diff --git a/workflow/scripts/extractRefData.py b/workflow/scripts/extractRefData.py
index fb3668e546ddf4a6ede435580e036b629587b2e0..bf06c95696354e6fe5d445718fbfb0769df4182d 100644
--- a/workflow/scripts/extractRefData.py
+++ b/workflow/scripts/extractRefData.py
@@ -5,15 +5,18 @@ import pandas as pd
import warnings
warnings.simplefilter(action='ignore', category=FutureWarning)
+
def get_args():
parser = argparse.ArgumentParser()
- parser.add_argument('-r', '--returnParam',help="The parameter to return (URL or MD5).",required=True)
+ parser.add_argument('-r', '--returnParam',
+ help="The parameter to return (URL or MD5).", required=True)
args = parser.parse_args()
return args
+
def main():
args = get_args()
- refQuery=pd.read_json("refQuery.json")
+ refQuery = pd.read_json("refQuery.json")
if refQuery["File_URL"].count() == 1:
if args.returnParam == "URL":
print(refQuery["File_URL"].values[0])
@@ -23,7 +26,8 @@ def main():
print(refQuery["File_MD5"].values[0])
else:
raise Exception("Multple references found: \n%s" %
- refQuery["RID"])
+ refQuery["RID"])
+
if __name__ == '__main__':
main()
diff --git a/workflow/scripts/parseMeta.py b/workflow/scripts/parseMeta.py
index 500054264f7c8c50310da92d9995f432930318d3..16411df357555991fefdcbd65a6cf0f1f0667017 100644
--- a/workflow/scripts/parseMeta.py
+++ b/workflow/scripts/parseMeta.py
@@ -5,52 +5,61 @@ import pandas as pd
import warnings
warnings.simplefilter(action='ignore', category=FutureWarning)
+
def get_args():
parser = argparse.ArgumentParser()
- parser.add_argument('-r', '--repRID',help="The replicate RID.",required=True)
- parser.add_argument('-m', '--metaFile',help="The metadata file to extract.",required=True)
- parser.add_argument('-p', '--parameter',help="The parameter to extract.",required=True)
+ parser.add_argument(
+ '-r', '--repRID', help="The replicate RID.", required=True)
+ parser.add_argument('-m', '--metaFile',
+ help="The metadata file to extract.", required=True)
+ parser.add_argument('-p', '--parameter',
+ help="The parameter to extract.", required=True)
args = parser.parse_args()
return args
def main():
args = get_args()
- metaFile = pd.read_csv(args.metaFile,sep=",",header=0)
+ metaFile = pd.read_csv(args.metaFile, sep=",", header=0)
# Check replicate RID metadata from 'File.csv'
if (args.parameter == "repRID"):
if (len(metaFile.Replicate_RID.unique()) > 1):
- print("There are multiple replicate RID's in the metadata: " + " ".join(metaFile.Replicate_RID.unique()))
+ print("There are multiple replicate RID's in the metadata: " +
+ " ".join(metaFile.Replicate_RID.unique()))
exit(1)
if not (metaFile.Replicate_RID.unique() == args.repRID):
- print("Replicate RID in metadata does not match run parameters: " + metaFile.Replicate_RID.unique() + " vs " + args.repRID)
+ print("Replicate RID in metadata does not match run parameters: " +
+ metaFile.Replicate_RID.unique() + " vs " + args.repRID)
exit(1)
else:
- rep=metaFile["Replicate_RID"].unique()[0]
+ rep = metaFile["Replicate_RID"].unique()[0]
print(rep)
if (len(metaFile[metaFile["File_Type"] == "FastQ"]) > 2):
- print("There are more then 2 fastq's in the metadata: " + " ".join(metaFile[metaFile["File_Type"] == "FastQ"].RID))
+ print("There are more then 2 fastq's in the metadata: " +
+ " ".join(metaFile[metaFile["File_Type"] == "FastQ"].RID))
exit(1)
# Check experiment RID metadata from 'Experiment.csv'
if (args.parameter == "expRID"):
if (len(metaFile.Experiment_RID.unique()) > 1):
- print("There are multiple experoment RID's in the metadata: " + " ".join(metaFile.Experiment_RID.unique()))
+ print("There are multiple experoment RID's in the metadata: " +
+ " ".join(metaFile.Experiment_RID.unique()))
exit(1)
else:
- exp=metaFile["Experiment_RID"].unique()[0]
