comparison stacks_refmap.xml @ 0:45385ba40a75 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/stacks2 commit b395fa36fa826e26085820ba3a9faacaeddcb460
author iuc
date Mon, 01 Jul 2019 11:03:22 -0400
parents
children 319b10947ec1
comparison
equal deleted inserted replaced
-1:000000000000 0:45385ba40a75
1 <tool id="stacks2_refmap" name="Stacks2: reference map" profile="@PROFILE@" version="@STACKS_VERSION@+galaxy@WRAPPER_VERSION@">
2 <description>the Stacks pipeline with a reference genome (ref_map.pl)</description>
3 <macros>
4 <import>macros.xml</import>
5 </macros>
6 <expand macro="requirements"/>
7 <expand macro="version_cmd"/>
8 <command detect_errors="aggressive"><![CDATA[
9 @FASTQ_INPUT_FUNCTIONS@
10 mkdir bam_inputs stacks_outputs&&
11 @BAM_INPUT@
12
13 ref_map.pl
14 --samples bam_inputs
15 #if str($popmap) != 'None':
16 --popmap '$popmap'
17 #end if
18 $paired_select
19 -o stacks_outputs
20 -T \${GALAXY_SLOTS:-1}
21 --var-alpha $model_options.var_alpha
22 --gt-alpha $model_options.gt_alpha
23
24 @EXTRACT_VCF@
25
26 #if $output_log
27 && mv stacks_outputs/ref_map.log $output_log
28 #end if
29 ]]></command>
30
31 <inputs>
32 <expand macro="bam_input_macro"/>
33 <param argument="--popmap" type="data" optional="true" format="tabular,txt" label="Population map" />
34 <param name="paired_select" type="select" label="Paired end options" help="select single/paired for single end data or to select advanced paired end options, --unpaired: treat reverse reads as if they were forward reads; --ignore-pe-reads: ignore paired-end reads even if present in the input">
35 <option value="" selected="true">single/paired</option>
36 <option value="--unpaired" selected="true">ignore read pairing (--unpaired)</option>
37 <option value="--ignore-pe-reads" selected="true">ignore paired-end reads (--ignore-pe-reads)</option>
38 </param>
39 <section name="model_options" title="Variant calling options (for gstacks)" expanded="true">
40 <expand macro="variant_calling_options_vg" varalpha_default="0.01"/>
41 </section>
42 <expand macro="in_log"/>
43 </inputs>
44 <outputs>
45 <expand macro="out_log"/> <!-- pipeline also writes other logs? .. could be a collection -->
46 <expand macro="gstacks_outputs_macro" tooladd="(gstacks)"/>
47 <expand macro="populations_output_light" tooladd="(populations)"/>
48 </outputs>
49
50 <tests>
51 <!-- bams as list -->
52 <test>
53 <param name="input_bam" ftype="bam" value="refmap/PopA_01.bam,refmap/PopA_02.bam"/>
54 <param name="popmap" ftype="tabular" value="denovo_map/popmap_cstacks.tsv" />
55 <param name="add_log" value="yes" />
56 <output ftype="txt" name="output_log"><assert_contents><has_text text="ref_map.pl is done." /></assert_contents></output>
57 <output_collection name="gstacks_out" type="list" count="2">
58 <element name="catalog.calls.vcf" file="refmap/catalog.calls.vcf" ftype="vcf" lines_diff="2"/>
59 <element name="catalog.fa.gz" file="refmap/catalog.fa.gz" ftype="fasta.gz" compare="sim_size"/>
60 </output_collection>
61 <output ftype="tabular" name="out_haplotypes" value="refmap/populations.haplotypes.tsv"/>
62 <output ftype="tabular" name="out_hapstats" value="refmap/populations.hapstats.tsv"/>
63 <output ftype="txt" name="out_populations_log_distribs" value="refmap/populations.log.distribs"/>
64 <output ftype="tabular" name="out_sumstats_sum" value="refmap/populations.sumstats_summary.tsv"/>
65 <output ftype="tabular" name="out_sumstats" value="refmap/populations.sumstats.tsv"/>
66 <output ftype="tabular" name="out_sql" value="refmap/populations.markers.tsv"/>
67 </test>
68 <test>
69 <param name="input_bam" ftype="bam" value="refmap/PopA_01.bam,refmap/PopA_02.bam"/>
70 <param name="popmap" ftype="tabular" value="denovo_map/popmap_cstacks.tsv" />
71 <param name="paired_select" value="--unpaired"/>
72 <param name="model_options|var_alpha" value="0.1" />
73 <param name="model_options|gt_alpha" value="0.1" />
74 <assert_command>
75 <has_text text="--unpaired" />
76 <has_text text="--var-alpha 0.1" />
77 <has_text text="--gt-alpha 0.1" />
78 </assert_command>
79 <param name="add_log" value="yes" />
80 <output ftype="txt" name="output_log"><assert_contents><has_text text="ref_map.pl is done." /></assert_contents></output>
81 <output_collection name="gstacks_out" type="list" count="2"/>
82 <output ftype="tabular" name="out_haplotypes"><assert_contents><has_text text="#"/></assert_contents></output>
83 <output ftype="tabular" name="out_hapstats"><assert_contents><has_text text="#"/></assert_contents></output>
84 <output ftype="txt" name="out_populations_log_distribs"><assert_contents><has_text text="#"/></assert_contents></output>
85 <output ftype="tabular" name="out_sumstats_sum"><assert_contents><has_text text="#"/></assert_contents></output>
86 <output ftype="tabular" name="out_sumstats"><assert_contents><has_text text="#"/></assert_contents></output>
87 <output ftype="tabular" name="out_sql"><assert_contents><has_text text="#"/></assert_contents></output>
88
89 </test>
90 </tests>
91
92 <help>
93 <![CDATA[
94 .. class:: infomark
95
96 **What it does**
97
98 This program expects data that have been aligned to a reference genome, and can accept data directly from Bowtie, or from any aligner that can produce SAM format. To avoid datasets names problems, we recommand the use of the *Map with BWA for STACKS tool*. This program will execute each of the Stacks components: first, running pstacks on each of the samples specified, building loci (based on the reference alignment) and calling SNPs in each. Second, cstacks will be run to create a catalog of all loci specified as 'parents' or 'samples' on the command line, again using alignment to match loci in the catalog. Finally, sstacks will be executed to match each sample against the catalog. The ref_map.pl program will also load the results of each stage of the analysis: individual loci, the catalog, and matches against the catalog into the database (although this can be disabled). After matching the program will build a database index to speed up access (index_radtags.pl) and enable web-based filtering.
99
100 --------
101
102 **Input files**
103
104 - SAM, BAM
105
106 - Population map::
107
108 indv_01 1
109 indv_02 1
110 indv_03 1
111 indv_04 2
112 indv_05 2
113 indv_06 2
114
115 **Output files**
116
117 - XXX.tags.tsv file:
118
119 See `Stacks output description <http://catchenlab.life.illinois.edu/stacks/manual/#files>`_
120
121 Notes: For the tags file, each stack will start in the file with a consensus sequence for the entire stack followed by the flags for that stack. Then, each individual read that was merged into that stack will follow. The next stack will start with another consensus sequence.
122
123
124 - XXX.snps.tsv file:
125
126 See `Stacks output description <http://catchenlab.life.illinois.edu/stacks/manual/#files>`_
127
128 Notes: If a stack has two SNPs called within it, then there will be two lines in this file listing each one.
129
130
131 - XXX.alleles.tsv file:
132
133 See `Stacks output description <http://catchenlab.life.illinois.edu/stacks/manual/#files>`_
134
135
136 - XXX.matches.tsv file:
137
138 See `Stacks output description <http://catchenlab.life.illinois.edu/stacks/manual/#files>`_
139
140 Notes: Each line in this file records a match between a catalog locus and a locus in an individual, for a particular haplotype. The Batch ID plus the Catalog ID together represent a unique locus in the entire population, while the Sample ID and the Stack ID together represent a unique locus in an individual sample.
141
142
143 - other files:
144
145 See `Stacks output description <http://catchenlab.life.illinois.edu/stacks/manual/#files>`_
146
147 @STACKS_INFOS@
148 ]]>
149 </help>
150 <expand macro="citation" />
151 </tool>