Mercurial > repos > rnateam > mirdeep2_mapper

comparison mapper.xml @ 3:79fdac89dd6e draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/mirdeep2/mirdeep2_mapper commit 04c75332ac618b43ce5c3f307f7866e97147e865
author rnateam
date Thu, 05 Apr 2018 08:54:49 -0400
parents f844a9c1698d
children
comparison
equal deleted inserted replaced
2:f844a9c1698d 3:79fdac89dd6e
1 <tool id="rbc_mirdeep2_mapper" name="MiRDeep2 Mapper" version="2.0.0"> 1 <tool id="rbc_mirdeep2_mapper" name="MiRDeep2 Mapper" version="2.0.0.8.1">
2 <description>process and map reads to a reference genome</description>
2 <macros> 3 <macros>
3 <macro name="map_params"> 4 <macro name="map_params">
4 <conditional name="refGenomeSource"> 5 <conditional name="refGenomeSource">
5 <param name="genomeSource" type="select" label="Will you select a reference genome from your history or use a built-in index?" help="Map to genome. (-p)"> 6 <param name="genomeSource" type="select" label="Will you select a reference genome from your history or use a built-in index?" help="Map to genome. (-p)">
6 <option value="indexed">Use a built-in index</option> 7 <option value="indexed">Use a built-in index</option>
13 <validator type="no_options" message="No indexes are available for the selected input dataset"/> 14 <validator type="no_options" message="No indexes are available for the selected input dataset"/>
14 </options> 15 </options>
15 </param> 16 </param>
16 </when> <!-- build-in --> 17 </when> <!-- build-in -->
17 <when value="history"> 18 <when value="history">
18 <param name="ownFile" type="data" format="fasta" metadata_name="dbkey" label="Select the reference genome" /> 19 <param name="ownFile" type="data" format="fasta" label="Select the reference genome" />
19 </when> <!-- history --> 20 </when> <!-- history -->
20 </conditional> <!-- refGenomeSource --> 21 </conditional> <!-- refGenomeSource -->
21 <param name="map_mismatch" type="boolean" truevalue="-q" falsevalue="" checked="false" label="Map with one mismatch in the seed (mapping takes longer)" help="(-q)"/> 22 <param name="map_mismatch" type="boolean" truevalue="-q" falsevalue="" checked="false" label="Map with one mismatch in the seed (mapping takes longer)" help="(-q)"/>
22 <param name="map_threshold" value="5" type="integer" optional="false" label="A read is allowed to map up to this number of positions in the genome" help="Map threshold. (-r)"> 23 <param name="map_threshold" value="5" type="integer" optional="false" label="A read is allowed to map up to this number of positions in the genome" help="Map threshold. (-r)">
23 <validator type="in_range" min="1" message="Minimum value is 1"/> 24 <validator type="in_range" min="1" message="Minimum value is 1"/>
24 </param> 25 </param>
25 </macro> 26 </macro>
26 </macros> 27 </macros>
27 <description> 28 <requirements>
29 <requirement type="package" version="2.0.0.8">mirdeep2</requirement>
30 </requirements>
31 <command detect_errors="aggressive">
28 <![CDATA[ 32 <![CDATA[
29 process and map reads to a reference genome
30 ]]>
31 </description>
32 <requirements>
33 <requirement type="package" version="2.0">mirdeep2_mapper</requirement>
34 <requirement type="package" version="0.12.7">bowtie</requirement>
35 <requirement type="package" version="5.18.1">perl</requirement>
36 </requirements>
37
38 <command>
39 <![CDATA[
40
41 #if $operation.collapse_map == "collapse_and_map" or $operation.collapse_map == "only_map" 33 #if $operation.collapse_map == "collapse_and_map" or $operation.collapse_map == "only_map"
42 #if $operation.refGenomeSource.genomeSource == "history" 34 #if $operation.refGenomeSource.genomeSource == "history"
