|
8
|
1 <tool id="cga_snpdiff" name="snpdiff" version="0.0.1">
|
|
|
2
|
|
|
3 <description>compares snp calls to a Complete Genomics variant file.</description> <!--adds description in toolbar-->
|
|
|
4
|
|
|
5 <requirements>
|
|
|
6 <requirement type="binary">cgatools</requirement>
|
|
|
7 </requirements>
|
|
|
8
|
|
|
9 <command> <!--run executable-->
|
|
|
10 cgatools snpdiff
|
|
|
11 --reference $crr.fields.path
|
|
|
12 --variants $varfile
|
|
|
13 --genotypes $genotype
|
|
|
14 --output-prefix cg_
|
|
|
15 --reports `echo ${report1} ${report2} ${report3} | sed 's/ */,/g'`
|
|
|
16 </command>
|
|
|
17
|
|
|
18 <outputs>
|
|
|
19 <data format="tabular" name="output1" from_work_dir="cg_Output.tsv" label="${tool.name} on ${on_string}: Output">
|
|
|
20 <filter>(report1 == 'Output')</filter>
|
|
|
21 </data>
|
|
|
22 <data format="tabular" name="output2" from_work_dir="cg_Verbose.tsv" label="${tool.name} on ${on_string}: Verbose">
|
|
|
23 <filter>(report2 == 'Verbose')</filter>
|
|
|
24 </data>
|
|
|
25 <data format="tabular" name="output3" from_work_dir="cg_Stats.tsv" label="${tool.name} on ${on_string}: Stats">
|
|
|
26 <filter>(report3 == 'Stats')</filter>
|
|
|
27 </data>
|
|
|
28 </outputs>
|
|
|
29
|
|
|
30 <inputs>
|
|
|
31 <!--form field to select crr file-->
|
|
|
32 <param name="crr" type="select" label="Genome build">
|
|
|
33 <options from_data_table="cg_crr_files" />
|
|
|
34 </param>
|
|
|
35
|
|
|
36 <!--conditional to select variant file input-->
|
|
|
37 <conditional name="data_sources">
|
|
|
38 <param name="data_source" type="select" label="Where is the input varfile?">
|
|
|
39 <option value="in" selected="true">imported into Galaxy</option>
|
|
|
40 <option value="out">located outside Galaxy (available only for local Galaxy instances)</option>
|
|
|
41 </param>
|
|
|
42 <when value="in">
|
|
|
43 <!--form field to select variant files-->
|
|
|
44 <param name="varfile" type="data" format="cg_var" label="Var file">
|
|
|
45 <validator type="unspecified_build" />
|
|
|
46 <validator type="dataset_metadata_in_file" filename="cg_crr_files.loc"
|
|
|
47 metadata_name="dbkey" metadata_column="1"
|
|
|
48 message="cgatools is not currently available for this build."/>
|
|
|
49 </param>
|
|
|
50 </when>
|
|
|
51 <when value="out">
|
|
|
52 <!--form field to select crr file-->
|
|
|
53 <param name="varfile" type="text" label="Variant file (/path/file_name)" size="40" help="Variant file can be compressed (gz, bz2)."/>
|
|
|
54 </when>
|
|
|
55 </conditional>
|
|
|
56
|
|
|
57 <!--conditional to select genotypes file input-->
|
|
|
58 <param name="genotype" type="data" format="tabular" label="Genotypes file with SNP calls" help="The genotypes file is a tab-delimited file with at
|
|
|
59 least the following columns (additional columns may be given): Chromosome (Required), Offset0Based (Required), GenotypesStrand (Optional), Genotypes (Optional)">
|
|
|
60 <validator type="unspecified_build" />
|
|
|
61 <validator type="dataset_metadata_in_file" filename="cg_crr_files.loc"
|
|
|
62 metadata_name="dbkey" metadata_column="1"
|
|
|
63 message="cgatools is not currently available for this build."/>
|
|
|
64 </param>
|
|
|
65
|
|
|
66 <param name="report1" type="select" label="Report Output">
|
|
|
67 <option value="">no</option>
|
|
|
68 <option value="Output">yes</option>
|
|
|
69 </param>
|
|
|
70 <param name="report2" type="select" label="Report Verbose">
|
|
|
71 <option value="">no</option>
|
|
|
72 <option value="Verbose">yes</option>
|
|
|
73 </param>
|
|
|
74 <param name="report3" type="select" label="Report Stats">
|
|
|
75 <option value="">no</option>
|
|
|
76 <option value="Stats">yes</option>
|
|
|
77 </param>
|
|
|
78
|
|
|
79 </inputs>
|
|
|
80
|
|
|
81 <help>
|
|
|
82
|
|
|
83 **What it does**
|
|
|
84
|
|
|
85 This tool ompares snp calls to a Complete Genomics variant file.
|
|
|
86
|
|
|
87 cgatools: http://sourceforge.net/projects/cgatools/files/
|
|
|
88
|
|
|
89 -----
|
|
|
90
|
|
|
91 **cgatools Manual**::
|
|
|
92
|
|
|
93 COMMAND NAME
|
|
|
94 snpdiff - Compares snp calls to a Complete Genomics variant file.
