v0.2.3

CHANGELOG

@@ -1,3 +1,13 @@
+2019-8-12 ribotish 0.2.3
+
+	Fix problem reading NCBI gff files.
+
+	Python3 compatibility.
+
+	Add support for transcript annotation starting at CDS start (no 5'UTR) in quality module.
+
+	Fix chrmap problem in genome fa file.
+
 2019-4-2 ribotish 0.2.2
 
 	Python3 compatibility. Ribo-TISH can run in python 3.7.2 now.

README.rst

@@ -1,6 +1,6 @@
-README for Ribo-TISH (0.2.2)
+README for Ribo-TISH (0.2.3)
 ==================================
-<2019-4-2 Peng Zhang>
+<2019-8-12 Peng Zhang>
 
 Introduction
 ============

bin/ribotish

@@ -6,7 +6,7 @@ This code is free software; you can redistribute it and/or modify it
 under the terms of the BSD License (see the file COPYING included with
 the distribution).
 @status: Alpha
-@version: 0.2.2
+@version: 0.2.3
 @author:  Peng Zhang
 @contact: [email protected]
 """

setup.py

@@ -1,5 +1,5 @@
 #!/usr/bin/python
-#Last-modified: 15 Jan 2018
+#Last-modified: 12 Aug 2019
 
 #         Module/Scripts Description
 # 
@@ -10,7 +10,7 @@
 # the distribution).
 # 
 # @status:  Alpha
-# @version: 0.2.2
+# @version: 0.2.3
 # @author:  Peng Zhang
 # @contact: [email protected]
 

src/__init__.py

@@ -1,2 +1,2 @@
 __all__=["run"]
-__version__ = '0.2.2'
+__version__ = '0.2.3'

src/zbio/bam.py

@@ -424,6 +424,26 @@ def is_m0(self):
       if self.read2.get_tag('MD')[-1] == '0' : 
         if not self.read2.get_tag('MD')[-2].isdigit() : return True
     return False
+  def mismatches(self):
+    import re
+    mm = {}
+    md = self.read.get_tag('MD')
+    ns = re.split('[ATGC^]+', md)
+    ms = re.split('\d+', md)
+    l = self.cdna_length()
+    p = 0
+    for i, n in enumerate(ns):
+      n = int(n)
+      if ms[i] != '':
+        q = p
+        p += len(ms[i])
+        if ms[i].startswith('^'): p -= 1
+        if self.is_reverse(): q = l - p
+        mm[q] = ms[i]
+      p += n
+    return mm
+
+
 def compatible_bam_iter(bamfile, trans, mis = 0, sense = True, maxNH = None, minMapQ = None, secondary = False, flank = 0): 
   '''compatible version of transReadsIter, slightly different
   '''

src/zbio/plot.py

@@ -104,7 +104,7 @@ def riboShow(ax, trans, cnts, start = 0, stop = -1, ymax = None, scale = 1, col
   for i in range(3):
     ax.bar(fx[i], fy[i], color=col[i], bottom = ymax * bottom,width=fw[i], alpha=0.2, linewidth = 0, align='edge')
 
-def orfShow(ax, orfs, start = 0, stop = -1, col = ['r','g','b'], cds = [None, None], title = 'Potential ORFs in 3 reading frames', alt = True, morecds = None, morecdsbox = False, morecdslabel = None):
+def orfShow(ax, orfs, start = 0, stop = -1, col = ['r','g','b'], cds = [None, None], title = 'Potential ORFs in 3 reading frames', alt = True, morecds = None, morecdsbox = False, morecdslabel = None, markpept = None):
   '''plot possible ORFs
   '''
   if stop < start : stop = trans.cdna_length()
@@ -150,7 +150,14 @@ def orfShow(ax, orfs, start = 0, stop = -1, col = ['r','g','b'], cds = [None, No
         ax.bar(newcds[0], [0.4] ,color='None', bottom=2-i+0.3, width=newcds[1]-newcds[0], alpha=0.8, fill=False, edgecolor=col[i], linewidth=2, align='edge')
       if morecdslabel is not None:
         ax.text(max(newcds[0],0), 2-i+0.8, morecdslabel[j], color=col[i])
-
+  if markpept is not None:
+    for j, mc in enumerate(markpept):
+      if mc[0]>stop or mc[1]< start: continue
+      i = mc[0] % 3
+      newcds = [c - start for c in mc]
+      if newcds[0] < 0: newcds[0] = 0
+      if mc[1] > stop: newcds[1] = rlen
+      ax.bar(newcds[0], [0.2], color='k', bottom=2-i+0.4, width=newcds[1]-newcds[0], alpha=0.8, linewidth=0, align='edge')
   # start & stop codons
   lx = [[],[],[]]
   ly = [[],[],[]]