Mercurial > repos > bgruening > repeat_masker

comparison repeatmasker.xml @ 4:04f5c3d7448e draft

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/repeat_masker commit cbba6947f1380751e1db3fa5b043af630523fd86
author iuc
date Fri, 04 May 2018 07:59:50 -0400
parents bdfc22c1c3e3
children 8404aa79a631
comparison
equal deleted inserted replaced
3:bdfc22c1c3e3 4:04f5c3d7448e
1 <tool id="repeatmasker_wrapper" name="RepeatMasker" version="4.0.7" profile="17.01"> 1 <tool id="repeatmasker_wrapper" name="RepeatMasker" version="4.0.7+galaxy1" profile="17.01">
2 <description>RepeatMasker</description> 2 <description>RepeatMasker</description>
3 3
4 <requirements> 4 <requirements>
5 <requirement type="package" version="4.0.7">repeatmasker</requirement> 5 <requirement type="package" version="4.0.7">repeatmasker</requirement>
6 </requirements> 6 </requirements>
9 RM_LIB_PATH=\$(dirname \$(which RepeatMasker))/../share/RepeatMasker/Libraries && 9 RM_LIB_PATH=\$(dirname \$(which RepeatMasker))/../share/RepeatMasker/Libraries &&
10 mkdir lib && 10 mkdir lib &&
11 export REPEATMASKER_LIB_DIR=\$(pwd)/lib && 11 export REPEATMASKER_LIB_DIR=\$(pwd)/lib &&
12 for file in \$(ls \$RM_LIB_PATH) ; do ln -s \$RM_LIB_PATH/\$file lib/\$file ; done && 12 for file in \$(ls \$RM_LIB_PATH) ; do ln -s \$RM_LIB_PATH/\$file lib/\$file ; done &&
13 #if $repeat_source.source_type == "repbase": 13 #if $repeat_source.source_type == "repbase":
14 cp '${repeat_source.repbase_file}' lib/RMRBSeqs.embl && 14 cp '${repeat_source.repbase_file}' 'lib/${repeat_source.repbase_file_name}' &&
15 #end if 15 #end if
16 ln -s '${input_fasta}' rm_input.fasta && 16 ln -s '${input_fasta}' rm_input.fasta &&
17 RepeatMasker -dir \$(pwd) 17 RepeatMasker -dir \$(pwd)
18 #if $repeat_source.source_type == "library": 18 #if $repeat_source.source_type == "library":
19 -lib '${repeat_source.repeat_lib}' 19 -lib '${repeat_source.repeat_lib}'
24 #else 24 #else
25 -species '${repeat_source.species_source.species_name}' 25 -species '${repeat_source.species_source.species_name}'
26 #end if 26 #end if
27 #end if 27 #end if
28 -parallel \${GALAXY_SLOTS:-1} 28 -parallel \${GALAXY_SLOTS:-1}
29 '${gff}' 29 ${gff}
30 '${ignore_n_stretches}' 30 ${excln}
31 '${advanced.is_only}' 31 ${advanced.is_only}
32 '${advanced.is_clip}' 32 ${advanced.is_clip}
33 '${advanced.no_is}' 33 ${advanced.no_is}
34 '${advanced.rodspec}' 34 ${advanced.rodspec}
35 '${advanced.primspec}' 35 ${advanced.primspec}
36 '${advanced.nolow}' 36 ${advanced.nolow}
37 '${advanced.noint}' 37 ${advanced.noint}
38 '${advanced.norna}' 38 ${advanced.norna}
39 '${advanced.alu}' 39 ${advanced.alu}
40 '${advanced.div}' 40 ${advanced.div}
41 '${advanced.search_speed}' 41 ${advanced.search_speed}
42 '${advanced.frag}' 42 -frag ${advanced.frag}
43 '${advanced.maxsize}' 43 ## -maxsize ${advanced.maxsize}
44 #if $advanced.gc is not None: 44 #if str($advanced.gc):
45 '${advanced.gc}' 45 -gc ${advanced.gc}
46 #end if 46 #end if
47 '${advanced.gccalc}' 47 ${advanced.gccalc}
48 '${advanced.nocut}' 48 ${advanced.nocut}
49 '${advanced.keep_alignments}' 49 ${advanced.keep_alignments}
50 '${advanced.invert_alignments}' 50 ${advanced.invert_alignments}
51 '${advanced.xout}' 51 ${advanced.xout}
52 '${advanced.xsmall}' 52 ${advanced.xsmall}
53 '${advanced.poly}' 53 ${advanced.poly}
54 rm_input.fasta && 54 rm_input.fasta &&
55 #if $advanced.is_only != '-is_only': 55 #if $advanced.is_only != '-is_only':
56 mv rm_input.fasta.masked '${output_masked_genome}' && 56 mv rm_input.fasta.masked '${output_masked_genome}' &&
57 sed -r 's/^ *// ; s/ *$//; s/\+ //; s/ +/\t/g ; 1,2c SW score\t% div.\t% del.\t% ins.\tquery sequence\tpos in query: begin\tend\t(left)\trepeat\tclass/family\tpos in repeat: begin\tend\t(left)\tID' rm_input.fasta.out >'${output_log}' && 57 sed -r 's/^ *// ; s/ *$//; s/\+ //; s/ +/\t/g ; 1,2c SW score\t% div.\t% del.\t% ins.\tquery sequence\tpos in query: begin\tend\t(left)\trepeat\tclass/family\tpos in repeat: begin\tend\t(left)\tID' rm_input.fasta.out >'${output_log}' &&
58 mv rm_input.fasta.tbl '${output_table}' && 58 mv rm_input.fasta.tbl '${output_table}' &&
77 <option selected="true" value="repbase">RepBase</option> 77 <option selected="true" value="repbase">RepBase</option>
78 <option value="library">Custom library of repeats</option> 78 <option value="library">Custom library of repeats</option>
79 </param> 79 </param>
80 <when value="repbase"> 80 <when value="repbase">