+ exp = metaFile["Experiment_RID"].unique()[0]
print(exp)
# Check study RID metadata from 'Experiment.csv'
if (args.parameter == "studyRID"):
if (len(metaFile.Study_RID.unique()) > 1):
- print("There are multiple study RID's in the metadata: " + " ".join(metaFile.Study_RID.unique()))
+ print("There are multiple study RID's in the metadata: " +
+ " ".join(metaFile.Study_RID.unique()))
exit(1)
else:
- study=metaFile["Study_RID"].unique()[0]
+ study = metaFile["Study_RID"].unique()[0]
print(study)
-
+
# Get endedness metadata from 'Experiment Settings.csv'
if (args.parameter == "endsMeta"):
if (metaFile.Paired_End.unique() == "Single End"):
@@ -60,7 +69,7 @@ def main():
else:
endsMeta = "uk"
print(endsMeta)
-
+
# Manually get endness count from 'File.csv'
if (args.parameter == "endsManual"):
if (len(metaFile[metaFile["File_Type"] == "FastQ"]) == 1):
@@ -68,7 +77,7 @@ def main():
elif (len(metaFile[metaFile["File_Type"] == "FastQ"]) == 2):
endsManual = "pe"
print(endsManual)
-
+
# Get strandedness metadata from 'Experiment Settings.csv'
if (args.parameter == "stranded"):
if (metaFile.Has_Strand_Specific_Information.unique() == "yes"):
@@ -76,10 +85,11 @@ def main():
elif (metaFile.Has_Strand_Specific_Information.unique() == "no"):
stranded = "unstranded"
else:
- print("Stranded metadata not match expected options: " + metaFile.Has_Strand_Specific_Information.unique())
+ print("Stranded metadata not match expected options: " +
+ metaFile.Has_Strand_Specific_Information.unique())
exit(1)
print(stranded)
-
+
# Get spike-in metadata from 'Experiment Settings.csv'
if (args.parameter == "spike"):
if (metaFile.Used_Spike_Ins.unique() == "yes"):
@@ -87,7 +97,8 @@ def main():
elif (metaFile.Used_Spike_Ins.unique() == "no"):
spike = "no"
else:
- print("Spike-ins metadata not match expected options: " + metaFile.Used_Spike_Ins.unique())
+ print("Spike-ins metadata not match expected options: " +
+ metaFile.Used_Spike_Ins.unique())
exit(1)
print(spike)
@@ -98,7 +109,8 @@ def main():
elif (metaFile.Species.unique() == "Homo sapiens"):
species = "Homo sapiens"
else:
- print("Species metadata not match expected options: " + metaFile.Species.unique())
+ print("Species metadata not match expected options: " +
+ metaFile.Species.unique())
exit(1)
print(species)
@@ -107,5 +119,6 @@ def main():
readLength = metaFile.Read_Length.unique()
print(str(readLength).strip('[]'))
+
if __name__ == '__main__':
main()
diff --git a/workflow/scripts/splitStudy.py b/workflow/scripts/splitStudy.py
index 82ffc2881857dd5d1d27eee5ea6a381b02d0e9f5..bf1129eb4913efe366f6fc148b55474d934b72a9 100644
--- a/workflow/scripts/splitStudy.py
+++ b/workflow/scripts/splitStudy.py
@@ -5,20 +5,25 @@ import pandas as pd
import warnings
warnings.simplefilter(action='ignore', category=FutureWarning)
+
def get_args():
parser = argparse.ArgumentParser()
- parser.add_argument('-s', '--studyRID',help="The study RID.",required=True)
+ parser.add_argument('-s', '--studyRID',
+ help="The study RID.", required=True)
args = parser.parse_args()
return args
+
def main():
args = get_args()
- studyRID=pd.read_json(args.studyRID+"_studyRID.json")
+ studyRID = pd.read_json(args.studyRID+"_studyRID.json")
if studyRID["RID"].count() > 0:
- studyRID["RID"].to_csv(args.studyRID+"_studyRID.csv",header=False,index=False)
+ studyRID["RID"].to_csv(
+ args.studyRID+"_studyRID.csv", header=False, index=False)
else:
raise Exception("No associated replicates found: %s" %
- studyRID)
+ studyRID)
+
if __name__ == '__main__':
main()
diff --git a/workflow/scripts/tinHist.py b/workflow/scripts/tinHist.py
index 3d292c2eb8cadb3b16466c6b19d0574184d439d7..a95a9c23b4cf5ac3b25c85580a7b2c326bcb0eb1 100644
--- a/workflow/scripts/tinHist.py
