changeset 0:951ae80a19fc draft

Uploaded

Binary file scripts/.DS_Store has changed

Binary file scripts/._.DS_Store has changed

Binary file scripts/tools/cg_scripts/.DS_Store has changed

Binary file scripts/tools/cg_scripts/._Calculate_TestVariants_Variant_Frequencies.xml has changed

Binary file scripts/tools/cg_scripts/._Calculate_TestVariants_Variant_Frequencies_0_1_0.pl has changed

Binary file scripts/tools/cg_scripts/._List_Unique_Variants.xml has changed

Binary file scripts/tools/cg_scripts/._List_Unique_Variants_2_1_0.pl has changed

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/scripts/tools/cg_scripts/Calculate_TestVariants_Variant_Frequencies.xml	Tue Jun 12 14:42:04 2012 -0400
@@ -0,0 +1,67 @@
+<tool id="pl_calculatefreq" name="Calculate_Variant_Frequencies" version="0.0.1">
+
+  <description>in cgatools-testvariants file</description> <!--adds description in toolbar-->
+  
+  <command interpreter="perl">
+  Calculate_TestVariants_Variant_Frequencies_0_1_0.pl
+  --Input $input
+  --First_Genome_Field_Nr $first_col
+  --Last_Genome_Field_Nr $last_col
+  --Output1 $output1
+	--Output2 $output2
+  </command>
+
+  <outputs>
+  	<data format="tabular" name="output1" label="TestVariant_Frequencies on "/>
+  	<data format="tabular" name="output2" label="TestVariant_Frequencies_Short on "/>
+  </outputs>
+
+  <inputs>
+    <param name="input" type="data" format="tabular" label="TestVariants input file">
+      <validator type="unspecified_build" />
+    </param>
+    <param name="first_col" type="text" label="What column number is the first genome"/>
+    <param name="last_col" type="text" label="What column number is the last genome"/>
+  </inputs>
+
+
+  <help>
+
+**What it does**
+
+This tool calculates the allele frequencies for all variants present in the testvariant file.
+
+-----
+
+**Instructions**::
+	
+	Calculate the frequencies of variants in a testvariants output file
+	Two values calculated:
+		Frequency vs all alleles
+		Frequency vs called alleles
+
+	Input: testvariants file
+	Outputs:
+		All data to *-Freq.tsv, including scores and quals
+		vars and freqs to *-Freq_Short.tsv
+		Exceptions to *-Freq_Log
+		Stats to *-Freq_Stats
+
+
+	perl Calculate_TestVariants_Variant_Frequencies_0_0_3.pl \
+	--Input input_file \
+	--First_Genome_Field_Nr col_nr1 \
+	--Last_Genome_Field_Nr col_nr2
+	--Output1 output1 \
+	--Output2 output_short \
+	eg
+	perl Calculate_TestVariants_Variant_Frequencies_0_0_3.pl \
+	--Input /data/Family_Quartet_testvariants.tsv \
+	--Output /data/Family_Quartet_testvariants
+	--First_Genome_Field_Nr 9 \
+	--Last_Genome_Field_Nr 11
+	--Output1 /data/Family_Quartet_testvariants
+	--Output2 /data/Family_Quartet_testvariants_short
+	
+  </help>
+</tool>

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/scripts/tools/cg_scripts/Calculate_TestVariants_Variant_Frequencies_0_1_0.pl	Tue Jun 12 14:42:04 2012 -0400
@@ -0,0 +1,271 @@
+#!/usr/bin/perl
+use strict;
+#use feature "say";
+#use File::Basename;
+$| = 1;
+
+# Get_TestVariants_Variant_Frequencies
+# Calculate the frequencies of variants in a testvariants output file
+# Two values calculated:
+#	Frequency vs all alleles
+# 	Frequency vs called alleles
+
+# Input is a testvariants file
+# Outputs:
+# All data to *-Freq.tsv, including scores and quals
+# vars and freqs to *-Freq_Short.tsv
+# Exceptions to *-Freq_Log
+# Stats to *-Freq_Stats
+
+# Format:
+# perl prog file dir
+# ie
+# perl Get_TestVariants_Variant_Frequencies \
+# --Input input_file \
+# --First_Genome_Field_Nr col_nr1 \
+# --Last_Genome_Field_Nr col_nr2
+# --Output1 output1 \
+# --Output2 output2 
+
+# eg
+# perl /perl/Get_TestVariants_Variant_Frequencies_0_0_1.pl \
+# --Input /data/Family_Quartet_testvariants.tsv \
+# --First_Genome_Field_Nr 9 \
+# --Last_Genome_Field_Nr 11
+# --Output1 output1 \
+# --Output2 output2 
+
+
+# Rick Tearle 2010-11
+
+my $Time -= time; # start time
+my $Debug = 0;
+
+# Parsing and storing input parameters
+# Only childfields can be repeated
+print "$0 @ARGV\nProcessing input parameters\n";
+my %ExpectedParams =  GetExpectedParams ();
+my %EnteredParams = GetEnteredParams ();
+
+# Setting up prog paras from input paras
+my $FileIn = $EnteredParams{input};
+unless (-f $FileIn) {die "Testvariants input file $FileIn not found\n";} # requires existing file
+#my $FileOut = $EnteredParams{output}; #
+#$DirectoryOut =~ s/\/$//; # remove trailing slash if present
+#unless (-d $DirectoryOut) {die "Output directory $DirectoryOut not found\n";} # requires existing file
+#print "$FileIn\n$DirectoryOut\n";
+#$FileIn =~ /(^.+\/)(.+?)\./; # get filename without path and without extensions
+
+# my $FileOut1 = $FileOut."-Freq.tsv";
+# my $FileOut2 = $FileOut."-Freq_Short.tsv";
+# my $FileOut3 = $FileOut."-Freq_Stats.tsv";
+# my $FileOut4 = $FileOut."-Freq_Log.tsv";
+
+print "\nOpening Input File:\n\t$FileIn\n";
+my $IN = OpenFile ($FileIn); # open the file with correct file format
+
+#print "\nOpening Output Files:\n\t$FileOut1\n\t$FileOut2\n\t$FileOut3\n\t$FileOut4\n"; #exit;
+open my $OUT1, ">", $EnteredParams{output1};
+open my $OUT2, ">", $EnteredParams{output2};
+#open my $OUT3, ">", $EnteredParams{output3};
+#open my $OUT4, ">", $EnteredParams{output4};
+
+# Get col header and genomes fields
+my $ColHeader = <$IN>; # get col header
+chomp $ColHeader;
+my @ColHeader = split /\t/, $ColHeader;
+my $StartGenomes = $EnteredParams{first_genome_field_nr} - 1; # first column with testvariants data, 1 based -> 0 based
+my $StopGenomes = $EnteredParams{last_genome_field_nr} - 1; # first column with testvariants data, 1 based -> 0 based
+if ($StartGenomes < 0) {die "No valid entry for First_Genome_Field_Nr, must be 1 or greater\n";}
+if ($StopGenomes < 0) {die "No valid entry for Last_Genome_Field_Nr, must be 1 or greater\n";}
+if ($StartGenomes > $StopGenomes) {die "Last_Genome_Field_Nr must be greater than or equal to First_Genome_Field_Nr\n";}
+if ($StartGenomes > int @ColHeader) {die "First_Genome_Field_Nr > number of fields in column header\n";}
+if ($StopGenomes > int @ColHeader) {die "Last_Genome_Field_Nr > number of fields in column header\n";}
+my $NrGenomes = $StopGenomes - $StartGenomes + 1;
+#print "$StartGenomes\t$StopGenomes\n"; #exit;
+#print "First Genome Field:\n\t$ColHeader[$StartGenomes]\n";
+#print "Last Genome Field:\n\t$ColHeader[$StopGenomes]\n\n";
+
+# print column headers
+print $OUT1 join("\t",@ColHeader),"\tAllFreq\tCalledFreq\n";
+print $OUT2 join("\t",@ColHeader[0..7]),"\tAllFreq\tCalledFreq\n";
+print join("\t",@ColHeader),"\n";
+print "First Genome Field: $ColHeader[$StartGenomes]\n";
+print "Last Genome Field: $ColHeader[$StopGenomes]\n";
+print "Nr Genomes: $NrGenomes\n\n";
+
+print "\nProcessing Variants....\n";
+my $VariantCount = 0; # variant locus counter, not used
+my %AllFreqCounts; # storing histogram of all freq counts