81 <param name="repbase_file" type="data" format="embl" label="RepBase (RMRBSeqs.embl) file" /> 81 <param name="repbase_file" type="data" format="embl" label="RepBase (RMRBSeqs.embl) file" />
82 <param name="repbase_file_name" type="hidden" value="RMRBSeqs.embl"/> <!-- This is an ugly hack to allow testing with a fake repbase -->
82 <conditional name="species_source"> 83 <conditional name="species_source">
83 <param label="Select species name from a list?" name="species_from_list" type="select"> 84 <param label="Select species name from a list?" name="species_from_list" type="select">
84 <option value="yes" selected="true">Yes</option> 85 <option value="yes" selected="true">Yes</option>
85 <option value="no">No</option> 86 <option value="no">No</option>
86 </param> 87 </param>
124 <param name="repeat_lib" type="data" format="fasta" label="Custom library of repeats" /> 125 <param name="repeat_lib" type="data" format="fasta" label="Custom library of repeats" />
125 <param name="cutoff" type="integer" argument="-cutoff" value="225" label="Cutoff score for masking repeats" /> 126 <param name="cutoff" type="integer" argument="-cutoff" value="225" label="Cutoff score for masking repeats" />
126 </when> 127 </when>
127 </conditional> 128 </conditional>
128 <param type="boolean" argument="-gff" truevalue="-gff" falsevalue="" label="Output annotation of repeats in GFF format" checked="false" /> 129 <param type="boolean" argument="-gff" truevalue="-gff" falsevalue="" label="Output annotation of repeats in GFF format" checked="false" />
129 <param name="ignore_n_stretches" type="boolean" argument="-excln" falsevalue="" label="Ignore stretches of Ns when computing statistics" checked="true" help="Scaffolds are sometimes joined with stretches of 25 or more Ns. This option ignores them when calculating repeat statistics" /> 130 <param argument="-excln" type="boolean" truevalue="-excln" falsevalue="" label="Ignore stretches of Ns when computing statistics" checked="true" help="Scaffolds are sometimes joined with stretches of 25 or more Ns. This option ignores them when calculating repeat statistics" />
130 <section name="advanced" title="Advanced options" expanded="false"> 131 <section name="advanced" title="Advanced options" expanded="false">
131 <param argument="-is_only" type="boolean" truevalue="-is_only" falsevalue="" checked="false" label="Only clip E coli insertion elements" /> 132 <param argument="-is_only" type="boolean" truevalue="-is_only" falsevalue="" checked="false" label="Only clip E coli insertion elements" />
132 <param argument="-is_clip" type="boolean" truevalue="-is_clip" falsevalue="" checked="false" label="Clip IS elements before analysis" help="Normally RepeatMasker will report on IS element, with this option selected it will clip them before analysis" /> 133 <param argument="-is_clip" type="boolean" truevalue="-is_clip" falsevalue="" checked="false" label="Clip IS elements before analysis" help="Normally RepeatMasker will report on IS element, with this option selected it will clip them before analysis" />
133 <param argument="-no_is" type="boolean" truevalue="-no_is" falsevalue="" checked="false" label="Skip bacterial insertion element check" /> 134 <param argument="-no_is" type="boolean" truevalue="-no_is" falsevalue="" checked="false" label="Skip bacterial insertion element check" />
134 <param argument="-rodspec" type="boolean" truevalue="-rodspec" falsevalue="" checked="false" label="Only check for rodent specific repeats" help="If this option is select a check for rodent specific repeats is done instead of a full RepeatMasker run" /> 135 <param argument="-rodspec" type="boolean" truevalue="-rodspec" falsevalue="" checked="false" label="Only check for rodent specific repeats" help="If this option is select a check for rodent specific repeats is done instead of a full RepeatMasker run" />
143 <option value="-q">Quick (5-10% less sensitive, 3-4 times speedup)</option> 144 <option value="-q">Quick (5-10% less sensitive, 3-4 times speedup)</option>
144 <option value="-qq">Rush (10% less sensitive)</option> 145 <option value="-qq">Rush (10% less sensitive)</option>
145 <option value="-s">Slow (0-5% more sensitive, 2.5 times slowdown)</option> 146 <option value="-s">Slow (0-5% more sensitive, 2.5 times slowdown)</option>
146 </param> 147 </param>
