diff --git a/workflow/scripts/check_design.py b/workflow/scripts/check_design.py
index 929a97dc3b12da8ddd254671bdb62ff4a194c063..acf4f014f2c4ed24d25da9bd5e268ace9bd2fadd 100644
--- a/workflow/scripts/check_design.py
+++ b/workflow/scripts/check_design.py
@@ -11,7 +11,7 @@ For more details:
%(prog)s --help
'''
-## SETTINGS
+# SETTINGS
logger = logging.getLogger(__name__)
logger.addHandler(logging.NullHandler())
@@ -57,7 +57,7 @@ def check_design_headers(design, paired):
design_headers = list(design.columns.values)
- if paired: # paired-end data
+ if paired: # paired-end data
design_template.extend(['fastq_read2'])
# Check if headers
@@ -79,7 +79,8 @@ def check_controls(design):
if len(missing_controls) > 0:
logger.error('Missing control experiments: %s', list(missing_controls))
- raise Exception("Missing control experiments: %s" % list(missing_controls))
+ raise Exception("Missing control experiments: %s" %
+ list(missing_controls))
def check_files(design, fastq, paired):
@@ -87,9 +88,9 @@ def check_files(design, fastq, paired):
logger.info("Running file check.")
- if paired: # paired-end data
+ if paired: # paired-end data
files = list(design['fastq_read1']) + list(design['fastq_read2'])
- else: # single-end data
+ else: # single-end data
files = design['fastq_read1']
files_found = fastq['name']
@@ -98,13 +99,14 @@ def check_files(design, fastq, paired):
if len(missing_files) > 0:
logger.error('Missing files from design file: %s', list(missing_files))
- raise Exception("Missing files from design file: %s" % list(missing_files))
+ raise Exception("Missing files from design file: %s" %
+ list(missing_files))
else:
file_dict = fastq.set_index('name').T.to_dict()
design['fastq_read1'] = design['fastq_read1'] \
.apply(lambda x: file_dict[x]['path'])
- if paired: # paired-end data
+ if paired: # paired-end data
design['fastq_read2'] = design['fastq_read2'] \
.apply(lambda x: file_dict[x]['path'])
return design
diff --git a/workflow/scripts/map_reads.py b/workflow/scripts/map_reads.py
index 4de2972b1edfec1c1f65158b6d6cbf56a639e948..ba6bbd0722a49ab09ddd84befbfe0a0ce3e07f19 100644
--- a/workflow/scripts/map_reads.py
+++ b/workflow/scripts/map_reads.py
@@ -8,7 +8,6 @@ import argparse
import shutil
import shlex
import logging
-import sys
from multiprocessing import cpu_count
import json
import utils
@@ -18,7 +17,7 @@ For more details:
%(prog)s --help
'''
-## SETTINGS
+# SETTINGS
logger = logging.getLogger(__name__)
logger.addHandler(logging.NullHandler())
@@ -56,8 +55,7 @@ def get_args():
return args
-
-## Functions
+# Functions
def check_tools():
@@ -102,7 +100,6 @@ def generate_sa(fastq, reference):
def align_se(fastq, sai, reference, fastq_basename):
'''Use BWA to align SE data.'''
- sam_filename = "%s.sam" % (fastq_basename)
bam_filename = '%s.srt.bam' % (fastq_basename)
steps = [
@@ -118,6 +115,7 @@ def align_se(fastq, sai, reference, fastq_basename):
return bam_filename
+
def align_pe(fastq, sai, reference, fastq_basename):
'''Use BWA to align PE data.'''
@@ -173,7 +171,7 @@ def main():
sai.append(sai_filename)
# Run alignment for either PE or SE
- if paired: # paired-end data
+ if paired: # paired-end data
fastq_r1_basename = os.path.basename(
utils.strip_extensions(fastq[0], STRIP_EXTENSIONS))
fastq_r2_basename = os.path.basename(
diff --git a/workflow/scripts/trim_reads.py b/workflow/scripts/trim_reads.py
index c3925a06eb72eb9f62936298042f2d600882c30e..f9f2524f942fb356c360696cee70ea80a403cc4b 100644
--- a/workflow/scripts/trim_reads.py
+++ b/workflow/scripts/trim_reads.py
@@ -2,19 +2,17 @@
'''Trim low quality reads and remove sequences less than 35 base pairs.'''
