Bug fix: fix bed start and end in bigwig_outlier_bed (#6312)

* fix all beds by padding the region end in the output bed file to suit UCSC math * update tests with padded bed region ends * flake8 pacification * odd. test outputs pass here - will test biocontainers...x * add 1 to start instead * hmmm. tests passing here... * updating tests and test data * having strange problems getting planemo to update existing but wrong test outputs * using a specialised bed file -> bigwig chr1 0 10 100 100 + chr1 20 30 100 100 + chr1 40 50 100 100 + chr1 60 70 100 100 + chr1 200 300 100 100 + chr1 300 400 0 0 + chr1 400 1000 100 100 + * add fakery * trying again with refreshed test data. Not sure what's going on...passes here. * placate flake8 * wrong fake.bed sample... * fix multiple bigwigs * more flake8 fixing. * remove bogus test parameter... * add nice histogram test * restore some histogram table reports - just use the old merlin note the odd offsets. caused me some grief. * reduce ram bloat by iterating instead of using a list comprehension for large bed texts.
galaxyproject · Sep 15, 2024 · 06c54e8 · 06c54e8
1 parent 982fe89
commit 06c54e8
Show file tree

Hide file tree

Showing 18 changed files with 2,471 additions and 4,883 deletions.
diff --git a/tools/bigwig_outlier_bed/bigwig_outlier_bed.py b/tools/bigwig_outlier_bed/bigwig_outlier_bed.py
@@ -146,7 +146,7 @@ def processVals(self, bw, isTop):
         else:
             bwex = np.r_[False, bw <= self.bwbot, False]
         bwexd = np.diff(bwex)
-        bwexdnz = bwexd.nonzero()[0]
+        bwexdnz = bwexd.nonzero()[0]  # start and end transition of each segment - nice!
         bwregions = np.reshape(bwexdnz, (-1, 2))
         return bwregions
 
@@ -155,10 +155,9 @@ def writeBed(self, bed, bedfname):
         potentially multiple
         """
         bed.sort()
-        beds = ["%s\t%d\t%d\t%s\t%d" % x for x in bed]
         with open(bedfname, "w") as bedf:
-            bedf.write("\n".join(beds))
-            bedf.write("\n")
+            for b in bed:
+                bedf.write("%s\t%d\t%d\t%s\t%d\n" % b)
 
     def makeTableRow(self, bw, bwlabel, chr):
         """
@@ -194,7 +193,6 @@ def makeBed(self):
         restab = []
         bwlabels = self.bwlabels
         bwnames = self.bwnames
-        bwnames.sort()
         reshead = "bigwig\tcontig\tn\tmean\tstd\tmin\tmax\tqtop\tqbot"
         for i, bwname in enumerate(bwnames):
             bwlabel = bwlabels[i].replace(" ", "")
@@ -251,8 +249,11 @@ def makeBed(self):
                     self.bwbot = np.quantile(bw, self.qlo)
                     bwlo = self.processVals(bw, isTop=False)
                     for j, seg in enumerate(bwlo):
+                        seglen = seg[1] - seg[0]
                         if seg[1] - seg[0] >= self.bedwin:
-                            score = -1 * np.sum(bw[seg[0]:seg[1]]) / float(seglen)
+                            score = (
+                                -1 * np.sum(bw[seg[0]:seg[1]]) / float(seglen)
+                            )
                             bedlo.append(
                                 (
                                     chr,

