Mercurial > repos > iuc > orthofinder_onlygroups

comparison orthofinder_only_groups.xml @ 2:649b98adce77 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/orthofinder commit 297228981612581ddd4588e042141a5b12fc7840
author iuc
date Tue, 06 Mar 2018 11:10:03 -0500
parents 918d141a166b
children 1aed170afb2b
comparison
equal deleted inserted replaced
1:918d141a166b 2:649b98adce77
1 <tool name="OrthoFinder OnlyGroups" id="orthofinder_onlygroups" version="1.1.4"> 1 <tool name="OrthoFinder OnlyGroups" id="orthofinder_onlygroups" version="2.1.2">
2 <description>finds orthogroups in a set of proteomes</description> 2 <description>finds orthogroups in a set of proteomes</description>
3 <requirements> 3 <requirements>
4 <requirement type="package" version="1.1.4">orthofinder</requirement> 4 <requirement type="package" version="2.1.2">orthofinder</requirement>
5 </requirements> 5 </requirements>
6 <command> 6 <command>
7 <![CDATA[ 7 <![CDATA[
8 ## prepare inputs 8 ## prepare inputs
9 #if $init.start=="fasta": 9 #if $init.start == "fasta":
10 #set $infiles = "" 10 #set $infiles = ""
11 #for $input in $init.input_fasta 11 #for $input in $init.input_fasta
12 ln -s '$input' '${input.element_identifier}.fasta' && 12 ln -s '$input' '${input.element_identifier}.fasta' &&
13 #set $infiles = $infiles + str($input.element_identifier) + "," 13 #set $infiles = $infiles + str($input.element_identifier) + ","
14 #end for 14 #end for
15 #set $infiles = $infiles[:-1] 15 #set $infiles = $infiles[:-1]
16 #elif $init.start=="blast": 16 #elif $init.start == "blast":
17 #set $infilesbl = "" 17 #set $infilesbl = ""
18 #for $input in $init.input_blast_out 18 #for $input in $init.input_blast_out
19 ln -s '$input' '$input.element_identifier' && 19 ln -s '$input' '$input.element_identifier' &&
20 #set $infilesbl = $infilesbl + str($input.element_identifier) + "," 20 #set $infilesbl = $infilesbl + str($input.element_identifier) + ","
21 #end for 21 #end for
22 #set $infilesbl = $infilesbl[:-1] 22 #set $infilesbl = $infilesbl[:-1]
23 23
24 #set $infilesfa = "" 24 #set $infilesfa = ""
25 #for $input in $init.input_blast_fa 25 #for $input in $init.input_blast_fa
26 ln -s '$input' '$input.element_identifier' && 26 ln -s '$input' '$input.element_identifier' &&
27 #set $infilesfa = $infilesfa + str($input.element_identifier) + "," 27 #set $infilesfa = $infilesfa + str($input.element_identifier) + ","
28 #end for 28 #end for
32 ln -s $init.seqIDs $init.seqIDs.element_identifier && 32 ln -s $init.seqIDs $init.seqIDs.element_identifier &&
33 #end if 33 #end if
34 34
35 ## start Orthofinder 35 ## start Orthofinder
36 orthofinder 36 orthofinder
37 #if $init.start=="fasta": 37 #if $init.start == "fasta":
38 -f . 38 -f .
39 #elif $init.start=="blast": 39 -S $init.search.search_program
40 #elif $init.start == "blast":
40 -b . 41 -b .