+my %CalledFreqCounts; # storing histogram of called freq counts
+my $Warnings;
+while (<$IN>)
+{
+	# testvariants fields: variantId chromosome begin end varType reference alleleSeq xRef GS000000XX1-ASM GS000000XX2-ASM [GS000000XXN-ASM]
+	my $Line = $_; # save line for output below
+    chomp $Line;
+    my @F = split /\t/, $Line; # split in to fields
+    $VariantCount++; # increment variant counter
+	my $UseFields = join ("",@F[$StartGenomes..$StopGenomes]); # get genome fields as string, to count 0s and 1s
+	my $Count1 = () = $UseFields =~ /1/g; # count the number of 1s
+	my $Count0 = () = $UseFields =~ /0/g; # count the number of 0s
+	my $CountN = () = $UseFields =~ /N/g; # count the number of Ns
+	my $NrAlleles = $Count1 + $Count0 + $CountN; # total count
+	unless ($NrAlleles == $NrGenomes *2 or $NrAlleles == $NrGenomes) # count does not match expected for diploid/haploid locus
+	{
+		print "$NrAlleles alleles for variant ",join(" ",@F[0..7]),"\n"; # log warning
+		#print "Expected $NrGenomes or ",$NrGenomes*2," alleles depending on ploidy of locus\n";
+		#if ($Warnings++ > 10) {die "Have found $Warnings exceptions for this file, termnating processing\n";} # terminate if too many warnings
+	}
+	my $AllFreq = sprintf("%0.3f",$Count1/$NrAlleles); # calculate freq of 1s vs all alleles
+	my $CalledFreq = sprintf("%0.3f",0);
+	if ($Count1+$Count0) {$CalledFreq = sprintf("%0.3f",$Count1/($Count1+$Count0));} # calculate freq of 1s vs called alleles, if there are any
+	$AllFreqCounts{$AllFreq}++; # increment all freq histogram
+	$CalledFreqCounts{$CalledFreq}++; # increment called freq histogram
+	#print "$Line\n$AlleleCount\t$Count1\t$Count0\t$AllFreq\t$CalledFreq\n"; #exit;
+	print $OUT1 "$Line\t$AllFreq\t$CalledFreq\n"; # output full testvariants plus frequencies for this var
+	print $OUT2 join("\t",@F[0..7]),"\t$AllFreq\t$CalledFreq\n"; # output just var info plus frequencies for this var
+	#exit if $VariantCount > 20;
+}
+close $OUT1;
+close $OUT2;
+
+# Print frequency histograms
+print "Nr Variants at each Frequency (All):\nFreq\tCount\n"; # header
+foreach my $Freq (sort {$a <=> $b} keys %AllFreqCounts) {print "$Freq\t$AllFreqCounts{$Freq}\n";}
+
+print "\nNr Variants at each Frequency (Called):\nFreq\tCount\n"; # header
+foreach my $Freq (sort {$a <=> $b} keys %CalledFreqCounts) {print "$Freq\t$CalledFreqCounts{$Freq}\n";}
+
+$Time += time;
+print "\ntime $Time\n";
+
+###########################################################################
+#                                   SUBS                                  #
+###########################################################################
+
+sub GetExpectedParams
+{
+	my %Hash =
+	(
+	"input" => -1,
+	"output_dir" => -1,
+	); # store parameters and values
+	return %Hash;
+}
+
+sub GetEnteredParams
+{
+	# Processing @ARGV
+	my %Hash;
+
+	my @ARGVs = split /--/, join (" ",@ARGV); # split args on --, into array
+	#print "Start\n", join ("\n",@ARGVs),"\n",int @ARGVs - 1,"\n\n" if $Debug;
+	#print "Key\tVal\n" if $Debug; #exit;
+	for my $n (1..$#ARGVs) # parse each
+	{
+		$ARGVs[$n] =~ s/\s+$//; # remove any trailing spaces
+		my ($Key, $Val) = split / /, $ARGVs[$n], 2; # put first element into key, any other elements into val
+		$Key = lc $Key;
+		$Hash{$Key} = $Val; # make a hash entry out of key and val
+		#print "$Key\t$EnteredParams{$Key}\n" if $Debug;
+	}
+		#print int(keys %Hash),"\n" if $Debug;
+		#foreach my $Arg (keys %Hash) {print "Arg: $Arg\t",$ExpectedParams{$Arg},"\n";}
+		#print "Arg string:\t",join (" ",@ARGV),"\n" if $Debug;
+		#exit if $Debug;
+	return %Hash; # hash now has each -- entry param, with associated values
+}
+
+sub SaveArrayAsString
+{
+	my $FH = shift;
+	my $Fields = shift;
+	#print "$Fields\n";
+	print $FH join("\t",@$Fields),"\n";
+}
+
+sub ConcatenateVariants
+{
+    my $ArrayIn = shift; # ptr to array
+    my $StateFieldNr = shift; # field to process
+    #print int(@$ArrayIn),"\n";
+    my @ArrayOut; # array to store records out
+    my $Nr = -1;
+    foreach my $Entry (@$ArrayIn)
+    {
+	}
+    return \@ArrayOut; # return ptr to array
+}
+
+sub LoadStateRecord
+{
+	my $Out = shift;
+	my $In = shift;
+	my $StateFieldNr = shift;
+
+				$Out->{State} = $$In[$StateFieldNr]; # get state for new record
+				$Out->{Chr} = $$In[1]; # get chr
+				$Out->{Begin} = $$In[2]; # get begin of state range
+				$Out->{End} = $$In[3]; # get current end of state range
+				$Out->{Records}++; # record added to new count
+}
+
+sub OpenFile
+{
+    my $File = shift;
+    my $FH;
+		open ($FH, "$File") or die ("$!: can't open file $File");
+    return $FH;
+}
+
+sub OpenFileold
+{
+    my $File = shift;
+    my $FH;
+
+    if ($File =~ /.bz2$/)
+    {
+		open ($FH, "bzcat $File |") or die ("$!: can't open file $File");
+    }
+    elsif ($File =~ /.gz$/)
+    {
+		open ($FH, "gunzip -c $File |") or die ("$!: can't open file $File");
+    }
+    elsif ($File =~ /.tsv$/)
+    {
+		open ($FH, "cat $File |") or die ("$!: can't open file $File");
+    }
+    else
+    {
+		die ("$!: do not recognise file type $File");
+    }
+    return $FH;
+}
+
+sub LoadNewRecord
+{
+    my $In = shift;
+    my $Out = shift;
+    $Out->{Chr} = $In->{Chr};
+    $Out->{State} = $In->{State};
+    $Out->{Begin} = $In->{Begin};
+    $Out->{End} = $In->{End};
+    $Out->{Records} = $In->{Records};
+}
+
+sub NewStateRecord
+{
+    my $Record =
+    {
+	Chr => "",
+        Begin => -1,
+        End => -1,
+		State => "",
+        Records => 0,
+		MIEs => 0,
+		StateErrors => 0,
+        Length => -1,
+    };
+    return $Record;
+}

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/scripts/tools/cg_scripts/List_Unique_Variants.xml	Tue Jun 12 14:42:04 2012 -0400
@@ -0,0 +1,323 @@
+<tool id="pl_listuniquevariants" name="List_Unique_Variants" version="0.0.1">
+
+  <description>with annotations from gene or var files</description> <!--adds description in toolbar-->
+  
+  <command interpreter="perl"> <!--run executable-->
+		#if $file_types.file_type =="var2" 
+			List_Unique_Variants_2_1_0.pl --File_Type V --Output_File $output 
+			--Var_Type $file_types.variants 
+			$file_types.scoresVAF 
+			$file_types.scoresEAF 
+			$file_types.varQuality
+			#if $file_types.data_sources.data_source == "in" 
+				#for $v in $file_types.data_sources.varfiles <!--get each var file-->
+				--Input_File ${v.input}
+				#end for
+			#else
+				`cat $file_types.data_sources.varlist`
+			#end if
+	
+		#else if $file_types.file_type =="var1"
+			List_Unique_Variants_2_1_0.pl --File_Type V --Output_File $output 
+			--Var_Type $file_types.variants 
+			$file_types.scores
+			#if $file_types.data_sources.data_source == "in" 
+				#for $v in $file_types.data_sources.varfiles <!--get each var file-->
+				--Input_File ${v.input}
+				#end for
+			#else
