Mercurial > repos > iuc > proteinortho

comparison proteinortho.xml @ 0:4850f0d15f01 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://gitlab.com/paulklemm_PHD/proteinortho commit 889335c0a31f156c3f90d4c2048cb4df155a53b2"
author iuc
date Tue, 18 Feb 2020 17:57:28 -0500
parents
children 26abc7846e6f
comparison
equal deleted inserted replaced
-1:000000000000 0:4850f0d15f01
1 <tool id="proteinortho" name="Proteinortho" version="@TOOL_VERSION@+galaxy@WRAPPER_VERSION@">
2 <description>detects orthologous proteins/genes within different species</description>
3 <macros>
4 <import>proteinortho_macros.xml</import>
5 </macros>
6 <expand macro="requirements"/>
7 <expand macro="version_command"/>
8 <command detect_errors="exit_code"><![CDATA[
9 ## the following ln-action is necessary, since the file names are used by proteinortho (output contains filenames => species names)
10 #import re
11 #for $f in $input_files#
12 ln -sf '$f' '${re.sub('[^\w\-_.]', '_', f.element_identifier)}' &&
13 #end for
14 #if $synteny.synteny_options == "specified":
15 #for $f in $synteny.input_files_syn#
16 ln -sf '$f' '${re.sub('[^\w\-_.]', '_', f.element_identifier)}' &&
17 #end for#
18 #end if
19 proteinortho
20 --project=result
21 --cpus="\${GALAXY_SLOTS:-4}"
22 --ram="\${GALAXY_MEMORY_MB:-16000}"
23 #if $more_options.selfblast:
24 $more_options.selfblast
25 #end if
26 #if $more_options.singles:
27 $more_options.singles
28 #end if
29 --p=$p
30 --e=$evalue
31 #if $more_options.cov:
32 --cov=$more_options.cov
33 #end if
34 #if $more_options.sim:
35 --sim=`LC_NUMERIC=C awk "BEGIN {printf \"%.2f\",$more_options.sim/100}"`
36 #end if
37 #if $more_options.identity:
38 --cov=$more_options.identity
39 #end if
40 #if $more_options.isoform != "no":
41 --isoform=$more_options.isoform
42 #end if
43 #if $synteny.synteny_options == "specified":
44 --synteny
45 --dups=$synteny.dups
46 --cs=$synteny.cs
47 --alpha=$synteny.alpha
48 #end if
49 #for $f in $input_files#
50 ${re.sub('[^\w\-_.]', '_', f.element_identifier)}
51 #end for#
52 #if $synteny.synteny_options == "specified":
53 #for $f in $synteny.input_files_syn#
54 ${re.sub('[^\w\-_.]', '_', f.element_identifier)}
55 #end for#
56 #end if
57 2> >(sed -E "s/.\[([0-9]{1,2}(;[0-9]{1,2})?)?[mGK]//g" 1>&2)
58 #if $synteny.synteny_options == "specified":
59 &&
60 mv result.poff-graph result.proteinortho-graph &&
61 mv result.poff.tsv result.proteinortho.tsv &&
62 mv result.poff.html result.proteinortho.html ;
63 #end if
64 ]]></command>
65 <inputs>
66 <param name="input_files" format="fasta" type="data" multiple="true" min="2" label="Select the input fasta files (>2)" help="The input fasta files. At least 2 are needed!"/>
67 <param argument="--p" type="select" label="Similarity comparision algorithm" help="In the first step of proteinortho an all-versus-all reciprocal best hit graph is build from the input files (using this algorithm).">
68 <option value="diamond" selected="true">diamond (aminoacid sequences)</option>
69 <option value="autoblast">auto detect NCBI-BLAST (protein and nucleotide sequences)</option>
70 <option value="blastp">NCBI-BLASTP+ (protein sequences)</option>
71 <option value="blastn">NCBI-BLASTN+ (nucleotide sequences)</option>
72 <option value="lastp">Last (aminoacid sequences)</option>
73 <option value="lastn">Last (nucleotide sequences)</option>
74 <option value="blatp">BLAT (aminoacid sequences)</option>
75 <option value="blatn">BLAT (nucleotide sequences)</option>
76 </param>
77 <param argument="--evalue" type="float" value="0.001" min="0" label="E-value threshold of the blast algorithm" help="This is the main parameter for the generation of the reciprocal best hit graph. Larger values results in more false positives (connections between proteins)."/>
