40
|
1 <tool id="bg_diamond" name="Diamond" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="19.01">
|
39
|
2 <description>alignment tool for short sequences against a protein database</description>
|
|
3 <macros>
|
|
4 <import>macros.xml</import>
|
|
5 </macros>
|
40
|
6 <xrefs>
|
|
7 <xref type="bio.tools">diamond</xref>
|
|
8 </xrefs>
|
|
9 <expand macro="requirements" />
|
39
|
10 <expand macro="stdio" />
|
|
11 <expand macro="version_command" />
|
|
12 <command detect_errors="aggressive">
|
|
13 <![CDATA[
|
|
14
|
|
15 #if $ref_db_source.db_source == "history":
|
|
16 ln -s $ref_db_source.reference_database ./database.dmnd
|
|
17 #else:
|
|
18 ln -s ${ref_db_source.index.fields.db_path} ./database.dmnd
|
|
19 #end if
|
|
20
|
|
21 &&
|
|
22
|
40
|
23 diamond
|
39
|
24 $method_cond.method_select
|
|
25 --quiet
|
|
26 --threads "\${GALAXY_SLOTS:-12}"
|
|
27 --db ./database
|
|
28 --query '$query'
|
|
29 #if $method_cond.method_select == "blastx"
|
|
30 --query-gencode '$method_cond.query_gencode'
|
|
31 --strand '$method_cond.query_strand'
|
|
32 --min-orf $method_cond.min_orf
|
|
33 #if $method_cond.frameshift_cond.frameshift_select == 'yes'
|
|
34 --frameshift $method_cond.frameshift_cond.frameshift
|
|
35 $method_cond.frameshift_cond.range_culling
|
|
36 #end if
|
|
37 #else if $method_cond.method_select == "blastp"
|
|
38 $method_cond.no_self_hits
|
|
39 #end if
|
|
40
|
|
41 @OUTPUT_ARGS@
|
|
42
|
|
43 #if $output_section.output.outfmt != '100'
|
|
44 --compress '0'
|
|
45 #end if
|
|
46 $sens_cond.sensitivity
|
|
47 $iterate
|
|
48 --algo $algo
|
|
49 #if $global_ranking
|
|
50 --global-ranking $global_ranking
|
|
51 #end if
|
|
52 #if str($gapopen) != "":
|
|
53 --gapopen '$gapopen'
|
|
54 #end if
|
|
55 #if str($gapextend) != "":
|
|
56 --gapextend '$gapextend'
|
|
57 #end if
|
|
58 --matrix '$matrix'
|
|
59 --comp-based-stats '$method_cond.comp_based_stats'
|
|
60 --masking '$masking'
|
|
61
|
|
62 @HITFILTER_ARGS@
|
|
63
|
|
64 #if str($filter_score.filter_score_select) == 'evalue':
|
|
65 --evalue '$filter_score.evalue'
|
|
66 #else:
|
|
67 --min-score '$filter_score.min_score'
|
|
68 #end if
|
|
69
|
|
70 --id '$id'
|
|
71 --query-cover '$query_cover'
|
|
72 --subject-cover '$subject_cover'
|
|
73 --block-size '$sens_cond.block_size'
|
|
74 #if $output_section.output_unal
|
|
75 #if "--un" in $output_section.output_unal
|
|
76 --un '$unalqueries'
|
|
77 #if $query.ext.startswith("fasta"):
|
|
78 --unfmt fasta
|
|
79 #else
|
|
80 --unfmt fastq
|
|
81 #end if
|
|
82 #end if
|
|
83 #if "--al" in $output_section.output_unal
|
|
84 --al '$alqueries'
|
|
85 #if $query.ext.startswith("fasta"):
|
|
86 --alfmt fasta
|
|
87 #else
|
|
88 --alfmt fastq
|
|
89 #end if
|
|
90 #end if
|
|
91 #end if
|
|
92 #if $output_section.max_hsps
|
|
93 --max-hsps $output_section.max_hsps
|
|
94 #end if
|
|
95 #if $tax_cond.tax_select == 'file':
|
|
96 --taxonlist `cat '$tax_cond.taxonlistfile' | grep -v "^#" | grep -v "^$" | tr "\n" "," | sed 's/,$//'`
|
|
97 #else if $tax_cond.tax_select == 'list':
|
|
98 --taxonlist '$tax_cond.taxonlist'
|
|
99 #end if
|
|
100 #if $advanced_section.seed_cut
|
|
101 --seed-cut $advanced_section.seed_cut
|
|
102 #end if
|
|
103 $advanced_section.freq_masking
|
|
104 --motif-masking $advanced_section.motif_masking
|
|
105 ]]>
|
|
106 </command>
|
|
107 <inputs>
|
|
108 <conditional name="method_cond">
|
|
109 <param name="method_select" type="select" label="Alignment mode" help="(blastp/blastx)">
|
|