+++ b/workflow/scripts/tinHist.py
@@ -6,38 +6,47 @@ import numpy as np
import warnings
warnings.simplefilter(action='ignore', category=FutureWarning)
+
def get_args():
parser = argparse.ArgumentParser()
- parser.add_argument('-r', '--repRID',help="The replicate RID.",required=True)
+ parser.add_argument(
+ '-r', '--repRID', help="The replicate RID.", required=True)
args = parser.parse_args()
return args
+
def main():
args = get_args()
- tin = pd.read_csv(args.repRID + '.sorted.deduped.tin.xls',sep="\t",header=0)
-
- hist = pd.cut(tin['TIN'],bins=pd.interval_range(start=0,freq=10,end=100,closed='right')).value_counts(sort=False)
+ tin = pd.read_csv(args.repRID + '.sorted.deduped.tin.xls',
+ sep="\t", header=0)
+
+ hist = pd.cut(tin['TIN'], bins=pd.interval_range(
+ start=0, freq=10, end=100, closed='right')).value_counts(sort=False)
labels = ["{0} - {1}".format(i, i + 9) for i in range(1, 100, 10)]
#labels[0] = '0 - 10'
- binned = tin.assign(Bins=lambda x: pd.cut(tin['TIN'],range(0,105,10),labels=labels,include_lowest=False,right=True))
- binned['chrom'] = binned['chrom'] = binned['chrom'].replace('chr1','chr01')
- binned['chrom'] = binned['chrom'].replace('chr2','chr02')
- binned['chrom'] = binned['chrom'].replace('chr3','chr03')
- binned['chrom'] = binned['chrom'].replace('chr4','chr04')
- binned['chrom'] = binned['chrom'].replace('chr5','chr05')
- binned['chrom'] = binned['chrom'].replace('chr6','chr06')
- binned['chrom'] = binned['chrom'].replace('chr7','chr07')
- binned['chrom'] = binned['chrom'].replace('chr8','chr08')
- binned['chrom'] = binned['chrom'].replace('chr9','chr09')
- hist = pd.pivot_table(binned, values='geneID', index = 'Bins', columns = 'chrom', aggfunc=np.size)
+ binned = tin.assign(Bins=lambda x: pd.cut(tin['TIN'], range(
+ 0, 105, 10), labels=labels, include_lowest=False, right=True))
+ binned['chrom'] = binned['chrom'] = binned['chrom'].replace(
+ 'chr1', 'chr01')
+ binned['chrom'] = binned['chrom'].replace('chr2', 'chr02')
+ binned['chrom'] = binned['chrom'].replace('chr3', 'chr03')
+ binned['chrom'] = binned['chrom'].replace('chr4', 'chr04')
+ binned['chrom'] = binned['chrom'].replace('chr5', 'chr05')
+ binned['chrom'] = binned['chrom'].replace('chr6', 'chr06')
+ binned['chrom'] = binned['chrom'].replace('chr7', 'chr07')
+ binned['chrom'] = binned['chrom'].replace('chr8', 'chr08')
+ binned['chrom'] = binned['chrom'].replace('chr9', 'chr09')
+ hist = pd.pivot_table(binned, values='geneID',
+ index='Bins', columns='chrom', aggfunc=np.size)
hist['TOTAL'] = hist.sum(axis=1)
- hist = hist[['TOTAL'] + [ i for i in hist.columns if i != 'TOTAL']]
+ hist = hist[['TOTAL'] + [i for i in hist.columns if i != 'TOTAL']]
hist = hist.T.fillna(0.0).astype(int)
#hist = hist.apply(lambda x: x/x.sum()*100, axis=1)
- hist.to_csv(args.repRID + '.tin.hist.tsv',sep='\t')
- medFile = open(args.repRID + '.tin.med.csv',"w")
- medFile.write(str(round(tin['TIN'][(tin['TIN']!=0)].median(),2)))
+ hist.to_csv(args.repRID + '.tin.hist.tsv', sep='\t')
+ medFile = open(args.repRID + '.tin.med.csv', "w")
+ medFile.write(str(round(tin['TIN'][(tin['TIN'] != 0)].median(), 2)))
medFile.close()
+
if __name__ == '__main__':
main()
diff --git a/workflow/scripts/utils.py b/workflow/scripts/utils.py
index 5e4478e3b1cef96e9b4c05033f75122f87aad06e..548b84c0642ee1479c1ac2e968ba1cd1aa9ed660 100644
--- a/workflow/scripts/utils.py
+++ b/workflow/scripts/utils.py
@@ -1,14 +1,5 @@
#!/usr/bin/env python3
-#
-# * --------------------------------------------------------------------------
-# * Licensed under MIT (https://git.biohpc.swmed.edu/BICF/Astrocyte/chipseq_analysis/LICENSE.md)
-# * --------------------------------------------------------------------------
-#
-
-'''General utilities.'''
