From e78c5af1c7d8601894bb63dfaba18f5a8561c2d7 Mon Sep 17 00:00:00 2001
From: Holly Ruess <holly.ruess@utsouthwestern.edu>
Date: Fri, 18 Jan 2019 09:38:37 -0600
Subject: [PATCH] add Pearson Correlation, make plots pdf
---
workflow/.DS_Store | Bin 0 -> 6148 bytes
workflow/main.nf | 2 +-
workflow/scripts/experiment_qc.py | 27 ++++++++++++++++++++++++---
workflow/tests/test_experiment_qc.py | 6 ++++--
4 files changed, 29 insertions(+), 6 deletions(-)
create mode 100644 workflow/.DS_Store
diff --git a/workflow/.DS_Store b/workflow/.DS_Store
new file mode 100644
index 0000000000000000000000000000000000000000..1cfdf47763f95697736ca7303755f243846e9ca2
GIT binary patch
literal 6148
zcmeHK&1%~~5T5l<ymlz{p->-n$;}75Y3)-$IPRghfI@O;N+Q*!5xA1E<e0>D(QCAC
zlqcxx^qbwaY2xM<N-;Aq`;F#j#eQ0LHAJKa^HG<mNkkgTSgK?Ai*THEOG?gD1}Zbh
zlyb_VMK+BlTiN3H9~t0pSEGzR(~M&J<NKu%BKOgB5@&g*^GlV=mFiwi>xOQ;XnYE;
z(?yVn`8*qhvyc3A66V*Dvrp4>va!SHEFLc|o3D=3BoE_cJTt}dXpEGL^Eer$i$OY1
zMwyu>umP>>x_;SgEtkD_-M07kO>foqmi>MQ_F-?es_WMW-J=gzUvKZ0-&Ws$SZ)=z
zp^=vk*YFd@qh;O%vt*JcUl8G{Dz@$zL|_9yimc}l6b6I=VPIz%aEGPd-<cK3LWBWf
z;JFy!^TC5M`VI?==IFp+S^!`LZX>X{m*5)Dq3^J;hzLa4QlKqWuEkKc9DdK``3?(<
zww#n}K9qa2avh2?Z^!(eNhjr7lu;NE1|BlNy&t5>_y7B+`+t)pgD@Zr>?Q-MG7N?T
ztj*o6TdU-|)`MO_Svaq-xG8~Qu43f!RosFaf!|{T=sPSd!UK^X0Yiff!oWXe;5UU>
BSiS%N
literal 0
HcmV?d00001
diff --git a/workflow/main.nf b/workflow/main.nf
index 29afb26..6c69eda 100644
--- a/workflow/main.nf
+++ b/workflow/main.nf
@@ -198,7 +198,7 @@ process experimentQC {
output:
- file '*.{png,npz}' into deepToolsStats
+ file '*.{pdf,npz}' into deepToolsStats
script:
diff --git a/workflow/scripts/experiment_qc.py b/workflow/scripts/experiment_qc.py
index 7386fcf..affbbc4 100644
--- a/workflow/scripts/experiment_qc.py
+++ b/workflow/scripts/experiment_qc.py
@@ -76,10 +76,10 @@ def generate_read_summary(design, extension):
return mbs_filename
-def check_correlation(mbs):
+def check_spearman_correlation(mbs):
'''Check Spearman pairwise correlation of samples based on read counts.'''
- spearman_filename = 'heatmap_SpearmanCorr.png'
+ spearman_filename = 'heatmap_SpearmanCorr.pdf'
spearman_params = "--corMethod spearman --skipZero" + \
" --plotTitle \"Spearman Correlation of Read Counts\"" + \
" --whatToPlot heatmap --colorMap RdYlBu --plotNumbers"
@@ -95,6 +95,25 @@ def check_correlation(mbs):
out, err = spearman_correlation.communicate()
+def check_pearson_correlation(mbs):
+ '''Check Pearson pairwise correlation of samples based on read counts.'''
+
+ pearson_filename = 'heatmap_PearsonCorr.pdf'
+ pearson_params = "--corMethod pearson --skipZero" + \
+ " --plotTitle \"Pearson Correlation of Read Counts\"" + \
+ " --whatToPlot heatmap --colorMap RdYlBu --plotNumbers"
+
+ pearson_command = (
+ "plotCorrelation -in %s %s -o %s"
+ % (mbs, pearson_params, pearson_filename)
+ )
+
+ logger.info("Running deeptools with %s", pearson_command)
+
+ pearson_correlation = subprocess.Popen(pearson_command, shell=True)
+ out, err = pearson_correlation.communicate()
+
+
def check_coverage(design, extension):
'''Asses the sequencing depth of samples.'''
@@ -166,7 +185,9 @@ def main():
# Run correlation
mbs_filename = generate_read_summary(design_df, extension)
- check_correlation(mbs_filename)
+ check_spearman_correlation(mbs_filename)
+ check_pearson_correlation(mbs_filename)
+
# Run coverage
check_coverage(design_df, extension)
diff --git a/workflow/tests/test_experiment_qc.py b/workflow/tests/test_experiment_qc.py
index 5256da5..6950950 100644
--- a/workflow/tests/test_experiment_qc.py
+++ b/workflow/tests/test_experiment_qc.py
@@ -33,7 +33,8 @@ def test_check_update_controls(design_bam):
@pytest.mark.singleend
def test_experiment_qc_singleend():
assert os.path.exists(os.path.join(test_output_path, 'sample_mbs.npz'))
- assert os.path.exists(os.path.join(test_output_path, 'heatmap_SpearmanCorr.png'))
+ assert os.path.exists(os.path.join(test_output_path, 'heatmap_SpearmanCorr.pdf'))
+ assert os.path.exists(os.path.join(test_output_path, 'heatmap_PearsonCorr.pdf'))
assert os.path.exists(os.path.join(test_output_path, 'coverage.png'))
assert os.path.exists(os.path.join(test_output_path, 'ENCLB144FDT_fingerprint.png'))
assert os.path.exists(os.path.join(test_output_path, 'ENCLB831RUI_fingerprint.png'))
@@ -41,7 +42,8 @@ def test_experiment_qc_singleend():
@pytest.mark.pairdend
def test_experiment_qc_pairedend():
assert os.path.exists(os.path.join(test_output_path, 'sample_mbs.npz'))
- assert os.path.exists(os.path.join(test_output_path, 'heatmap_SpearmanCorr.png'))
+ assert os.path.exists(os.path.join(test_output_path, 'heatmap_SpearmanCorr.pdf'))
+ assert os.path.exists(os.path.join(test_output_path, 'heatmap_PearsonCorr.pdf'))
assert os.path.exists(os.path.join(test_output_path, 'coverage.png'))
assert os.path.exists(os.path.join(test_output_path, 'ENCLB568IYX_fingerprint.png'))
assert os.path.exists(os.path.join(test_output_path, 'ENCLB637LZP_fingerprint.png'))
--
GitLab