43 bowtie-build '$operation.refGenomeSource.ownFile' custom_bowtie_indices && 35 bowtie-build '$operation.refGenomeSource.ownFile' custom_bowtie_indices &&
44 #end if 36 #end if
45 #end if 37 #end if
46 38
47 mapper.pl 39 mapper.pl
48 40
49 '$reads' 41 #if $input.type == "single":
50 42 '$input.reads'
51 #if $reads.extension.startswith("fasta") 43
52 -c 44 #if $input.reads.extension.startswith("fasta")
53 #else if $reads.extension.startswith("fastq") 45 -c
54 -e 46 #else if $input.reads.extension.startswith("fastq")
55 -h 47 -e
48 -h
49 #end if
50 #else:
51 '$samples' -d
52
53 #if $input.reads_list[0].reads.extension.startswith("fasta")
54 -c
55 #else if $input.reads_list[0].reads.extension.startswith("fastq")
56 -e
57 -h
58 #end if
56 #end if 59 #end if
57 60
58 $remove_non_canon 61 $remove_non_canon
59 62
60 $convert_rna_dna 63 $convert_rna_dna
61 64
62 #if $clip_adapter.clip == "true" 65 #if $clip_adapter.clip == "true"
63 -k $clip_adapter.adapter_seq 66 -k $clip_adapter.adapter_seq
64 #end if 67 #end if
66 -l $discard_short_reads 69 -l $discard_short_reads
67 70
68 #if $operation.collapse_map == "collapse_and_map" or $operation.collapse_map == "only_collapse" 71 #if $operation.collapse_map == "collapse_and_map" or $operation.collapse_map == "only_collapse"
69 -m -s '$output_reads_collapsed' 72 -m -s '$output_reads_collapsed'
70 #end if 73 #end if
71 74
72 #if $operation.collapse_map == "collapse_and_map" or $operation.collapse_map == "only_map" 75 #if $operation.collapse_map == "collapse_and_map" or $operation.collapse_map == "only_map"
73 -p 76 -p
74 77
75 #if $operation.refGenomeSource.genomeSource == "history" 78 #if $operation.refGenomeSource.genomeSource == "history"
76 custom_bowtie_indices 79 custom_bowtie_indices
77 #else 80 #else
78 '$operation.refGenomeSource.index.fields.path' 81 '$operation.refGenomeSource.index.fields.path'
79 #end if 82 #end if
80 $operation.map_mismatch 83 $operation.map_mismatch
81 -r $operation.map_threshold 84 -r $operation.map_threshold
82 85
83 -t '$output_mapping' 86 -t '$output_mapping'
84 #end if 87 #end if
85 88
86 -v -n 89 -v -n
87 ]]> 90 ]]>
88 </command> 91 </command>
89 <stdio> 92 <configfiles>
90 <!-- Anything other than zero is an error --> 93 <configfile name="samples"><![CDATA[#if $input.type == "multiple":
91 <exit_code range="1:" /> 94 #for $r in $input.reads_list:
92 <exit_code range=":-1" /> 95 $r.reads $r.sample_name
93 <!-- In case the return code has not been set propery check stderr too --> 96 #end for
94 <regex match="Error:" /> 97 #end if]]></configfile>
95 <regex match="Exception:" /> 98 </configfiles>
96 </stdio>
97 <inputs> 99 <inputs>
98 <param format="fastq, fasta" name="reads" type="data" optional="false" label="Deep sequencing reads" help="Reads in fastq or FASTA format"/> 100 <conditional name="input">
101 <param name="type" type="select" label="Pool multiple read sets">
102 <option value="single" selected="true">No</option>
103 <option value="multiple">Yes</option>
104 </param>
105 <when value="single">
106 <param format="fastq,fasta" name="reads" type="data" label="Deep sequencing reads" help="Reads in fastq or FASTA format"/>
107 </when>
108 <when value="multiple">
109 <repeat name="reads_list" title="Reads">
110 <param name="sample_name" value="" type="text" label="Sample name" help="Must be a 3 letters/digits code">
111 <validator type="expression" message="The sample name must be a 3 letters/digits code">len(value) == 3 and value.isalnum()</validator>
112 </param>
113 <param format="fastq,fasta" name="reads" type="data" optional="false" label="Deep sequencing reads" help="Reads in fastq or FASTA format"/>
114 </repeat>
115 </when>
116 </conditional>
