diff CG_cgatools/tools/cgatools/snpdiff.xml @ 0:ffb2b0244ab2 draft

Uploaded

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/CG_cgatools/tools/cgatools/snpdiff.xml	Tue Jun 12 11:54:38 2012 -0400
@@ -0,0 +1,116 @@
+<tool id="cga_snpdiff" name="snpdiff" version="0.0.1">
+
+  <description>compares snp calls to a Complete Genomics variant file.</description> <!--adds description in toolbar-->
+
+  <requirements>
+  	<requirement type="binary">cgatools</requirement>
+  </requirements>
+
+  <command> <!--run executable-->
+  	cgatools snpdiff --beta -h
+  </command>
+
+  <outputs>
+  	<data format="tabular" name="output" />
+  </outputs>
+  
+  <inputs>
+  </inputs>
+
+  <help>
+  
+**What it does**
+
+This tool ompares snp calls to a Complete Genomics variant file.
+
+cgatools: http://sourceforge.net/projects/cgatools/files/
+
+-----
+
+**cgatools Manual**::
+
+		COMMAND NAME
+		  snpdiff - Compares snp calls to a Complete Genomics variant file.
+		
+		DESCRIPTION
+		  Compares the snp calls in the "genotypes" file to the calls in a Complete 
+		  Genomics variant file. The genotypes file is a tab-delimited file with at 
+		  least the following columns (additional columns may be given):
+				
+		    Chromosome      (Required) The name of the chromosome.
+		    Offset0Based    (Required) The 0-based offset in the chromosome.
+		    GenotypesStrand (Optional) The strand of the calls in the Genotypes 
+		                    column (+ or -, defaults to +).
+		    Genotypes       (Optional) The calls, one per allele. The following 
+		                    calls are recognized:
+		                    A,C,G,T A called base.
+		                    N       A no-call.
+		                    -       A deleted base.
+		                    .       A non-snp variation.
+				
+		  The output is a tab-delimited file consisting of the columns of the 
+		  original genotypes file, plus the following additional columns:
+				
+		    Reference         The reference base at the given position.
+		    VariantFile       The calls made by the variant file, one per allele. 
+		                      The character codes are the same as is described for 
+		                      the Genotypes column.
+		    DiscordantAlleles (Only if Genotypes is present) The number of 
+		                      Genotypes alleles that are discordant with calls in 
+		                      the VariantFile. If the VariantFile is described as 
+		                      haploid at the given position but the Genotypes is 
+		                      diploid, then each genotype allele is compared 
+		                      against the haploid call of the VariantFile.
+		    NoCallAlleles     (Only if Genotypes is present) The number of 
+		                      Genotypes alleles that were no-called by the 
+		                      VariantFile. If the VariantFile is described as 
+		                      haploid at the given position but the Genotypes is 
+		                      diploid, then a VariantFile no-call is counted twice.
+				
+		  The verbose output is a tab-delimited file consisting of the columns of the
+		  original genotypes file, plus the following additional columns:
+				
+		    Reference   The reference base at the given position.
+		    VariantFile The call made by the variant file for one allele (there is 
+		                a line in this file for each allele). The character codes 
+		                are the same as is described for the Genotypes column.
+		    [CALLS]     The rest of the columns are pasted in from the VariantFile,
+		                describing the variant file line used to make the call.
+				
+		  The stats output is a comma-separated file with several tables describing 
+		  the results of the snp comparison, for each diploid genotype. The tables 
+		  all describe the comparison result (column headers) versus the genotype 
+		  classification (row labels) in different ways. The "Locus classification" 
+		  tables have the most detailed match classifications, while the "Locus 
+		  concordance" tables roll these match classifications up into "discordance" 
+		  and "no-call". A locus is considered discordant if it is discordant for 
+		  either allele. A locus is considered no-call if it is concordant for both 
+		  alleles but has a no-call on either allele. The "Allele concordance" 
+		  describes the comparison result on a per-allele basis.
+		
+		OPTIONS
+		  -h [ --help ] 
+		      Print this help message.
+		
+		  --reference arg
+		      The input crr file.
+		
+		  --variants arg
+		      The input variant file.
+		
+		  --genotypes arg
+		      The input genotypes file.
+		
+		  --output-prefix arg
+		      The path prefix for all output reports.
+		
+		  --reports arg (=Output,Verbose,Stats)
+		      Comma-separated list of reports to generate. A report is one of:
+		        Output  The output genotypes file.
+		        Verbose The verbose output file.
+		        Stats   The stats output file.
+						
+		SUPPORTED FORMAT_VERSION
+		  0.3 or later
+  </help>
+</tool>