110 <option value="blastp">Amino acid query sequences (blastp)</option>
|
|
111 <option value="blastx">DNA query sequences (blastx)</option>
|
|
112 </param>
|
|
113 <when value="blastx">
|
|
114 <param argument="--query-gencode" type="select" label="Genetic code used for translation of query in BLASTX mode" help="">
|
|
115 <option value="1">Standard Code</option>
|
|
116 <option value="2">Vertebrate Mitochondrial Code</option>
|
|
117 <option value="3">Yeast Mitochondrial Code</option>
|
|
118 <option value="4">Mold, Protozoan, and Coelenterate Mitochondrial Code and the Mycoplasma/Spiroplasma Code</option>
|
|
119 <option value="5">Invertebrate Mitochondrial Code</option>
|
|
120 <option value="6">Ciliate, Dasycladacean and Hexamita Nuclear Code</option>
|
|
121 <option value="9">Echinoderm and Flatworm Mitochondrial Code</option>
|
|
122 <option value="10">Euplotid Nuclear Code</option>
|
|
123 <option value="11">Bacterial, Archaeal and Plant Plastid Code</option>
|
|
124 <option value="12">Alternative Yeast Nuclear Code</option>
|
|
125 <option value="13">Ascidian Mitochondrial Code</option>
|
|
126 <option value="14">Alternative Flatworm Mitochondrial Code</option>
|
|
127 <option value="16">Chlorophycean Mitochondrial Code</option>
|
|
128 <option value="21">Trematode Mitochondrial Code</option>
|
|
129 <option value="22">Scenedesmus obliquus Mitochondrial Code</option>
|
|
130 <option value="23">Thraustochytrium Mitochondrial Code</option>
|
|
131 <option value="24">Pterobranchia Mitochondrial Code</option>
|
|
132 <option value="25">Candidate Division SR1 and Gracilibacteria Code</option>
|
|
133 <option value="26">Pachysolen tannophilus Nuclear Code</option>
|
|
134 </param>
|
|
135 <param argument="--min-orf" type="integer" value="1" label="ignore translated sequences without an open reading frame of at least this length" help="By default this feature is disabled for sequences of length below 30, set to 20 for sequences of length below 100, and set to 40 otherwise. Setting this option to 1 will disable this feature" />
|
|
136
|
|
137 <param name="query_strand" argument="--strand" type="select" label="query strands to search" help="">
|
|
138 <option value="both" selected="True">Both</option>
|
|
139 <option value="plus">Plus</option>
|
|
140 <option value="minus">Minus</option>
|
|
141 </param>
|
|
142 <conditional name="frameshift_cond">
|
|
143 <param name="frameshift_select" type="select" label="Allow for frameshifts?" help="">
|
|
144 <option value="yes">yes</option>
|
|
145 <option value="no" selected="true">no</option>
|
|
146 </param>
|
|
147 <when value="yes">
|
|
148 <param argument="--range-culling" type="boolean" truevalue="--range-culling" falsevalue="" checked="false" label="restrict hit culling to overlapping query ranges" help="This feature is designed for long query DNA sequences that may span several genes. In these cases, the default of reporting the 25 best overall hits could cause hits to a lower scoring gene to be overshadowed. But just increasing the number of alignments reported will bloat the output size and reduce performance. Using this feature along with -k 25 (default), a hit will only be deleted if at least 50% of its query range is spanned by at least 25 higher or equal scoring hits. Using this feature along with --top 10, a hit will only be deleted if its score is more than 10% lower than that of a higher scoring hit over at least 50% of its query range. The percentage is configurable using --range-cover. Note that this feature is currently only available in frameshift alignment mode"/>