78 <param argument="--conn" type="float" value="0.1" min="0." max="10." label="Minimal algebraic connectivity" help="This is the main parameter for the clustering step. Choose larger values then more splits are done, resulting in more and smaller clusters."/>
79 <section name="more_options" title="Additional Options" expanded="False">
80 <param argument="--cov" type="integer" value="50" min="0" max="100" label="Minimal coverage of best blast alignments in %"/>
81 <param argument="--sim" type="integer" value="95" min="0" max="100" label="Minimal sequence similarity in %"/>
82 <param argument="--identity" type="integer" value="25" min="0" max="100" label="Minimal percent identity of best blast hits in %"/>
83 <param argument="--selfblast" type="boolean" checked="false" truevalue="--selfblast" falsevalue="" label="Apply selfblast, detects paralogs without orthologs "/>
84 <param argument="--singles" type="boolean" checked="false" truevalue="--singles" falsevalue="" label="Report singleton genes without any hit "/>
85 <param argument="--isoform" type="select" label="Use isoform information" help="The reciprocal best hit graph is build using isoform information (isoforms are treated equivalent). For ncbi : simply add the additional files to the input (file names need to match). For uniprot : the isoforms need to contain the word isoform and the corresponding identifier. For trinity simply use the trinity output format.">
86 <option value="no" selected="true">Don't use isoform information</option>
87 <option value="ncbi">ncbi style (..._additional.fasta)</option>
88 <option value="uniprot">uniprot style (...isoform of...)</option>
89 <option value="trinity">trinity style (...i4)</option>
90 </param>
91 </section>
92 <conditional name="synteny">
93 <param name="synteny_options" type="select" label="Activate synteny feature (POFF)" help="To enhance the prediction accuracy, the relative order of genes (synteny) can be used as additional feature for the discrimination of orthologs. For more details see doi:10.1371/journal.pone.0105015.">
94 <option value="no" selected="true">no</option>
95 <option value="specified">yes</option>
96 </param>
97 <when value="no"/>
98 <when value="specified">
99 <param argument="--dups" type="integer" value="0" min="0" max="100" label="Number of reiterations for adjacencies heuristic, to determine duplicated regions"/>
100 <param argument="--cs" type="integer" value="3" min="0" max="100" label="Size of a maximum common substring (MCS) for adjacency matches"/>
101 <param argument="--alpha" type="float" value="0.5" min="0." max="1." label="Minimal percent identity of best blast hits"/>
102 <param name="input_files_syn" type="data" format="gff" multiple="true" min="2" label="Select the GFF3 files matching the input fasta files" help="The GFF3 files need matching names with the input fasta files. If you provide mybacteria123.faa or mybacteria123.fasta ... then you need to provide mybacteria123.gff here accoringly. The attributes column (#9) must contain the attribute Name=GENE IDENTIFIER where GENE IDENTIFIER corresponds to the respective (protein) identifier in the FASTA input. For example see https://gitlab.com/paulklemm_PHD/proteinortho/-/blob/master/test/C.gff"/>
103 </when>
104 </conditional>
105 </inputs>
106 <outputs>
107 <data name="blastgraph" format="tabular" label="${tool.name} on ${on_string}: RBH graph" from_work_dir="result.blast-graph"/>
108 <data name="proteinortho" format="tabular" label="${tool.name} on ${on_string}: orthology-groups" from_work_dir="result.proteinortho.tsv"/>
109 <data name="proteinorthograph" format="tabular" label="${tool.name} on ${on_string}: orthology-pairs" from_work_dir="result.proteinortho-graph"/>