41 #end if 42 #end if
42 43
43 -I $I -og -t \${GALAXY_SLOTS:-1} -a \${GALAXY_SLOTS:-1} && 44 -I $I -og -t \${GALAXY_SLOTS:-1} -a \${GALAXY_SLOTS:-1} &&
44 45
45 #if $init.start=="fasta": 46 #if $init.start == "fasta":
46 mv Results_* results 47 mv Results_* results
47 #if $init.keepblastout=="yes": 48 #if $init.search.search_program == "blast":
48 && mkdir -p results/WorkingDirectory/blast results/WorkingDirectory/fa && 49 #if $init.search.keepblastout:
49 mv results/WorkingDirectory/Blast* results/WorkingDirectory/blast/ && 50 && mkdir -p results/WorkingDirectory/blast results/WorkingDirectory/fa &&
50 mv results/WorkingDirectory/*.fa results/WorkingDirectory/fa/ 51 mv results/WorkingDirectory/Blast* results/WorkingDirectory/blast/ &&
52 mv results/WorkingDirectory/*.fa results/WorkingDirectory/fa/
53 #end if
51 #end if 54 #end if
52 #elif $init.start=="blast": 55 #elif $init.start == "blast":
53 mkdir results && 56 mkdir results &&
54 mv *.csv results/ && 57 mv *.csv results/ &&
55 mv Orthogroups.txt results/ 58 mv Orthogroups.txt results/
56 #end if 59 #end if
57 60 ]]>
58 ]]>
59 </command> 61 </command>
60 <inputs> 62 <inputs>
61 <!-- Control where Orthofinder starts --> 63 <!-- Control where Orthofinder starts -->
62 <conditional name="init"> 64 <conditional name="init">
63 <param name="start" type="select" label="Orthofinder starting point" help="OrthoFinder_OnlyGroups works in 2 steps. Choose 'From fasta proteomes' to run OrthoFinder_OnlyGroups from scratch and 'From blast results' if you have all the blast results from a previous OrthoFinder_OnlyGroups run."> 65 <param name="start" type="select" label="Orthofinder starting point" help="OrthoFinder_OnlyGroups works in 2 steps. Choose 'From fasta proteomes' to run OrthoFinder_OnlyGroups from scratch and 'From blast results' if you have all the blast results from a previous OrthoFinder_OnlyGroups run.">
65 <option value="blast">From blast results</option> 67 <option value="blast">From blast results</option>
66 </param> 68 </param>
67 69
68 <when value="fasta"> 70 <when value="fasta">
69 <param name="input_fasta" type="data" format="fasta" multiple="true" label="Select input fasta proteomes" help="One fasta file per species; species and sequences names in the results will remain the same than in the input files."/> 71 <param name="input_fasta" type="data" format="fasta" multiple="true" label="Select input fasta proteomes" help="One fasta file per species; species and sequences names in the results will remain the same than in the input files."/>
70 <param name="keepblastout" type="boolean" checked="true" truevalue="yes" falsevalue="no" label="Do you want to get the blast results ?" help="Used to re-run OrthoFinder_OnlyGroups from pre-computed blast results"/> 72 <conditional name="search">
73 <param name="search_program" type="select" label="Sequence search program" help="Choose between blast, blast_gz, diamond">
74 <option value="blast" selected="true">blast</option>
75 <option value="blast_gz">blast_gz</option>
76 <option value="diamond">diamond</option>
77 </param>
78 <when value="blast">
79 <param name="keepblastout" type="boolean" checked="true" label="Do you want to get the blast results?" help="Used to re-run OrthoFinder_OnlyGroups from pre-computed blast results"/>
80 </when>
81 <when value="diamond"></when>
82 <when value="blast_gz"></when>
83 </conditional>
71 </when> 84 </when>
72 85
73 <when value="blast"> 86 <when value="blast">
