if len(info_run) == 0:
print("No info run given. Saving results in UNNAMED")
info_run = "UNNAMED"
if os.path.isdir(f"{output_dir}/{info_run}") == False:
os.makedirs(f"{output_dir}/{info_run}")
else:
if info_run != "UNNAMED":
sys.exit(
"ERROR: You already used this name for a previous run. \nUse a different name!"
)
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~#
#~~~~~~~~~~~~~~~~~~~Preliminary steps and transformation~~~~~~~~~~~~~~~~~~~~~~#
#Concatenate#
no_arc, input_files = concatenate_fcs(
input_dir) #Does sanity check of files in input
#Downsampling#
#Test lenght of input files -> Go with minimun denominator -> select, at random,
# that number of cells from other files
if no_arc["file_origin"].value_counts().size > 1:
downs_inputs = yes_or_NO(
"Multiple input files detected. Would you like to donwsample the number of cells?",
default="YES")
if downs_inputs:
print("Downsampling taking place. Check output folder for more info")
print(no_arc["file_origin"].value_counts())
no_arc = downsample_data(no_arc, info_run, output_dir)
print(no_arc["file_origin"].value_counts())
else:
print("Multiple input files; no downsampling")
if len(pnn_extracted) != 0:
raise fcsparser.api.ParserFeatureNotImplementedError
except fcsparser.api.ParserFeatureNotImplementedError:
print("WARNING: Non-standard .fcs file detected: ", denominator)
#use rpy2 to read the files and load into python
compare_to = read_rFCS(denom_path)[0]
else:
sys.exit(
"ERROR: Reference not recognised.\nPlease state exact and full name of file to be used as denominator!"
)
input_files = filelist
else:
denominator = 'concatenated-inputs'
print(
'Concatenated input files will be used as the reference distribution')
compare_to, input_files = concatenate_fcs(
input_dir) #compare_from=inputfile
#Keep only selected markers
if filter_markers:
selected_markers = read_marker_csv(input_dir)
print(compare_to.columns)
file_cols = compare_to.columns
[x for x in file_cols if x[0].isdigit()]
for x in file_cols:
if x[0].isdigit():
if x not in selected_markers:
compare_to = compare_to.drop(x, axis=1)
print(compare_to.columns)
# compare_to = downsample_data(compare_to, info_run, output_dir) #Customtest_1
compare_to_arc, marker_list = arcsinh_transf(cofactor,
filelist = [f for f in os.listdir(input_dir) if f.endswith(".txt")]
if len(filelist) == 0:
sys.exit(f"ERROR: There are no .txt files in {input_dir}!")
#Check the files found in the directory:
print("Downsample script supports only .txt files. Input files:")
for i in filelist:
print(i)
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~#
print(
"This script now downsamples multiple files on the input to the condition with less cells"
)
info_run = input("Write downsampling info run (using no spaces!): ")
concatenated_df = concatenate_fcs(input_dir)[0]
downsampled_conc_df = downsample_data(concatenated_df, info_run, output_dir)
# Since after downsampling file_origin is also an index, drop index from dataframe
for name, group in downsampled_conc_df.reset_index(
drop=True).groupby("file_identifier"):
print(name)
print(group)
group.reset_index()
# group['post-downsample_cell-index'] = group.index
group.to_csv(f"{output_dir}/{info_run}/{name}_downsample_{info_run}.txt",
index=False,
sep='\t')
print(f"Downsampled files saved in {output_dir}")