comparison salmonKallistoMtxTo10x.py @ 7:60fa6080f86f draft

planemo upload for repository https://github.com/ebi-gene-expression-group/container-galaxy-sc-tertiary/tree/develop/tools/salmon-kallisto-mtx-to-10x/.shed.yml commit 26982f271bc98aed93b20c68d73ed610ddada16e

6:17f7e1e51fad

# Read gene and cell labels, apply cell prefix

cb_names = [cell_prefix + s for s in pd.read_csv(cb_file, header=None)[0].values]
gene_names = pd.read_csv(gene_file, header=None)[0].values
umi_counts = mmread( quant_file )
    
# Write outputs to a .mtx file readable by tools expecting 10X outputs.
# Barcodes file works as-is, genes need to be two-column, duplicating the
# identifiers. Matrix itself needs to have genes by row, so we transpose. 

pathlib.Path(mtx_out).mkdir(parents=True, exist_ok=True)

7:60fa6080f86f

# Read gene and cell labels, apply cell prefix

cb_names = [cell_prefix + s for s in pd.read_csv(cb_file, header=None)[0].values]
gene_names = pd.read_csv(gene_file, header=None)[0].values
umi_counts = mmread( quant_file )
   
nrows = umi_counts.shape[0]  
ncols = umi_counts.shape[1]  

# Add a dimension check

if len(cb_names) != nrows:
    print('The number of matrix rows (%d) does not match the number of supplied barcodes (%d)' % (nrows, len(cb_names)))
    sys.exit(1)

if len(gene_names) != ncols:
    print('The number of matrix columns (%d) does not match the number of supplied genes (%d)' % (ncols, len(gene_names)))
    sys.exit(1)

# Write outputs to a .mtx file readable by tools expecting 10X outputs.
# Barcodes file works as-is, genes need to be two-column, duplicating the
# identifiers. Matrix itself needs to have genes by row, so we transpose. 

pathlib.Path(mtx_out).mkdir(parents=True, exist_ok=True)