Estimated filtering fix (#813)

* oops

* fix testing and set a max number of filtered reads

* apparently a bunch of things were getting skipped

* fix wrappers

* update computeMatrix wrapper

CHANGES.txt

@@ -1,3 +1,7 @@
+3.2.1
+
+ * Changed a bug in `estimateReadFiltering` where the estimated number of filtered reads was typically too low.
+
 3.2.0
 
  * Added access in the Galaxy wrapper to the `--labels` option in most tools (issue #738)

azure-pipelines.yml

@@ -62,5 +62,5 @@ jobs:
     displayName: Installing deepTools
   - script: |
       source activate foo
-      ./.planemo.sh
+      ./.planemo.sh $TESTGALAXY
     displayName: Run planemo

deeptools/estimateReadFiltering.py

@@ -329,43 +329,43 @@ def main(args=None):
         # nFiltered
         metric = 0.0
         if totals[idx] > 0:
-            metric = blacklisted[idx] + float(nFiltered[idx]) / float(totals[idx]) * nFiltered[idx]
-        of.write("\t{}".format(round(metric, 1)))
+            metric = blacklisted[idx] + float(nFiltered[idx]) / float(totals[idx]) * mapped[idx]
+        of.write("\t{}".format(min(round(metric, 1), mapped[idx])))
         # MAPQ
         metric = 0.0
         if totals[idx] > 0:
             metric = float(MAPQs[idx]) / float(totals[idx]) * mapped[idx]
-        of.write("\t{}".format(round(metric, 1)))
+        of.write("\t{}".format(min(round(metric, 1), mapped[idx])))
         # samFlagInclude
         metric = 0.0
         if totals[idx] > 0:
             metric = float(flagIncludes[idx]) / float(totals[idx]) * mapped[idx]
-        of.write("\t{}".format(round(metric, 1)))
+        of.write("\t{}".format(min(round(metric, 1), mapped[idx])))
         # samFlagExclude
         metric = 0.0
         if totals[idx] > 0:
             metric = float(flagExcludes[idx]) / float(totals[idx]) * mapped[idx]
-        of.write("\t{}".format(round(metric, 1)))
+        of.write("\t{}".format(min(round(metric, 1), mapped[idx])))
         # Internally determined duplicates
         metric = 0.0
         if totals[idx] > 0:
             metric = float(internalDupes[idx]) / float(totals[idx]) * mapped[idx]
-        of.write("\t{}".format(round(metric, 1)))
+        of.write("\t{}".format(min(round(metric, 1), mapped[idx])))
         # Externally marked duplicates
         metric = 0.0
         if totals[idx] > 0:
             metric = float(externalDupes[idx]) / float(totals[idx]) * mapped[idx]
-        of.write("\t{}".format(round(metric, 1)))
+        of.write("\t{}".format(min(round(metric, 1), mapped[idx])))
         # Singletons
         metric = 0.0
         if totals[idx] > 0:
             metric = float(singletons[idx]) / float(totals[idx]) * mapped[idx]
-        of.write("\t{}".format(round(metric, 1)))
+        of.write("\t{}".format(min(round(metric, 1), mapped[idx])))
         # filterRNAstrand
         metric = 0.0
         if totals[idx] > 0:
             metric = float(rnaStrand[idx]) / float(totals[idx]) * mapped[idx]
-        of.write("\t{}".format(round(metric, 1)))
+        of.write("\t{}".format(min(round(metric, 1), mapped[idx])))
         of.write("\n")
 
     if args.outFile is not None:

deeptools/test/test_readFiltering.py

@@ -34,7 +34,7 @@ def test_estimate_read_filtering_minimal():
 
 def test_estimate_read_filtering_params():
     """
-    Minimal testing
+    --minMappingQuality 10 --samFlagExclude 512 --ignoreDuplicates -bl
     """
     outfile = '/tmp/test_params.txt'
     args = '-b {} --minMappingQuality 10 --samFlagExclude 512 --ignoreDuplicates -bl {} -o {}'.format(BAMFILE_FILTER, BEDFILE_FILTER, outfile).split()
@@ -48,7 +48,7 @@ def test_estimate_read_filtering_params():
     _[0] = os.path.basename(_[0])
     resp[1] = "\t".join(_)
     expected = ['Sample\tTotal Reads\tMapped Reads\tAlignments in blacklisted regions\tEstimated mapped reads filtered\tBelow MAPQ\tMissing Flags\tExcluded Flags\tInternally-determined Duplicates\tMarked Duplicates\tSingletons\tWrong strand\n',
-                'test_filtering.bam\t193\t193\t7\t176.1\t41.4\t0.0\t186.5\t31.6\t0.0\t0.0\t0.0\n']
+                'test_filtering.bam\t193\t193\t7\t193\t41.4\t0.0\t186.5\t31.6\t0.0\t0.0\t0.0\n']
     assert_equal(resp, expected)
     unlink(outfile)
 