-
-
import shlex
import logging
import subprocess
@@ -32,7 +23,8 @@ def run_pipe(steps, outfile=None):
if n == first_step_n:
if n == last_step_n and outfile: # one-step pipeline with outfile
with open(outfile, 'w') as fh:
- print("one step shlex: %s to file: %s" % (shlex.split(step), outfile))
+ print("one step shlex: %s to file: %s" %
+ (shlex.split(step), outfile))
p = Popen(shlex.split(step), stdout=fh)
break
print("first step shlex to stdout: %s" % (shlex.split(step)))
@@ -40,12 +32,14 @@ def run_pipe(steps, outfile=None):
p = Popen(shlex.split(step), stdout=PIPE)
elif n == last_step_n and outfile: # only treat the last step specially if you're sending stdout to a file
with open(outfile, 'w') as fh:
- print("last step shlex: %s to file: %s" % (shlex.split(step), outfile))
+ print("last step shlex: %s to file: %s" %
+ (shlex.split(step), outfile))
p_last = Popen(shlex.split(step), stdin=p.stdout, stdout=fh)
p.stdout.close()
p = p_last
else: # handles intermediate steps and, in the case of a pipe to stdout, the last step
- print("intermediate step %d shlex to stdout: %s" % (n, shlex.split(step)))
+ print("intermediate step %d shlex to stdout: %s" %
+ (n, shlex.split(step)))
p_next = Popen(shlex.split(step), stdin=p.stdout, stdout=PIPE)
p.stdout.close()
p = p_next
@@ -54,7 +48,8 @@ def run_pipe(steps, outfile=None):
def block_on(command):
- process = subprocess.Popen(shlex.split(command), stderr=subprocess.STDOUT, stdout=subprocess.PIPE)
+ process = subprocess.Popen(shlex.split(
+ command), stderr=subprocess.STDOUT, stdout=subprocess.PIPE)
for line in iter(process.stdout.readline, b''):
sys.stdout.write(line.decode('utf-8'))
process.communicate()
@@ -77,7 +72,7 @@ def count_lines(filename):
"compress",
"bzip2",
"gzip"
- ]
+ ]
mime_type = mimetypes.guess_type(filename)[1]
if mime_type in compressed_mimetypes:
catcommand = 'gzip -dc'
@@ -86,7 +81,7 @@ def count_lines(filename):
out, err = run_pipe([
'%s %s' % (catcommand, filename),
'wc -l'
- ])
+ ])
return int(out)
diff --git a/workflow/tests/test_alignReads.py b/workflow/tests/test_alignReads.py
index eae8780f5641404ac9caabe32089369a3b0b1ea2..11f0f3d0d09236a3f3494a2c851fb4294f2a1323 100644
--- a/workflow/tests/test_alignReads.py
+++ b/workflow/tests/test_alignReads.py
@@ -6,18 +6,24 @@ import os
import utils
data_output_path = os.path.dirname(os.path.abspath(__file__)) + \
- '/../../'
+ '/../../'
@pytest.mark.alignData
def test_alignData_se():
- assert os.path.exists(os.path.join(data_output_path, 'Q-Y5F6_1M.se.unal.gz'))
- assert os.path.exists(os.path.join(data_output_path, 'Q-Y5F6_1M.se.sorted.bam'))
- assert os.path.exists(os.path.join(data_output_path, 'Q-Y5F6_1M.se.sorted.bam.bai'))
+ assert os.path.exists(os.path.join(
+ data_output_path, 'Q-Y5F6_1M.se.unal.gz'))
+ assert os.path.exists(os.path.join(
+ data_output_path, 'Q-Y5F6_1M.se.sorted.bam'))
+ assert os.path.exists(os.path.join(
