diff --git a/workflow/scripts/call_peaks_macs.py b/workflow/scripts/call_peaks_macs.py
index 38e03cc89d6c91d1d9f8247aa7396e2f9262cde6..cc003c9e892fe49b90c1fad285bd378bffbd9364 100644
--- a/workflow/scripts/call_peaks_macs.py
+++ b/workflow/scripts/call_peaks_macs.py
@@ -71,7 +71,7 @@ def check_tools():
logger.info('Checking for required libraries and components on this system')
macs_path = shutil.which("macs2")
- if r_path:
+ if macs_path:
logger.info('Found MACS2: %s', macs_path)
# Get Version
@@ -135,7 +135,6 @@ def call_peaks_macs(experiment, xcor, control, prefix, genome_size, chrom_sizes)
fragment_length = frag_lengths.split(',')[0] # grab first value
logger.info("Fraglen %s", fragment_length)
-
# Generate narrow peaks and preliminary signal tracks
command = 'macs2 callpeak ' + \
@@ -155,7 +154,6 @@ def call_peaks_macs(experiment, xcor, control, prefix, genome_size, chrom_sizes)
narrowpeak_fn = '%s.narrowPeak' % (prefix)
clipped_narrowpeak_fn = 'clipped-%s' % (narrowpeak_fn)
-
steps = ['slopBed -i %s -g %s -b 0' % (int_narrowpeak_fn, chrom_sizes),
'bedClip stdin %s %s' % (chrom_sizes, clipped_narrowpeak_fn)]
diff --git a/workflow/scripts/experiment_qc.py b/workflow/scripts/experiment_qc.py
index cf22338664a16157da2ad3b1c107a2af6d2372de..0418d0e34bee026e2756eec12462bfc85ba73dce 100644
--- a/workflow/scripts/experiment_qc.py
+++ b/workflow/scripts/experiment_qc.py
@@ -198,7 +198,6 @@ def main():
check_spearman_correlation(mbs_filename)
check_pearson_correlation(mbs_filename)
-
# Run coverage
check_coverage(design_df, extension)
diff --git a/workflow/scripts/map_qc.py b/workflow/scripts/map_qc.py
index ab63c423f613cef1fcdc2eaf91828b9b6d95b128..ecb6170013b1491c9eac3abf4dbd9a8c7d33c213 100644
--- a/workflow/scripts/map_qc.py
+++ b/workflow/scripts/map_qc.py
@@ -197,7 +197,6 @@ def dedup_mapped(bam, bam_basename, paired):
shlex.split(sambamba_markdup_command),
stderr=temp_file)
-
# Remove duplicates
final_bam_prefix = bam_basename + ".dedup"
final_bam_filename = final_bam_prefix + ".bam"
diff --git a/workflow/scripts/motif_search.py b/workflow/scripts/motif_search.py
index 0c2e3f8c4efdefccaa016dfb4e3b75569ce0f5fa..fd82853ad00a151e9217eeb9416c8923b05538ab 100644
--- a/workflow/scripts/motif_search.py
+++ b/workflow/scripts/motif_search.py
@@ -56,6 +56,7 @@ def get_args():
# Functions
+
def check_tools():
'''Checks for required componenets on user system'''
@@ -114,7 +115,7 @@ def motif_search(filename, genome, experiment, peak):
else:
peak_no = peak
- sorted_fn = '%s.%s.narrowPeak' % (file_basename, peak)
+ sorted_fn = '%s.%s.narrowPeak' % (file_basename, peak_no)
out, err = utils.run_pipe([
'sort -k %dgr,%dgr %s' % (5, 5, filename),
@@ -127,8 +128,7 @@ def motif_search(filename, genome, experiment, peak):
if err:
logger.error("bedtools error: %s", err)
-
- #Call memechip
+ # Call memechip
out, err = utils.run_pipe([
'meme-chip -oc %s -meme-minw 5 -meme-maxw 15 -meme-nmotifs 10 %s -norand' % (out_motif, out_fa)])
if err:
diff --git a/workflow/scripts/overlap_peaks.py b/workflow/scripts/overlap_peaks.py