74 <param name="input_blast_out" type="data_collection" collection_type="list" format="txt" label="Select the pre-computed blast files" help="blastX_Y.txt files from the blast output files of a previous OrthoFinder_OnlyGroups run." /> 87 <param name="input_blast_out" type="data_collection" collection_type="list" format="txt" label="Select the pre-computed blast files" help="blastX_Y.txt files from the blast output files of a previous OrthoFinder_OnlyGroups run." />
75 <param name="input_blast_fa" type="data_collection" collection_type="list" format="fasta" label="Select the fasta files" help="= SpeciesX.fa files from the blast output files of a previous OrthoFinder_OnlyGroups run." /> 88 <param name="input_blast_fa" type="data_collection" collection_type="list" format="fasta" label="Select the fasta files" help="= SpeciesX.fa files from the blast output files of a previous OrthoFinder_OnlyGroups run." />
76 <param name="specIDs" type="data" format="txt" label="Select the SpeciesIds file" help="SpeciesIDs.txt file from the blast output files of a previous OrthoFinder_OnlyGroups run."/> 89 <param name="specIDs" type="data" format="txt" label="Select the SpeciesIds file" help="SpeciesIDs.txt file from the blast output files of a previous OrthoFinder_OnlyGroups run."/>
77 <param name="seqIDs" type="data" format="txt" label="Select the SequencesIds file" help="SequencesIDs.txt file from the blast output files of a previous OrthoFinder_OnlyGroups run."/> 90 <param name="seqIDs" type="data" format="txt" label="Select the SequencesIds file" help="SequencesIDs.txt file from the blast output files of a previous OrthoFinder_OnlyGroups run."/>
78 </when> 91 </when>
79 </conditional> 92 </conditional>
80
81 <param argument="-I" type="float" value="1.5" label="Inflation parameter" help="Modify inflation parameter for MCL. Not recommended." /> 93 <param argument="-I" type="float" value="1.5" label="Inflation parameter" help="Modify inflation parameter for MCL. Not recommended." />
82 </inputs> 94 </inputs>
83 <outputs> 95 <outputs>
84 <!-- Orthogroups results --> 96 <!-- Orthogroups results -->
85 <data format="txt" name="orthogroups1" label="Orthogroups.txt" from_work_dir="results/Orthogroups.txt" /> 97 <data format="txt" name="orthogroups1" label="Orthogroups.txt" from_work_dir="results/Orthogroups.txt" />
86 <data format="csv" name="orthogroups2" label="Orthogroups.csv" from_work_dir="results/Orthogroups.csv" /> 98 <data format="csv" name="orthogroups2" label="Orthogroups.csv" from_work_dir="results/Orthogroups.csv" />
87 <data format="csv" name="specs_overlap" label="Orthogroups_SpeciesOverlaps.csv" from_work_dir="results/Orthogroups_SpeciesOverlaps.csv" /> 99 <data format="csv" name="specs_overlap" label="Orthogroups_SpeciesOverlaps.csv" from_work_dir="results/Orthogroups_SpeciesOverlaps.csv" />
88 <data format="csv" name="unassigned_genes" label="Orthogroups_UnassignedGenes.csv" from_work_dir="results/Orthogroups_UnassignedGenes.csv" /> 100 <data format="csv" name="unassigned_genes" label="Orthogroups_UnassignedGenes.csv" from_work_dir="results/Orthogroups_UnassignedGenes.csv" />
89 <data format="csv" name="stat_overall" label="Statistics_Overall.csv" from_work_dir="results/Statistics_Overall.csv" /> 101 <data format="csv" name="stat_overall" label="Statistics_Overall.csv" from_work_dir="results/Statistics_Overall.csv" />
