Mercurial > repos > rnateam > mirdeep2_mapper

comparison mapper.xml @ 4:dbbe92348c7a 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 08:55:27 -0400
parents a8d24f4b6d95
children
comparison
equal deleted inserted replaced
3:a8d24f4b6d95 4:dbbe92348c7a
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 <description>process and map reads to a reference genome</description>
3 <macros> 3 <macros>
4 <macro name="map_params"> 4 <macro name="map_params">
5 <conditional name="refGenomeSource"> 5 <conditional name="refGenomeSource">
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 <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)">
26 </macro> 26 </macro>
27 </macros> 27 </macros>
28 <requirements> 28 <requirements>
29 <requirement type="package" version="2.0.0.8">mirdeep2</requirement> 29 <requirement type="package" version="2.0.0.8">mirdeep2</requirement>
30 </requirements> 30 </requirements>
31 <stdio> 31 <command detect_errors="aggressive">
32 <!-- Anything other than zero is an error -->
33 <exit_code range="1:" />
34 <exit_code range=":-1" />
35 <!-- In case the return code has not been set propery check stderr too -->
36 <regex match="Error:" />
37 <regex match="Exception:" />
38 </stdio>
39 <command>
40 <![CDATA[ 32 <![CDATA[
41
42 #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"
43 #if $operation.refGenomeSource.genomeSource == "history" 34 #if $operation.refGenomeSource.genomeSource == "history"
44 bowtie-build '$operation.refGenomeSource.ownFile' custom_bowtie_indices && 35 bowtie-build '$operation.refGenomeSource.ownFile' custom_bowtie_indices &&
45 #end if 36 #end if
46 #end if 37 #end if
47 38
48 mapper.pl 39 mapper.pl
49 40
50 '$reads' 41 #if $input.type == "single":
51 42 '$input.reads'
52 #if $reads.extension.startswith("fasta") 43
53 -c 44 #if $input.reads.extension.startswith("fasta")
54 #else if $reads.extension.startswith("fastq") 45 -c
55 -e 46 #else if $input.reads.extension.startswith("fastq")
56 -h 47 -e
48 -h
49 #end if
50 #else:
51 '$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
57 #end if 59 #end if
58 60
59 $remove_non_canon 61 $remove_non_canon
60 62
61 $convert_rna_dna 63 $convert_rna_dna
62 64
63 #if $clip_adapter.clip == "true" 65 #if $clip_adapter.clip == "true"
64 -k $clip_adapter.adapter_seq 66 -k $clip_adapter.adapter_seq
65 #end if 67 #end if
67 -l $discard_short_reads 69 -l $discard_short_reads
68 70
69 #if $operation.collapse_map == "collapse_and_map" or $operation.collapse_map == "only_collapse" 71 #if $operation.collapse_map == "collapse_and_map" or $operation.collapse_map == "only_collapse"
70 -m -s '$output_reads_collapsed' 72 -m -s '$output_reads_collapsed'
71 #end if 73 #end if
72 74
73 #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"
74 -p 76 -p
75 77
76 #if $operation.refGenomeSource.genomeSource == "history" 78 #if $operation.refGenomeSource.genomeSource == "history"
77 custom_bowtie_indices 79 custom_bowtie_indices
78 #else 80 #else
79 '$operation.refGenomeSource.index.fields.path' 81 '$operation.refGenomeSource.index.fields.path'
80 #end if 82 #end if
81 $operation.map_mismatch 83 $operation.map_mismatch
82 -r $operation.map_threshold 84 -r $operation.map_threshold
83 85
84 -t '$output_mapping' 86 -t '$output_mapping'
85 #end if 87 #end if
86 88
87 -v -n 89 -v -n
88 ]]> 90 ]]>
89 </command> 91 </command>
92 <configfiles>
93 <configfile name="samples"><![CDATA[#if $input.type == "multiple":
94 #for $r in $input.reads_list:
95 $r.reads $r.sample_name
96 #end for
97 #end if]]></configfile>
98 </configfiles>
90 <inputs> 99 <inputs>
91 <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>
92 <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)"/>
93 <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)"/>
94 119
95 <conditional name="clip_adapter"> 120 <conditional name="clip_adapter">
96 <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)">