+				`cat $file_types.data_sources.varlist`
+			#end if
+	
+		#else if $file_types.file_type =="gene"
+			List_Unique_Variants_2_1_0.pl --File_Type G --Output_File $output 
+			--Var_Type $file_types.variants 
+			--Component $file_types.component 
+			--Impact $file_types.impact 
+			#if $file_types.data_sources.data_source == "in" 
+				#for $g in $file_types.data_sources.genefiles <!--get each var file-->
+				--Input_File ${g.input}
+				#end for
+			#else
+				`cat $file_types.data_sources.genelist`
+			#end if
+		#end if
+  </command>
+
+  <outputs>
+    <data format="tabular" name="output" />
+  </outputs>
+
+  <inputs>
+    <conditional name="file_types">
+			<!--form field to select file type-->
+			<param name="file_type" type="select" label="Select the input file type">
+				<option value="var2" selected="True">var files, format 2.x</option>
+				<option value="var1">var files, format 1.x</option>
+				<option value="gene">gene files</option>
+			</param>
+			
+			<when value="var2">
+				<!--form field to select all variant types to annotate-->
+				<param name="variants" label="Select variant types to include" type="select" multiple="true" >
+					<!--<validator type="no_options" message="Please select at least one variant type."/>-->
+					<option value="All" selected="true">All</option>
+					<option value="snp">snp</option>
+					<option value="ins">ins</option>
+					<option value="del">del</option>
+					<option value="sub">sub</option>
+					<option value="ref">ref</option>
+				</param>
+ 
+				<!--form field to select varScoresVAF-->
+				<param name="scoresVAF" type="select" label="Include varScoreVAF?">
+					<option value="--Scores_VAF yes" selected="true">yes</option>
+					<option value="--Scores_VAF no">no</option>
+				</param>
+				<!--form field to select varScoresEAF-->
+				<param name="scoresEAF" type="select" label="Include varScoreEAF?">
+					<option value="--Scores_EAF yes" selected="true">yes</option>
+					<option value="--Scores_EAF no">no</option>
+				</param>
+				<!--form field to select varQuality-->
+				<param name="varQuality" type="select" label="Include varQuality?">
+					<option value="--Score_Qualities yes" selected="true">yes</option>
+					<option value="--Score_Qualities no">no</option>
+				</param>
+				
+				<!--conditional to select variant file input-->
+				<conditional name="data_sources">
+					<param name="data_source" type="select" label="Where are the input var files?">
+						<option value="in" selected="true">imported into Galaxy</option>
+						<option value="out">located outside Galaxy (available only for local Galaxy instances)</option>
+					</param>
+					<when value="in">
+						<!--form field to select variant files-->
+						<repeat name="varfiles" title="Variant files">
+							<param name="input" type="data" format="cg_var" label="Dataset">
+								<validator type="unspecified_build" />
+								<validator type="dataset_metadata_in_file" filename="cg_crr_files.loc"
+								 metadata_name="dbkey" metadata_column="1"
+								 message="cgatools is not currently available for this build."/>
+							</param>
+						</repeat>
+					</when>
+					<when value="out">
+						<!--form field to select crr file-->
+						<param name="varlist" type="text" label="List of variant files (/path/file)" size="200" help="file with list of var files (/path/varfile), var files can be compressed (gz, bz2)."/>
+					</when>
+				</conditional>
+			</when>
+			
+			<when value="var1">
+				<!--form field to select all variant types to annotate-->
+				<param name="variants" label="Select variant types to include" type="select" multiple="true" >
+					<!--<validator type="no_options" message="Please select at least one variant type."/>-->
+					<option value="All" selected="true">All</option>
+					<option value="snp">snp</option>
+					<option value="ins">ins</option>
+					<option value="del">del</option>
+					<option value="sub">sub</option>
+					<option value="ref">ref</option>
+				</param>
+ 
+				<!--form field to select scores-->
+				<param name="scores" type="select" label="Include totalScore?">
+					<option value="--Scores yes" selected="true">yes</option>
+					<option value="--Scores no">no</option>
+				</param>
+				
+				<!--conditional to select variant file input-->
+				<conditional name="data_sources">
+					<param name="data_source" type="select" label="Where are the input var files?">
+						<option value="in" selected="true">imported into Galaxy</option>
+						<option value="out">located outside Galaxy (available only for local Galaxy instances)</option>
+					</param>
+					<when value="in">
+						<!--form field to select variant files-->
+						<repeat name="varfiles" title="Variant files">
+							<param name="input" type="data" format="cg_var" label="Dataset">
+								<validator type="unspecified_build" />
+								<validator type="dataset_metadata_in_file" filename="cg_crr_files.loc"
+								 metadata_name="dbkey" metadata_column="1"
+								 message="cgatools is not currently available for this build."/>
+							</param>
+						</repeat>
+					</when>
+					<when value="out">
+						<!--form field to select crr file-->
+						<param name="varlist" type="text" label="List of variant files (/path/file)" size="200" help="file with list of var files (/path/varfile), var files can be compressed (gz, bz2)."/>
+					</when>
+				</conditional>
+			</when>
+
+			<when value="gene">
+				<!--form field to select all variant types to annotate-->
+				<param name="variants" label="Select variant types to include" type="select" multiple="true" >
+					<!--<validator type="no_options" message="Please select at least one variant type."/>-->
+					<option value="All" selected="true">All</option>
+					<option value="snp">snp</option>
+					<option value="ins">ins</option>
+					<option value="del">del</option>
+					<option value="sub">sub</option>
+					<option value="ref">ref</option>
+				</param>
+ 
+				<!--form field to select component in gene file-->
+				<param name="component" type="select" label="Select component types to include" multiple="true" >
+				  <option value="All" selected="true">All</option>
+					<option value="CDS">CDS</option>
+					<option value="INTRON">INTRON</option>
+					<option value="DONOR">DONOR</option>
+					<option value="ACCEPTOR">ACCEPTOR</option>
+					<option value="TSS-UPSTREAM">TSS-UPSTREAM</option>
+					<option value="SPAN5">SPAN5</option>
+					<option value="SPAN3">SPAN3</option>
+					<option value="SPAN">SPAN</option>
+					<option value="UTR5">UTR5</option>
+					<option value="UTR3">UTR3</option>
+					<option value="UTR">UTR</option>
+				</param>
+				
+				<!--form field to select impact in gene file-->
+				<param name="impact" type="select" label="Select impact types to include" multiple="true" >
