diff --git a/.gitlab-ci.yml b/.gitlab-ci.yml
index 3e6393ed8d83c8b402f9b37d1713fe2244c49433..83ef6e5f6e80f646f93eff71bf9016c85e1f96fe 100644
--- a/.gitlab-ci.yml
+++ b/.gitlab-ci.yml
@@ -57,6 +57,7 @@ single_end_diff:
- master
script:
- nextflow run workflow/main.nf --designFile "$CI_PROJECT_DIR/test_data/design_diff_SE.txt" --genome 'GRCm38' --astrocyte false -resume
+ - pytest -m singleend
- pytest -m singlediff
artifacts:
expire_in: 2 days
@@ -67,6 +68,7 @@ paired_end_diff:
stage: multiple
script:
- nextflow run workflow/main.nf --designFile "$CI_PROJECT_DIR/test_data/design_diff_PE.txt" --genome 'GRCh38' --pairedEnd true --astrocyte false -resume
+ - pytest -m pairedend
- pytest -m paireddiff
artifacts:
expire_in: 2 days
diff --git a/CHANGELOG.md b/CHANGELOG.md
index bc28c53bfc58c5288b3b912d06152a1657e3db0a..90cc2d75a828b8e52e7753b986e0efa88c230366 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -12,6 +12,7 @@ All notable changes to this project will be documented in this file.
- Add and Update tests
- Use GTF files instead of TxDb and org libraries in Annotate Peaks
- Make gtf and geneName files as param inputs
+- Fix xcor to increase file size for --random-source
## [publish_1.0.6 ] - 2019-05-31
### Added
diff --git a/workflow/conf/biohpc.config b/workflow/conf/biohpc.config
index b2135584edf920a7fc432589ec0ae99a76d573e0..037d1e43e37c7daeb21489a00dff85701c8f8fd0 100644
--- a/workflow/conf/biohpc.config
+++ b/workflow/conf/biohpc.config
@@ -65,7 +65,7 @@ process {
cpus = 32
}
withName: multiqcReport {
- module = ['python/3.6.1-2-anaconda', 'pandoc/2.7', 'multiqc/1.7']
+ module = ['python/3.6.1-2-anaconda', 'pandoc/2.7', 'singularity/3.0.2']
executor = 'local'
}
}
diff --git a/workflow/main.nf b/workflow/main.nf
index f654471c74632c7efdd23836df63c9aba78c2099..bf87941930e7a3737c8610703d224887c113a4d1 100644
--- a/workflow/main.nf
+++ b/workflow/main.nf
@@ -653,14 +653,11 @@ process multiqcReport {
script:
"""
- module load python/3.6.1-2-anaconda
- module load pandoc/2.7
- module load multiqc/1.7
echo $workflow.nextflow.version > version_nextflow.txt
- multiqc --version > version_multiqc.txt
+ singularity exec /project/shared/bicf_workflow_ref/singularity_images/multiqc.sif multiqc --version > version_multiqc.txt
python --version &> version_python.txt
python3 $baseDir/scripts/generate_references.py -r $references -o software_references
python3 $baseDir/scripts/generate_versions.py -o software_versions
- multiqc -c $multiqc .
+ singularity exec /project/shared/bicf_workflow_ref/singularity_images/multiqc.sif multiqc -c $multiqc .
"""
}
diff --git a/workflow/scripts/plotProfile.sh b/workflow/scripts/plotProfile.sh
index 7f62dc5bdd9e13026315222b076b8b939f839d00..0f50501c410d2ab0a7549190ba830aa0a90d7602 100644
--- a/workflow/scripts/plotProfile.sh
+++ b/workflow/scripts/plotProfile.sh
@@ -10,6 +10,7 @@ computeMatrix reference-point \
-R $gtf \
--skipZeros \
-o computeMatrix.gz
+ -p max/2
plotProfile -m computeMatrix.gz \
-out plotProfile.png \
diff --git a/workflow/scripts/xcor.py b/workflow/scripts/xcor.py
index 3bf8dbfa1e7da470ec0eea413970a72b01a968c1..66fa9aec4d7030288b3bd57d7e156247d82c97ec 100644
--- a/workflow/scripts/xcor.py
+++ b/workflow/scripts/xcor.py
@@ -103,14 +103,20 @@ def xcor(tag, paired):
uncompressed_tag_filename = tag_basename
# Subsample tagAlign file
- number_reads = 15000000
+ number_reads = 20000000
subsampled_tag_filename = \
tag_basename + ".%d.tagAlign.gz" % (number_reads/1000000)
+ tag_extended = 'cat.tagAlign.gz'
+ out, err = utils.run_pipe([
+ "zcat %s %s %s" %
+ (tag, tag, tag)
+ ], outfile=tag_extended)
+
steps = [
'zcat %s' % (tag),
'grep -v "chrM"',
- 'shuf -n %d --random-source=%s' % (number_reads, tag)]
+ 'shuf -n %d --random-source=%s' % (number_reads, tag_extended)]
if paired:
steps.extend([r"""awk 'BEGIN{OFS="\t"}{$4="N";$5="1000";print $0}'"""])
diff --git a/workflow/tests/test_annotate_peaks.py b/workflow/tests/test_annotate_peaks.py
index 22e1d78ef149890c1b518225f6e01b2e259aabdb..73656357dc176169246c8196f20c60555e87dfac 100644
--- a/workflow/tests/test_annotate_peaks.py
+++ b/workflow/tests/test_annotate_peaks.py
@@ -41,4 +41,4 @@ def test_upsetplot_pairedend():
def test_annotation_pairedend():
annotation_file = test_output_path + 'ENCSR729LGA.chipseeker_annotation.tsv'
assert os.path.exists(annotation_file)
- assert utils.count_lines(annotation_file) >= 25466
+ assert utils.count_lines(annotation_file) >= 25367
diff --git a/workflow/tests/test_call_peaks_macs.py b/workflow/tests/test_call_peaks_macs.py
index 28881bd6e61a084ffa51a83647db9cd76ace6854..cd94e1783a25ffa953b3666f7cb3172c33f4f0bd 100644
--- a/workflow/tests/test_call_peaks_macs.py
+++ b/workflow/tests/test_call_peaks_macs.py
@@ -26,7 +26,7 @@ def test_peaks_xls_singleend():
@pytest.mark.singleend
def test_peaks_bed_singleend():
peak_file = test_output_path + 'ENCSR238SGC/1/' + 'ENCLB144FDT.narrowPeak'
- assert utils.count_lines(peak_file) == 227389
+ assert utils.count_lines(peak_file) == 226738
@pytest.mark.pairedend
@@ -47,4 +47,4 @@ def test_peaks_xls_pairedend():
@pytest.mark.pairedend
def test_peaks_bed_pairedend():
peak_file = test_output_path + 'ENCSR729LGA/2/' + 'ENCLB568IYX.narrowPeak'
- assert utils.count_lines(peak_file) == 113821
+ assert utils.count_lines(peak_file) == 112631
diff --git a/workflow/tests/test_diff_peaks.py b/workflow/tests/test_diff_peaks.py
index ed22fd83d5db04fac6c3c4924cafd81455a55c5a..93655d177a322b2d44056df79485909413444317 100644
--- a/workflow/tests/test_diff_peaks.py
+++ b/workflow/tests/test_diff_peaks.py
@@ -71,4 +71,4 @@ def test_diffbind_pairedend_single_rep():
assert os.path.exists(os.path.join(test_output_path, 'ENCSR729LGA_vs_ENCSR757EMK_diffbind.bed'))
diffbind_file = test_output_path + 'ENCSR729LGA_vs_ENCSR757EMK_diffbind.csv'
assert os.path.exists(diffbind_file)
- assert utils.count_lines(diffbind_file) >= 66201
+ assert utils.count_lines(diffbind_file) >= 65182
diff --git a/workflow/tests/test_overlap_peaks.py b/workflow/tests/test_overlap_peaks.py
index 67435d9968bcf4c681c43685cb85a35475cb8b1e..c450551ab5ac582977163c5d59220f5e807615c6 100644
--- a/workflow/tests/test_overlap_peaks.py
+++ b/workflow/tests/test_overlap_peaks.py
@@ -44,4 +44,4 @@ def test_overlap_peaks_singleend():
def test_overlap_peaks_pairedend():
assert os.path.exists(os.path.join(test_output_path, 'ENCSR729LGA.rejected.narrowPeak'))
peak_file = test_output_path + 'ENCSR729LGA.replicated.narrowPeak'
- assert utils.count_lines(peak_file) >= 25758
+ assert utils.count_lines(peak_file) >= 25657
diff --git a/workflow/tests/test_xcor.py b/workflow/tests/test_xcor.py
index fd475943f3f60317c4e0d5dd1ef067cc23fd842d..19777a0be7f045cfb91ca3f1d96fdba7bd39322c 100644
--- a/workflow/tests/test_xcor.py
+++ b/workflow/tests/test_xcor.py
@@ -17,9 +17,9 @@ def test_cross_plot_singleend():
def test_cross_qc_singleend():
qc_file = os.path.join(test_output_path,"ENCLB144FDT/ENCLB144FDT.cc.qc")
df_xcor = pd.read_csv(qc_file, sep="\t", header=None)
- assert df_xcor[2].iloc[0] == '190,200,210'
- assert df_xcor[8].iloc[0] == 1.025906
- assert round(df_xcor[9].iloc[0], 6) == 1.139671
+ assert df_xcor[2].iloc[0] == '185,195,205'
+ assert df_xcor[8].iloc[0] == 1.02454
+ assert df_xcor[9].iloc[0] == 0.8098014
@pytest.mark.pairedend
@@ -31,6 +31,6 @@ def test_cross_qc_pairedend():
def test_cross_plot_pairedend():
qc_file = os.path.join(test_output_path,"ENCLB568IYX/ENCLB568IYX.cc.qc")
df_xcor = pd.read_csv(qc_file, sep="\t", header=None)
- assert df_xcor[2].iloc[0] == '220,430,475'
- assert round(df_xcor[8].iloc[0],6) == 1.060018
- assert df_xcor[9].iloc[0] == 4.099357
+ assert df_xcor[2].iloc[0] == '215,225,455'
+ assert round(df_xcor[8].iloc[0],6) == 1.056201
+ assert df_xcor[9].iloc[0] == 3.599357