X-Git-Url: http://woldlab.caltech.edu/gitweb/?p=erange.git;a=blobdiff_plain;f=MakeBamFromRds.py;h=0b4946b1c3e9d4338da5e4a57b77791316ebad9b;hp=bfb48fde3fc0bebc9bdceaa1dc16f83dd566da59;hb=HEAD;hpb=0d3e3112fd04c2e6b44a25cacef1d591658ad181

diff --git a/MakeBamFromRds.py b/MakeBamFromRds.py
index bfb48fd..0b4946b 100644
--- a/MakeBamFromRds.py
+++ b/MakeBamFromRds.py
@@ -22,13 +22,13 @@ import pysam
 import ReadDataset
 from commoncode import getConfigParser, getConfigOption, getConfigBoolOption, getConfigIntOption
 
+VERSION = "1.0"
 
 def main(argv=None):
     if not argv:
         argv = sys.argv
 
-    verstring = "makeBamFromRds: version 1.0"
-    print verstring
+    print "makeBamFromRds: version %s" % VERSION
 
     doPairs = False
     
@@ -134,7 +134,7 @@ def makeBamFromRds(rdsfile, outfilename, withUniqs=True, withMulti=True,
     for chrom in chromRemoveList:
         chromList.remove(chrom)
 
-    header = {"HD": {"VN": "1.0"}}
+    header = {"HD": {"VN": VERSION}}
     if referenceSequenceList:
         header["SQ"] = referenceSequenceList
 
@@ -176,7 +176,7 @@ def processSpliceReads(RDS, outfile, chrom, withFlag, useFlagLike, readlength, d
         pass
     else:
         for read in spliceDict[chrom]:
-            if fastaSequenceDict.has_key(chrom):
+            if chrom in fastaSequenceDict:
                 read["sense"], noncanonical = fixSpliceSense(fastaSequenceDict[chrom], read["startR"], read["stopL"], read["sense"])
                 noncanonicalSplices += noncanonical
 
@@ -205,7 +205,7 @@ def writeBAMEntry(outfile, chrom, outputDict, readlength):
 
     alignedRead.rname = outfile.references.index(chrom)
 
-    if outputDict.has_key("startL"):
+    if "startL" in outputDict:
         startL = outputDict["startL"] - 1
         stopL = outputDict["stopL"] - 1
         startR = outputDict["startR"] - 1
@@ -217,6 +217,13 @@ def writeBAMEntry(outfile, chrom, outputDict, readlength):
         alignedRead.pos = outputDict["start"] - 1
         alignedRead.cigar = [(0, readlength)]
 
+    #TODO: add sequence info
+    #cistematic.core.retrieveSequence(genome, chrom, start, stop, sense="F", db="")
+    #ooooo. let's do this with PyGr
+
+    #TODO: add quality - max for each base, but default is to not include just like current
+    # rdsToFastq() sets everything to max
+
     if paired:
         if pairID == "1":
             alignedRead.is_read1 = True
@@ -227,7 +234,7 @@ def writeBAMEntry(outfile, chrom, outputDict, readlength):
         else:
             pass
 
-    if outputDict.has_key("mismatch"):
+    if "mismatch" in outputDict:
         mismatchTag = getMismatches(outputDict["mismatch"])
         if mismatchTag:
             tagList.append(("MD", str(mismatchTag)))
@@ -300,7 +307,7 @@ def fixSpliceSense(fastaSequence, startRight, stopLeft, sense=""):
     spliceJunction = string.join([leftJunctionSig, rightJunctionSig], "")
     spliceJunction = spliceJunction.upper()
     print spliceJunction
-    if spliceSense.has_key(spliceJunction):
+    if spliceJunction in spliceSense:
         sense = spliceSense[spliceJunction]
     else:
         noncanonical += 1