99 <param name="remove_non_canon" type="boolean" truevalue="-j" falsevalue="" checked="false" label="Remove reads with non-standard nucleotides" help="Remove all entries that have a sequence that contains letters other than a,c,g,t,u,n,A,C,G,T,U,N. (-j)"/> 117 <param name="remove_non_canon" type="boolean" truevalue="-j" falsevalue="" checked="false" label="Remove reads with non-standard nucleotides" help="Remove all entries that have a sequence that contains letters other than a,c,g,t,u,n,A,C,G,T,U,N. (-j)"/>
100 <param name="convert_rna_dna" type="boolean" truevalue="-i" falsevalue="" checked="false" label="Convert RNA to DNA alphabet (to map against genome)" help="(-i)"/> 118 <param name="convert_rna_dna" type="boolean" truevalue="-i" falsevalue="" checked="false" label="Convert RNA to DNA alphabet (to map against genome)" help="(-i)"/>
101 119
102 <conditional name="clip_adapter"> 120 <conditional name="clip_adapter">
103 <param name="clip" type="select" label="Clip 3' Adapter Sequence" help="(-k)"> 121 <param name="clip" type="select" label="Clip 3' Adapter Sequence" help="(-k)">
109 <validator type="regex" message="Adapter can ONLY contain a,c,g,t,u,n,A,C,G,T,U,N">^[ACGTUacgtu]+$</validator> 127 <validator type="regex" message="Adapter can ONLY contain a,c,g,t,u,n,A,C,G,T,U,N">^[ACGTUacgtu]+$</validator>
110 </param> 128 </param>
111 </when> 129 </when>
112 <when value="false"/> 130 <when value="false"/>
113 </conditional> 131 </conditional>
114 132
115 <param name="discard_short_reads" value="18" type="integer" optional="false" label="Discard reads shorter than this length" help="Set to 0 to keep all reads. (-l)"> 133 <param name="discard_short_reads" value="18" type="integer" optional="false" label="Discard reads shorter than this length" help="Set to 0 to keep all reads. (-l)">
116 <validator type="in_range" min="0" message="Minimum value is 0"/> 134 <validator type="in_range" min="0" message="Minimum value is 0"/>
117 </param> 135 </param>
118 136
119 <conditional name="operation"> 137 <conditional name="operation">
120 <param name="collapse_map" type="select" label="Collapse reads and/or Map" help="(-m) and/or (-p)"> 138 <param name="collapse_map" type="select" label="Collapse reads and/or Map" help="(-m) and/or (-p)">
121 <option value="collapse_and_map">Collapse reads and Map</option> 139 <option value="collapse_and_map">Collapse reads and Map</option>
122 <option value="only_map">Map</option> 140 <option value="only_map">Map</option>
123 <option value="only_collapse">Collapse</option> 141 <option value="only_collapse">Collapse</option>
149 </filter> 167 </filter>
150 </data> 168 </data>
151 </outputs> 169 </outputs>
152 <tests> 170 <tests>
153 <test> 171 <test>
154 <param name="reads" value="reads.fa"/> 172 <conditional name="input">
173 <param name="type" value="single"/>
174 <param name="reads" value="reads.fa"/>
175 </conditional>
155 <param name="remove_non_canon" value="True"/> 176 <param name="remove_non_canon" value="True"/>
156 <param name="clip" value="true"/> 177 <param name="clip" value="true"/>
157 <param name="adapter_seq" value="TCGTATGCCGTCTTCTGCTTGT"/> 178 <param name="adapter_seq" value="TCGTATGCCGTCTTCTGCTTGT"/>
158 <param name="discard_short_reads" value="18"/> 179 <param name="discard_short_reads" value="18"/>
159 <param name="collapse_map" value="collapse_and_map"/> 180 <param name="collapse_map" value="collapse_and_map"/>
176 <has_line_matching expression="^.*22\t1\t22\ttcaccgggagaaaaactggtgt\tchrII:11534525-11540624\t22\t3382\t3403.*$"/> 197 <has_line_matching expression="^.*22\t1\t22\ttcaccgggagaaaaactggtgt\tchrII:11534525-11540624\t22\t3382\t3403.*$"/>
