu

because of The BiocParallel errors. If you are using windows, just set register(SnowParam(workers = 1, progressbar = TRUE)). just use one core

Same question: `devtools::install_github('linxihui/NNLM')` * installing *source* package ‘NNLM’ ... ** using staged installation ** libs using C++ compiler: ‘Apple clang version 14.0.3 (clang-1403.0.22.14.1)’ using SDK: ‘MacOSX13.3.sdk’ clang++ -arch arm64 -std=gnu++17...

re-install SEACells from github can give you the chance to using GPU by adding use_gpu=True

cnmf_obj.consensus(k=selected_K, density_threshold=density_threshold, show_clustering=True, close_clustergram_fig=False)

add norm_tpm.X = norm_tpm.X.astype(np.float32) and norm_counts.X = norm_counts.X.astype(np.float32) can solve this problem

Traceback (most recent call last): File "", line 1, in File "/data/person/wup/public/miniconda3/envs/celldancer/lib/python3.9/site-packages/celldancer/__init__.py", line 2, in from .velocity_estimation import velocity File "/data/person/wup/public/miniconda3/envs/celldancer/lib/python3.9/site-packages/celldancer/velocity_estimation.py", line 9, in import torch File "/data/person/wup/public/miniconda3/envs/celldancer/lib/python3.9/site-packages/torch/__init__.py", line 197,...

Same question： Can you give a hint on how to better choose global gene sets or the rational behind their selection? How to choose the best global gene sets.

It should by definition not have any NA value. But I don't know why this problem has arisen. adata_raw = adata.copy() preprocessor = dyn.pp.Preprocessor(cell_cycle_score_enable=True) preprocessor.config_monocle_recipe(adata_raw) preprocessor.filter_cells_by_outliers_kwargs["keep_filtered"] = False preprocessor.filter_genes_by_outliers_kwargs["inplace"]=True preprocessor.select_genes_kwargs["n_top_genes"]=3000...

Really helpful

The same issue persists. Besides that, why is it mandatory to specify groups when providing a palette? This restriction prevents me from customizing cell group colors freely, which is very...