102 <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>
103 </param> 128 </param>
104 </when> 129 </when>
105 <when value="false"/> 130 <when value="false"/>
106 </conditional> 131 </conditional>
107 132
108 <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)">
109 <validator type="in_range" min="0" message="Minimum value is 0"/> 134 <validator type="in_range" min="0" message="Minimum value is 0"/>
110 </param> 135 </param>
111 136
112 <conditional name="operation"> 137 <conditional name="operation">
113 <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)">
114 <option value="collapse_and_map">Collapse reads and Map</option> 139 <option value="collapse_and_map">Collapse reads and Map</option>
115 <option value="only_map">Map</option> 140 <option value="only_map">Map</option>
116 <option value="only_collapse">Collapse</option> 141 <option value="only_collapse">Collapse</option>
142 </filter> 167 </filter>
143 </data> 168 </data>
144 </outputs> 169 </outputs>
145 <tests> 170 <tests>
146 <test> 171 <test>
147 <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>
148 <param name="remove_non_canon" value="True"/> 176 <param name="remove_non_canon" value="True"/>
149 <param name="clip" value="true"/> 177 <param name="clip" value="true"/>
150 <param name="adapter_seq" value="TCGTATGCCGTCTTCTGCTTGT"/> 178 <param name="adapter_seq" value="TCGTATGCCGTCTTCTGCTTGT"/>
151 <param name="discard_short_reads" value="18"/> 179 <param name="discard_short_reads" value="18"/>
152 <param name="collapse_map" value="collapse_and_map"/> 180 <param name="collapse_map" value="collapse_and_map"/>
169 <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.*$"/>
170 <has_line_matching expression="^.*25\t1\t25\ttcaccgggtggaaactagcagtggc\tchrII:11534525-11540624\t25\t3060\t3084.*$"/> 198 <has_line_matching expression="^.*25\t1\t25\ttcaccgggtggaaactagcagtggc\tchrII:11534525-11540624\t25\t3060\t3084.*$"/>
171 </assert_contents> 199 </assert_contents>
172 </output> 200 </output>
173 </test> 201 </test>
202 <test>
203 <conditional name="input">
204 <param name="type" value="multiple"/>
205 <repeat name="reads_list">
206 <param name="sample_name" value="sa1"/>
207 <param name="reads" value="reads_sample1.fa"/>
208 </repeat>
209 <repeat name="reads_list">
210 <param name="sample_name" value="sa2"/>
211 <param name="reads" value="reads_sample2.fa"/>
212 </repeat>
213 </conditional>
214 <param name="remove_non_canon" value="True"/>
215 <param name="clip" value="true"/>
216 <param name="adapter_seq" value="TCGTATGCCGTCTTCTGCTTGT"/>
217 <param name="discard_short_reads" value="18"/>
218 <param name="collapse_map" value="collapse_and_map"/>
219 <param name="genomeSource" value="history"/>
220 <param name="ownFile" value="cel_cluster.fa"/>
221 <output name="output_reads_collapsed">
222 <assert_contents>
223 <has_text text=">sa1_220_x1"/>
224 <has_text text="TCACCGGGTGTACATCAGC"/>
225 <has_text text=">sa2_0_x250"/>
226 <has_text text="AATGACACTGGTTATCTTTTCCATCG"/>
227 </assert_contents>
228 </output>
229 <output name="output_mapping">
230 <assert_contents>
231 <has_line_matching expression="^.*22\t1\t22\ttcaccgggtggaaactagcagt\tchrII:11534525-11540624\t22\t3060\t3081.*$"/>
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>
174 </tests> 237 </tests>
175 <help> 238 <help>
176 <![CDATA[ 239 <![CDATA[
177 **What it does** 240 **What it does**
178 241
179 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.
180 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.
181 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.
182 245
183 **Input** 246 **Input**
184 247
185 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.
186 249
187 **Output** 250 **Output**
188 251
189 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.
190 253
191 Arf format: 254 Arf format:
192 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:
193 256
194 1. read identifier 257 1. read identifier