Closed achamess closed 3 months ago
Thanks for the feedback. In previous versions I appended "cluster_" to the number to avoid these python type problems, but I thought the current version was ok with numeric cluster labels. What is the dtype category you are currently using?
In a test analysis that i have up , the cluster assignment vector, louvain in this case, is:
Name: louvain, Length: 1846, dtype: category Categories (6, object): ['0', '1', '2', '3', '4', '5']
Thanks for the response. Sorry for my late reply. Initially, the cluster label is numeric but I did force it to a category and I get the error still
D1_GTGGAGATCTGCTTAT 15
D1_GCACGGTCACTCAGAT 15
D1_TATACCTGTCTTACTT 15
D1_TATATCCAGAGCATCG 15
D1_CGTGATAAGGTATCTC 15
..
V2_CTTTCGGAGCTCGACC 18
V2_AGAGCCCAGGAAGTAG 8
V2_AACGAAACAATAAGGT 23
V2_AAGTACCTCGCATTAG 8
V2_GTTCGCTGTTGGGACA 8
Name: L1_Round4, Length: 17906, dtype: category
Categories (26, object): ['0', '1', '2', '3', ..., '22', '23', '24', '25']
Thanks for the response. Sorry for my late reply. Initially, the cluster label is numeric but I did force it to a category and I get the error still
D1_GTGGAGATCTGCTTAT 15 D1_GCACGGTCACTCAGAT 15 D1_TATACCTGTCTTACTT 15 D1_TATATCCAGAGCATCG 15 D1_CGTGATAAGGTATCTC 15 .. V2_CTTTCGGAGCTCGACC 18 V2_AGAGCCCAGGAAGTAG 8 V2_AACGAAACAATAAGGT 23 V2_AAGTACCTCGCATTAG 8 V2_GTTCGCTGTTGGGACA 8 Name: L1_Round4, Length: 17906, dtype: category Categories (26, object): ['0', '1', '2', '3', ..., '22', '23', '24', '25']
The same error as me! Don't know what's wrong with the data...
Thanks of the ticket. Code refactored in v4.0.
I converted a Seurat object to AnnData using SeuratDisk. It seemed to work.
These are the features of the resulting object:
The cluster assignment I want to use is 'SCT_snn_res.0.8'. I changed this to dtype category and then changed the function call to NS_Forest to reflect that I want to use this column.
When I run
adata_markers = NS_Forest(adata)
It starts up, but I get this error: