added PSC1 and PPC2. adjusted PMC1 category. adjusted PS1 and BSC1 sc…

…ores. fixed VEP defaults. fixed frequency options.

bin/charger

@@ -1,15 +1,16 @@
 #!/bin/python
 # CharGer - Characterization of Germline variants
 # author: Adam D Scott ([email protected]) & Kuan-lin Huang ([email protected])
-# version: v0.2.1 - 2017*05
+# version: v0.3.0 - 2017*09
 
 import sys
 import getopt
 from charger import charger
 import time
+import argparse
 
 def parseArgs( argv ):
-	helpText = "\nCharGer - v0.2.1\n\n"
+	helpText = "\nCharGer - v0.3.0\n\n"
 	helpText += "Usage: "
 	helpText += "charger <input file> [options]\n\n"
 	helpText += "Accepted input data files:\n"
@@ -38,7 +39,10 @@ def parseArgs( argv ):
 	helpText += "  -a assumed de novo file, standard .maf\n"
 	helpText += "  -c co-segregation file, standard .maf\n"
 	helpText += "  -H HotSpot3D clusters file, .clusters\n"
-	helpText += "  -r recurrence threshold (default = 2)\n"
+	helpText += "Thresholds:\n"
+	helpText += "  --recurrence-threshold HotSpot3D recurrence threshold (default = 2)\n"
+	helpText += "  --rare-threshold Allele frequency threshold for rare (default = 0.0005 (0.05%)):\n"
+	helpText += "  --common-threshold Allele frequency threshold for common (default = 0.005 (0.5%)):\n"
 	helpText += "Local VEP (works with .vcf input only; suppresses ReST too):\n"
 	helpText += "  --vep-script Path to VEP\n"
 	helpText += "  --vep-config config-file for VEP\n"
@@ -57,9 +61,9 @@ def parseArgs( argv ):
 	helpText += "  --mac-clinvar-tsv ClinVar from MacArthur lab (clinvar_alleles.tsv.gz)\n"
 	#helpText += "  --mac-clinvar-vcf ClinVar from MacArthur lab (clinvar_alleles.vcf.gz)\n"
 	helpText += "Filters:\n"
-	helpText += "  --rare Allele frequency threshold for rare/common (default = 1, process variant with any frequency):\n"
-	helpText += "  --vcf-any-filter Allow variants that do not pass all filters in .vcf input (flag)\n"
-	helpText += "  --mutation-types Comma delimited list (no spaces) of types to allow\n"
+	helpText += "  --frequency-filter Keep if allele frequency lower (default = 1, process variant with any frequency):\n"
+	helpText += "  --vcf-any-filter Keep variants that do not pass all filters in .vcf input (flag)\n"
+	helpText += "  --mutation-types Keep types, as a comma delimited list (no spaces)\n"
 	helpText += "ReST batch sizes:\n"
 	helpText += "  -v VEP (#variants, default/max allowed = 150)\n"
 	helpText += "  -b ClinVar summary (#variants, default/max allowed = 500)\n"
@@ -76,7 +80,6 @@ def parseArgs( argv ):
 	helpText += "  -C codon\n"
 	helpText += "  -p peptide change\n"
 	helpText += "  -L variant classification\n"
-	helpText += "  -F allele frequency\n"
 	helpText += "\n"
 	helpText += "  -h this message\n"
 	helpText += "\n"
@@ -117,35 +120,38 @@ def parseArgs( argv ):
 	clustersFile = None
 	pathogenicVariantsFile = None
 	annotateInput = ""
-	vepScript = ""
-	vepConfig = ""
-	#vepDir = None
+	vepScript = None
+	vepConfig = None
 	vepCache = None
 	vepOutput = None
-	ensemblRelease = ""
-	vepVersion = ""
-	grch = ""
-	fork = ""
+	ensemblRelease = str( 75 )
+	vepVersion = str( 87 )
+	grch = str( 37 )
+	fork = str( 1 )
 	referenceFasta = None
 	exacVCF = None
 	macClinVarVCF = None
 	macClinVarTSV = None
 	doURLTest = True
-	thresholdAF = 1
+	rareAF = 0.0005 #from germline studies
+	commonAF = 0.05 #from ACMG suggestion
+	keepAF = 1
 	anyFilter = False
 	mutationTypes = []
 
