Mercurial > repos > artbio > small_rna_signatures

changeset 6:4da23f009c9e draft

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/small_rna_signatures commit 6c727f4b2288c9b2517b28addf1eed6409d682a4
author artbio
date Sun, 10 Sep 2017 10:27:19 -0400
parents a7fd04208764
children 07771982ef9b
files overlapping_reads.py overlapping_reads.xml
diffstat 2 files changed, 34 insertions(+), 1 deletions(-) [+]
line wrap: on
line diff
--- a/overlapping_reads.py	Sat Sep 09 11:57:39 2017 -0400
+++ b/overlapping_reads.py	Sun Sep 10 10:27:19 2017 -0400
@@ -85,6 +85,32 @@
                 list(set(all_query_positions[chrom])))
         return all_query_positions
 
+    def countpairs(self, uppers, lowers):
+        query_range = self.query_range
+        target_range = self.target_range
+        uppers = [seq for seq in uppers if (len(seq) in query_range or len(seq) in target_range)]
+        uppers_expanded = []
+        for seq in uppers:
+            expand = [seq for i in range(self.readdic[seq])]
+            uppers_expanded.extend(expand)
+        uppers = uppers_expanded
+        lowers = [seq for seq in lowers if (len(seq) in query_range or len(seq) in target_range)]
+        lowers_expanded = []
+        for seq in lowers:
+            expand = [seq for i in range(self.readdic[seq])]
+            lowers_expanded.extend(expand)
+        lowers = lowers_expanded
+        paired = []
+        for upread in uppers:
+            for downread in lowers:
+                if (len(upread) in query_range and len(downread) in
+                    target_range) or (len(upread) in target_range and
+                                      len(downread) in query_range):
+                    paired.append(upread)
+                    lowers.remove(downread)
+                    break
+        return len(paired)
+
     def pairing(self):
         F = open(self.output, 'w')
         query_range = self.query_range
@@ -92,11 +118,16 @@
         overlap = self.overlap
         stringresult = []
         header_template = '>%s|coord=%s|strand %s|size=%s|nreads=%s\n%s\n'
+        total_pairs = 0
+        print ('Chromosome\tNbre of pairs')
         for chrom in sorted(self.chromosomes):
+            number_pairs = 0
             for pos in self.all_query_positions[chrom]:
                 stringbuffer = []
                 uppers = self.alignement_dic[chrom, pos, 'F']
                 lowers = self.alignement_dic[chrom, pos+overlap-1, 'R']
+                number_pairs += self.countpairs(uppers, lowers)
+                total_pairs += number_pairs
                 if uppers and lowers:
                     for upread in uppers:
                         for downread in lowers:
@@ -114,6 +145,8 @@
                                      len(downread), self.readdic[downread],
                                      self.revcomp(downread)))
                 stringresult.extend(sorted(set(stringbuffer)))
+            print('%s\t%s' % (chrom, number_pairs))
+        print('Total nbre of pairs that can be simultaneously formed\t%s' % total_pairs)
         F.write(''.join(stringresult))
 
     def revcomp(self, sequence):
--- a/overlapping_reads.xml	Sat Sep 09 11:57:39 2017 -0400
+++ b/overlapping_reads.xml	Sun Sep 10 10:27:19 2017 -0400
@@ -1,4 +1,4 @@
-<tool id="overlapping_reads" name="Get overlapping reads" version="0.9.4">
+<tool id="overlapping_reads" name="Get overlapping reads" version="0.9.5">
     <description />
     <requirements>
         <requirement type="package" version="0.11.2.1=py27_0">pysam</requirement>