+				  <option value="All" selected="true">All</option>
+					<option value="NO-CHANGE">NO-CHANGE</option>
+					<option value="SYNONYMOUS">SYNONYMOUS</option>
+					<option value="MISSENES">MISSENES</option>
+					<option value="NONSENSE">NONSENSE</option>
+					<option value="NONSSTOP">NONSSTOP</option>
+					<option value="DELETE">DELETE</option>
+					<option value="INSERT">INSERT</option>
+					<option value="DELETE+">DELETE+</option>
+					<option value="INSERT+">INSERT+</option>
+					<option value="FRAMESHIFT">FRAMESHIFT</option>
+					<option value="MISSTART">MISSTART</option>
+					<option value="DISRUPT">DISRUPT</option>
+					<option value="UNKNOWN-VNC">UNKNOWN-VNC</option>
+					<option value="UNKNOWN-INC">UNKNOWN-INC</option>
+					<option value="UNKNOWN-TR">UNKNOWN-TR</option>
+				</param>
+				
+				<!--conditional to select gene file input-->
+				<conditional name="data_sources">
+					<param name="data_source" type="select" label="Where are the input gene files?">
+						<option value="in" selected="true">imported into Galaxy</option>
+						<option value="out">located outside Galaxy (available only for local Galaxy instances)</option>
+					</param>
+					<when value="in">
+						<!--form field to select variant files-->
+						<repeat name="genefiles" title="Gene files">
+							<param name="input" type="data" format="cg_gene" label="Dataset">
+								<validator type="unspecified_build" />
+								<validator type="dataset_metadata_in_file" filename="cg_crr_files.loc"
+								 metadata_name="dbkey" metadata_column="1"
+								 message="cgatools is not currently available for this build."/>
+							</param>
+						</repeat>
+					</when>
+					<when value="out">
+						<!--form field to select crr file-->
+						<param name="genelist" type="text" label="List of gene files (/path/file)" size="200" help="file with list of gene files (/path/genefile), gene files can be compressed (gz, bz2)."/>
+					</when>
+				</conditional>
+			</when>
+			
+		</conditional>	
+  </inputs>
+
+
+  <help>
+
+**What it does**
+
+This tool identifies all called variants present in the var or gene files and generates annotated variant list.
+
+-----
+
+**Instructions**::
+
+		List Unique Variants for Pipeline 1.x and 2.x
+		[Uses header if available, checks for position of xref field if not]
+		Take one or more var or gene files
+		Extract a non-redundant set of variants
+	
+		For var files:
+		The fields used to define non-redundant variants are are:
+			chromosome begin end varType reference alleleSeq xRef
+		User can nominate class(es) of varType to filter on
+		Outputs varScoreEAF, varScoreVAF and varQuality as a default but user can turn
+			them off (separately)
+		Scores and qualities stored in separate fields, all values for a variant across
+			a set of genomes.
+		Values for different genomes separated by ':', for two hom entries for the same
+			genome by '|'
+		Output is accepted by testvariants to generate a variant table, all fields kept
+			in testvariants output
+	
+		For gene files:
+		The fields used to define non-redundant gene variants are:
+			chromosome begin end varType reference call xRef geneId mrnaAcc proteinAcc symbol
+			orientation component componentIndex codingRegionKnown impact nucleotidePos
+			proteinPos annotationRefSequence sampleSequence genomeRefSequence
+		User can nominate class(es) of varType, component or impact to filter on
+		All gene entries kept ie  multiple entries if multiple transcripts
+	
+		NB Now treating xref as a separate component in var recs, as it is not consistent
+			between X and Y vars
+		Not fixed for gene recs yet
+	
+		perl List_Unique_Variants_2_0_11.pl
+		--File_Type [V|G]
+		--Input_File input_file_1 [set of var or gene files]
+		--Input_File input_file_2
+		...
+		--Input_File input_file_n
+		--Output_File filename
+		--Var_Type [For both file types, 'All' or any value from the varType field,
+				multiple values allowed, separated by comma]
+		--Component [Gene file specific,'All' or any value from component field of gene
+				file, multiple allowed; 'All" is default]
+		--Impact All [Gene file specific,'All' or any value from impact field of gene
+				file, multiple allowed; 'All" is default]
+		--Scores [1.x var file specific, yes|no, yes is default]
+		--Scores_VAF [2.0 var file specific, yes|no, yes is default]
+		--Scores_EAF [2.0 var file specific, yes|no, yes is default]
+		--Score_Qualities [yes|no, yes is default]
+		eg
+		perl List_Unique_Variants_2_0_11.pl \
+		--File_Type V \
+		--Input_File /Yoruban_Trio_1100_37/GS19238-1100-37/GS00028-DNA_A01/ASM/gene-GS19238-1100-37-ASM.tsv.bz2 \
+		--Input_File /Yoruban_Trio_1100_37/GS19239-1100-37/GS00028-DNA_B01/ASM/gene-GS19239-1100-37-ASM.tsv.bz2 \
+		--Input_File /Yoruban_Trio_1100_37/GS19240-1100-37/GS00028-DNA_C01/ASM/gene-GS19240-1100-37-ASM.tsv.bz2 \
+		--Output_File /Users/rtearle/Documents/TBF/YRI_Trio_Protein_Coding.tsv \
+		--Var_Type All
+		--Component All
+		--Impact All
+		--Scores_VAF yes \
+		--Scores_EAF yes \
+		--Score_Qualities yes
+	
+		var fields
+		1.x	locus ploidy haplotype chromosome begin end varType reference alleleSeq
+				totalScore hapLink xRef
+		2.0	locus ploidy allele chromosome begin end varType reference alleleSeq
+				varScoreVAF varScoreEAF varQuality hapLink xRef
+	
+		gene fields
+		1.x index locus allele chromosome begin end varType reference call xRef geneId
+				mrnaAcc proteinAcc symbol orientation component componentIndex
+				codingRegionKnown impact nucleotidePos proteinPos annotationRefSequence
+				sampleSequence genomeRefSequence
+		2.0 index locus allele chromosome begin end varType reference call xRef geneId
+				mrnaAcc proteinAcc symbol orientation component componentIndex hasCodingRegion
+				impact nucleotidePos proteinPos annotationRefSequence sampleSequence
+				genomeRefSequence pfam
+	
+		Parsing and storing input parameters
+		Only input_file fields can be repeated
+		input paramaters are case insensitive
+
+
+  </help>
+</tool>

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/scripts/tools/cg_scripts/List_Unique_Variants_2_1_0.pl	Tue Jun 12 14:42:04 2012 -0400
@@ -0,0 +1,583 @@
+#!/usr/bin/perl
+use strict;
+use File::Basename;
+$| = 1;
+
+# List Unique Variants for Pipeline 1.x and 2.x
+# [Uses header if available, checks for position of xref field if not]
+# Take one or more var or gene files
+# Extract a non-redundant set of variants
+
+# For var files:
+# The fields used to define non-redundant variants are are:
+# chromosome begin end varType reference alleleSeq xRef
+# User can nominate class(es) of varType to filter on
+# Outputs varScoreEAF, varScoreVAF and varQuality as a default but user can turn them off (separately)
+# Scores and qualities stored in separate fields, all values for a variant across a set of genomes.
