erange version 4.0a dev release

[erange.git] / getSNPs.py

diff --git a/getSNPs.py b/getSNPs.py
index 0adde42c0b09a921f45c9edf01070077e68bf805..f6071ae444be9ca294ac4c4ff39b50a74e3d0cb4 100755 (executable)
--- a/getSNPs.py
+++ b/getSNPs.py
@@ -19,10 +19,12 @@
     totalRatioMin = total # of reads supporting a base change at position S / total # reads that pass through position S
 """
 
-import sys, optparse
-from commoncode import readDataset, writeLog
+import sys
+import optparse
+from commoncode import writeLog, getConfigParser, getConfigBoolOption, getConfigIntOption
+import ReadDataset
 
-print "%prog: version 3.5"
+print "getSNPs: version 3.6"
 
 try:
     import psyco
@@ -41,11 +43,7 @@ def main(argv=None):
 
     usage = __doc__
 
-    parser = optparse.OptionParser(usage=usage)
-    parser.add_option("--nosplices", action="store_false", dest="doSplices")
-    parser.add_option("--enforceChr", action="store_true", dest="forceChr")
-    parser.add_option("--cache", type="int", dest="cachePages")
-    parser.set_defaults(doSplices=True, forceChr=False, cachePages=0)
+    parser = makeParser(usage)
     (options, args) = parser.parse_args(argv[1:])
 
     if len(args) < 4:
@@ -65,6 +63,23 @@ def main(argv=None):
     writeSNPsToFile(hitfile, uniqStartMin, totalRatioMin, outfilename, doCache, options.cachePages, options.doSplices, options.forceChr)
 
 
+def makeParser(usage=""):
+    parser = optparse.OptionParser(usage=usage)
+    parser.add_option("--nosplices", action="store_false", dest="doSplices")
+    parser.add_option("--enforceChr", action="store_true", dest="forceChr")
+    parser.add_option("--cache", type="int", dest="cachePages")
+
+    configParser = getConfigParser()
+    section = "getSNPs"
+    doSplices = getConfigBoolOption(configParser, section, "doSplices", True)
+    forceChr = getConfigBoolOption(configParser, section, "forceChr", False)
+    cachePages = getConfigIntOption(configParser, section, "cachePages", 0)
+
+    parser.set_defaults(doSplices=True, forceChr=False, cachePages=0)
+
+    return parser
+
+
 def writeSNPsToFile(hitfile, uniqStartMin, totalRatioMin, outfilename, doCache, cachePages=0, doSplices=True, forceChr=False):
     writeLog("snp.log", sys.argv[0], "rdsfile: %s uniqStartMin: %1.2f totalRatioMin: %1.2f" % (hitfile, uniqStartMin, totalRatioMin))
 
@@ -86,7 +101,7 @@ def writeSNPsToFile(hitfile, uniqStartMin, totalRatioMin, outfilename, doCache,
 
 def getSNPs(hitfile, uniqStartMin, totalRatioMin, doCache, cachePages=0, doSplices=True, forceChr=False):
 
-    hitRDS = readDataset(hitfile, verbose=True, cache=doCache)
+    hitRDS = ReadDataset.ReadDataset(hitfile, verbose=True, cache=doCache)
     if cachePages > 20000:
         hitRDS.setDBcache(cachePages)
 
@@ -157,7 +172,9 @@ def getMatchDict(rds, chrom, withSplices=True):
     except:
         readDict[chrom] = []
 
-    for (start, stop) in readDict[chrom]:
+    for read in readDict[chrom]:
+        start = read["start"]
+        stop = read["stop"]
         if finalDict.has_key(start):
             finalDict[start].append(stop)
         else:
@@ -169,7 +186,14 @@ def getMatchDict(rds, chrom, withSplices=True):
         except:
             spliceDict[chrom] = []
 
-        for (start, stop) in spliceDict[chrom]:
+        for read in spliceDict[chrom]:
+            try:
+                start = read["startL"]
+                stop = read["stopL"]
+            except KeyError:
+                start = read["startR"]
+                stop = read["stopR"]
+
             if finalDict.has_key(start):
                 finalDict[start].append(stop)
             else: