annotate testing_cgatools-982e19c29ec0/cgatools/tools/cgatools_1.6/snpdiff.xml @ 0:ef23f9cd599b draft default tip

Uploaded
author devteam
date Thu, 27 Sep 2012 13:37:59 -0400
parents
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
1 <tool id="cg_snpdiff" name="snpdiff 1.6" version="1.0.1">
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
2 <!--
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
3 This tool creates a GUI for the snpdiff function of cgatools from Complete Genomics, Inc.
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
4 written 6-18-2012 by bcrain@completegenomics.com
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
5 updated 8-13-2012 by bcrain@completegenomics.com
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
6 -->
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
7
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
8 <description>compares snp calls to var or masterVar file.</description> <!--adds description in toolbar-->
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
9
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
10 <command> <!--run executable-->
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
11 <!-- print version of cgatools to STDOUT-->
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
12 cgatools | head -1;
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
13
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
14 <!-- print command lines to STDOUT-->
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
15 echo "cgatools snpdiff
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
16 --reference $crr.fields.path
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
17 --variants $data_sources.varfile
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
18 --genotypes $genotype
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
19 --output-prefix cg_
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
20 --reports `echo ${report1} ${report2} ${report3} | sed 's/ */,/g'`
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
21 ";
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
22
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
23 <!-- execute cgatools-->
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
24 cgatools snpdiff
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
25 --reference $crr.fields.path
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
26 --variants $data_sources.varfile
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
27 --genotypes $genotype
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
28 --output-prefix cg_
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
29 --reports `echo ${report1} ${report2} ${report3} | sed 's/ */,/g'`
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
30
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
31 </command>
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
32
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
33 <outputs>
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
34 <data format="tabular" name="output1" from_work_dir="cg_Output.tsv" label="${tool.name} Output">
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
35 <filter>(report1 == 'Output')</filter>
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
36 </data>
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
37 <data format="tabular" name="output2" from_work_dir="cg_Verbose.tsv" label="${tool.name} Verbose">
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
38 <filter>(report2 == 'Verbose')</filter>
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
39 </data>
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
40 <data format="tabular" name="output3" from_work_dir="cg_Stats.tsv" label="${tool.name} Stats">
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
41 <filter>(report3 == 'Stats')</filter>
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
42 </data>
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
43 </outputs>
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
44
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
45 <inputs>
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
46 <!--form field to select crr file-->
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
47 <param name="crr" type="select" label="Reference genome (.crr file)">
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
48 <options from_data_table="cg_crr_files" />
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
49 </param>
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
50
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
51 <!--conditional to select data in/outside galaxy-->
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
52 <conditional name="data_sources">
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
53 <param name="data_source" type="select" label="Where is the input var or masterVar file?">
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
54 <option value="in" selected="true">imported into Galaxy</option>
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
55 <option value="out">located outside Galaxy (data on server or mounted drive)</option>
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
56 </param>
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
57
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
58 <!--form field to select input file-->
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
59 <when value="in">
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
60 <param name="varfile" type="data" format="cg_var,cg_mastervar" label="Var or masterVar file">
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
61 <validator type="dataset_ok_validator" />
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
62 <validator type="dataset_metadata_in_file" filename="cg_crr_files.loc"
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
63 metadata_name="dbkey" metadata_column="1"
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
64 message="cgatools is not currently available for this build."/>
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
65 </param>
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
66 </when>
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
67
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
68 <!--form field to enter input file-->
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
69 <when value="out">
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
70 <param name="varfile" type="text" label="Var or masterVar file (/path/file)" size="40" help="Var or masterVar file can be compressed (gz, bz2), e.g. /harddrive/GS00000XXXX-DID/GS00000YYYY-ASM/GS00123-DNA_G01_2000/ASM/var-GS00000YYYY-ASM.tsv.bz2">
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
71 <validator type="empty_field" message="You must supply a var or masterVar file"/>
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
72 </param>
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
73 </when>
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
74 </conditional>
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
75
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
76 <!--param to select genotypes file input-->
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
77 <param name="genotype" type="data" format="tabular" label="Genotypes file with SNP calls" help="The genotypes file is a tab-delimited file with at least the following columns: Chromosome, Offset0Based, Genotypes (Optional)">
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
78 <validator type="dataset_ok_validator" />
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
79 <validator type="dataset_metadata_in_file" filename="cg_crr_files.loc"
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
80 metadata_name="dbkey" metadata_column="1"
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
81 message="cgatools is not currently available for this build."/>
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
82 <!--<validator type="expression" message="Dataset does not match selected build.">value.dbkey == $crr.fields.dbkey</validator>-->
