Mercurial > repos > iuc > bigscape

comparison bigscape.xml @ 0:ccaa79de86c2 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/galaxyproject/tools-iuc/tree/master/tools/bigscape/ commit 8a0f3092ca824856263328efe66941409f527ca4
author iuc
date Sun, 11 Aug 2024 21:08:49 +0000
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:ccaa79de86c2
1 <tool id="bigscape" name="BiG-SCAPE" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="21.05">
2 <description>Construct sequence similarity networks of BGCs and group them into GCF</description>
3 <macros>
4 <token name="@TOOL_VERSION@">1.1.9</token>
5 <token name="@VERSION_SUFFIX@">2</token>
6 </macros>
7 <xrefs>
8 <xref type="bio.tools">BiG-SCAPE</xref>
9 </xrefs>
10 <requirements>
11 <requirement type="package" version="@TOOL_VERSION@">bigscape</requirement>
12 </requirements>
13 <command detect_errors="exit_code">
14 <![CDATA[
15
16 #set $path_to_html = $html.files_path
17 mkdir -p '$path_to_html' result input &&
18 #for $files in $inputdir:
19 #set $filename = "region." + $files.element_identifier
20 ln -s '$files' './input/${filename}.gbk' &&
21 #end for
22
23 mkdir pfam &&
24 ln -s '$pfam_dir' './pfam/$pfam_dir.element_identifier' &&
25 hmmpress './pfam/Pfam-A.hmm' &&
26
27 #if $anchor.is_select == "yes":
28 ln -s '$anchorfile' '$anchorfile.element_identifier' &&
29 #end if
30 #if $list.is_select == "yes":
31 cat '$__tool_directory__/domain_includelist.txt' > save.txt &&
32 cat '$domain_includelist' > '$__tool_directory__/domain_includelist.txt' &&
33 #end if
34
35 bigscape
36 --inputdir input
37 #if $mibig.is_select == "yes"
38 $mibig.mibig.value
39 #end if
40 --outputdir result
41 #if $use_label.is_select == "yes":
42 --label '${label}'
43 #end if
44 --pfam_dir pfam
45 --cores \${GALAXY_SLOTS:-8}
46 ${verbose}
47 ${log}
48 ${include_singletons}
49 --domain_overlap_cutoff ${domain_overlap_cutoff}
50 --min_bgc_size ${min_big_size}
51 ${mix}
52 ${no_classify}
53 #if $banned_classes.value:
54 --banned_classes
55 #for $banned in str($banned_classes).split( "," ):
56 '$banned'
57 #end for
58 #end if
59 --cutoffs #for $c in $cutoff# ${c.cutoffs} #end for#
60 ${clans_off}
61 #if $clan_cutoff.is_select == "yes":
62 --clan_cutoff $clan_cutoff_val1 $clan_cutoff_val2
63 #end if
64 ${hybrids_off}
65 --mode ${mode.value}
66 #if $anchor.is_select == "yes":
67 --anchorfile '${anchorfile.element_identifier}'
68 #end if
69 ${force_hmmscan}
70 #if $list.is_select == "yes":
71 --domain_includelist
72 #end if
73 &&
74
75 cp './result/index.html' '$html' &&
76 cp -r './result/html_content' '$path_to_html'
77
78 #if $list.is_select == "yes":
79 && cat save.txt > '$__tool_directory__/domain_includelist.txt'
80 #end if
81
82 #if $log:
83 && cp log.txt '$logfile'
84 #end if
85 ]]>
86 </command>
87 <inputs>
88 <param argument="--inputdir" format="genbank" multiple="true" type="data"
89 label="Data files to include in the clustering"
90 help="Add your .gbk files here. Do not wonder, in the filename 'region. will be added to ensure that every file will be included!" />
91 <conditional name="mibig">
92 <param name="is_select" type="select" label="Include BGCs from MIBiG database?"
93 help="Select yes and select which version of the database you want to use" >
94 <option value="yes" selected="False">Yes</option>
95 <option value="no" selected="True">No</option>
96 </param>
97 <when value="yes">
98 <param name="mibig" type="select" optional="false" label="Version from the MIBiG database"
99 help="Select which version of the MIBiG databse you want to use." >
100 <option value="--mibig">3.1</option>
101 <option value="--mibig21">2.1</option>
102 <option value="--mibig14">1.4</option>
103 <option value="--mibig13">1.3</option>
104 </param>
105 </when>
106 <when value="no" />
107 </conditional>
108 <conditional name="use_label" >
109 <param name="is_select" type="select" label="Adding extra string to BiG-SCAPE runs?"