+ data_output_path, 'Q-Y5F6_1M.se.sorted.bam.bai'))
@pytest.mark.alignData
def test_alignData_pe():
- assert os.path.exists(os.path.join(data_output_path, 'Q-Y5F6_1M.pe.unal.gz'))
- assert os.path.exists(os.path.join(data_output_path, 'Q-Y5F6_1M.pe.sorted.bam'))
- assert os.path.exists(os.path.join(data_output_path, 'Q-Y5F6_1M.pe.sorted.bam.bai'))
+ assert os.path.exists(os.path.join(
+ data_output_path, 'Q-Y5F6_1M.pe.unal.gz'))
+ assert os.path.exists(os.path.join(
+ data_output_path, 'Q-Y5F6_1M.pe.sorted.bam'))
+ assert os.path.exists(os.path.join(
+ data_output_path, 'Q-Y5F6_1M.pe.sorted.bam.bai'))
diff --git a/workflow/tests/test_consistency.py b/workflow/tests/test_consistency.py
index 073b12826b798ac94d16fda4291dfba2c1a42203..49991489ef71eccb2a88a039420661dfc1f0a303 100644
--- a/workflow/tests/test_consistency.py
+++ b/workflow/tests/test_consistency.py
@@ -6,19 +6,24 @@ from io import StringIO
import os
test_output_path = os.path.dirname(os.path.abspath(__file__)) + \
- '/../../'
+ '/../../'
+
@pytest.mark.consistencySE
def test_consistencySE():
- assert os.path.exists(os.path.join(test_output_path, 'SE_multiqc_data.json'))
- assert readAssigned("assignedSE.txt","assignedExpectSE.txt")
+ assert os.path.exists(os.path.join(
+ test_output_path, 'SE_multiqc_data.json'))
+ assert readAssigned("assignedSE.txt", "assignedExpectSE.txt")
+
@pytest.mark.consistencyPE
def test_consistencyPE():
- assert os.path.exists(os.path.join(test_output_path, 'PE_multiqc_data.json'))
- assert readAssigned("assignedPE.txt","assignedExpectPE.txt")
+ assert os.path.exists(os.path.join(
+ test_output_path, 'PE_multiqc_data.json'))
+ assert readAssigned("assignedPE.txt", "assignedExpectPE.txt")
+
-def readAssigned(fileAssigned,fileExpectAssigned):
+def readAssigned(fileAssigned, fileExpectAssigned):
data = False
assigned = open(fileAssigned, "r")
expect = open(fileExpectAssigned, "r")
diff --git a/workflow/tests/test_dataQC.py b/workflow/tests/test_dataQC.py
index e77d4680fd8eac61c3a9b9a8fd175136a61244b9..55df66deaeda6dac18ea26455dd1e3948ceb28ba 100644
--- a/workflow/tests/test_dataQC.py
+++ b/workflow/tests/test_dataQC.py
@@ -6,12 +6,16 @@ from io import StringIO
import os
test_output_path = os.path.dirname(os.path.abspath(__file__)) + \
- '/../../'
+ '/../../'
+
@pytest.mark.dataQC
def test_dataQC():
- assert os.path.exists(os.path.join(test_output_path, 'Q-Y5F6_1M.se.sorted.deduped.tin.xls'))
- assert countLines(os.path.join(test_output_path, 'Q-Y5F6_1M.se.sorted.deduped.tin.xls'))
+ assert os.path.exists(os.path.join(
+ test_output_path, 'Q-Y5F6_1M.se.sorted.deduped.tin.xls'))
+ assert countLines(os.path.join(test_output_path,
+ 'Q-Y5F6_1M.se.sorted.deduped.tin.xls'))
+
def countLines(fileName):
data = False
diff --git a/workflow/tests/test_dedupReads.py b/workflow/tests/test_dedupReads.py
index 49cf420e2f0e2de923ae580c51dcdf42549f0713..89fc2b10fa4db847ccc16d5cce664bf551b29ee3 100644