index 71438f779ab96695ead05a5653221ae99f5b3f6a..cd71c5a176e8d1c4b2067435ebf5b42779f2df8b 100644
--- a/workflow/scripts/overlap_peaks.py
+++ b/workflow/scripts/overlap_peaks.py
@@ -6,6 +6,7 @@ import os
import argparse
import logging
import shutil
+import subprocess
import pandas as pd
import utils
diff --git a/workflow/scripts/pool_and_psuedoreplicate.py b/workflow/scripts/pool_and_psuedoreplicate.py
index f3d702f64b0cf1b9283b8ab4e26e9fbe7df57922..e050d7e034af1717c5ca3ad9b5fc198987f7bc2e 100644
--- a/workflow/scripts/pool_and_psuedoreplicate.py
+++ b/workflow/scripts/pool_and_psuedoreplicate.py
@@ -153,7 +153,6 @@ def self_psuedoreplication(tag_file, prefix, paired):
logger.info("Running psuedo with %s", psuedo_command)
subprocess.check_call(shlex.split(psuedo_command))
-
# Convert read pairs to reads into standard tagAlign file
for i, index in enumerate([0, 1]):
@@ -344,7 +343,6 @@ def main():
tmp_metadata['tag_align'] = path_to_file
design_new_df = design_new_df.append(tmp_metadata)
-
# Write out new dataframe
design_new_df.to_csv(experiment_id + '_ppr.tsv',
header=True, sep='\t', index=False)
diff --git a/workflow/scripts/software_report.py b/workflow/scripts/software_report.py
index 406b9bde9189f71093e54ade0268ce2dd40ace8e..2e605e3bb952fe3ffd891fa04800edb7f01650a0 100644
--- a/workflow/scripts/software_report.py
+++ b/workflow/scripts/software_report.py
@@ -1,11 +1,13 @@
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
+'''Make YAML of software versions.'''
+
from __future__ import print_function
from collections import OrderedDict
import re
-regexes = {
+software_regex = {
'Trim Galore!': ['version_trimgalore.txt', r"version (\S+)"],
'Cutadapt': ['version_cutadapt.txt', r"Version (\S+)"],
'BWA': ['version_bwa.txt', r"Version: (\S+)"],
@@ -42,7 +44,7 @@ results['DiffBind'] = '<span style="color:#999999;\">N/A</span>'
results['deepTools'] = '<span style="color:#999999;\">N/A</span>'
# Search each file using its regex
-for k, v in regexes.items():
+for k, v in software_regex.items():
with open(v[0]) as x:
versions = x.read()
match = re.search(v[1], versions)
@@ -61,6 +63,6 @@ print(
<dl class="dl-horizontal">
'''
)
-for k,v in results.items():
- print(" <dt>{}</dt><dd>{}</dd>".format(k,v))
+for k, v in results.items():
+ print(" <dt>{}</dt><dd>{}</dd>".format(k, v))
print(" </dl>")
diff --git a/workflow/scripts/xcor.py b/workflow/scripts/xcor.py
index 3b1328cc80759d8e653d9c7d333102302113d43e..14e4ed30143755b4deece75f8d2cb8f43bc4703e 100644
--- a/workflow/scripts/xcor.py
+++ b/workflow/scripts/xcor.py
@@ -96,13 +96,11 @@ def xcor(tag, paired):
tag_basename = os.path.basename(utils.strip_extensions(tag, STRIP_EXTENSIONS))
uncompressed_tag_filename = tag_basename
-
# Subsample tagAlign file
number_reads = 15000000
subsampled_tag_filename = \
tag_basename + ".%d.tagAlign.gz" % (number_reads/1000000)
-
steps = [
'zcat %s' % (tag),
'grep -v "chrM"',
@@ -142,7 +140,6 @@ def xcor(tag, paired):
return cc_scores_filename
-
def main():
args = get_args()
paired = args.paired