110 help="Select yes if you want to add an extra string to the outputs">
111 <option value="yes" selected="False">Yes</option>
112 <option value="no" selected="True">No</option>
113 </param>
114 <when value="yes">
115 <param argument="--label" type="text" value="" optional="false" label="Adding extra string to BiG-SCAPE runs name"
116 help="By default the BiG-SCAPE runs are named as (YYYY-MM-DD_HH-MM-SS_[extra]) where extra means the mode and if activated (hybrids).">
117 <validator type="empty_field" />
118 </param>
119 </when>
120 <when value="no" />
121 </conditional>
122 <param argument="--pfam_dir" format="hmm3" type="data"
123 label="Data file Pfam-A.hmm"
124 help="Add Pfam-A.hmm.gz file here, please. Look at the help section where you can download it!" />
125 <param argument="--verbose" type="boolean" truevalue="--verbose" falsevalue="" checked="False"
126 label="Print more detailed information about each step"
127 help="Getting more information about the analysis if toggled is true." />
128 <param name="log" type="boolean" truevalue="> log.txt" falsevalue="" checked="False"
129 label="Extra log file as output"
130 help="When using you will receive a log file for the printed output of the toll. Can be useful when using the option above!" />
131 <param argument="--include_singletons" type="boolean" truevalue="--include_singletons" falsevalue="" checked="False"
132 label="Include BGCs with lower cutoff distance"
133 help="With this option you can include BGCs who don't have a distance lower than the cutoff distance specified" />
134 <param argument="--domain_overlap_cutoff" type="float" value="0.1" min="0.0" max="1.0"
135 label="Specify when domains are considered to overlap"
136 help="When using this option you can specify at which percentage domains are considered to overlap. The domain with the best score is kept. The default value is 0.1" />
137 <param argument="--min_big_size" type="integer" value="0"
138 label="Minimum size of a BGC (bp)"
139 help="Minimum size of a BGC to be included in the analysis. The Default value is 0 base pairs. This also includes the sum of all loci in a multi-record GenBank file." />
140 <param argument="--mix" type="boolean" truevalue="--mix" falsevalue="" checked="False"
141 label="mix all classes in the analysis"
142 help="BiG-SCAPE separates the analysis according to the BGC product by default. If used BiG-SCAPE will mix all classes and analyse them." />
143 <param argument="--no_classify" type="boolean" truevalue="--no_classify" falsevalue="" checked="False"
144 label="No classified output based on the BGC product"
145 help="By default, BiG-SCAPE classifies the output based on the BGC product. If toggled it will deactivate it. Note: when (--mix) is not activated, BiG-SCAPE will not create any network file!" />
146 <param argument="--banned_classes" type="select" optional="true" multiple="true" display="checkboxes"
147 label="Excluded classes from classification in BiG-SCAPE"
148 help="You can exclude any of these classes to not be classified. Multiple banned classes are possible." >
149 <option value="PKSI" selected="False">PKSI</option>
150 <option value="PKSother" selected="False">PKSother</option>
151 <option value="NRPS" selected="False">NRPS</option>
152 <option value="RiPPs" selected="False">RiPPs</option>
153 <option value="Saccharides" selected="False">Saccharides</option>
154 <option value="Terpene" selected="False">Terpene</option>
155 <option value="PKS-NRP_Hybrids" selected="False">PKS-NRP_Hybrids</option>
156 <option value="Others" selected="False">Others</option>
157 </param>
158 <repeat name="cutoff" title="Cutoffs" default="1"
159 help="Generate networks using multiple raw distance cutoff values. The default value here is 0.3.">
160 <param argument="--cutoffs" type="float" value="0.3" min="0.1" max="1.0"
161 label="GCF cutoff value"/>
162 </repeat>
163 <param argument="--clans-off" type="boolean" truevalue="--clans-off" falsevalue="" checked="False"
164 label="Turn off cluster GCFs into GCCs"
165 help="By default, BiG-SCAPE will perform a second layer of clustering to group GCFs into GCCs. Toggle to deactivate this." />
166 <conditional name="clan_cutoff" >
167 <param name="is_select" type="select" label="Change cutoff values for cluster GCF into GCC?"