110 </outputs>
111 <tests>
112 <test expect_num_outputs="3"> <!-- test normal -->
113 <param name="input_files" value="L.fasta,C.fasta,C2.fasta,E.fasta,M.fasta"/>
114 <output name="proteinortho">
115 <assert_contents>
116 <has_text text="# Species&#009;Genes&#009;Alg.-Conn."/>
117 <has_text text="2&#009;5&#009;0.16"/>
118 <has_text text="M_640,M_642,M_649"/>
119 </assert_contents>
120 </output>
121 <output name="blastgraph">
122 <assert_contents>
123 <has_text text="L_10&#009;E_10&#009;"/>
124 </assert_contents>
125 </output>
126 <output name="proteinorthograph">
127 <assert_contents>
128 <has_text text="L_11&#009;E_11&#009;"/>
129 </assert_contents>
130 </output>
131 </test>
132 <test expect_num_outputs="3"> <!-- various parameter -->
133 <param name="input_files" value="L.fasta,C.fasta,C2.fasta,E.fasta,M.fasta"/>
134 <param name="evalue" value="1"/>
135 <param name="conn" value="1"/>
136 <param name="cov" value="42"/>
137 <param name="sim" value="42"/>
138 <param name="identity" value="42"/>
139 <param name="selfblast" value="true"/>
140 <param name="singles" value="true"/>
141 <output name="proteinortho">
142 <assert_contents>
143 <has_text text="# Species&#009;Genes&#009;Alg.-Conn."/>
144 <has_text text="1&#009;1&#009;0"/>
145 <has_text text="&#009;C_177&#009;"/>
146 </assert_contents>
147 </output>
148 <output name="blastgraph">
149 <assert_contents>
150 <has_text text="C_1&#009;C_1&#009;"/>
151 </assert_contents>
152 </output>
153 <output name="proteinorthograph">
154 <assert_contents>
155 <has_text text="C_12&#009;C_21&#009;"/>
156 </assert_contents>
157 </output>
158 </test>
159 <test expect_num_outputs="3"> <!-- synteny -->
160 <param name="input_files" value="L.fasta,C.fasta,C2.fasta,E.fasta,M.fasta"/>
161 <param name="input_files_syn" value="L.gff,C.gff,C2.gff,E.gff,M.gff"/>
162 <param name="synteny_options" value="specified"/>
163 <output name="proteinortho">
164 <assert_contents>
165 <has_text text="# Species&#009;Genes&#009;Alg.-Conn."/>
166 <has_text text="4&#009;5&#009;0.144"/>
167 <has_text text="E_313,E_315"/>
168 </assert_contents>
169 </output>
170 <output name="proteinorthograph">
171 <assert_contents>
172 <has_text text="M_313&#009;L_313&#009;"/>
173 </assert_contents>
174 </output>
175 </test>
176 <test expect_num_outputs="3"> <!-- blast -->
177 <param name="input_files" value="L.fasta,C.fasta,C2.fasta,E.fasta,M.fasta"/>
178 <param name="--p" value="blastp"/>
179 <output name="proteinortho">
180 <assert_contents>
181 <has_text text="# Species&#009;Genes&#009;Alg.-Conn."/>
182 <has_text text="2&#009;5&#009;0.16"/>
183 <has_text text="M_640,M_642,M_649"/>
184 </assert_contents>
185 </output>
186 <output name="blastgraph">
187 <assert_contents>
188 <has_text text="M_3&#009;L_3&#009;"/>
189 </assert_contents>
190 </output>
191 <output name="proteinorthograph">
192 <assert_contents>
193 <has_text text="M_317&#009;L_317&#009;"/>
194 </assert_contents>
195 </output>
196 </test>
197 <test expect_num_outputs="3"> <!-- auto blast -->
198 <param name="input_files" value="L.fasta,C.fasta,C2.fasta,E.fasta,M.fasta"/>
199 <param name="--p" value="autoblast"/>
200 <output name="proteinortho">
201 <assert_contents>
202 <has_text text="# Species&#009;Genes&#009;Alg.-Conn."/>
203 <has_text text="2&#009;5&#009;0.16"/>
204 <has_text text="M_640,M_642,M_649"/>
205 </assert_contents>
206 </output>
207 <output name="blastgraph">
208 <assert_contents>
209 <has_text text="M_3&#009;L_3&#009;"/>
210 </assert_contents>
211 </output>
212 <output name="proteinorthograph">
213 <assert_contents>
214 <has_text text="M_317&#009;L_317&#009;"/>
215 </assert_contents>
216 </output>
217 </test>
218 <test expect_num_outputs="3"> <!-- last -->
219 <param name="input_files" value="L.fasta,C.fasta,C2.fasta,E.fasta,M.fasta"/>
220 <param name="--p" value="lastp"/>
221 <output name="proteinortho">
222 <assert_contents>
223 <has_text text="# Species&#009;Genes&#009;Alg.-Conn."/>
224 <has_text text="2&#009;5&#009;0.16"/>
225 <has_text text="M_640,M_642,M_649"/>
226 </assert_contents>
227 </output>
228 <output name="blastgraph">
229 <assert_contents>
230 <has_text text="M_636&#009;E_317&#009;"/>
231 </assert_contents>
232 </output>
233 <output name="proteinorthograph">
234 <assert_contents>
235 <has_text text="E_11&#009;C_11&#009;"/>
236 </assert_contents>
237 </output>
238 </test>
239 <test expect_num_outputs="3"> <!-- blat -->
