Mercurial > repos > drosofff > msp_sr_readmap_and_size_histograms

changeset 24:bf7388df53cf draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_sr_readmap_and_size_histograms commit 3effd45f45c37a6cdaf9b7b1da1ed4d10d3b0e38
author drosofff
date Sat, 08 Oct 2016 07:18:45 -0400
parents d6b93af0da55
children
files README.rst readmap.py readmap.xml smRtools.py smRtools.pyc test-data/Readmap_dataframe.tab test-data/Readmaps.pdf test-data/Size_distribution.pdf test-data/Size_distribution_and_Readmaps.pdf test-data/Size_distribution_dataframe.tab
diffstat 10 files changed, 104 insertions(+), 76 deletions(-) [+]
line wrap: on
line diff
--- a/README.rst	Sun Apr 24 09:23:44 2016 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,2 +0,0 @@
-Starting with version 1.2.0, this tool requires a galaxy release 16.01 or newer and conda dependency resolution to be active.
-
--- a/readmap.py	Sun Apr 24 09:23:44 2016 -0400
+++ b/readmap.py	Sat Oct 08 07:18:45 2016 -0400
@@ -52,16 +52,19 @@
                         biosample=fileLabel[i], size_inf=minquery, size_sup=maxquery, norm=norm)
   return MasterListOfGenomes
 
-def dataframe_sanityzer (listofdatalines):
-  Dict = defaultdict(float) 
+def remove_null_entries(listofdatalines):
+  """
+  This function removes genes that have no reads aligned.
+  """
+  Dict = defaultdict(float)
   for line in listofdatalines:
     fields= line.split("\t")
-    Dict[fields[0]] += float (fields[2])
+    Dict[fields[0]] += abs(float(fields[2]))
   filtered_list = []
   for line in listofdatalines:
     fields= line.split("\t")
     if Dict[fields[0]] != 0:
-      filtered_list.append(line) 
+      filtered_list.append(line)
   return filtered_list
 
 
@@ -108,9 +111,8 @@
         plottable = dict[gene].readplot()
         plottable = handle_start_stop_coordinates(plottable, readDict)
         for line in plottable:
-          #print >>readmap, "%s\t%s" % (line, sample)
           listoflines.append ("%s\t%s" % (line, sample))
-    listoflines = dataframe_sanityzer(listoflines)
+    listoflines = remove_null_entries(listoflines)
     for line in listoflines:
       print >>readmap, line
 
@@ -124,19 +126,15 @@
       else:
         dict=readDict[sample].instanceDict
       for gene in dict.keys():
-        histogram = dict[gene].size_histogram(minquery=args.minquery, maxquery=args.maxquery)
+        histogram = dict[gene].size_histogram(minquery=minquery, maxquery=maxquery)
         for polarity in histogram.keys():
           if polarity=='both':
             continue
-          #for size in xrange(args.minquery, args.maxquery):
-          #  if not size in histogram[polarity].keys():
-          #    histogram[size]=0
           for size, count in histogram[polarity].iteritems():
-            #print >>size_distrib, "%s\t%s\t%s\t%s\t%s" % (gene, size, count, polarity, sample) # test, changed the order accordingly
             listoflines.append ("%s\t%s\t%s\t%s\t%s" % (gene, size, count, polarity, sample) )
-    listoflines = dataframe_sanityzer(listoflines)
+    listoflines = remove_null_entries(listoflines)
     for line in listoflines:
-      print >>size_distrib, line  
+      print >>size_distrib, line
 
 def gff_item_subinstances(readDict, gff3):
   GFFinstanceDict=OrderedDict()
--- a/readmap.xml	Sun Apr 24 09:23:44 2016 -0400
+++ b/readmap.xml	Sat Oct 08 07:18:45 2016 -0400
@@ -4,9 +4,9 @@
         <requirement type="package" version="1.0.0">bowtie</requirement>
         <requirement type="package" version="0.9.0">pysam</requirement>
         <requirement type="package" version="1.9.3">numpy</requirement>
-        <requirement type="package" version="1.3.0">r-optparse</requirement>
-        <requirement type="package" version="0.6_26">r-latticeextra</requirement>
-        <requirement type="package" version="2.0.0">r-gridextra</requirement>
+        <requirement type="package" version="1.3.0=r3.2.2_1">r-optparse</requirement>
+        <requirement type="package" version="0.6_26=r3.2.2_2a">r-latticeextra</requirement>
+        <requirement type="package" version="2.0.0=r3.2.2_0a">r-gridextra</requirement>
     </requirements>
     <command><![CDATA[
         python2 $__tool_directory__/readmap.py
@@ -151,9 +151,6 @@
             <param name="rows_per_page" value="8" />
             <output name="readmap_dataframe" ftype="tabular" file="Readmap_dataframe.tab" />
             <output name="size_distribution_dataframe" ftype="tabular" file="Size_distribution_dataframe.tab" />
-            <output name="readmap_PDF" ftype="pdf" file="Readmaps.pdf" />
-            <output name="size_PDF" ftype="pdf" file="Size_distribution.pdf" />
-            <output name="combi_PDF" ftype="pdf" file="Size_distribution_and_Readmaps.pdf" />
         </test>
     </tests>
 </tool>
--- a/smRtools.py	Sun Apr 24 09:23:44 2016 -0400
+++ b/smRtools.py	Sat Oct 08 07:18:45 2016 -0400
@@ -142,26 +142,6 @@
           self.alignedReads += 1
       F.close()
       return self.instanceDict
-#    elif self.alignmentFileFormat == "sam":
-#      F = open (self.alignmentFile, "r")
-#      dict = {"0":"+", "16":"-"}
-#      for line in F:
-#        if line[0]=='@':
-#            continue
-#        fields = line.split()
-#        if fields[2] == "*": continue
-#        polarity = dict[fields[1]]
-#        gene = fields[2]
-#        offset = int(fields[3])
-#        size = len (fields[9])
-#        if self.size_inf:
-#          if (size>=self.size_inf and size<= self.size_sup):
-#            self.instanceDict[gene].addread (polarity, offset, size)
-#            self.alignedReads += 1
-#       else:
-#          self.instanceDict[gene].addread (polarity, offset, size)
-#          self.alignedReads += 1
-#      F.close()
     elif self.alignmentFileFormat == "bam" or self.alignmentFileFormat == "sam":
       import pysam
       samfile = pysam.Samfile(self.alignmentFile)
@@ -184,22 +164,6 @@
           self.alignedReads += 1
       return self.instanceDict
 
-#  def size_histogram (self):
-#    size_dict={}
-#    size_dict['F']= defaultdict (int)
-#    size_dict['R']= defaultdict (int)
-#    size_dict['both'] = defaultdict (int)
-#    for item in self.instanceDict:
-#      buffer_dict_F = self.instanceDict[item].size_histogram()['F']
-#      buffer_dict_R = self.instanceDict[item].size_histogram()['R']
-#      for size in buffer_dict_F:
-#        size_dict['F'][size] += buffer_dict_F[size]
-#      for size in buffer_dict_R:
-#        size_dict['R'][size] -= buffer_dict_R[size]
-#    allSizeKeys = list (set (size_dict['F'].keys() + size_dict['R'].keys() ) )
-#    for size in allSizeKeys:
-#      size_dict['both'][size] = size_dict['F'][size] + size_dict['R'][size]
-#    return size_dict
   def size_histogram (self): # in HandleSmRNAwindows
     '''refactored on 7-9-2014 to debug size_histogram tool'''
     size_dict={}
@@ -361,24 +325,7 @@
     for offset in range (min(dicsize.keys()), max(dicsize.keys())+1):
       dicsize[size] = dicsize.get(size, 0) # to fill offsets with null values
     return dicsize
-    
-#  def size_histogram(self):
-#    norm=self.norm
-#    hist_dict={}
-#    hist_dict['F']={}
-#    hist_dict['R']={}
-#    for offset in self.readDict:
-#      for size in self.readDict[offset]:
-#        if offset < 0:
-#          hist_dict['R'][size] = hist_dict['R'].get(size, 0) - 1*norm
-#        else:
-#          hist_dict['F'][size] = hist_dict['F'].get(size, 0) + 1*norm
-#   ## patch to avoid missing graphs when parsed by R-lattice. 27-08-2014. Test and validate !    
-#    if not (hist_dict['F']) and (not hist_dict['R']):
-#      hist_dict['F'][21] = 0
-#      hist_dict['R'][21] = 0
-#   ##
-#    return hist_dict
+
 
   def size_histogram(self, minquery=None, maxquery=None): # in SmRNAwindow
     '''refactored on 7-9-2014 to debug size_histogram tool'''
@@ -480,7 +427,6 @@
       return ". | %s" % (freqDic["Trev"] / reverse_sum * 100)
     else:
       return "%s | %s" % (freqDic["Tfor"] / forward_sum * 100, freqDic["Trev"] / reverse_sum * 100)
-
     