90 <data format="csv" name="stat_specs" label="Statistics_PerSpecies.csv" from_work_dir="results/Statistics_PerSpecies.csv" /> 102 <data format="csv" name="stat_specs" label="Statistics_PerSpecies.csv" from_work_dir="results/Statistics_PerSpecies.csv" />
91 103
92 <!-- working directory : blast outputs--> 104 <!-- working directory : blast outputs-->
93 <collection name="wdblast" type="list" label="Blast_outputs"> 105 <collection name="wdblast" type="list" label="Blast_outputs">
94 <discover_datasets pattern="__name_and_ext__" directory="results/WorkingDirectory/blast/" /> 106 <discover_datasets pattern="__name_and_ext__" directory="results/WorkingDirectory/blast" />
95 <filter>init['start']=="fasta" and init['keepblastout']</filter> 107 <filter>init['start'] == "fasta" and init['search']['search_program'] == "blast" and init['search']['keepblastout']</filter>
96 </collection> 108 </collection>
97 <collection name="wdfasta" type="list" label="Fasta_from_blast" > 109 <collection name="wdfasta" type="list" label="Fasta_from_blast" >
98 <discover_datasets pattern="__name_and_ext__" directory="results/WorkingDirectory/fa/" /> 110 <discover_datasets pattern="(?P&lt;designation&gt;.+)\.fa" directory="results/WorkingDirectory/fa" format="fasta" />
99 <filter>init['start']=="fasta" and init['keepblastout']</filter> 111 <filter>init['start'] == "fasta" and init['search']['search_program'] == "blast" and init['search']['keepblastout']</filter>
112 </collection>
113 <collection name="genetrees" type="list" label="Gene trees">
114 <discover_datasets pattern="(?P&lt;designation&gt;.+)\.txt" directory="results/WorkingDirectory/trees" format="nhx" />
115 <filter>dogenetrees</filter>
100 </collection> 116 </collection>
101 <data format="txt" name="SpeciesIDs" label="SpeciesIDs.txt" from_work_dir="results/WorkingDirectory/SpeciesIDs.txt" > 117 <data format="txt" name="SpeciesIDs" label="SpeciesIDs.txt" from_work_dir="results/WorkingDirectory/SpeciesIDs.txt" >
102 <filter>init['start']=="fasta" and init['keepblastout']</filter> 118 <filter>init['start'] == "fasta" and init['search']['search_program'] == "blast" and init['search']['keepblastout']"</filter>
103 </data> 119 </data>
104 <data format="txt" name="SequenceIDs" label="SequencesIDs.txt" from_work_dir="results/WorkingDirectory/SequenceIDs.txt" > 120 <data format="txt" name="SequenceIDs" label="SequencesIDs.txt" from_work_dir="results/WorkingDirectory/SequenceIDs.txt" >
105 <filter>init['start']=="fasta" and init['keepblastout']</filter> 121 <filter>init['start'] == "fasta" and init['search']['search_program'] == "blast" and init['search']['keepblastout']</filter>
106 </data> 122 </data>
107 </outputs> 123 </outputs>
108 <tests> 124 <tests>
109 <!-- test orthofinder -f . -og when input files has no extension fasta/faa/fa ... --> 125 <!-- test orthofinder -f . -og when input files has no extension fasta/faa/fa ... -->
110 <test> 126 <test>
111 <conditional name="init"> 127 <conditional name="init">
112 <param name="start" value="fasta" /> 128 <param name="start" value="fasta" />
113 <param name="input_fasta" ftype="fasta" value="inputs/no_fa_ext/AcAcaud_trinity,inputs/no_fa_ext/AmAmphi_trinity,inputs/no_fa_ext/ApApomp_trinity,inputs/no_fa_ext/AsAsp1_trinity" /> 129 <param name="input_fasta" ftype="fasta" value="inputs/no_fa_ext/AcAcaud_trinity,inputs/no_fa_ext/AmAmphi_trinity,inputs/no_fa_ext/ApApomp_trinity,inputs/no_fa_ext/AsAsp1_trinity" />
114 <param name="keepblastout" value="no" /> 130 <conditional name="search">
131 <param name="search_program" value="blast"/>