240 <param name="input_files" value="L.fasta,C.fasta,C2.fasta,E.fasta,M.fasta"/>
241 <param name="--p" value="blastp"/>
242 <output name="proteinortho">
243 <assert_contents>
244 <has_text text="# Species&#009;Genes&#009;Alg.-Conn."/>
245 <has_text text="2&#009;5&#009;0.16"/>
246 <has_text text="M_640,M_642,M_649"/>
247 </assert_contents>
248 </output>
249 <output name="blastgraph">
250 <assert_contents>
251 <has_text text="E_10&#009;C_10&#009;"/>
252 </assert_contents>
253 </output>
254 <output name="proteinorthograph">
255 <assert_contents>
256 <has_text text="E_10&#009;C_10&#009;"/>
257 </assert_contents>
258 </output>
259 </test>
260 </tests>
261 <help><![CDATA[Proteinortho with POFF - An orthology detection tool
262
263 **What it does**
264
265 Proteinortho is a tool to detect orthologous proteins/genes within different species (at least 2).
266
267 | It compares similarities of given gene/protein sequences and clusters them to find significant groups.
268 | The algorithm was designed to handle large-scale data and can be applied to hundreds of species at one.
269 | Details can be found in (doi:10.1186/1471-2105-12-124).
270 | To enhance the prediction accuracy, the relative order of genes (synteny) can be used as additional feature for the discrimination of orthologs. The corresponding extension, namely PoFF (details see doi:10.1371/journal.pone.0105015), is already build in Proteinortho.
271
272 ----
273
274 **Proteinortho in a nutshell**
275
276 ----
277
278 * **(i) Build adaptive reciprocal best hit graph (RBH)**
279
280 | Using the blast algorithm (diamond,blast,blat,...) all input sequences are compared against each other.
281 | If two proteins find each other with respect to multiple criteria like minimal evalue, similarity compared to the best hit, ... then a edge is drawn between the two proteins.
282 | The result of this step is outputted to RBH
283
284 * **(ii) Cluster the RBH**
285
286 | Using two clustering algorithms, edges are removed that weakly connect two connected components to reduce false positive hits.
287 | The resulting connected components are outputted in orthology-groups / -PAIRS
288
289 ----
290
291 **Proteinortho output files**
292
293 ----
294
295 * **RBH**
296
297 | The result of the (i) step, the reciprocal best hit graph.
298 | First a comment line announces 2 species (# ecoli.faa human.faa), then each line corresponds to a reciprocal best hit between 2 proteins/genes of the announced species. The output format is shown below.
299 | *seqidA*,*seqidB* = the 2 ids/names of the proteins involved
300 | *evalue_ab* = evalue with seqidA as query and seqidB as part of the database
301 | *bitscore_ab* = bitscore with seqidA as query ...
302 | *evalue_ba* = evalue with seqidB as query ...
303 | ...
304
305 .. csv-table::
306
307 seqidA,seqidB,evalue_ab,bitscore_ab,evalue_ba,bitscore_ba
308
309 ----
310
311 * **orthology-groups**
312
313 | The result of the (ii) step, the clustered reciprocal best hit graph or the orthology groups.
314 | Every line corresponds to an orthology group of proteins/genes.
315 | The first 3 columns characterize general properties of that group: number of proteins, species and the algebraic connectivity. The higher the algebraic connectivity the more edges are there and the better the group is connected to itself in general.
316 | Then a column for each species follows containing the proteins of that species. If a species contributes with more than one protein to a group of orthologs, then they are ordered by connectivity.
317
318 .. csv-table::
319
320 Species,Genes,Alg.-Conn.
321
322 ----
323
324 * **orthology-pairs**
325
326 | The same as orthology-groups but every edge is printed one-by-one here. The output is formatted the same as the RBH graph:
327
328 .. csv-table::
329
330 seqidA,seqidB,evalue_ab,bitscore_ab,evalue_ba,bitscore_ba
331
332 ----
333
334 **Proteinortho-Tools for downstream analysis**
335
336 * `proteinortho grab proteins` : find gene(s)/protein(s) in a given fasta file and retrieve their sequence(s). You can also use a orthology-groups file.
337 * `proteinortho summary` : Summaries the orthology-pairs/RBH files to determine how the species are connected to each other.
338
339 More information can be found on github https://gitlab.com/paulklemm_PHD/proteinortho
340 ]]>
341 </help>
342 <expand macro="citations"/>
343 </tool>