 	try:
 		#haven't used ijquy
-		charCommands = "DEtlxhwOkX:s:A:R:S:P:M:G:m:f:T:o:v:b:B:p:C:F:g:d:e:n:a:c:r:H:z:L:" 
+		charCommands = "DEtlxhwOkX:s:A:R:S:P:M:G:m:f:T:o:v:b:B:p:C:g:d:e:n:a:c:H:z:L:" 
 		opts, args = getopt.getopt( argv , charCommands , \
 		["maf=" , "vcf=" , "tsv=" , "output=" , "use-tcga" , \
 		"run-vep" , "run-clinvar" , "run-exac" , \
 		"vepBatchSize=" , "summaryBatchSize=" , "searchBatchSize=" , \
 		"peptideChange=" , "codon=" , "alleleFrequency=" , \
 		"geneList=" , "diseases=" , "expression=" , \
 		"deNovo=" , "assumedDeNovo=" , "coSegregation=" , \
-		"recurrence=" , "rare=" , "vcf-any-filter" , "mutation-types=" , \
+		"rare-threshold=" , "common-threshold=" , \
+		"recurrence-threshold=" , "frequency-filter=" , \
+		"vcf-any-filter" , "mutation-types=" , \
 		"hotspot3d=" , "pathogenicVariants=" , \
 		"vep-script=" , "vep-config=", "vep-dir=" , "vep-cache=" , "vep-output=" , \
 		"ensembl-release=" , "vep-version=" , \
@@ -233,10 +239,14 @@ def parseArgs( argv ):
 			asHTML = True
 		elif opt in ( "-O" , "--override" ):
 			override = True
-		elif opt in ( "-r" , "--recurrence" ):
+		elif opt in ( "-r" , "--recurrence-threshold" ):
 			recurrenceThreshold = float( arg )
-		elif opt in ( "--rare" ):
-			thresholdAF = float( arg )
+		elif opt in ( "--rare-threshold" ):
+			rareAF = float( arg )
+		elif opt in ( "--common-threshold" ):
+			commonAF = float( arg )
+		elif opt in ( "--frequency-filter" ):
+			keepAF = float( arg )
 		elif opt in ( "--mutation-types" ):
 			mutationTypes = arg.split( "," )
 		elif opt in ( "--vcf-any-filter" ):
@@ -315,7 +325,9 @@ def parseArgs( argv ):
 	"variantClassificationColumn" : variantClassificationColumn, \
 	"alleleFrequencyColumn" : alleleFrequencyColumn, \
 	"recurrenceThreshold" : recurrenceThreshold , \
-	"thresholdAF" : thresholdAF , \
+	"rareAF" : rareAF , \
+	"commonAF" : commonAF , \
+	"keepAF" : keepAF , \
 	"anyFilter" : anyFilter , \
 	"mutationTypes" : mutationTypes , \
 	"clustersFile" : clustersFile , \
@@ -378,7 +390,9 @@ def main( argv ):
 	asHTML = values["html"]
 	override = values["override"]
 	recurrenceThreshold = values["recurrenceThreshold"]
-	thresholdAF = values["thresholdAF"]
+	rareAF = values["rareAF"]
+	commonAF = values["commonAF"]
+	keepAF = values["keepAF"]
 	anyFilter = values["anyFilter"]
 	mutationTypes = values["mutationTypes"]
 	clustersFile = values["clustersFile"]
@@ -452,7 +466,9 @@ def main( argv ):
 	peptideChange=peptideChangeColumn , \
 	variantClassification=variantClassificationColumn , \
 	alleleFrequency=alleleFrequencyColumn , \
-	thresholdAF = thresholdAF , \
+	rareAF = rareAF , \
+	commonAF = commonAF , \
+	keepAF = keepAF , \
 	anyFilter = anyFilter , \
 	mutationTypes = mutationTypes , \
 	)
@@ -495,16 +511,16 @@ def main( argv ):
 	exacVCF=exacVCF , \
 	macClinVarTSV=macClinVarTSV , \
 	macClinVarVCF=macClinVarVCF , \
-	thresholdAF = thresholdAF , \
+	rareAF = rareAF , \
+	commonAF = commonAF , \
+	keepAF = keepAF , \
 	anyFilter = anyFilter , \
 	mutationTypes = mutationTypes , \
 	#timeout=(20,20) , \
 	)
 
 	t3 = time.time() 
 
-	rareThreshold = 0.0005 #from germline studies
-	commonThreshold = 0.05 #from ACMG suggestion
 	minimumEvidence = 2
 
 	CharGer.PVS1( )
@@ -513,7 +529,7 @@ def main( argv ):
 	CharGer.PS3( )
 	CharGer.PS4( )
 	CharGer.PM1( recurrenceThreshold , hotspot3d=clustersFile )
-	CharGer.PM2( rareThreshold )
+	CharGer.PM2( rareAF )
 	CharGer.PM3( )
 	CharGer.PM4( )
 	CharGer.PM5( )
@@ -524,7 +540,7 @@ def main( argv ):
 	CharGer.PP4( )
 	CharGer.PP5( )
 
-	CharGer.BA1( commonThreshold )
+	CharGer.BA1( commonAF )
 	CharGer.BS1( )
 	CharGer.BS2( )
 	CharGer.BS3( )
@@ -537,10 +553,15 @@ def main( argv ):
 	CharGer.BP6( )
 	CharGer.BP7( )
 
+	CharGer.PSC1( )
+	CharGer.PMC1( )
+	CharGer.PPC1( )
+	CharGer.PPC2( )
+
 	CharGer.BSC1( )
 	CharGer.BMC1( )
 
-	print( str( rareThreshold ) + " < " + str( commonThreshold ) )
+	print( str( rareAF ) + " < " + str( commonAF ) )
 	t4 = time.time() 
 
 	CharGer.classify( system="ACMG" )