def kallisto_table(kallisto_dir, index):
"""
convert kallisto output to a count table where the rows are
equivalence classes and the columns are cells
"""
quant_dir = os.path.join(kallisto_dir, "quant")
out_file = os.path.join(quant_dir, "matrix.csv")
if file_exists(out_file):
return out_file
tsvfile = os.path.join(quant_dir, "matrix.tsv")
ecfile = os.path.join(quant_dir, "matrix.ec")
cellsfile = os.path.join(quant_dir, "matrix.cells")
fastafile = os.path.splitext(index)[0] + ".fa"
fasta_names = fasta.sequence_names(fastafile)
ec_names = get_ec_names(ecfile, fasta_names)
df = pd.read_csv(tsvfile,
header=None,
names=["ec", "cell", "count"],
sep="\t")
df["ec"] = [ec_names[x] for x in df["ec"]]
df = df.pivot(index='ec', columns='cell', values='count')
cellnames = get_cell_names(cellsfile)
colnames = [cellnames[x] for x in df.columns]
df.columns = colnames
df.to_csv(out_file)
return out_file
def kallisto_table(kallisto_dir, index):
"""
convert kallisto output to a count table where the rows are
equivalence classes and the columns are cells
"""
quant_dir = os.path.join(kallisto_dir, "quant")
out_file = os.path.join(quant_dir, "matrix.csv")
if file_exists(out_file):
return out_file
tsvfile = os.path.join(quant_dir, "matrix.tsv")
ecfile = os.path.join(quant_dir, "matrix.ec")
cellsfile = os.path.join(quant_dir, "matrix.cells")
fastafile = os.path.splitext(index)[0] + ".fa"
fasta_names = fasta.sequence_names(fastafile)
ec_names = get_ec_names(ecfile, fasta_names)
df = pd.read_table(tsvfile, header=None, names=["ec", "cell", "count"])
df["ec"] = [ec_names[x] for x in df["ec"]]
df = df.pivot(index='ec', columns='cell', values='count')
cellnames = get_cell_names(cellsfile)
colnames = [cellnames[x] for x in df.columns]
df.columns = colnames
df.to_csv(out_file)
return out_file