galaxy/wrapper/bamCompare.xml

@@ -166,8 +166,8 @@
                 <expand macro="skipNAs" />
                 <param argument="--skipZeroOverZero" type="select" label="Skip bins of no coverage"
                     help="Skip bins where BOTH files lack coverage.">
-                    <option value="no" selected="true">No</option>
-                    <option value="yes">Yes, skip them.</option>
+                    <option value="" selected="true">No</option>
+                    <option value="--skipZeroOverZero">Yes, skip them.</option>
                 </param>
 
                 <param argument="--ignoreForNormalization" type="text" value="" size="50"

galaxy/wrapper/computeMatrix.xml

@@ -24,6 +24,7 @@
             --scoreFileName #echo ' '.join($files)#
 
             --outFileName '$outFileName'
+            --samplesLabel #echo ' '.join($labels)#
 
             @THREADS@
 
@@ -72,9 +73,6 @@
                 #if $advancedOpt.scale is not None and str($advancedOpt.scale) != '':
                     --scale $advancedOpt.scale
                 #end if
-                #if $advancedOpt.samplesLabel is not None and str($advancedOpt.samplesLabel) != '':
-                    --samplesLabel $advancedOpt.samplesLabel
-                #end if
 
                 @ADVANCED_OPTS_GTF@
 
@@ -91,6 +89,7 @@
         </repeat>
 
         <expand macro="multiple_input_bigwigs" MIN="1" LABEL="Score file" TITLE="Score files"/>
+        <expand macro="custom_sample_labels" />
 
         <conditional name="mode" >
             <param name="mode_select" type="select"
@@ -207,15 +206,6 @@
                     bias the average values. (--maxThreshold)"/>
                 <param name="scale" type="float" optional="True" label="Scaling factor"
                     help="If set, all values are multiplied by this number. (--scale)"/>
-                <param argument="--samplesLabel" type="text" size="30"
-                    label="Labels for the samples (each bigwig)"
-                    help="The default is to use the history item label. The sample labels should be separated by
-                    spaces and quoted if a label itself contains a space E.g. label-1 &quot;label 2&quot;">
-                    <sanitizer>
-                        <valid initial="string.printable">
-                        </valid>
-                    </sanitizer>
-                </param>
 
                 <expand macro="gtf_options" />
 

galaxy/wrapper/deepTools_macros.xml

@@ -512,7 +512,7 @@ is vital to you, select Yes below.">
 
     <token name="@multiple_input_bigwigs@">
 <![CDATA[
-        #if $custom_labels_conditional.custom_labels_select == "Yes":
+        #if $custom_sample_labels_conditional.custom_labels_select == "Yes":
             #set custom_labels=labels
         #end if
         #set files=[]
@@ -533,7 +533,7 @@ is vital to you, select Yes below.">
                 #silent $labels.append("'%s'" % $identifier)
             #end for
         #end if
-        #if $custom_labels_conditional.custom_labels_select == "Yes":
+        #if $custom_sample_labels_conditional.custom_labels_select == "Yes":
             #set labels=custom_labels
         #end if
 ]]>

galaxy/wrapper/test-data/estimateReadFiltering.txt

@@ -1,3 +1,3 @@
 Sample	Total Reads	Mapped Reads	Alignments in blacklisted regions	Estimated mapped reads filtered	Below MAPQ	Missing Flags	Excluded Flags	Internally-determined Duplicates	Marked Duplicates	Singletons	Wrong strand
-paired_chr2L.bam	12644	12589	0	1395.9	4149.0	0.0	0.0	0.0	0.0	55.0	0.0
-paired_chr2L.bam	12644	12589	0	1395.9	4149.0	0.0	0.0	0.0	0.0	55.0	0.0
+paired_chr2L.bam	12644	12589	0	4192.0	4149.0	0.0	0.0	0.0	0.0	55.0	0.0
+paired_chr2L.bam	12644	12589	0	4192.0	4149.0	0.0	0.0	0.0	0.0	55.0	0.0