diff --git a/tools/bigwig_outlier_bed/bigwig_outlier_bed.xml b/tools/bigwig_outlier_bed/bigwig_outlier_bed.xml
@@ -3,7 +3,7 @@
   <macros>
   <token name="@TOOL_VERSION@">0.2.0</token>
   <token name="@PYTHON_VERSION@">3.12.3</token>
-  <token name="@VERSION_SUFFIX@">0</token>
+  <token name="@VERSION_SUFFIX@">1</token>
   </macros>
   <edam_topics>
       <edam_topic>topic_0157</edam_topic>
@@ -25,13 +25,13 @@
   </required_files>
   <version_command><![CDATA[python -c "import pybigtools; from importlib.metadata import version; print(version('pybigtools'))"]]></version_command>
   <command><![CDATA[python '${__tool_directory__}/bigwig_outlier_bed.py'
---bigwig 
-#for bw in $bigwig: 
- '$bw' 
+#set bwns = [x.name for x in $bigwig]
+#set bwfs = [x for x in $bigwig]
+#for $bwf in $bwfs:
+--bigwig '$bwf'
 #end for
---bigwiglabels
-#for bw in $bigwig: 
-  '$bw.name'
+#for $bwn in $bwns:
+--bigwiglabels '$bwn'
 #end for
 --outbeds '$outbeds'
 #if $outbeds in ['outhilo', 'outall']:
@@ -94,29 +94,29 @@
     <test expect_num_outputs="1">
       <output name="bedouthilo" value="bedouthilo_sample" compare="diff" lines_diff="0"/>
       <param name="outbeds" value="outhilo"/>
-      <param name="bigwig" value="bigwig_sample"/>
+      <param name="bigwig" value="fake.bigwig"/>
       <param name="minwin" value="10"/>
-      <param name="qhi" value="0.99"/>
+      <param name="qhi" value="0.6"/>
       <param name="qlo" value="0.01"/>
       <param name="tableout" value="donotmake"/>
     </test>
     <test expect_num_outputs="1">
       <output name="tableoutfile" value="table_only_sample" compare="diff" lines_diff="0"/>
       <param name="outbeds" value="outtab"/>
-      <param name="bigwig" value="bigwig_sample,1.bigwig"/>
+      <param name="bigwig" value="fake.bigwig"/>
       <param name="minwin" value="10"/>
-      <param name="qhi" value="0.99"/>
-      <param name="qlo" value="0.01"/>
+      <param name="qhi" value="0.7"/>
+      <param name="qlo" value="0.3"/>
       <param name="tableout" value="create"/>
     </test>
     <test expect_num_outputs="2">
-      <output name="bedouthilo" value="bedouthilo_sample" compare="diff" lines_diff="0"/>
+      <output name="bedouthilo" value="bedouthilo_sample_2" compare="diff" lines_diff="0"/>
       <output name="tableoutfile" value="table_sample" compare="diff" lines_diff="0"/>
       <param name="outbeds" value="outhilo"/>
       <param name="bigwig" value="bigwig_sample"/>
       <param name="minwin" value="10"/>
-      <param name="qhi" value="0.99"/>
-      <param name="qlo" value="0.01"/>
+      <param name="qhi" value="0.7"/>
+      <param name="qlo" value="0.3"/>
       <param name="tableout" value="create"/>
     </test>
     <test expect_num_outputs="2">
@@ -125,7 +125,7 @@
       <param name="outbeds" value="outhi"/>
       <param name="bigwig" value="bigwig_sample"/>
       <param name="minwin" value="10"/>
-      <param name="qhi" value="0.99"/>
+      <param name="qhi" value="0.69"/>
       <param name="qlo" value=""/>
       <param name="tableout" value="create"/>
     </test>
@@ -134,24 +134,25 @@
       <output name="bedoutlo" value="bedoutlo_sample" compare="diff" lines_diff="0"/>
       <output name="tableoutfile" value="table3_sample" compare="diff" lines_diff="0"/>
       <param name="outbeds" value="outlohi"/>
-      <param name="bigwig" value="bigwig_sample"/>
-      <param name="minwin" value="1"/>
-      <param name="qhi" value="0.9"/>
-      <param name="qlo" value="0.1"/>
+      <param name="bigwig" value="fake.bigwig"/>
+      <param name="minwin" value="10"/>
+      <param name="qhi" value="0.5"/>
+      <param name="qlo" value="0.5"/>
       <param name="tableout" value="create"/>
     </test>
-    <test expect_num_outputs="4">
-      <output name="bedouthilo" value="bedouthilo2_sample" compare="diff" lines_diff="0"/>
-      <output name="bedoutlo" value="bedoutlo2_sample" compare="diff" lines_diff="0"/>
+    <test expect_num_outputs="2">
       <output name="bedouthi" value="bedouthi2_sample" compare="diff" lines_diff="0"/>
       <output name="tableoutfile" value="table2_sample" compare="diff" lines_diff="0"/>
-      <param name="outbeds" value="outall"/>
-      <param name="bigwig" value="bigwig_sample,1.bigwig"/>
-      <param name="minwin" value="1"/>
-      <param name="qhi" value="0.9"/>
-      <param name="qlo" value="0.1"/>
+      <param name="outbeds" value="outhi"/>
+      <param name="bigwig" value="fake.bigwig,bigwig_sample"/>
+      <param name="minwin" value="10"/>
+      <param name="qhi" value="0.5"/>
+      <param name="qlo" value="0.5"/>
       <param name="tableout" value="create"/>
     </test>
+
+
+
   </tests>
   <help><![CDATA[