Merge branch '73-single_pool' of...

Merge branch '73-single_pool' of git.biohpc.swmed.edu:BICF/Astrocyte/chipseq_analysis into 73-single_pool

CHANGELOG.md

@@ -15,6 +15,10 @@ All notable changes to this project will be documented in this file.
 - Fix xcor to increase file size for --random-source
 - Fix skip diff test for paired-end data
 - Add test data for single control and single replicate
+- Fix python version for MultiQC report
+- Fix xcor to get lowest non zero value above 50
+- Fix references to display in Multiqc report
+
 
 ## [publish_1.0.6 ] - 2019-05-31
 ### Added

test_data/test_cross.qc

+Test.20.tagAlign.gz	18588987	0,20,33	0.211525291335199,0.211232019956852,0.211139666755398	35	0.2123067	1500	0.209429	1.01001	0.7284536       0

workflow/main.nf

@@ -654,10 +654,10 @@ process multiqcReport {
 
   """
   echo $workflow.nextflow.version > version_nextflow.txt
-  singularity exec /project/shared/bicf_workflow_ref/singularity_images/multiqc.sif multiqc --version > version_multiqc.txt
+  singularity exec /project/shared/bicf_workflow_ref/singularity_images/bicf-multiqc-2.0.0.img 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
-  singularity exec /project/shared/bicf_workflow_ref/singularity_images/multiqc.sif multiqc -c $multiqc .
+  singularity exec /project/shared/bicf_workflow_ref/singularity_images/bicf-multiqc-2.0.0.img multiqc -c $multiqc .
   """
 }

workflow/scripts/call_peaks_macs.py

@@ -138,8 +138,20 @@ def call_peaks_macs(experiment, xcor, control, prefix, genome_size, chrom_sizes)
     with open(xcor, 'r') as xcor_fh:
         firstline = xcor_fh.readline()
         frag_lengths = firstline.split()[2]  # third column
-        fragment_length = frag_lengths.split(',')[0]  # grab first value
-        logger.info("Fraglen %s", fragment_length)
+        frag_lengths_array = frag_lengths.split(',')
+        fragment_length = 0
+        fragment = False
+        # Loop through all values of fragment length
+        for f in frag_lengths.split(','):
+            fragment_length = f
+            logger.info("Fraglen %s", fragment_length)
+            if int(fragment_length) > 50:
+                fragment = True
+                break
+
+        if fragment == False:
+            logger.info('Error in cross-correlation analysis: %s', frag_lengths_array)
+            raise Exception("Error in cross-correlation analysis: %s" % frag_lengths_array)
 
     # Generate narrow peaks and preliminary signal tracks
 

workflow/scripts/generate_versions.py

@@ -46,7 +46,7 @@ SOFTWARE_REGEX = {
     'MEME-ChIP': ['motifSearch_vf/version_memechip.txt', r"Version (\S+)"],
     'DiffBind': ['diffPeaks_vf/version_DiffBind.txt', r"Version (\S+)\""],
     'deepTools': ['experimentQC_vf/version_deeptools.txt', r"deeptools (\S+)"],
-    'Python': ['version_python.txt', r"python, version (\S+)"],
+    'Python': ['version_python.txt', r"Python (\S+)"],
     'MultiQC': ['version_multiqc.txt', r"multiqc, version (\S+)"],
 }
 

workflow/tests/test_call_peaks_macs.py

@@ -3,10 +3,29 @@
 import pytest
 import os
 import utils
+from io import StringIO
+import call_peaks_macs
 
 test_output_path = os.path.dirname(os.path.abspath(__file__)) + \
                 '/../output/callPeaksMACS/'
 
+test_data_path = os.path.dirname(os.path.abspath(__file__)) + \
+		'/../../test_data/'
+        
+
+@pytest.mark.unit
+def test_fragment_length():
+    experiment = "experiment.tagAlign.gz"
+    control = "control.tagAlign.gz"
+    prefix = 'test'
+    genome_size = 'hs'
+    chrom_sizes = 'genomefile.txt'
+    cross_qc = os.path.join(test_data_path, 'test_cross.qc')
+    with pytest.raises(Exception) as excinfo:
+        call_peaks_macs.call_peaks_macs(experiment, cross_qc, control, prefix, genome_size, chrom_sizes)
+    assert str(excinfo.value) == "Error in cross-correlation analysis: ['0', '20', '33']"
+
+
 
 @pytest.mark.singleend
 def test_fc_signal_singleend():

workflow/tests/test_generate_software_references.py

@@ -4,6 +4,7 @@ import pytest
 import os
 import utils
 import yaml
+from bs4 import BeautifulSoup
 
 test_output_path = os.path.dirname(os.path.abspath(__file__)) + \
                 '/../output/multiqcReport/'
@@ -21,3 +22,14 @@ def test_software_references_output():
         data_loaded = yaml.load(stream)
 
     assert len(data_loaded['data'].split('<ul>')) == 19
+
+
+@pytest.mark.singleend
+def test_software_references_html():
+    multiqc_report = os.path.join(test_output_path, 'multiqc_report.html')
+    html_file = open(multiqc_report, 'r')
+    source_code = html_file.read()
+    multiqc_html = BeautifulSoup(source_code, 'html.parser')
+    references = multiqc_html.find(id="mqc-module-section-Software_References")
+    assert references is not None
+    assert len(references.find_all('ul')) == 18

workflow/tests/test_generate_software_versions.py

@@ -21,3 +21,4 @@ def test_software_versions_output():
         data_loaded = yaml.load(stream)
 
     assert  len(data_loaded['data'].split('<dt>')) == 18
+    assert  'Not Run' not in data_loaded['data'].split('<dt>')[17]