D = D.astype(float)
###Applying a threshold for the read depth
#User input and input check
q = zp.question(
title="Mutation Filtering",
text=
"Do you want to apply a threshold for read depth? Values below the threshold will be treated as absent."
)
if q == True:
thresh = zp.entry(title="Mutation Filtering", text="Threshold:")
try:
thresh = float(int(thresh))
except:
zp.error(title="Mutation Filtering",
text="Invalid input! Input must be an integer number!")
sys.exit(1)
#Application
for col in D.columns:
if ":DP" in col:
D[col] = D[col].apply(lambda x: 0.0 if x < thresh else x)
D[col.split(":")[0] + ":AF"].loc[D.loc[D[col] == 0].index] = 0
###Applying a threshold for the allele frequency
#User input and input check
q = zp.question(
title="Mutation Filtering",
text=
"Do you want to apply a threshold for allele frequency? Values below the threshold will be treated as absent."
)
mname = "pielou_evenness"
if metric == "Goods_coverage":
metric = "goods_coverage"
label = "Good's coverage"
mname = "goods_coverage"
if metric == "Chao1":
metric = "chao1"
label = "Chao1"
mname = "chao1"
if metric == "Faith_PD":
try:
tree_file = sys.argv[3]
except:
zp.error(
title="CoMA",
text=
"A tree file is required for the calculation of Faith's phylogenetic diversity!"
)
print("\nProcess terminated!")
print(
"\n________________________________________________________________________________\n"
)
sys.exit(1)
metric = "faith_pd"
label = "Faith's PD"
mname = "faith_pd"
ftype = zp.entry(
title="CoMA",
text=
"Which fileformat do you prefer?\n\neps, jpeg, pdf, png, ps, raw, rgba, svg, svgz, tiff\n"
outf.write(sample + len(variables.split(",")) * "\t" + "\n")
zp.message(
title="CoMA",
text=
"Please fill in all missing data in the map file; save then as tab-delimited text file. When you are finished, a quick check will be done to prove your input.\n\nClick now OK to start entering your metadata!",
height=100)
os.system("libreoffice --calc %s" % (outfile))
with open(outfile) as outf:
outf.readline()
if len(outf.readline().strip().split("\t")) == 1:
zp.error(
title="CoMA",
text=
"ATTENTION: Your map file is not tab-delimited! Please repeat this step and save the text file correctly using 'tab' as separator."
)
print("\nProcess terminated!")
print(
"\n________________________________________________________________________________\n"
)
sys.exit(0)
errors = 0
for line in outf:
if len([x for x in line.strip().split("\t") if x != "\t"]) <= len(
variables.split(",")):
zp.error(title="CoMA",
text="ATTENTION: This line includes empty cells:\n\n" +
line)
errors += 1
tax_list[j].add(taxa[j].strip())
return tax_list
input_file = sys.argv[1]
mapping = pz.question(
title="CoMA",
text=
"Do you want to use the information in the mapping file to group your samples?"
)
if mapping == True:
try:
map_file = sys.argv[2]
except:
pz.error(title="CoMA",
text="No mapping file provided, process terminated!")
print("\nNo mapping file provided, process terminated!")
print(
"\n________________________________________________________________________________\n"
)
sys.exit(1)
map_DF = pd.read_csv(map_file, delimiter="\t", index_col=0)
var = pz.entry(
title="CoMA",
text=
"Based on which metadata variable do you want to group your samples?\n\nYou can select between the following variables:\n\n"
+ ", ".join(map_DF.columns) + "\n")
if len(map_DF[var].value_counts()) > 3:
pz.error(
title="CoMA",
text=
metric = "chebyshev"
mname = "chebyshev"
if metric == "Braycurtis":
metric = "braycurtis"
mname = "braycurtis"
if metric == "Dice":
metric = "dice"
mname = "dice"
if metric == "weighted_unifrac" or metric == "unweighted_unifrac":
try:
tree_file = sys.argv[3]
except:
zp.error(
title="CoMA",
text=
"A tree file is required for the calculation of the Unifrac distance!"
)
print("\nProcess terminated!")
print(
"\n________________________________________________________________________________\n"
)
sys.exit(1)
if metric == "Minkowski":
try:
p = int(sys.argv[3])
except:
zp.error(title="CoMA", text="P-norm must be a positive integer!")
print("\nProcess terminated!")
print(
#
# USAGE: python group.py otu_table_file
import zenipy as pz
import sys
import os
import statistics
import time
method = pz.entry(title="CoMA", text="Please choose the method for grouping:\n\nSum: sum of all reads\nMean: mean of all reads\nMedian: median of all reads\n")
if method == None:
print("\nGrouping process terminated!")
print("\n________________________________________________________________________________\n")
sys.exit(3)
if method not in ["Sum", "Mean", "Median"]:
pz.error(title="CoMA", text="Invalid Input, process terminated!")
print("\nGrouping process terminated!")
print("\n________________________________________________________________________________\n")
sys.exit(3)
input_file = "otu_table.txt"
output_file = "otu_table_out.txt"
with open(input_file) as inf:
inf.readline()
samples = [str(a.strip()) + "\n" for a in inf.readline().strip().split("\t")[1:-1]]
num = [str(b) + "\t" for b in range(1, len(samples) + 1)]
samples = [c + d for (c, d) in zip(num, samples)]
count = 0
groups = []