168 help="Select yes if you want to change cutoffs for cluster families into clans.">
169 <option value="yes" selected="False">Yes</option>
170 <option value="no" selected="True">No</option>
171 </param>
172 <when value="yes">
173 <param name="clan_cutoff_val1" type="float" value="0.3" min="0.1" max="1.0" label="GCF cutoff value"
174 help="This value is for finding GCFs which will be used for clan calling. The default value is 0.3." />
175 <param name="clan_cutoff_val2" type="float" value="0.7" min="0.1" max="1.0" label="GCC cutoff value"
176 help="This value is for clustering families into clans. The default value is 0.7. Every pair of GCFs linked with a distance of this value or less will be taken into account!" />
177 </when>
178 <when value="no" />
179 </conditional>
180 <param argument="--hybrids-off" type="boolean" truevalue="--hybrids-off" falsevalue="" checked="False"
181 label="Exclude hybrid predicted products"
182 help="By default, BGCs with hybrid predicted products from the PKS/NRPS Hybrids and Others classes will be included in each subclass. Since the same cluster can appear in different classes you can turn this off here." />
183 <param argument="--mode" type="select"
184 label="Alignment Mode"
185 help="Here you can choose between 3 Alignment Mode which is used in comparing each pair of gene clusters. For more information look into the help section!" >
186 <option value="glocal">glocal</option>
187 <option value="global">global</option>
188 <option value="auto">auto</option>
189 </param>
190 <conditional name="anchor">
191 <param name="is_select" type="select" label="Change Anchorfile?"
192 help="Select yes if you want to use an Anchorfile. BiG-SCAPE has a default file which is always used and only these domains are counted in the result. Look in the help section to see what are the default domains!" >
193 <option value="yes" selected="False">Yes</option>
194 <option value="no" selected="True">No</option>
195 </param>
196 <when value="yes">
197 <param argument="--anchorfile" type="data" format="txt" optional="false"
198 label="Using a different Anchorfile instead of default file"
199 help="Use a custom Anchorfile (in .txt format) to give certain domains a special weight in the DSS index. This file is important because otherwise certain domains (given from Pfam IDs) will not be listed in the results!" />
200 </when>
201 <when value="no" />
202 </conditional>
203 <param argument="--force_hmmscan" type="boolean" truevalue="--force_hmmscan" falsevalue="" checked="False"
204 label="Use hmmscan for the domain prediction"
205 help="Even if BiG-SCAPE finds processed domtables files we can force the domain prediction with hmmscan. Toggle to force hmmscan!" />
206 <conditional name="list">
207 <param name="is_select" type="select" label="Use a domain list to include domains?"
208 help="Select yes if you want to use a list to filter the input to certain domains. Look in the help section how this list should look like">
209 <option value="yes" selected="False">Yes</option>
210 <option value="no" selected="True">No</option>
211 </param>
212 <when value="yes">
213 <param argument="--domain_includelist" type="data" format="txt" optional="false"
214 label="Use a .txt file to include domains"
215 help="Upload a text file where the inputs are filtered based on the Pfam IDs/domains given in this file!" />
216 </when>
217 <when value="no" />
218 </conditional>
219 </inputs>
220 <outputs>
221 <data name="html" format="html" label="${tool.name}: HTML"/>
222 <collection name="tsv_collection_1" type="list" format="tabular" label="${tool.name}: NETWORK ANNOTATIONS COLLECTION">
223 <discover_datasets pattern="Network_Annotations_(?P&lt;designation&gt;.+)\.tsv" directory="result/network_files" recurse="true"/>
224 </collection>
225 <collection name="tsv_collection_2" type="list" format="tabular" label="${tool.name}: CLAN TABULAR FILES COLLECTION">
226 <discover_datasets pattern="(?P&lt;identifier_0&gt;[^_]+)_clans_(?P&lt;designation&gt;.+)\.tsv" directory="result/network_files" recurse="true"/>
227 <filter> clans_off == False </filter>
228 </collection>
229 <collection name="tsv_collection_3" type="list:list" format="tabular" label="${tool.name}: CLUSTERING TABULAR FILES COLLECTION">
230 <discover_datasets pattern="(?P&lt;identifier_0&gt;[^_]+)_clustering_(?P&lt;identifier_1&gt;.+)\.tsv" directory="result/network_files" recurse="true"/>
231 </collection>
232 <collection name="newtwork_collection" type="list" format="network" label="${tool.name}: NETWORK FILES COLLECTION">
233 <discover_datasets pattern="(?P&lt;designation&gt;.+)\.network" directory="result/network_files" recurse="true"/>
234 </collection>
235 <data name="logfile" format="txt" label="${tool.name}: LOG FILE">
236 <filter>log == True</filter>
237 </data>
238 </outputs>
239 <tests>
240 <test expect_num_outputs="5">
241 <param name="pfam_dir" value="Pfam-A.hmm" ftype="hmm3"/>
242 <param name="inputdir" value="NC_010530.1.region005.gbk,NC_012963.1.region001.gbk,NW_009799099.1.region003.gbk,NW_021940918.1.region003.gbk,NW_009799102.1.region001.gbk,NW_022985561.1.region002.gbk,NW_022985549.1.region005.gbk,NW_022985575.1.region001.gbk" ftype="genbank" />
243 </test>
244 <test expect_num_outputs="6">
245 <param name="pfam_dir" value="Pfam-A.hmm" ftype="hmm3"/>
246 <param name="inputdir" value="NC_010530.1.region005.gbk,NC_012963.1.region001.gbk,NW_009799099.1.region003.gbk,NW_021940918.1.region003.gbk,NW_009799102.1.region001.gbk,NW_022985561.1.region002.gbk,NW_022985549.1.region005.gbk,NW_022985575.1.region001.gbk" ftype="genbank" />
247 <param name="log" value="true" />
248 <repeat name="cutoff">
249 <param name="cutoffs" value="1.0"/>
250 </repeat>
251 <output name="html" >
252 <assert_contents>
253 <has_line line="&lt;!DOCTYPE html&gt;" />
254 </assert_contents>
255 </output>
256 <output name="logfile">
257 <assert_contents>
258 <has_line line=" - - Processing input files - -" />
259 </assert_contents>
260 </output>
261 <output_collection name="tsv_collection_1" type="list">
262 <element name="Full" >
263 <assert_contents>
264 <has_text text="Accession ID" n="1"/>
265 </assert_contents>
266 </element>
267 </output_collection>
268 <output_collection name="tsv_collection_2" type="list">
269 <element name="NRPS">
270 <assert_contents>
271 <has_text text="Clan Number" n="1"/>
272 </assert_contents>
273 </element>
274 </output_collection>
275 <output_collection name="tsv_collection_3" type="list:list">
276 <element name="NRPS">
277 <element name="c0.30">
278 <assert_contents>
279 <has_text text="Family Number" n="1" />
280 </assert_contents>
281 </element>
282 <element name="c1.00">
283 <assert_contents>
284 <has_text text="Family Number" n="1" />
285 </assert_contents>
286 </element>
287 </element>
288 </output_collection>
289 <output_collection name="newtwork_collection" type="list">
290 <element name="NRPS_c0.30">
291 <assert_contents>
292 <has_text text="Raw distance" n="1"/>
293 </assert_contents>
294 </element>
295 </output_collection>
296 </test>
297 <test expect_num_outputs="5">
298 <param name="pfam_dir" value="Pfam-A.hmm" ftype="hmm3"/>
299 <param name="inputdir" value="NC_012963.1.region001.no-genbank-suffix,NC_010530.1.region005.gbk,NC_012963.1.region001.gbk,NW_009799099.1.region003.gbk,NW_021940918.1.region003.gbk,NW_009799102.1.region001.gbk,NW_022985561.1.region002.gbk,NW_022985549.1.region005.gbk,NW_022985575.1.region001.gbk" ftype="genbank" />
300 <param name="log" value="true" />
301 <param name="clans_off" value="true" />
302 </test>
303 <test expect_num_outputs="5">
304 <param name="pfam_dir" value="Pfam-A.hmm" ftype="hmm3"/>
305 <param name="inputdir" value="NC_012963.1.region001.no-genbank-suffix,NC_010530.1.region005.gbk" ftype="genbank" />
306 <param name="log" value="true" />
307 <param name="clans_off" value="true" />
308 </test>
309 </tests>
310 <help>
311 <![CDATA[
312 .. class:: infomark
313
314 **What is BiG-SCAPE**
315
316 BiG-SCAPE (Biosynthetic Gene Similarity Clustering and Prospecting Engine) is a software package, written in Python, that constructs sequence similarity networks of Biosynthetic Gene Clusters (BGCs) and groups them into Gene Cluster Families (GCFs).
317
318 .. class:. infomark
319
320 **What it does**
321
322 BiG-SCAPE does this by rapidly calculating a distance matrix between gene clusters based on a comparison of their protein domain content, order, copy number and sequence identity.
323
324 In principle, BiG-SCAPE can also be used on any other gene clusters, such as pathogenicity islands, secretion system-encoding gene clusters, or even whole viral genomes.
325
326 Here is a grapic how BiG-SCAPE works:
327
328 .. image:: bigscape_corason.png
329 :alt: BiG-SCAPE + CORASON workflow
330
331 For more information you can visit `BiG-SCAPE on GitHub <https://github.com/medema-group/BiG-SCAPE>`_ or go on the `combine website <https://bigscape-corason.secondarymetabolites.org/index.html>`_.
332
333 **Input**
334
335 BiG-SCAPE uses two kind of inputs:
336
337 - The genbank files from antiSMASH
338
339 .. class:: infomark
340
341 Note: By default, BiG-SCAPE includes any Genbank file where the filename contains either region or cluster. To ensure every file will be included we add 'region.' in in the file name!
342
343 - The Pfamm-A.hmm file
344
345 .. class:: infomark
346
347 Note: You can download `Pfam-A.hmm.gz <https://ftp.ebi.ac.uk/pub/databases/Pfam/current_release/Pfam-A.hmm.gz>`_ here and then unzip it or you can use the command: *$ wget https://ftp.ebi.ac.uk/pub/databases/Pfam/current_release/Pfam-A.hmm.gz && gunzip Pfam-A.hmm.gz* in e.g. VSC.
348
349 There are two additional inputs which can be used:
350
351 - An anchor_domains.txt file
352
353 .. class:: infomark:
354
355 Example (default file which will be used):
356
357 ::
358
359 PF00668 Condensation domain [NRPS]
360 PF00501 AMP-binding enzyme [NRPS]
361 PF00109 Beta-ketoacyl synthase N-terminal [PKS]
362 PF02801 Beta-ketoacyl synthase C-terminal [PKS]
363 PF01397 Terpene synthase, N-terminal domain (Terpene_synth) [Terpene]
364 PF03936 Terpene synthase family, metal binding domain (Terpene_synth_C) [Terpene]
365 PF00195 Chalcone and stilbene synthases, N-terminal domain (Cahl_sti_synt_N)
366 PF02797 Chalcone and stilbene synthases, C-terminal domain (Chal_sti_synt_C)
367 PF05147 Lanthionine synthetase C-like protein (LANC_like) [lantipeptide/RiPP]
368 PF00494 Squalene/phytoene synthase (SQS_PSY) [Terpene]
369 PF00432 Prenyltransferase and squalene oxidase repeat (Prenyltrans)
370 PF02624 YcaO cyclodehydratase, ATP-ad MG2+-binding (YcaO) [RiPP]
371
372 The first column contains the Pfam model ID while the second column is optionally for writing a comment. The columns are tab-separated!
373
374 - A domain_includelist.txt
375
376 .. class:: infomark
377
378 Example:
379
380 ::
381
382 PF00067 Cytochrome P450
383 PF01451 Any Comment
384
385 The first column contains the Pfam model ID while the second column is optionally for writing a comment. The columns are tab-separated and any line that starts with a # will be ignored!
386
387
388 **Output**
389
390 BiG-SCAPE will produce one HTML Output together with a dataset with different tabular files depending on the input. When the log file option is set it will create another output, where all prints made from this tool are stored.
391
392
393 **Additionally information for the alignment Mode**
394
395 - glocal: This is the default mode. Here the subset of the domains used to calculate distance is redefined by finding the longest slice of common domain content per gene in both BGCs, and then expanding each slice.
396
397 - global: The whole list of domains of each BGC are compared.
398
399 - auto: Use glocal mode when at least one of the BGCs in each pair has the contig_edge annotation from antiSMASH. Otherwise global will be used.
400 ]]>
401 </help>
402 <citations>
403 <citation type="doi">10.1038/s41589-019-0400-9</citation>
404 </citations>
405 </tool>