--- a/workflow/tests/test_dedupReads.py
+++ b/workflow/tests/test_dedupReads.py
@@ -6,16 +6,24 @@ import os
import utils
data_output_path = os.path.dirname(os.path.abspath(__file__)) + \
- '/../../'
+ '/../../'
@pytest.mark.dedupData
def test_dedupData():
- assert os.path.exists(os.path.join(data_output_path, 'Q-Y5F6_1M.se.sorted.deduped.bam'))
- assert os.path.exists(os.path.join(data_output_path, 'Q-Y5F6_1M.se.sorted.deduped.bam.bai'))
- assert os.path.exists(os.path.join(data_output_path, 'Q-Y5F6_1M.se.sorted.deduped.chr8.bam'))
- assert os.path.exists(os.path.join(data_output_path, 'Q-Y5F6_1M.se.sorted.deduped.chr8.bam.bai'))
- assert os.path.exists(os.path.join(data_output_path, 'Q-Y5F6_1M.se.sorted.deduped.chr4.bam'))
- assert os.path.exists(os.path.join(data_output_path, 'Q-Y5F6_1M.se.sorted.deduped.chr4.bam.bai'))
- assert os.path.exists(os.path.join(data_output_path, 'Q-Y5F6_1M.se.sorted.deduped.chrY.bam'))
- assert os.path.exists(os.path.join(data_output_path, 'Q-Y5F6_1M.se.sorted.deduped.chrY.bam.bai'))
+ assert os.path.exists(os.path.join(
+ data_output_path, 'Q-Y5F6_1M.se.sorted.deduped.bam'))
+ assert os.path.exists(os.path.join(
+ data_output_path, 'Q-Y5F6_1M.se.sorted.deduped.bam.bai'))
+ assert os.path.exists(os.path.join(
+ data_output_path, 'Q-Y5F6_1M.se.sorted.deduped.chr8.bam'))
+ assert os.path.exists(os.path.join(
+ data_output_path, 'Q-Y5F6_1M.se.sorted.deduped.chr8.bam.bai'))
+ assert os.path.exists(os.path.join(
+ data_output_path, 'Q-Y5F6_1M.se.sorted.deduped.chr4.bam'))
+ assert os.path.exists(os.path.join(
+ data_output_path, 'Q-Y5F6_1M.se.sorted.deduped.chr4.bam.bai'))
+ assert os.path.exists(os.path.join(
+ data_output_path, 'Q-Y5F6_1M.se.sorted.deduped.chrY.bam'))
+ assert os.path.exists(os.path.join(
+ data_output_path, 'Q-Y5F6_1M.se.sorted.deduped.chrY.bam.bai'))
diff --git a/workflow/tests/test_downsampleData.py b/workflow/tests/test_downsampleData.py
index fd42c49e169e387dd9662903b20866c40aec8907..6d98ad656b0bcb0a3e8aee5507149cdcf3cec5f0 100644
--- a/workflow/tests/test_downsampleData.py
+++ b/workflow/tests/test_downsampleData.py
@@ -6,8 +6,9 @@ from io import StringIO
import os
test_output_path = os.path.dirname(os.path.abspath(__file__)) + \
- '/../../'
+ '/../../'
+
@pytest.mark.downsampleData
def test_downsampleData():
- assert os.path.exists(os.path.join(test_output_path, 'sampled.1.fq'))
\ No newline at end of file
+ assert os.path.exists(os.path.join(test_output_path, 'sampled.1.fq'))
diff --git a/workflow/tests/test_fastqc.py b/workflow/tests/test_fastqc.py
index 89303fe78e081a26fd6a8ea633997dffb8f920a6..07e76108fbfc92f945060d8e5d1e1ea8f74e6a4a 100644
--- a/workflow/tests/test_fastqc.py
+++ b/workflow/tests/test_fastqc.py
@@ -6,8 +6,10 @@ from io import StringIO
import os
test_output_path = os.path.dirname(os.path.abspath(__file__)) + \
- '/../../'
+ '/../../'
+
@pytest.mark.fastqc
def test_fastqc():