+# Values for different genomes separated by ':', for two hom entries for the same genome by '|'
+# Output is accepted by testvariants to generate a variant table, all fields kept in testvariants output
+
+# For gene files:
+# The fields used to define non-redundant gene variants are:
+# chromosome begin end varType reference call xRef geneId mrnaAcc proteinAcc symbol orientation component componentIndex codingRegionKnown impact nucleotidePos proteinPos annotationRefSequence sampleSequence genomeRefSequence
+# User can nominate class(es) of varType, component or impact to filter on
+# All gene entries kept ie  multiple entries if multiple transcripts
+
+# NB Now treating xref as a separate component in var recs, as it is not consistent between X and Y vars
+# Not fixed for gene recs yet
+
+# perl List_Unique_Variants_2_0_9.pl
+# --File_Type [V|G]
+# --Input_File input_file_1 [set of var or gene files]
+# --Input_File input_file_2
+# ...
+# --Input_File input_file_n
+# --Output_File filename
+# --Var_Type [For both file types, 'All' or any value from the varType field, multiple values allowed, separated by comma]
+# --Component [Gene file specific,'All' or any value from component field of gene file, multiple allowed; 'All" is default]
+# --Impact All [Gene file specific,'All' or any value from impact field of gene file, multiple allowed; 'All" is default]
+# --Scores [1.x var file specific, yes|no, yes is default]
+# --Scores_VAF [2.0 var file specific, yes|no, yes is default]
+# --Scores_EAF [2.0 var file specific, yes|no, yes is default]
+# --Score_Qualities [yes|no, yes is default]
+# eg
+# perl /Users/rtearle/Documents/Programming/Perl/Scripts/Dev/List_Unique_Variants_2_0_4 \
+# --File_Type V \
+# --Input_File /Yoruban_Trio_1100_37/GS19238-1100-37/GS00028-DNA_A01/ASM/gene-GS19238-1100-37-ASM.tsv.bz2 \
+# --Input_File /Yoruban_Trio_1100_37/GS19239-1100-37/GS00028-DNA_B01/ASM/gene-GS19239-1100-37-ASM.tsv.bz2 \
+# --Input_File /Yoruban_Trio_1100_37/GS19240-1100-37/GS00028-DNA_C01/ASM/gene-GS19240-1100-37-ASM.tsv.bz2 \
+# --Output_File /Users/rtearle/Documents/TBF/YRI_Trio_Protein_Coding.tsv \
+# --Var_Type All
+# --Component All
+# --Impact All
+# --Scores_VAF yes \
+# --Scores_EAF yes \
+# --Score_Qualities yes
+
+# var fields
+# 1.x
+# locus ploidy haplotype chromosome begin end varType reference alleleSeq totalScore hapLink xRef
+# 2.0
+# locus ploidy allele chromosome begin end varType reference alleleSeq varScoreVAF varScoreEAF varQuality hapLink xRef
+
+# gene fields
+# 1.x index locus allele chromosome begin end varType reference call xRef geneId mrnaAcc proteinAcc symbol orientation
+#  component componentIndex codingRegionKnown impact nucleotidePos proteinPos annotationRefSequence sampleSequence genomeRefSequence
+# 2.0 index locus allele chromosome begin end varType reference call xRef geneId mrnaAcc proteinAcc symbol orientation
+# component componentIndex hasCodingRegion impact nucleotidePos proteinPos annotationRefSequence sampleSequence genomeRefSequence pfam
+
+# Parsing and storing input parameters
+# Only input_file fields can be repeated
+# input paramaters are case insensitive
+
+print "$0 @ARGV\nProcessing input parameters\n";
+my $NrParams;
+my %ExpectedParams =  GetExpectedParams (); # list of expected parms
+my %EnteredParams = GetEnteredParams (); # list of entered params
+
+# Input Files
+my $FileType = $EnteredParams{file_type};
+if ($FileType ne "V" and $FileType ne "G") {die "File Type must be 'V' or 'G', not '$FileType'\n";}
+my $FilesIn = $EnteredParams{input_file}; # ptr to list of input files
+print "File Type: $FileType\nInput Files:\n";
+my $NrInputFiles = int(@$FilesIn);
+foreach my $File (@$FilesIn) {print "$File\n";} # requires existing files
+foreach my $File (@$FilesIn) {unless (-f $File) {die "Input file $File not found\n";}} # requires existing files
+for my $n (0.. $NrInputFiles-2) # look for duplicates in list
+	{for my $m ($n+1.. $NrInputFiles-1) {if ($$FilesIn[$n] eq $$FilesIn[$m] ) {die "File $$FilesIn[$n] is repeated in input file list\n";}}}
+
+# Output Dir
+#my $DirectoryOut = $EnteredParams{output_dir}; # output dir
+#$DirectoryOut =~ s/\/$//; # remove trailing slash if present
+#unless (-d $DirectoryOut) {mkdir $DirectoryOut or die "Cannot find/create output directory $DirectoryOut\n";} # uses existing dir or makes a new dir if it can
+
+# Ouput File
+my $FileOut = $EnteredParams{output_file}; # output file
+print "FileOut: $FileOut\n";
+$FileOut =~ /(^.+\/)?(.+$)/; # split in to path and filename
+my $DirectoryOut = $1; # assign path  # NEED MORE TESTING EG EMPTY PATH #
+$FileOut = $2; # assign file prefix
+print "File: $FileOut\nDir: $DirectoryOut\n"; #exit;
+# if (-f $DirectoryOut.$FileOut) # ouput file exists, create a new one based on the name
+# {
+# 	print "Output file $FileOut exists, modifying to unique file name ";
+# 	$FileOut =~ /^(.+?)\./; # find name without extensions
+# 	my $Stub = $1; # set stub to name without extensions
+# 	$FileOut =~ /(\..+)?$/; # get extension(s)
+# 	my $Ext = $1; # set ext to extensions
+# 	my $n = 1; # n will increment to find a unique name
+# 	my $Suff = ""; # suff tracks n
+# 	while (-f $DirectoryOut.$Stub.$Suff.$Ext) {$Suff = "-$n"; $n++;} # loop till we have a new unique filename
+# 	$FileOut = $Stub.$Suff.$Ext; # file out now has same name, same extensions, but also -n at the end of the name, making it unique
+# 	print "$FileOut\n";
+# }
+
+#print "Files\n",join("\n",@$FilesIn),"\n\n";
+#print "Ouput Dir\n$DirectoryOut\n";
+#print "Ouput File\n$FileOut\n";
+