   def readplot (self):
     norm=self.norm
Binary file smRtools.pyc has changed
--- a/test-data/Readmap_dataframe.tab	Sun Apr 24 09:23:44 2016 -0400
+++ b/test-data/Readmap_dataframe.tab	Sat Oct 08 07:18:45 2016 -0400
@@ -1267,6 +1267,12 @@
 FBti0020400	8755	1.0	F	sample1.srbowtie_out
 FBti0020400	8849	3.0	F	sample1.srbowtie_out
 FBti0020400	9398	0	F	sample1.srbowtie_out
+FBti0019480	0	0	F	sample1.srbowtie_out
+FBti0019480	417	2.0	F	sample1.srbowtie_out
+FBti0019480	503	-3.0	R	sample1.srbowtie_out
+FBti0019480	619	1.0	F	sample1.srbowtie_out
+FBti0019480	634	-1.0	R	sample1.srbowtie_out
+FBti0019480	669	0	F	sample1.srbowtie_out
 FBti0020401	0	0	F	sample2.srbowtie_out
 FBti0020401	142	-1.0	R	sample2.srbowtie_out
 FBti0020401	160	1.0	F	sample2.srbowtie_out
@@ -2520,6 +2526,13 @@
 FBti0020400	9192	1.0	F	sample2.srbowtie_out
 FBti0020400	9333	-1.0	R	sample2.srbowtie_out
 FBti0020400	9398	0	F	sample2.srbowtie_out
+FBti0019480	0	0	F	sample2.srbowtie_out
+FBti0019480	327	1.0	F	sample2.srbowtie_out
+FBti0019480	446	1.0	F	sample2.srbowtie_out
+FBti0019480	503	-3.0	R	sample2.srbowtie_out
+FBti0019480	594	1.0	F	sample2.srbowtie_out
+FBti0019480	619	1.0	F	sample2.srbowtie_out
+FBti0019480	669	0	F	sample2.srbowtie_out
 FBti0020401	0	0	F	sample3.srbowtie_out
 FBti0020401	250	1.0	F	sample3.srbowtie_out
 FBti0020401	274	-1.0	R	sample3.srbowtie_out
@@ -3670,3 +3683,13 @@
 FBti0020400	9306	-1.0	R	sample3.srbowtie_out
 FBti0020400	9334	-1.0	R	sample3.srbowtie_out
 FBti0020400	9398	0	F	sample3.srbowtie_out
+FBti0019480	0	0	F	sample3.srbowtie_out
+FBti0019480	23	1.0	F	sample3.srbowtie_out
+FBti0019480	384	1.0	F	sample3.srbowtie_out
+FBti0019480	493	5.0	F	sample3.srbowtie_out
+FBti0019480	501	-1.0	R	sample3.srbowtie_out
+FBti0019480	502	-7.0	R	sample3.srbowtie_out
+FBti0019480	503	-1.0	R	sample3.srbowtie_out
+FBti0019480	594	1.0	F	sample3.srbowtie_out
+FBti0019480	619	1.0	F	sample3.srbowtie_out
+FBti0019480	669	0	F	sample3.srbowtie_out
Binary file test-data/Readmaps.pdf has changed
Binary file test-data/Size_distribution.pdf has changed
Binary file test-data/Size_distribution_and_Readmaps.pdf has changed
--- a/test-data/Size_distribution_dataframe.tab	Sun Apr 24 09:23:44 2016 -0400
+++ b/test-data/Size_distribution_dataframe.tab	Sat Oct 08 07:18:45 2016 -0400
@@ -879,6 +879,28 @@
 FBti0020400	28	16.0	F	sample1.srbowtie_out
 FBti0020400	29	0.0	F	sample1.srbowtie_out
 FBti0020400	30	0	F	sample1.srbowtie_out
+FBti0019480	20	0	R	sample1.srbowtie_out
+FBti0019480	21	0	R	sample1.srbowtie_out
+FBti0019480	22	-1.0	R	sample1.srbowtie_out
+FBti0019480	23	0	R	sample1.srbowtie_out
+FBti0019480	24	-2.0	R	sample1.srbowtie_out
+FBti0019480	25	-1.0	R	sample1.srbowtie_out
+FBti0019480	26	0.0	R	sample1.srbowtie_out
+FBti0019480	27	0	R	sample1.srbowtie_out
+FBti0019480	28	0	R	sample1.srbowtie_out
+FBti0019480	29	0	R	sample1.srbowtie_out
+FBti0019480	30	0	R	sample1.srbowtie_out