177 <has_line_matching expression="^.*25\t1\t25\ttcaccgggtggaaactagcagtggc\tchrII:11534525-11540624\t25\t3060\t3084.*$"/> 198 <has_line_matching expression="^.*25\t1\t25\ttcaccgggtggaaactagcagtggc\tchrII:11534525-11540624\t25\t3060\t3084.*$"/>
178 </assert_contents> 199 </assert_contents>
179 </output> 200 </output>
180 </test> 201 </test>
202 <test>
203 <conditional name="input">
204 <param name="type" value="multiple"/>
205 <repeat name="reads_list">
206 <param name="sample_name" value="sa1"/>
207 <param name="reads" value="reads_sample1.fa"/>
208 </repeat>
209 <repeat name="reads_list">
210 <param name="sample_name" value="sa2"/>
211 <param name="reads" value="reads_sample2.fa"/>
212 </repeat>
213 </conditional>
214 <param name="remove_non_canon" value="True"/>
215 <param name="clip" value="true"/>
216 <param name="adapter_seq" value="TCGTATGCCGTCTTCTGCTTGT"/>
217 <param name="discard_short_reads" value="18"/>
218 <param name="collapse_map" value="collapse_and_map"/>
219 <param name="genomeSource" value="history"/>
220 <param name="ownFile" value="cel_cluster.fa"/>
221 <output name="output_reads_collapsed">
222 <assert_contents>
223 <has_text text=">sa1_220_x1"/>
224 <has_text text="TCACCGGGTGTACATCAGC"/>
225 <has_text text=">sa2_0_x250"/>
226 <has_text text="AATGACACTGGTTATCTTTTCCATCG"/>
227 </assert_contents>
228 </output>
229 <output name="output_mapping">
230 <assert_contents>
231 <has_line_matching expression="^.*22\t1\t22\ttcaccgggtggaaactagcagt\tchrII:11534525-11540624\t22\t3060\t3081.*$"/>
232 <has_line_matching expression="^.*21\t1\t21\ttcaccgggtggaaactagcag\tchrII:11534525-11540624\t21\t3060\t3080.*$"/>
233 <has_line_matching expression="^.*22\t1\t22\ttcaccgggtgtacatcagctaa\tchrII:11534525-11540624\t22\t3631\t3652.*$"/>
234 </assert_contents>
235 </output>
236 </test>
181 </tests> 237 </tests>
182 <help> 238 <help>
183 <![CDATA[ 239 <![CDATA[
184 **What it does** 240 **What it does**
185 241
186 The MiRDeep2 Mapper module is designed as a tool to process deep sequencing reads and/or map them to the reference genome. 242 The MiRDeep2 Mapper module is designed as a tool to process deep sequencing reads and/or map them to the reference genome.
187 The module works in sequence space, and can process or map data that is in sequence FASTA format. 243 The module works in sequence space, and can process or map data that is in sequence FASTA format.
188 A number of the functions of the mapper module are implemented specifically with Solexa/Illumina data in mind. 244 A number of the functions of the mapper module are implemented specifically with Solexa/Illumina data in mind.
189 245
190 **Input** 246 **Input**
191 247
192 Default input is a file in FASTA format, seq.txt or qseq.txt format. More input can be given depending on the options used. 248 Default input is a file in FASTA format, seq.txt or qseq.txt format. More input can be given depending on the options used.
193 249
194 **Output** 250 **Output**
195 251
196 The output depends on the options used. Either a FASTA file with processed reads or an arf file with with mapped reads, or both, are output. 252 The output depends on the options used. Either a FASTA file with processed reads or an arf file with with mapped reads, or both, are output.
197 253
198 Arf format: 254 Arf format:
199 Is a proprietary file format generated and processed by miRDeep2. It contains information of reads mapped to a reference genome. Each line in such a file contains 13 columns: 255 Is a proprietary file format generated and processed by miRDeep2. It contains information of reads mapped to a reference genome. Each line in such a file contains 13 columns:
200 256
201 1. read identifier 257 1. read identifier