132 <param name="keepblastout" value="false" />
133 </conditional>
115 </conditional> 134 </conditional>
116 <param name="inflation" value="1.5" /> 135 <param name="inflation" value="1.5" />
117 <output name="specs_overlap"> 136 <output name="specs_overlap">
118 <assert_contents> 137 <assert_contents>
119 <has_text text="AcAcaud_trinity"/> 138 <has_text text="AcAcaud_trinity"/>
162 <!-- test orthofinder -f -og --> 181 <!-- test orthofinder -f -og -->
163 <test> 182 <test>
164 <conditional name="init"> 183 <conditional name="init">
165 <param name="start" value="fasta" /> 184 <param name="start" value="fasta" />
166 <param name="input_fasta" ftype="fasta" value="inputs/proteomes/Mycoplasma_agalactiae.faa,inputs/proteomes/Mycoplasma_gallisepticum.faa,inputs/proteomes/Mycoplasma_genitalium.faa,inputs/proteomes/Mycoplasma_hyopneumoniae.faa" /> 185 <param name="input_fasta" ftype="fasta" value="inputs/proteomes/Mycoplasma_agalactiae.faa,inputs/proteomes/Mycoplasma_gallisepticum.faa,inputs/proteomes/Mycoplasma_genitalium.faa,inputs/proteomes/Mycoplasma_hyopneumoniae.faa" />
167 <param name="keepblastout" value="no" /> 186 <conditional name="search">
187 <param name="search_program" value="blast"/>
188 <param name="keepblastout" value="false" />
189 </conditional>
168 </conditional> 190 </conditional>
169 <param name="inflation" value="1.5" /> 191 <param name="inflation" value="1.5" />
170 <output name="specs_overlap"> 192 <output name="specs_overlap">
171 <assert_contents> 193 <assert_contents>
172 <has_text text="Mycoplasma_agalactiae"/> 194 <has_text text="Mycoplasma_agalactiae"/>
210 <has_text text="Number of genes"/> 232 <has_text text="Number of genes"/>
211 <has_n_columns n="5"/> 233 <has_n_columns n="5"/>
212 </assert_contents> 234 </assert_contents>
213 </output> 235 </output>
214 </test> 236 </test>
215 237
216 <test> 238 <test>
217 <conditional name="init"> 239 <conditional name="init">
218 <param name="start" value="fasta" /> 240 <param name="start" value="fasta" />
219 <param name="input_fasta" ftype="fasta" value="inputs/proteomes/Mycoplasma_agalactiae.faa,inputs/proteomes/Mycoplasma_gallisepticum.faa,inputs/proteomes/Mycoplasma_genitalium.faa,inputs/proteomes/Mycoplasma_hyopneumoniae.faa" /> 241 <param name="input_fasta" ftype="fasta" value="inputs/proteomes/Mycoplasma_agalactiae.faa,inputs/proteomes/Mycoplasma_gallisepticum.faa,inputs/proteomes/Mycoplasma_genitalium.faa,inputs/proteomes/Mycoplasma_hyopneumoniae.faa" />
220 <param name="keepblastout" value="yes" /> 242 <conditional name="search">
243 <param name="search_program" value="blast"/>
244 <param name="keepblastout" value="true" />
245 </conditional>
221 </conditional> 246 </conditional>
222 <param name="inflation" value="1.5" /> 247 <param name="inflation" value="1.5" />
223 <output name="specs_overlap"> 248 <output name="specs_overlap">
224 <assert_contents> 249 <assert_contents>
225 <has_text text="Mycoplasma_agalactiae"/> 250 <has_text text="Mycoplasma_agalactiae"/>
266 </output> 291 </output>
267 <output name="SequenceIDs" value="inputs/blastids/SequenceIDs.txt" /> 292 <output name="SequenceIDs" value="inputs/blastids/SequenceIDs.txt" />
268 <output_collection name="wdfasta" type="list" count="4"/> 293 <output_collection name="wdfasta" type="list" count="4"/>
269 <output_collection name="wdblast" type="list" count="16"/> 294 <output_collection name="wdblast" type="list" count="16"/>
270 </test> 295 </test>