|
|
|
95
|
|
|
96 DESCRIPTION
|
|
|
97 Compares the snp calls in the "genotypes" file to the calls in a Complete
|
|
|
98 Genomics variant file. The genotypes file is a tab-delimited file with at
|
|
|
99 least the following columns (additional columns may be given):
|
|
|
100
|
|
|
101 Chromosome (Required) The name of the chromosome.
|
|
|
102 Offset0Based (Required) The 0-based offset in the chromosome.
|
|
|
103 GenotypesStrand (Optional) The strand of the calls in the Genotypes
|
|
|
104 column (+ or -, defaults to +).
|
|
|
105 Genotypes (Optional) The calls, one per allele. The following
|
|
|
106 calls are recognized:
|
|
|
107 A,C,G,T A called base.
|
|
|
108 N A no-call.
|
|
|
109 - A deleted base.
|
|
|
110 . A non-snp variation.
|
|
|
111
|
|
|
112 The output is a tab-delimited file consisting of the columns of the
|
|
|
113 original genotypes file, plus the following additional columns:
|
|
|
114
|
|
|
115 Reference The reference base at the given position.
|
|
|
116 VariantFile The calls made by the variant file, one per allele.
|
|
|
117 The character codes are the same as is described for
|
|
|
118 the Genotypes column.
|
|
|
119 DiscordantAlleles (Only if Genotypes is present) The number of
|
|
|
120 Genotypes alleles that are discordant with calls in
|
|
|
121 the VariantFile. If the VariantFile is described as
|
|
|
122 haploid at the given position but the Genotypes is
|
|
|
123 diploid, then each genotype allele is compared
|
|
|
124 against the haploid call of the VariantFile.
|
|
|
125 NoCallAlleles (Only if Genotypes is present) The number of
|
|
|
126 Genotypes alleles that were no-called by the
|
|
|
127 VariantFile. If the VariantFile is described as
|
|
|
128 haploid at the given position but the Genotypes is
|
|
|
129 diploid, then a VariantFile no-call is counted twice.
|
|
|
130
|
|
|
131 The verbose output is a tab-delimited file consisting of the columns of the
|
|
|
132 original genotypes file, plus the following additional columns:
|
|
|
133
|
|
|
134 Reference The reference base at the given position.
|
|
|
135 VariantFile The call made by the variant file for one allele (there is
|
|
|
136 a line in this file for each allele). The character codes
|
|
|
137 are the same as is described for the Genotypes column.
|
|
|
138 [CALLS] The rest of the columns are pasted in from the VariantFile,
|
|
|
139 describing the variant file line used to make the call.
|
|
|
140
|
|
|
141 The stats output is a comma-separated file with several tables describing
|
|
|
142 the results of the snp comparison, for each diploid genotype. The tables
|
|
|
143 all describe the comparison result (column headers) versus the genotype
|
|
|
144 classification (row labels) in different ways. The "Locus classification"
|
|
|
145 tables have the most detailed match classifications, while the "Locus
|
|
|
146 concordance" tables roll these match classifications up into "discordance"
|
|
|
147 and "no-call". A locus is considered discordant if it is discordant for
|
|
|
148 either allele. A locus is considered no-call if it is concordant for both
|
|
|
149 alleles but has a no-call on either allele. The "Allele concordance"
|
|
|
150 describes the comparison result on a per-allele basis.
|
|
|
151
|
|
|
152 OPTIONS
|
|
|
153 -h [ --help ]
|
|
|
154 Print this help message.
|
|
|
155
|
|
|
156 --reference arg
|
|
|
157 The input crr file.
|
|
|
158
|
|
|
159 --variants arg
|
|
|
160 The input variant file.
|
|
|
161
|
|
|
162 --genotypes arg
|
|
|
163 The input genotypes file.
|
|
|
164
|
|
|
165 --output-prefix arg
|
|
|
166 The path prefix for all output reports.
|
|
|
167
|
|
|
168 --reports arg (=Output,Verbose,Stats)
|
|
|
169 Comma-separated list of reports to generate. A report is one of:
|
|
|
170 Output The output genotypes file.
|
|
|
171 Verbose The verbose output file.
|
|
|
172 Stats The stats output file.
|
|
|
173
|
|
|
174 SUPPORTED FORMAT_VERSION
|
|
|
175 0.3 or later
|
|
|
176 </help>
|
|
|
177 </tool>
|