- assert os.path.exists(os.path.join(test_output_path, 'Q-Y5F6_1M.R1_fastqc.zip'))
+ assert os.path.exists(os.path.join(
+ test_output_path, 'Q-Y5F6_1M.R1_fastqc.zip'))
diff --git a/workflow/tests/test_getBag.py b/workflow/tests/test_getBag.py
index 1c63c9d95ac33aceeaa965852ede7bfc5e86bdc7..a99acc6963e51bd27b8e7acf0865e182876dbd01 100644
--- a/workflow/tests/test_getBag.py
+++ b/workflow/tests/test_getBag.py
@@ -6,8 +6,10 @@ from io import StringIO
import os
test_output_path = os.path.dirname(os.path.abspath(__file__)) + \
- '/../../'
+ '/../../'
+
@pytest.mark.getBag
def test_getBag():
- assert os.path.exists(os.path.join(test_output_path, 'Replicate_Q-Y5F6.zip'))
+ assert os.path.exists(os.path.join(
+ test_output_path, 'Replicate_Q-Y5F6.zip'))
diff --git a/workflow/tests/test_getData.py b/workflow/tests/test_getData.py
index a14be93ea8103aadf44aca3156ee28036cb6113e..95e2018eb5de04c55bdd8c6a118c961065add807 100644
--- a/workflow/tests/test_getData.py
+++ b/workflow/tests/test_getData.py
@@ -6,9 +6,12 @@ from io import StringIO
import os
test_output_path = os.path.dirname(os.path.abspath(__file__)) + \
- '/../../'
+ '/../../'
+
@pytest.mark.getData
def test_getData():
- assert os.path.exists(os.path.join(test_output_path, 'Replicate_Q-Y5F6/bagit.txt'))
- assert os.path.exists(os.path.join(test_output_path, 'Replicate_Q-Y5F6/data/assets/Study/Q-Y4GY/Experiment/Q-Y4DP/Replicate/Q-Y5F6/mMARIS_Six2-#3.gene.rpkm.txt'))
+ assert os.path.exists(os.path.join(
+ test_output_path, 'Replicate_Q-Y5F6/bagit.txt'))
+ assert os.path.exists(os.path.join(
+ test_output_path, 'Replicate_Q-Y5F6/data/assets/Study/Q-Y4GY/Experiment/Q-Y4DP/Replicate/Q-Y5F6/mMARIS_Six2-#3.gene.rpkm.txt'))
diff --git a/workflow/tests/test_inferMetadata.py b/workflow/tests/test_inferMetadata.py
index 518664ced5ab4dd4e713dede9c58b9d87594799a..7485163631e2604ac2d5477a5c27b2fc9b235b44 100644
--- a/workflow/tests/test_inferMetadata.py
+++ b/workflow/tests/test_inferMetadata.py
@@ -6,9 +6,10 @@ from io import StringIO
import os
test_output_path = os.path.dirname(os.path.abspath(__file__)) + \
- '/../../'
+ '/../../'
+
@pytest.mark.inferMetadata
def test_inferMetadata():
- assert os.path.exists(os.path.join(test_output_path, 'Q-Y5F6_1M.se.inferMetadata.log'))
-
+ assert os.path.exists(os.path.join(
+ test_output_path, 'Q-Y5F6_1M.se.inferMetadata.log'))
diff --git a/workflow/tests/test_makeBigWig.py b/workflow/tests/test_makeBigWig.py
index 9292ac64714017fde8371927cee616374a457b3a..d8f62f5edfb3b57868d0b4b18ed6a0deb6bd651e 100644
--- a/workflow/tests/test_makeBigWig.py
+++ b/workflow/tests/test_makeBigWig.py
@@ -6,7 +6,7 @@ import os
import utils
data_output_path = os.path.dirname(os.path.abspath(__file__)) + \
- '/../../'
+ '/../../'
@pytest.mark.makeBigWig
diff --git a/workflow/tests/test_makeFeatureCounts.py b/workflow/tests/test_makeFeatureCounts.py
index d33527a9c7bffcaa9919639b72842cc8cf63b14f..e67bca804a3a1bcf1787a55088a95528076f08fe 100644