147 <param type="integer" argument="-frag" value="40000" label="Maximum contiguous sequence searched" help="Maximum length of sequencing that is search without fragmenting" /> 148 <param type="integer" argument="-frag" value="40000" label="Maximum contiguous sequence searched" help="Maximum length of sequencing that is search without fragmenting" />
148 <param type="integer" argument="-maxsize" value="4000000" label="Maximum length for IS or repeat clipped sequences" /> 149 <!-- -maxsize option is in the help, but not in the code of repeatmasker-->
149 <param type="integer" argument="-gc" optional="True" label="Select matrices for this GC%" help="Valid values are a percentage or -1 to choose the default" /> 150 <!--param type="integer" argument="-maxsize" value="4000000" label="Maximum length for IS or repeat clipped sequences" /-->
151 <param type="integer" argument="-gc" optional="true" label="Select matrices for this GC%" help="Valid values are a percentage or -1 to choose the default" />
150 <param type="boolean" argument="-gccalc" truevalue="-gcccalc" falsevalue="" checked="false" label="Calculate GC % for all sequences" help="By default RepeatMasker skips calculating GC % for small sequences" /> 152 <param type="boolean" argument="-gccalc" truevalue="-gcccalc" falsevalue="" checked="false" label="Calculate GC % for all sequences" help="By default RepeatMasker skips calculating GC % for small sequences" />
151 <param type="boolean" argument="-nocut" truevalue="-nocut" falsevalue="" checked="false" label="Skips cutting of repeats" /> 153 <param type="boolean" argument="-nocut" truevalue="-nocut" falsevalue="" checked="false" label="Skips cutting of repeats" />
152 <param name="xout" type="boolean" argument="-x" truevalue="-x" falsevalue="" checked="false" label="Mask with X instead of N characters" /> 154 <param name="xout" type="boolean" argument="-x" truevalue="-x" falsevalue="" checked="false" label="Mask with X instead of N characters" />
153 <param name="keep_alignments" type="boolean" argument="-ali" truevalue="-ali" falsevalue="" checked="false" label="Output alignments file" /> 155 <param name="keep_alignments" type="boolean" argument="-ali" truevalue="-ali" falsevalue="" checked="false" label="Output alignments file" />
154 <param name="invert_alignments" type="boolean" argument="-inv" truevalue="-inv" falsevalue="" checked="false" label="Invert alignments in alignment file" help="Show alignments in the orientation of the repeat sequence, not the query sequence" /> 156 <param name="invert_alignments" type="boolean" argument="-inv" truevalue="-inv" falsevalue="" checked="false" label="Invert alignments in alignment file" help="Show alignments in the orientation of the repeat sequence, not the query sequence" />
201 <output name="output_log" file="small.fasta.log" /> 203 <output name="output_log" file="small.fasta.log" />
202 <output name="output_alignment" file="small.fasta.align" /> 204 <output name="output_alignment" file="small.fasta.align" />
203 <output name="output_polymorphic" file="small.fasta.poly" /> 205 <output name="output_polymorphic" file="small.fasta.poly" />
204 <output name="output_gff" file="small.fasta.gff" lines_diff="4" /> 206 <output name="output_gff" file="small.fasta.gff" lines_diff="4" />
205 </test> 207 </test>
208 <test expect_num_outputs="4">
209 <param name="input_fasta" value="small.fasta" ftype="fasta" />
210 <param name="source_type" value="repbase" />
211 <param name="repbase_file" value="fake_repbase.embl" />
212 <param name="repbase_file_name" value="fake.embl" />
213 <param name="species_list" value="anopheles" />
214 <output name="output_masked_genome" file="small.fasta.masked" />
215 <output name="output_table" file="small_repbase.fasta.stats" lines_diff="2" />
216 <output name="output_repeat_catalog" file="small.fasta.cat" />
217 <output name="output_log" file="small_repbase.fasta.log" />
218 </test>
206 </tests> 219 </tests>
207 <help><![CDATA[ 220 <help><![CDATA[
208 RepeatMasker is a program that screens DNA for interspersed repeats and low 221 RepeatMasker is a program that screens DNA for interspersed repeats and low
209 complexity DNA sequences. The database of repeats to screen for can be 222 complexity DNA sequences. The database of repeats to screen for can be
210 provided as a FASTA file or downloaded from RepBase_. If the RepBase option is 223 provided as a FASTA file or downloaded from RepBase_. If the RepBase option is