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")
else:
print("Only one input file detected; no downsampling")
#Transformation#
#Literature recommends cofactor of 5 for cytof data
arc, cols = arcsinh_transf(cofactor, no_arc)
#Storing marker columns for later use below
from aux.aux_functions import yes_or_NO
#2 options for the PCA plots:
#Either run basic PCA on R and plot in shiny app (less graphical customisation, simpler plots)
#Leverage PCA shiny apps.
#PCAshiny from Factoshiny -> Very basic
#Interactive PCA Explorer
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~I/O~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~#
base_dir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
aux_dir = os.path.dirname(os.path.abspath(__file__))+"/aux"
input_dir = f"{base_dir}/Analysis/Vis_PCA"
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~#
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~User Input~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~#
emd = yes_or_NO("Perform PCA on the EMD scores?", default="YES")
dremi = yes_or_NO("Perform PCA on the DREMI scores?")
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~#
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~Execute shiny Apps~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~#
#Input files should have either emd or dremi on their name
if emd==True and dremi==False:
emd_file = []
for file in os.listdir(input_dir):
if file.endswith(".txt"):
if "emd" in file.lower():
emd_file.append(file)
if len(emd_file) != 1:
sys.exit("ERROR: Please have only ONE .txt file with 'emd' in its name!")
emd_file = f"{input_dir}/{emd_file[0]}"
info_run = input("Write EMD info run (using no spaces!): ")
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!"
)
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~#
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~User Input~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~#
filter_markers = yes_or_NO(
"Do you want to filter out markers from the panel? (If so please provide .csv file)",
default="YES")
print(
"In EMD, the individual Variable distributions are compared against a reference distribution"
)
print(
"By default concatenated input files will be used as the reference distribution."
)
user_defined_denominator = yes_or_NO(
"Would you like to define your own reference instead?")
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~#
#~~~~~~~~~~~~~~~~~~~~~Preparatory steps and transformation~~~~~~~~~~~~~~~~~~~~#
# set up the files to be analysed (compare_from and compare_to)
# denominator can be concatenated input files or the user-defined txt file
output_dir = f"{base_dir}/Utils_Data/output/{folder_name}"
###~Sanity check for contents~###
filelist = [f for f in os.listdir(input_dir) if f.endswith(".txt")]
if len(filelist) == 0:
sys.exit(f"ERROR: There are no files in {input_dir}!")
#Check the files found in the directory:
print("Input files:")
for i in filelist:
print(i)
###~Co-factor~###
#Check if user wants to filter the markers based on a .csv marker file
cofactor = 5
user_cofactor = yes_or_NO(
"Using alpha=5 for the transformation. Would you like to change this value?"
)
if user_cofactor:
cofactor = int(input("Enter the new alpha to use (5=default): "))
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~#
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~Perform transformation~~~~~~~~~~~~~~~~~~~~~~~~~~#
#Identify marker columns
for input_file in filelist:
markers = []
dataset = pd.read_csv(f"{input_dir}/{input_file}", sep='\t')
print("Data read!")
markers.append([x for x in dataset.columns if x[0].isdigit()])
print("Processed columns")
for i in markers:
print("Columns identified as markers: \n", i)
import subprocess
import os
import sys
from aux.aux_functions import yes_or_NO
#Import yes or no question to choose the different plotings
#Run the separate R shiny apps accordingly
#Simultaneous emd and DREMI should both be possible since the ports are random
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~I/O~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~#
base_dir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
aux_dir = os.path.dirname(os.path.abspath(__file__)) + "/aux"
input_dir = f"{base_dir}/Analysis/Vis_Heatmap"
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~#
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~User Input~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~#
emd = yes_or_NO("Plot EMD scores on a heatmap?", default="YES")
dremi = yes_or_NO("Plot DREMI scores on a heatmap?")
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~#
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~Execute shiny Apps~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~#
#Input files should have either emd or dremi on their name.
if emd == True and dremi == False:
emd_file = []
for file in os.listdir(input_dir):
if file.endswith(".txt"):
if "emd" in file.lower():
emd_file.append(file)
if len(emd_file) != 1:
sys.exit(
"ERROR: Please have only ONE .txt file with 'emd' in its name!")
emd_file = f"{input_dir}/{emd_file[0]}"