+# Extract Header & Column Header
+my $IN = OpenFile ($$FilesIn[0]); # open the first file with correct file format
+my $Header = GetHeaderAsString ($IN); # get header
+unless ($Header) {close $IN; $IN = OpenFile ($$FilesIn[0]);} # if there is no header, close and reopen file, ie start file again
+my $ColHeader = <$IN>; # get col header, first remaining line
+chomp $ColHeader;
+
+# Get version if filetype is var - needed because there are new fields in 2.0 and posn of xRef changed
+my ($Version, $XrefField);
+if ($FileType eq "V")
+{
+	($Version, $XrefField) = GetVersion ($Header, $ColHeader);
+	#print "$Version $XrefField\n"; exit;
+	unless ($Version) {die "Cannot determine format version of first file in list\nNeed either a native Complete header or a native Complete Column Header with an xRef field\n";}
+}
+
+# Shared input params
+my $OutputVarTypes = lc $EnteredParams{var_type} || $ExpectedParams{var_type}; # var types listed in file in lc
+$OutputVarTypes =~ s/\,/\|/g; # create regex string
+$OutputVarTypes =~ s/\,| //; # remove extraneous commas, spaces
+
+# Input Params for var file
+my ($KeepScoresVAF, $KeepScoresEAF, $KeepQuals, $KeepScores, $VarExtras);
+if ($FileType eq "V")
+{
+	if ($Version == 2)
+	{
+		$KeepQuals = lc $EnteredParams{score_quality} || $ExpectedParams{score_quality}; # keep scoresQuality for 2.0
+		$KeepQuals = 1 if $KeepQuals eq "yes"; # converting to boolean
+		$KeepScoresVAF = lc $EnteredParams{scores_vaf} || $ExpectedParams{scores_vaf}; # keep scoresVAF for 2.0
+		$KeepScoresVAF = 1 if $KeepScoresVAF eq "yes"; # converting to boolean
+		$KeepScoresEAF = lc $EnteredParams{scores_eaf} || $ExpectedParams{scores_eaf}; # keep scoresEAF for 2.0	$KeepQuals = lc $EnteredParams{score_qualities} || $ExpectedParams{score_qualities}; # keep scoresQuality for 2.0
+		$KeepScoresEAF = 1 if $KeepScoresEAF eq "yes"; # converting to boolean
+	}
+	else # Version 1
+	{
+		$KeepScores = lc $EnteredParams{scores} || $ExpectedParams{scores}; # keep scores for 1.x
+		$KeepScores = 1 if $KeepScores eq "yes"; # converting to boolean
+	}
+	$VarExtras = 1 if $KeepScoresVAF or $KeepScoresEAF or $KeepQuals or $KeepScores; # flag to process var file for scores info
+}
+
+# Input Params for gene file
+my $OutputComponents = uc $EnteredParams{component} || $ExpectedParams{component}; # components listed in file in uc
+my $OutputImpacts = uc $EnteredParams{impact} || $ExpectedParams{impact}; # impacts listed in file in uc
+
+# Loading chr nrs, setting up var hash
+my @ChrNames = ('chr1', 'chr2', 'chr3', 'chr4', 'chr5', 'chr6', 'chr7', 'chr8', 'chr9', 'chr10',
+				'chr11', 'chr12', 'chr13', 'chr14', 'chr15', 'chr16', 'chr17', 'chr18', 'chr19',
+				'chr20', 'chr21', 'chr22', 'chrX', 'chrY', 'chrM'); # using this array forces the output order of chrs into the correct order
+my %Vars; # hash to store var records in an array for each chr
+foreach my $Chr (@ChrNames) {$Vars{$Chr} = {};} # print "$Chr\t";}  # set up hash of hashes, one for each chr
+#print "\n"; #exit;
+
+# Create ouput col header
+if ($FileType eq "V")
+{
+	# 1.x locus ploidy haplotype chromosome begin end varType reference alleleSeq totalScore hapLink xRef
+	# 2.0 locus ploidy allele chromosome begin end varType reference alleleSeq varScoreVAF varScoreEAF varQuality hapLink xRef
+	my @Fields = split "\t", $ColHeader;
+	$ColHeader = join("\t",@Fields[3..8])."\t".$Fields[$XrefField];
+	if ($Version == 2) # 2.0
+	{
+		if ($KeepScoresVAF) {$ColHeader .= "\tvarScoreVAF";}
+		if ($KeepScoresEAF) {$ColHeader .= "\tvarScoreEAF";}
+		if ($KeepQuals) {$ColHeader .= "\tvarQuality";}
+	}
+	else # 1.x
+	{
+		if ($KeepScores) {$ColHeader .= "\ttotalScore";}
+	}
+}
+elsif ($FileType eq "G")
+{
+	# 1.x index locus allele chromosome begin end varType reference call xRef geneId mrnaAcc proteinAcc symbol orientation
+	#  component componentIndex codingRegionKnown impact nucleotidePos proteinPos annotationRefSequence sampleSequence genomeRefSequence
+	# 2.0 index locus allele chromosome begin end varType reference call xRef geneId mrnaAcc proteinAcc symbol orientation
+	# component componentIndex hasCodingRegion impact nucleotidePos proteinPos annotationRefSequence sampleSequence genomeRefSequence pfam
+	my @Fields = split "\t", $ColHeader;
+	$ColHeader = join("\t",@Fields[3..30]); # 30 much more than needed
+	$OutputComponents =~ s/\,/\|/g; # create regex string
+	$OutputComponents =~ s/\,| //; # remove extraneous commas, spaces
+	$OutputComponents =~ s/\,| //; # remove extraneous commas, spaces
+	$OutputImpacts =~ s/\,/\|/g; # create regex string
+	$OutputImpacts =~ s/\,| //; # remove extraneous commas, spaces
+	#print "OutputVarTypes: $OutputVarTypes\nOutputComponents: $OutputComponents\nOutputImpacts: $OutputImpacts\n";
+}
+else
+{
+	die "FileType $FileType not understood\n"; # redundant
+}
+
+# Set up Processing Subs
+if ($FileType eq "G") # use gene subs for 'G'
+{
+	*ExtractSub2Use = \&ExtractGeneFields;
+	*AddRecSub2Use = \&AddGeneRec;
+}
+else # use var subs for 'V'
+{
+	*ExtractSub2Use = \&ExtractVarFields;
+	*AddRecSub2Use = \&AddVarRec;
+}
+#print "Gene: ",\&ExtractGeneFields," ",\&AddGeneRec," Var: ",\&ExtractVarFields," ",\&AddVarRec," Using: ",\&ExtractSub2Use," ",\&AddRecSub2Use,"\n"; exit;
+
+# Process Files
+my $RecCount = 0; # total nr recs that are coding/splicing/spanning
+my $FileCount = 0; # keeps track of nr files to use to format eg scores field
+my $XRef;
+foreach my $File (@$FilesIn)
+{
+	print "Processing file $File\n";
+	$FileCount++; # counting nr files
+
+	# Open file, process header, col header
