In [8]:
'''
set filter of the external data (dataset of interest)
'''
# set filter
ram.bc.filter = ( ram.bc.select_component( 0 ) & ram.bc.get_filter( f'filtered_barcodes_subsampled_{str_num_subsampled_cells}_entries_clus_info' ) ) | ( ram.bc.select_component( 1 ) & ram.bc.get_filter( name_col_bc_all ) )
ram.ft.load_str( )
# save as a filter
ram.bc.save_as_filter(
ram.bc.select_component( 1 ) & ram.bc.get_filter( name_col_bc_all ),
'filter_external_data'
)
"""
plot co-embedded cells
"""
# settings
# ram.int_index_component_reference = None # in order to retrieve gene expression data from ELDB, set index to the reference RamData to None (if ram.int_index_component_reference == 0, only PBMC3k dataset's count data will be retrieved)
ram.ft.filter = None # retrieve expression of any genes
# set filter
ram.bc.filter = ( ram.bc.select_component( 0 ) & ram.bc.get_filter( f'filtered_barcodes_subsampled_{str_num_subsampled_cells}_entries_clus_info' ) ) | ( ram.bc.select_component( 1 ) & ram.bc.get_filter( name_col_bc_all ) ) # for RamData-0 (ELDB), select the subsampled cells. for RamData-1 (PBMC3k), select all filtered cells
# define a list of genes of interest
dict_marker_genes = {
'Proliferating' : [ 'MKI67' ],
'T-cell' : [ 'CD3D' ],
'CD4 T-cell' : [ 'CD4' ],
'CD8 T-cell' : [ 'CD8A', 'CD8B' ],
'Naive T / TCM' : [ 'CCR7', 'SELL' ],
'Effector Phenotype' : [ 'FAS', 'CD44', 'IL2RG', 'IL7R', 'CD69' ],
'TREG' : [ 'FOXP3', 'IL2RA' ],
'MAIT' : [ 'KLRB1', 'SLC4A10' ],
'SOX4+ CD4 T' : [ 'SOX4' ],
'gamma delta T' : [ 'TNFSF13B' ],
'NK' : [ 'GNLY', 'GZMB' ],
'NK Recruiting (CD56 bright)' : [ 'XCL1', 'GZMK' ],
'B cell' : [ 'MS4A1', 'CD79A' ],
'B memory' : [ 'CD27' ],
'Plasma cell' : [ 'JCHAIN', 'TXNDC5' ],
'Monocyte' : [ 'CD86' ],
'Classical Monocyte' : [ 'CD14' ],
'Non-classical Monocyte' : [ 'FCGR3A' ],
'Macrophage' : [ 'CD68' ],
'Macrophage (M1)' : [ 'CD86', 'FCGR2A', ],
'Macrophage (M2)' : [ 'CD163', 'MSR1' ],
'Dendritic' : [ 'FCER1A' ],
"cDC1" : [ 'THBD', 'CLEC9A' ],
'cDC2' : [ 'CD1C', 'SIRPA' ],
'pDC' : [ 'CLEC4C', 'IL3RA', 'LILRA4' ],
'Platelet' : [ 'ITGA2B' ],
'HPSC' : [ 'CD34' ],
}
l_marker_genes = [ ] # collect the marker genes
for e in dict_marker_genes :
l_marker_genes += dict_marker_genes[ e ]
adata = ram[
'normalized_log1p_capped',
:,
[ "str", 'raw_sum', 'filter_external_data', name_anno_predicted, name_anno_ori, { name_umap_combined } ],
l_marker_genes,
[ 'str' ]
] # for detailed descriptions, please see "Tutorial 1) Processing and analysis of the 3k PBMCs dataset using SC-Elephant.""
adata.obsm[ 'X_umap' ] = adata.obsm[ name_umap_combined ]
adata.obs[ 'filter_external_data' ] = adata.obs[ 'filter_external_data' ].astype( str ).astype( object )
sc.pl.umap( adata, color = 'filter_external_data', size = 1 )
"""
plot predicted annotations
"""
sc.pl.umap( adata, color = name_anno_ori, size = 5 ) # cell types annotations from the Extended PBMC3k dataset
sc.pl.umap( adata, color = name_anno_predicted, size = 5 ) # cell types annotations from the Extended PBMC3k dataset
2023-11-18 21:33:13,362 [SC-Elephant] <INFO> (load_str) - completed loading of 10504 number of strings 2023-11-18 21:33:28,991 [SC-Elephant] <INFO> (load_str) - completed loading of 262431 number of strings 2023-11-18 21:33:35,612 [SC-Elephant] <INFO> (load_str) - completed loading of 62914 number of strings ... storing 'filter_external_data' as categorical