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
83 </param>
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
84
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
85 <!--params to select reports-->
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
86 <param name="report1" type="select" label="Create report Output">
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
87 <option value="">no</option>
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
88 <option value="Output" selected="true">yes</option>
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
89 </param>
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
90 <param name="report2" type="select" label="Create report Verbose">
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
91 <option value="">no</option>
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
92 <option value="Verbose">yes</option>
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
93 </param>
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
94 <param name="report3" type="select" label="Create report Stats">
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
95 <option value="">no</option>
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
96 <option value="Stats">yes</option>
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
97 </param>
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
98 </inputs>
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
99
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
100 <help>
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
101
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
102 **What it does**
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
103
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
104 This tool ompares snp calls to a Complete Genomics variant file.
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
105
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
106 **cgatools 1.6.0 Documentation**
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
107
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
108 Userguide: http://cgatools.sourceforge.net/docs/1.6.0/cgatools-user-guide.pdf
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
109
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
110 Release notes: http://cgatools.sourceforge.net/docs/1.6.0/cgatools-release-notes.pdf
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
111
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
112 **Command line reference**::
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
113
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
114 COMMAND NAME
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
115 snpdiff - Compares snp calls to a Complete Genomics variant file.
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
116
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
117 DESCRIPTION
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
118 Compares the snp calls in the "genotypes" file to the calls in a Complete
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
119 Genomics variant file. The genotypes file is a tab-delimited file with at
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
120 least the following columns (additional columns may be given):
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
121
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
122 Chromosome (Required) The name of the chromosome.
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
123 Offset0Based (Required) The 0-based offset in the chromosome.
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
124 GenotypesStrand (Optional) The strand of the calls in the Genotypes
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
125 column (+ or -, defaults to +).
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
126 Genotypes (Optional) The calls, one per allele. The following
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
127 calls are recognized:
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
128 A,C,G,T A called base.
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
129 N A no-call.
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
130 - A deleted base.
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
131 . A non-snp variation.
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
132
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
133 The output is a tab-delimited file consisting of the columns of the
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
134 original genotypes file, plus the following additional columns:
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
135
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
136 Reference The reference base at the given position.
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
137 VariantFile The calls made by the variant file, one per allele.
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
138 The character codes are the same as is described for
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
139 the Genotypes column.
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
140 DiscordantAlleles (Only if Genotypes is present) The number of
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
141 Genotypes alleles that are discordant with calls in
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
142 the VariantFile. If the VariantFile is described as
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
143 haploid at the given position but the Genotypes is
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
144 diploid, then each genotype allele is compared
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
145 against the haploid call of the VariantFile.
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
146 NoCallAlleles (Only if Genotypes is present) The number of
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
147 Genotypes alleles that were no-called by the
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
148 VariantFile. If the VariantFile is described as
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
149 haploid at the given position but the Genotypes is
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
150 diploid, then a VariantFile no-call is counted twice.
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
151
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
152 The verbose output is a tab-delimited file consisting of the columns of the
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
153 original genotypes file, plus the following additional columns:
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
154
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
155 Reference The reference base at the given position.
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
156 VariantFile The call made by the variant file for one allele (there is
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
157 a line in this file for each allele). The character codes
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
158 are the same as is described for the Genotypes column.
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
159 [CALLS] The rest of the columns are pasted in from the VariantFile,
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
160 describing the variant file line used to make the call.
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
161
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
162 The stats output is a comma-separated file with several tables describing
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
163 the results of the snp comparison, for each diploid genotype. The tables
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
164 all describe the comparison result (column headers) versus the genotype
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
165 classification (row labels) in different ways. The "Locus classification"
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
166 tables have the most detailed match classifications, while the "Locus
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
167 concordance" tables roll these match classifications up into "discordance"
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
168 and "no-call". A locus is considered discordant if it is discordant for
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
169 either allele. A locus is considered no-call if it is concordant for both
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
170 alleles but has a no-call on either allele. The "Allele concordance"
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
171 describes the comparison result on a per-allele basis.
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
172
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
173 OPTIONS
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
174 -h [ --help ]
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
175 Print this help message.
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
176
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
177 --reference arg
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
178 The input crr file.
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
179
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
180 --variants arg
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
181 The input variant file.
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
182
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
183 --genotypes arg
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
184 The input genotypes file.
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
185
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
186 --output-prefix arg
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
187 The path prefix for all output reports.
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
188
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
189 --reports arg (=Output,Verbose,Stats)
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
190 Comma-separated list of reports to generate. A report is one of:
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
191 Output The output genotypes file.
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
192 Verbose The verbose output file.
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
193 Stats The stats output file.
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
194
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
195 SUPPORTED FORMAT_VERSION
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
196 0.3 or later
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
197 </help>
ef23f9cd599b Uploaded
devteam
parents:
diff changeset
198 </tool>