+	my $IN = OpenFile ($File); # open the file with correct file format
+	my $Header = GetHeaderAsString ($IN); # get  header
+	unless ($Header) {close $IN; $IN = OpenFile ($$FilesIn[0]);} # if no header, close and reopen file, ie start file again
+	my $ColHeader = <$IN>; # get col header, first remaining line
+	unless ($ColHeader =~ /^>/) {print "Suspect column header for file $File:\n$ColHeader\n;"}
+
+	my $Count = 0; # cnr recs for this file that are coding/splicing/spanning
+	while (<$IN>) # loop through remainder of file ie data
+	{
+		my ($Rec, $Chr, $ScoreVAF, $ScoreEAF, $ScoreQual, $XRef) = ExtractSub2Use ($_, $XrefField); # sub extracts wanted fields in rec as string, chr, other fields optionally
+		next unless $Rec;
+		AddRecSub2Use ($Rec, $Vars{$Chr}, $ScoreVAF, $ScoreEAF, $ScoreQual, $FileCount, $XRef) if $Rec; # only process if rec is not empty
+		$Count++; # increment count of coding/splicing/spanning vars
+	}
+	print "Nr matched records for this file: $Count\n";
+	$RecCount += $Count; # add this file's count to total count
+	close $IN;
+}
+print "Nr matched records across all files:\t $RecCount\n"; # total count
+
+# Open file out, write col header
+print "Sorting and Saving to file $DirectoryOut$FileOut ...\n";
+open my $OUT, ">", $DirectoryOut . $FileOut or die "could not write to $DirectoryOut/$FileOut\n";
+if ($FileType eq "V")
+{
+	print $OUT "variantId\t";
+} # first col header for var file
+else
+{
+	$ColHeader =~ s/\tcall\t/\talleleSeq\t/;
+	print $OUT "index\t";
+} # first col header for gene file
+print $OUT "$ColHeader\n"; # remainder of col header
+
+$RecCount = 0; # reuse total count for nr of non-reduntant vars
+$FileCount--; # reduce by one, used below to add missing delimiters
+foreach my $Chr (@ChrNames) # sort records in each chr array and print with count
+{
+	foreach my $Rec (sort {SortStringsasArrays ($a, $b)} keys %{$Vars{$Chr}}) # using sub to sort on being, end fields
+	{
+		next unless $Rec;
+		$RecCount++; # increment count of coding/splicing/spanning vars
+		print $OUT "$RecCount\t$Rec"; # printing rec and count
+		print $OUT "\t",$Vars{$Chr}->{$Rec}->[4] if $FileType eq "V"; # print xref if var files
+
+		if ($VarExtras)
+		{
+			my $FieldDelimiterCount = () = $Vars{$Chr}->{$Rec}->[3] =~ /:/g;
+			#print "$SpacerCount $Vars{$Chr}->{$Rec}->[1]\n";
+			#exit if $TmpCount++ > 10;
+			my $Addition = ":" x ($FileCount - $FieldDelimiterCount);
+			if ($Version == 2)
+			{
+				print $OUT "\t",$Vars{$Chr}->{$Rec}->[1],$Addition if $KeepScoresVAF;
+				print $OUT "\t",$Vars{$Chr}->{$Rec}->[2],$Addition if $KeepScoresEAF;
+				print $OUT "\t",$Vars{$Chr}->{$Rec}->[3],$Addition if $KeepQuals;
+			}
+			else
+			{
+				print $OUT "\t",$Vars{$Chr}->{$Rec}->[1],$Addition if $KeepScores;
+			}
+			#print $OUT "$Rec\t$Vars{$Chr}->{$Rec}\n"; # printing rec and count
+		}
+		print $OUT "\n";
+	}
+}
+print "Nr saved records:\t $RecCount\n"; # count of non-redundant vars, c/f all vars abovve
+
+
+###########################################################################
+#                                   SUBS                                  #
+###########################################################################
+
+sub GetExpectedParams
+{
+	my %Hash = # hash to store expected params
+	(
+		"file_type" => -1,
+		"input_file" => [],
+		"output_file" => -1,
+		"var_type" => "all",
+		"component" => "ALL",
+		"impact" => "ALL",
+		"scores" => "yes",
+		"scores_eaf" => "yes",
+		"scores_vaf" => "yes",
+		"score_quality" => "yes",
+	);
+	$NrParams = int keys %Hash;
+	return %Hash;
+}
+
+sub GetEnteredParams
+{
+	# Processing @ARGV
+	my %Hash;
+	my @ARGVs = split /--/, join (" ",@ARGV); # split args on --, into array
+	for my $n (1..$#ARGVs) # parse each [nb arg 0 is empty so ignored]
+	{
+		$ARGVs[$n] =~ s/\s+$//; # remove any trailing spaces
+		my ($Key, $Val) = split / /, $ARGVs[$n], 2; # put first element into key, any other elements into val
+		$Key = lc $Key; # make lower case, ie case insensitive
+		if ($Key eq "input_file") # multiple entries expected, setting up array
+		{
+			push @{$Hash{$Key}}, $Val; # add input to input hash
+
+		}
+		else
+		{
+			$Hash{$Key} = $Val; # make a hash entry out of key and val
+		}
+	}
+	return %Hash; # hash now has each --entry param, with associated values
+}
+
+sub OpenFile
+{
+    my $File = shift;
+    my $FH;
+		open $FH, $File;
+		return $FH;
+}
+
+sub OpenFileold
+{
+    my $File = shift;
+    my $FH;
+
+    if ($File =~ /.bz2$/)
+    {
+			open ($FH, "bzcat $File |") or die ("$!: can't open file $File");
+    }
+		elsif ($File =~ /.gz$/)
+    {
+			open ($FH, "gunzip -c $File |") or die ("$!: can't open file $File");
+    }
+    elsif ($File =~ /.tsv$/ or $File =~ /.txt$/)
+    {
+			open ($FH, "cat $File |") or die ("$!: can't open file $File");
+    }
+    else
+    {
+			print ("Do not recognise file type for file $File.\nOpening as text file\n");
+			open ($FH, "cat $File |") or die ("$!: can't open file $File");
+    }
+    return $FH;
+}
+
+sub GetHeaderAsString
+{
+    my $FH = shift;
+    my $Header = "";
+    my $Count = 0;
+    while (<$FH>) # loop until a line is empty
+    {
+			chomp;
+			if ($_ eq "") # exit when empty line
+			{
+				return $Header ; # return ref to array
+			}
+			else
+			{
+				$Header .= $_;
+			}
+			return "" if $Count++ > 50; # too many lines for a header, must be no header, return empty array
+    }
+}
+
+sub GetVersion
+{
+	my $Header = shift;
+	my $ColHeader = shift;
+
+	my $Version = 0; # need to know if it is 1.x or 2.x
