src/hg/tcga/scripts/processData.py 1.8

Index: src/hg/tcga/scripts/processData.py
===================================================================
RCS file: /projects/compbio/cvsroot/kent/src/hg/tcga/scripts/processData.py,v
retrieving revision 1.7
retrieving revision 1.8
diff -b -B -U 4 -r1.7 -r1.8
--- src/hg/tcga/scripts/processData.py	25 Apr 2009 02:17:38 -0000	1.7
+++ src/hg/tcga/scripts/processData.py	27 Apr 2009 23:49:23 -0000	1.8
@@ -12,14 +12,17 @@
     print "\t\tmethyl3Beta -- JHU-USC Methylation - OMA003: Avg Beta Values"
     print "\t\tharvard -- Harvard CGH 244A GBM"
     print "\t\tharvardOV -- Harvard CGH 244A Ovarian"
     print "\t\tmskcc -- MSKCC 244A" 
+    print "\t\tmskccOV -- MSKCC Ovarian 244A"
+    print "\t\tmskccOV1x1M - MSKCC Ovarian 1x1M" 
     print "\t\thuEx -- human exon array"
     print "\t\tbroadABI -- Broad ABI SNP data -- GBM"
     print "\t\tbroadABI -- Broad ABI SNP data -- Ovarian"
     print "\t\tbaylorABI -- Baylor ABI SNP data"
     print "\t\twustlABI -- WUSTL ABI SNP Data"
     print "\t\tsnp6 -- Broad SNP 6.0"
+    print "\t\tbroadAffyOV -- Affy U133A Ovarian"
     print ""
     
 def handleOpts(argv):
     opts, args = getopt.getopt(argv, "ht:", ["help", "type="])
@@ -83,23 +86,53 @@
         Data = CGH244A(baseDir, patterns, bed12file, bed15file, prefix)
 
     elif type == "harvardOV":
         baseDir = "/data/TCGA/O_harvardOVCGH/working/"
-        patterns = ["*data.txt"]
+        patterns = ["*normalized", "*.data.txt"]
         bed12file = baseDir + "agilentCGH244A.bed"
         bed15file = baseDir + "harvardOVCGH244A_bed15.bed"
         prefix = "harvardOVCGH"
         
         Data = CGH244A(baseDir, patterns, bed12file, bed15file, prefix)
 
+    elif type == "broadAffyOV":
+        baseDir = "/data/TCGA/O_broadAffyOV/working/"
+        patterns = ["*_rma"]
+        bed12file = baseDir + "affyU133A.bed"
+        bed15file = baseDir + "broadAffyOV_bed15.bed"
+        prefix = "broadAffyOV"
+        
+        Data = AffyU133A(baseDir, patterns, bed12file, bed15file, prefix)
+        
     elif type == "mskcc":
         baseDir = "/data/TCGA/O_mskccCGH/working/"
         patterns = ["*data.txt"]
         bed12file = baseDir + "agilentCGH244A.bed"
         bed15file = baseDir + "mskccCGH244A_bed15.bed"
         prefix = "mskccCGH"
         
         Data = CGH244A(baseDir, patterns, bed12file, bed15file, prefix)
+        Data.dataStartIndex = 3
+        
+    elif type == "mskccOV":
+        baseDir = "/data/TCGA/O_mskccOVCGH/working/"
+        patterns = ["*transformation"]
+        bed12file = baseDir + "agilentCGH244A.bed"
+        bed15file = baseDir + "mskccOVCGH244A_bed15.bed"
+        prefix = "mskccOVCGH"
+                
+        Data = CGH244A(baseDir, patterns, bed12file, bed15file, prefix)
+        Data.dataStartIndex = 2
+
+    elif type == "mskccOV1x1M":
+        baseDir = "/data/TCGA/O_mskccOV1x1M/working/"
+        patterns = ["*transformation"]
+        bed12file = baseDir + "agilent1x1M.bed"
+        bed15file = baseDir + "mskccOV1x1M_bed15.bed"
+        prefix = "mskccOV1x1M"
+                
+        Data = CGH1x1M(baseDir, patterns, bed12file, bed15file, prefix)
+        
     elif type == "huEx":
         baseDir = "/data/TCGA/C_lblHuEx/working/"
         patterns = ["*data.txt"]
         bed12file = baseDir + "affyHuEx1_bed12.bed"
@@ -163,12 +197,12 @@
         Data.sampleIdField = "Tumor_Sample_Barcode"
 
         Data.collapseStatus = {}
         Data.collapseStatus["Somatic"] = ["Somatic"]
-        Data.collapseStatus["Germline"] = ["Germline", "LOH", "Unknown"]
+        Data.collapseStatus["Germline"] = ["Germline"] #, "LOH", "Unknown"]
         
         Data.collapseClass = {}
-        Data.collapseClass["Quiet"] = ["Silent", "Targeted_Region"]
+        Data.collapseClass["Quiet"] = ["Silent"]
         Data.collapseClass["Loud"] = ["Frame_Shift_Del", "Frame_Shift_Ins",
                                       "In_Frame_Del", "In_Frame_Ins",
                                       "Missense_Mutation", "Nonsense_Mutation",
                                       "Splice_Site_Indel", "Splice_Site_SNP"]  
@@ -286,8 +320,11 @@
 
         print "Writing entry for microarrayGroups.ra file..."
         dataObject.writeRaFile()
         
+        print "Add txLength data to score field, only works on SNP data..."
+        dataObject.addTxLength()
+        
 if __name__ == "__main__":
     main(sys.argv[1:])