From a0a029583122ead30da94c010c731be59c1ae701 Mon Sep 17 00:00:00 2001
From: Jeremy Mathews <Jeremy.Mathews@utsouthwestern.edu>
Date: Tue, 3 Sep 2019 07:09:29 -0500
Subject: [PATCH] Update cross correlation and related tests
---
.gitlab-ci.yml | 2 ++
workflow/scripts/xcor.py | 2 +-
workflow/tests/test_call_peaks_macs.py | 4 ++--
workflow/tests/test_xcor.py | 12 ++++++------
4 files changed, 11 insertions(+), 9 deletions(-)
diff --git a/.gitlab-ci.yml b/.gitlab-ci.yml
index 3e6393e..83ef6e5 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/workflow/scripts/xcor.py b/workflow/scripts/xcor.py
index 096afc9..66fa9ae 100644
--- a/workflow/scripts/xcor.py
+++ b/workflow/scripts/xcor.py
@@ -103,7 +103,7 @@ 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)
diff --git a/workflow/tests/test_call_peaks_macs.py b/workflow/tests/test_call_peaks_macs.py
index f8a0842..cd94e17 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) == 199317
+ 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_xcor.py b/workflow/tests/test_xcor.py
index 4b65aa9..19777a0 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] == '220,240,255'
- assert df_xcor[8].iloc[0] == 1.024935
- assert round(df_xcor[9].iloc[0], 6) == 0.697252
+ 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] == '220,420,450'
- assert round(df_xcor[8].iloc[0],6) == 1.058694
- assert df_xcor[9].iloc[0] == 3.004596
+ 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
--
GitLab