+	my $XrefField = -1;
+
+	if ($FileType eq "V")
+	{
+		if ($Header)
+		{
+			$Header =~ /#FORMAT_VERSION\t(\d)/;
+			if ($1 == 1) {$Version = 1; $XrefField = 11;}
+			elsif ($1 == 2) {$Version = 2; $XrefField = 13;}
+			else {print "Warning: Format Version not found in Header\n";} # not in header
+		}
+		unless ($Version)
+		{
+			my @ColHeader = split /\t/, $ColHeader;
+			for my $n (0..int(@ColHeader)-1)
+			{
+				if ($ColHeader eq "xRef")
+				{
+					$XrefField = $n;
+					if ($n == 11) 	 {$Version = 1;}
+					elsif ($n == 13) {$Version = 2;}
+					last;
+				}
+			}
+		}
+	}
+	return ($Version, $XrefField);
+}
+
+sub ExtractGeneFields # expects a gene file rec, strips out file specific fields, gets chr
+{
+	my $Rec = shift;
+	# gene fields
+	# >index locus allele chromosome begin end varType reference call xRef geneId mrnaAcc
+	# proteinAcc symbol orientation component componentIndex hasCodingRegion impact
+	# nucleotidePos proteinPos annotationRefSequence sampleSequence genomeRefSequence pfam
+
+	chomp $Rec; # remove return
+	my @Fields = split "\t", $Rec;
+	#print "$Fields[6] $Fields[15] $Fields[18]\t$OutputVarTypes $OutputComponents $OutputImpacts\n";
+	unless ($OutputVarTypes eq "all" or $Fields[6] =~ /$OutputVarTypes/) {return ("","");} # nominated vals not found, leave
+	unless ($OutputComponents eq "ALL" or $Fields[15] =~ /$OutputComponents/) {return ("","");} # nominated vals not found, leave
+	unless ($OutputImpacts eq "ALL" or $Fields[18] =~ /$OutputImpacts/) {return ("","");} # nominated vals not found, leave
+	my $Chr = $Fields[3]; # assign chr
+	$Rec = join("\t",@Fields[3..24]);
+	#$Rec =~ s/\t$//; # remove trailing tab if there is one
+
+	return ($Rec, $Chr);
+}
+
+sub ExtractVarFields # expects a gene file rec, strips out file specific fields, gets chr
+{
+	my $Rec = shift;
+	my $XrefField = shift;
+	# var fields
+	# 1.x locus ploidy haplotype chromosome begin end varType reference alleleSeq totalScore hapLink xRef
+	# 2.0 locus ploidy allele chromosome begin end varType reference alleleSeq varScoreVAF varScoreEAF varQuality hapLink xRef
+
+	chomp $Rec; # remove return
+	my @Fields = split "\t", $Rec;
+	#print "$Fields[6] $OutputVarTypes \n"; exit;
+	unless ($OutputVarTypes eq "all" or $Fields[6] =~ /$OutputVarTypes/) {return ("","");} # nominated vals not found, leave
+	my $Chr = $Fields[3]; # assign chr
+	#$Rec = join("\t",@Fields[3..8]);
+	$Rec = join("\t",@Fields[3..8]);
+	#$Rec =~ s/\t$//; # remove trailing tab if there is one
+
+	if ($VarExtras)
+	{
+		return ($Rec, $Chr, $Fields[9], $Fields[10], $Fields[11], $Fields[$XrefField]) if $Version == 2;
+		return ($Rec, $Chr, $Fields[9], $Fields[$XrefField]) # $Version == 1;
+	}
+	else
+	{
+		return ($Rec, $Chr);
+	}
+}
+
+sub AddVarRec
+{
+	my $Rec = shift;
+	my $RecHash = shift;
+	my $ScoreVAF = shift;
+	my $ScoreEAF = shift;
+	my $ScoreQual = shift;
+	my $FileCount = shift;
+	my $XRef = shift;
+
+	if ($VarExtras) # need to extract scores information
+	{
+		# locus ploidy allele chromosome begin end varType reference alleleSeq varScoreVAF varScoreEAF varQuality hapLink xRef
+		# Set delimiter
+		my $Delimiter;
+		if ($RecHash->{$Rec}) # hash entry for this var already exists
+		{
+			if ($RecHash->{$Rec}->[0] == $FileCount)
+			{
+				$Delimiter = "|"; # same chr, var is hom, use |
+			}
+			else # diff chr, use :
+			{
+				my $FieldDelimiterCount = () = $RecHash->{$Rec}->[3] =~ /:/g; # count nr field delims
+				$Delimiter = ":" x ($FileCount - $FieldDelimiterCount - 1); # delimiters for any processed files, that didnt have this var
+			}
+			$RecHash->{$Rec}->[4] = $XRef if length $XRef > length $RecHash->{$Rec}->[4]; # replace xref if new xref is longer
+		}
+		else  # new var
+		{
+			$RecHash->{$Rec} = []; # create array to hold it
+			$Delimiter = ":" x ($FileCount - 1); # delimiters for prev processed files, that didnt have this var
+			$RecHash->{$Rec}->[4] = $XRef; # add xref
+		}
+
+		# Process var
+		$RecHash->{$Rec}->[0] = $FileCount;
+		if ($Version == 2)
+		{
+			$RecHash->{$Rec}->[1] .= $Delimiter.$ScoreVAF; # add delimiter, varScoreVAF
+			$RecHash->{$Rec}->[2] .= $Delimiter.$ScoreEAF; # add delimiter, varScoreVAF
+			$RecHash->{$Rec}->[3] .= $Delimiter.($ScoreQual eq "VQHIGH" ? "H" : "L"); # add delimiter, qual
+		}
+		else
+		{
+			$RecHash->{$Rec}->[1] .= $Delimiter.$ScoreVAF; # add delimiter, totalScore
+		}
+
+	}
+	else # just the rec, no var extras being extrcted
+	{
+		$RecHash->{$Rec}++; # hash with rec as key, increment count for this key
+		$RecHash->{$Rec}->[4] = $XRef if length $XRef > length $RecHash->{$Rec}->[4]; # replace xref if new xref is longer, wasting space here
+	}
+}
+
+sub AddGeneRec
+{
+	my $Rec = shift;
+	my $RecHash = shift;
+
+		$RecHash->{$Rec}++; # hash with rec as key, increment count for this key
+}
+
+sub SortStringsasArrays # sorts based on begin and end of two recs
+{
+	my $String1 = shift; # first string
+	my $String2 = shift; # second string
+
+	my @Array1 = split "\t", $String1; # put fields into array
+	my @Array2 = split "\t", $String2;
+
+	# array[1] is begin, array[2] is end, returning order based on these fields
+	if ($Array1[1] < $Array2[1]) # begin of 1 < begin of 2
+	{
+		return -1;
+	}
+	elsif ($Array1[1] == $Array2[1]) # begin of 1 == begin of 2
+	{
+		if ($Array1[2] < $Array2[2]) # end of 1 < end of 2
+		{
+			return -1;
+		}
+		elsif ($Array1[2] == $Array2[2]) # end of 1 == end of 2
+		{
+			return 0;
+		}
+		else # end of 1 > end of 2
+		{
+			return 1;
+		}
+	}
+	else # begin of 1 > begin of 2
+	{
+		return 1;
+	}
+
+}