+FBti0019480	20	0	F	sample1.srbowtie_out
+FBti0019480	21	0	F	sample1.srbowtie_out
+FBti0019480	22	0.0	F	sample1.srbowtie_out
+FBti0019480	23	0	F	sample1.srbowtie_out
+FBti0019480	24	0.0	F	sample1.srbowtie_out
+FBti0019480	25	1.0	F	sample1.srbowtie_out
+FBti0019480	26	2.0	F	sample1.srbowtie_out
+FBti0019480	27	0	F	sample1.srbowtie_out
+FBti0019480	28	0	F	sample1.srbowtie_out
+FBti0019480	29	0	F	sample1.srbowtie_out
+FBti0019480	30	0	F	sample1.srbowtie_out
 FBti0020401	20	-2.0	R	sample2.srbowtie_out
 FBti0020401	21	0	R	sample2.srbowtie_out
 FBti0020401	22	0.0	R	sample2.srbowtie_out
@@ -1759,6 +1781,28 @@
 FBti0020400	28	15.0	F	sample2.srbowtie_out
 FBti0020400	29	1.0	F	sample2.srbowtie_out
 FBti0020400	30	0	F	sample2.srbowtie_out
+FBti0019480	20	0.0	R	sample2.srbowtie_out
+FBti0019480	21	0	R	sample2.srbowtie_out
+FBti0019480	22	0	R	sample2.srbowtie_out
+FBti0019480	23	0	R	sample2.srbowtie_out
+FBti0019480	24	-2.0	R	sample2.srbowtie_out
+FBti0019480	25	-1.0	R	sample2.srbowtie_out
+FBti0019480	26	0.0	R	sample2.srbowtie_out
+FBti0019480	27	0.0	R	sample2.srbowtie_out
+FBti0019480	28	0	R	sample2.srbowtie_out
+FBti0019480	29	0	R	sample2.srbowtie_out
+FBti0019480	30	0	R	sample2.srbowtie_out
+FBti0019480	20	1.0	F	sample2.srbowtie_out
+FBti0019480	21	0	F	sample2.srbowtie_out
+FBti0019480	22	0	F	sample2.srbowtie_out
+FBti0019480	23	0	F	sample2.srbowtie_out
+FBti0019480	24	1.0	F	sample2.srbowtie_out
+FBti0019480	25	0.0	F	sample2.srbowtie_out
+FBti0019480	26	1.0	F	sample2.srbowtie_out
+FBti0019480	27	1.0	F	sample2.srbowtie_out
+FBti0019480	28	0	F	sample2.srbowtie_out
+FBti0019480	29	0	F	sample2.srbowtie_out
+FBti0019480	30	0	F	sample2.srbowtie_out
 FBti0020401	20	-1.0	R	sample3.srbowtie_out
 FBti0020401	21	0.0	R	sample3.srbowtie_out
 FBti0020401	22	-1.0	R	sample3.srbowtie_out
@@ -2639,3 +2683,25 @@
 FBti0020400	28	12.0	F	sample3.srbowtie_out
 FBti0020400	29	0	F	sample3.srbowtie_out
 FBti0020400	30	0	F	sample3.srbowtie_out
+FBti0019480	20	0	R	sample3.srbowtie_out
+FBti0019480	21	-1.0	R	sample3.srbowtie_out
+FBti0019480	22	0.0	R	sample3.srbowtie_out
+FBti0019480	23	-2.0	R	sample3.srbowtie_out
+FBti0019480	24	-5.0	R	sample3.srbowtie_out
+FBti0019480	25	-1.0	R	sample3.srbowtie_out
+FBti0019480	26	0.0	R	sample3.srbowtie_out
+FBti0019480	27	0.0	R	sample3.srbowtie_out
+FBti0019480	28	0	R	sample3.srbowtie_out
+FBti0019480	29	0	R	sample3.srbowtie_out
+FBti0019480	30	0	R	sample3.srbowtie_out
+FBti0019480	20	0	F	sample3.srbowtie_out
+FBti0019480	21	0.0	F	sample3.srbowtie_out
+FBti0019480	22	1.0	F	sample3.srbowtie_out
+FBti0019480	23	0.0	F	sample3.srbowtie_out
+FBti0019480	24	3.0	F	sample3.srbowtie_out
+FBti0019480	25	2.0	F	sample3.srbowtie_out
+FBti0019480	26	2.0	F	sample3.srbowtie_out
+FBti0019480	27	1.0	F	sample3.srbowtie_out
+FBti0019480	28	0	F	sample3.srbowtie_out
+FBti0019480	29	0	F	sample3.srbowtie_out
+FBti0019480	30	0	F	sample3.srbowtie_out