--- a/workflow/tests/test_makeFeatureCounts.py
+++ b/workflow/tests/test_makeFeatureCounts.py
@@ -6,11 +6,14 @@ import os
import utils
data_output_path = os.path.dirname(os.path.abspath(__file__)) + \
- '/../../'
+ '/../../'
@pytest.mark.makeFeatureCounts
def test_makeFeatureCounts():
- assert os.path.exists(os.path.join(data_output_path, 'Q-Y5F6_1M.se.countData'))
- assert os.path.exists(os.path.join(data_output_path, 'Q-Y5F6_1M.se.countTable.csv'))
- assert os.path.exists(os.path.join(data_output_path, 'Q-Y5F6_1M.se.tpmTable.csv'))
+ assert os.path.exists(os.path.join(
+ data_output_path, 'Q-Y5F6_1M.se.countData'))
+ assert os.path.exists(os.path.join(
+ data_output_path, 'Q-Y5F6_1M.se.countTable.csv'))
+ assert os.path.exists(os.path.join(
+ data_output_path, 'Q-Y5F6_1M.se.tpmTable.csv'))
diff --git a/workflow/tests/test_outputBag.py b/workflow/tests/test_outputBag.py
index 4132d834996e5557024dbbf587d4aca41594bf9e..c73e6474efdb9093b0cc66c00b220426be707690 100644
--- a/workflow/tests/test_outputBag.py
+++ b/workflow/tests/test_outputBag.py
@@ -6,7 +6,8 @@ from io import StringIO
import os
test_output_path = os.path.dirname(os.path.abspath(__file__)) + \
- '/../../'
+ '/../../'
+
@pytest.mark.outputBag
def test_outputBag():
diff --git a/workflow/tests/test_parseMetadata.py b/workflow/tests/test_parseMetadata.py
index 59677bbba7d40058bdeb78ccceeeeddba4565a14..fa488800e4b6aeb5b1be2685d75b2801667f0855 100644
--- a/workflow/tests/test_parseMetadata.py
+++ b/workflow/tests/test_parseMetadata.py
@@ -6,13 +6,15 @@ from io import StringIO
import os
test_output_path = os.path.dirname(os.path.abspath(__file__)) + \
- '/../../'
+ '/../../'
+
@pytest.mark.parseMetadata
def test_parseMetadata():
assert os.path.exists(os.path.join(test_output_path, 'design.csv'))
assert readLine(os.path.join(test_output_path, 'design.csv'))
+
def readLine(fileName):
data = False
file = open(fileName, "r")
diff --git a/workflow/tests/test_trimData.py b/workflow/tests/test_trimData.py
index ba0eeda481262647abc9e4a8bf362515ac0dc0e7..40dd2dcb79c4f9d615e20f48364247aa61265f7f 100644
--- a/workflow/tests/test_trimData.py
+++ b/workflow/tests/test_trimData.py
@@ -6,14 +6,18 @@ from io import StringIO
import os
test_output_path = os.path.dirname(os.path.abspath(__file__)) + \
- '/../../'
+ '/../../'
+
@pytest.mark.trimData
def test_trimData_se():
- assert os.path.exists(os.path.join(test_output_path, 'Q-Y5F6_1M.se_trimmed.fq.gz'))
+ assert os.path.exists(os.path.join(
+ test_output_path, 'Q-Y5F6_1M.se_trimmed.fq.gz'))
@pytest.mark.trimData
def test_trimData_pe():
- assert os.path.exists(os.path.join(test_output_path, 'Q-Y5F6_1M.pe_R1_val_1.fq.gz'))
- assert os.path.exists(os.path.join(test_output_path, 'Q-Y5F6_1M.pe_R2_val_2.fq.gz'))
+ assert os.path.exists(os.path.join(
+ test_output_path, 'Q-Y5F6_1M.pe_R1_val_1.fq.gz'))
+ assert os.path.exists(os.path.join(
+ test_output_path, 'Q-Y5F6_1M.pe_R2_val_2.fq.gz'))