271 296
297 <!-- test -S diamond -->
298 <test>
299 <conditional name="init">
300 <param name="start" value="fasta" />
301 <param name="input_fasta" ftype="fasta" value="inputs/proteomes/Mycoplasma_agalactiae.faa,inputs/proteomes/Mycoplasma_gallisepticum.faa,inputs/proteomes/Mycoplasma_genitalium.faa,inputs/proteomes/Mycoplasma_hyopneumoniae.faa" />
302 <conditional name="search">
303 <param name="search_program" value="diamond"/>
304 </conditional>
305 </conditional>
306 <param name="inflation" value="1.5" />
307 <output name="specs_overlap">
308 <assert_contents>
309 <has_text text="Mycoplasma_agalactiae"/>
310 <has_text text="Mycoplasma_gallisepticum"/>
311 <has_text text="Mycoplasma_genitalium"/>
312 <has_text text="Mycoplasma_hyopneumoniae"/>
313 <has_n_columns n="5"/>
314 </assert_contents>
315 </output>
316 <output name="unassigned_genes">
317 <assert_contents>
318 <has_text text="Mycoplasma_agalactiae"/>
319 <has_text text="Mycoplasma_gallisepticum"/>
320 <has_text text="Mycoplasma_genitalium"/>
321 <has_text text="Mycoplasma_hyopneumoniae"/>
322 <has_n_columns n="5"/>
323 </assert_contents>
324 </output>
325 <output name="stat_overall">
326 <assert_contents>
327 <has_text text="Number of genes in orthogroups"/>
328 <has_text text="Number of unassigned genes"/>
329 <has_text text="Percentage of orthogroups"/>
330 <has_text text="Number of orthogroups"/>
331 <has_text text="Number of genes"/>
332 <has_text text="G50 (assigned genes)"/>
333 <has_text text="G50 (all genes)"/>
334 <has_text text="O50 (assigned genes)"/>
335 <has_text text="O50 (all genes)"/>
336 </assert_contents>
337 </output>
338 <output name="stat_specs">
339 <assert_contents>
340 <has_text text="Mycoplasma_agalactiae"/>
341 <has_text text="Mycoplasma_gallisepticum"/>
342 <has_text text="Mycoplasma_genitalium"/>
343 <has_text text="Mycoplasma_hyopneumoniae"/>
344 <has_text text="Number of genes per-species in orthogroup"/>
345 <has_text text="Percentage of orthogroups"/>
346 <has_text text="Number of orthogroups"/>
347 <has_text text="Number of genes"/>
348 <has_n_columns n="5"/>
349 </assert_contents>
350 </output>
351 </test>
352
272 <!-- test orthofinder -b -og --> 353 <!-- test orthofinder -b -og -->
273 <test> 354 <test>
274 <conditional name="init"> 355 <conditional name="init">
275 <param name="start" value="blast" /> 356 <param name="start" value="blast" />
276 <param name="input_blast_out"> 357 <param name="input_blast_out">
337 - A dataset collection / multiple datasets for the blast outputs 418 - A dataset collection / multiple datasets for the blast outputs
338 - A dataset collection / multiple datasets for .fa files 419 - A dataset collection / multiple datasets for .fa files
339 - The SpeciesIDs.txt file 420 - The SpeciesIDs.txt file
340 - The SequencesIDs.txt file 421 - The SequencesIDs.txt file
341 422
423 ----------
424 Parameters
425 ----------
426 - Sequence search program : You can choose either blast, blast_gz, or diamond (diamond is faster)
427 - Get the blast results : Check "Yes" if, while using blast as the sequence search program, you want to retrieve the blast output files
428 - Inflation : the inflation parameter; modify this parameter is not recommended.
429
342 </help> 430 </help>
343 <citations> 431 <citations>
344 <citation type="doi">10.1186/s13059-015-0721-2</citation> 432 <citation type="doi">10.1186/s13059-015-0721-2</citation>
345 </citations> 433 </citations>
346 </tool> 434 </tool>