-import os
import subprocess
import argparse
import shutil
import logging
-import sys
EPILOG = '''
For more details:
%(prog)s --help
'''
-## SETTINGS
+# SETTINGS
logger = logging.getLogger(__name__)
logger.addHandler(logging.NullHandler())
@@ -65,7 +63,7 @@ def check_tools():
def trim_reads(fastq, paired):
'''Run trim_galore on 1 or 2 files.'''
- if paired: # paired-end data
+ if paired: # paired-end data
trim_params = '--paired -q 25 --illumina --gzip --length 35'
trim_command = "trim_galore %s %s %s " \
% (trim_params, fastq[0], fastq[1])
diff --git a/workflow/scripts/utils.py b/workflow/scripts/utils.py
index 98d65aa0d185e5eb605230dab98b74dfceba1b2a..5162646d56b5281a88cd7195dba784865cffe7f8 100644
--- a/workflow/scripts/utils.py
+++ b/workflow/scripts/utils.py
@@ -3,9 +3,6 @@
'''General utilities.'''
-import sys
-import os
-import subprocess
import shlex
import logging
diff --git a/workflow/tests/test_check_design.py b/workflow/tests/test_check_design.py
index 394d5251b382b682bf758debdedd12aaf5637551..a63bc7772068ec265fcd1bc656e3d36e92ffa853 100644
--- a/workflow/tests/test_check_design.py
+++ b/workflow/tests/test_check_design.py
@@ -1,11 +1,9 @@
#!/usr/bin/env python3
-import os
import pytest
import pandas as pd
from io import StringIO
import check_design
-import sys
DESIGN_STRING = """sample_id\tbiosample\tfactor\ttreatment\treplicate\tcontrol_id\tfastq_read1
@@ -49,11 +47,12 @@ def design_2(design):
design_df = design.drop(design.index[2])
return design_df
+
@pytest.fixture
def design_3(design):
# Drop A_2 and B_2 and append as fastq_read2
- design_df = design.drop(design.index[[1,3]])
- design_df['fastq_read2'] = design.loc[[1,3],'fastq_read1'].values
+ design_df = design.drop(design.index[[1, 3]])
+ design_df['fastq_read2'] = design.loc[[1, 3], 'fastq_read1'].values
return design_df
@@ -94,10 +93,10 @@ def test_check_files_missing_files(design, fastq_files_1):
def test_check_files_output_singleend(design, fastq_files):
paired = False
new_design = check_design.check_files(design, fastq_files, paired)
- assert new_design.loc[0,'fastq_read1'] == "/path/to/file/A_1.fastq.gz"
+ assert new_design.loc[0, 'fastq_read1'] == "/path/to/file/A_1.fastq.gz"
def test_check_files_output_pairedend(design_3, fastq_files):
paired = True
new_design = check_design.check_files(design_3, fastq_files, paired)
- assert new_design.loc[0,'fastq_read2'] == "/path/to/file/A_2.fastq.gz"
+ assert new_design.loc[0, 'fastq_read2'] == "/path/to/file/A_2.fastq.gz"
diff --git a/workflow/tests/test_utils.py b/workflow/tests/test_utils.py
index 0997c95bc6780b2ac77f16525a5538b9a62bb4ae..3bbe48abcabc3a027e978dbea73b2a9d350e794d 100644
--- a/workflow/tests/test_utils.py
+++ b/workflow/tests/test_utils.py
@@ -1,13 +1,12 @@
#!/usr/bin/env python3
import pytest
-import shutil
-import shlex
import utils
STRIP_EXTENSIONS = ['.gz', '.fq', '.fastq', '.fa', '.fasta']
+
@pytest.fixture
def steps():
steps = []
@@ -56,15 +55,15 @@ def test_run_last_step_file(steps_2, capsys, tmpdir):
def test_strip_extensions():
- filename = utils.strip_extensions('ENCFF833BLU.fastq.gz',STRIP_EXTENSIONS)
+ filename = utils.strip_extensions('ENCFF833BLU.fastq.gz', STRIP_EXTENSIONS)
assert filename == 'ENCFF833BLU'
def test_strip_extensions_not_valid():
- filename = utils.strip_extensions('ENCFF833BLU.not.valid',STRIP_EXTENSIONS)
+ filename = utils.strip_extensions('ENCFF833BLU.not.valid', STRIP_EXTENSIONS)
assert filename == 'ENCFF833BLU.not.valid'
def test_strip_extensions_missing_basename():
- filename = utils.strip_extensions('.fastq.gz',STRIP_EXTENSIONS)
+ filename = utils.strip_extensions('.fastq.gz', STRIP_EXTENSIONS)
assert filename == '.fastq'