|
|
149 <param argument="--frameshift" type="integer" value="0" label="frame shift penalty" help="Values around 15 are reasonable for this parameter. Enabling this feature will have the aligner tolerate missing bases in DNA sequences and is most recommended for long, error-prone sequences like MinION reads. In the pairwise output format, frameshifts will be indicated by \ and / for a shift by +1 and -1 nucleotide in the direction of translation respectively." />
|
|
150 </when>
|
|
151 <when value="no"/>
|
|
152 </conditional>
|
|
153
|
|
154 <param argument="--comp-based-stats" type="select" label="Composition based statistics" help="Compositionally biased sequences often cause false positive matches, which are effectively filtered by this algorithm in a way similar to the composition based statistics used by BLAST">
|
|
155 <option value="0">Disable</option>
|
|
156 <option value="1" selected="True">Default mode (Hauser, 2016)</option>
|
|
157 </param>
|
|
158 </when>
|
|
159 <when value="blastp">
|
|
160 <param argument="--no-self-hits" type="boolean" truevalue="--no-self-hits" falsevalue="" checked="true"
|
|
161 label="Suppress reporting of identical self-hits between sequences"
|
|
162 help="The FASTA sequence identifiers as well as the sequences of query and target need to be identical for a hit to be deleted"/>
|
|
163
|
|
164 <param argument="--comp-based-stats" type="select" label="Composition based statistics" help="Compositionally biased sequences often cause false positive matches, which are effectively filtered by this algorithm in a way similar to the composition based statistics used by BLAST">
|
|
165 <option value="0">Disable</option>
|
|
166 <option value="1" selected="True">Default mode (Hauser, 2016)</option>
|
|
167 <option value="2">Compositional matrix adjust conditioned on sequence properties, simplified (Yu, 2005)</option>
|
|
168 <option value="3">Compositional matrix adjust conditioned on sequence properties (Yu, 2005)</option>
|
|
169 <option value="4">Compositional matrix adjust unconditionally (Yu, 2005)</option>
|
|
170 </param>
|
|
171 </when>
|
|
172 </conditional>
|
|
173 <param argument="--query" type="data" format="fasta,fastq" label="Input query file in FASTA or FASTQ format" />
|
|
174 <conditional name="ref_db_source">
|
|
175 <param name="db_source" type="select" label="Will you select a reference database from your history or use a built-in index?" help="Built-ins were indexed using default options">
|
|
176 <option value="indexed">Use a built-in index</option>
|
|
177 <option value="history">Use one from the history</option>
|
|
178 </param>
|
|
179 <when value="indexed">
|
|
180 <param name="index" type="select" label="Select a reference database" help="If your database of interest is not listed, contact your Galaxy admin">
|
40
|
181 <options from_data_table="diamond_database">
|
39
|
182 <filter type="sort_by" column="2"/>
|
|
183 <validator type="no_options" message="No indexes are available for the selected input dataset"/>
|
|
184 </options>
|
|
185 </param>
|
|
186 </when>
|
|
187 <when value="history">
|
|
188 <param name="reference_database" argument="--db" type="data" format="dmnd" label="Select the reference database" />
|
|
189 </when>
|
|
190 </conditional>
|
|
191 <conditional name="tax_cond">
|
|
192 <param name="tax_select" type="select" label="Restrict search taxonomically?" help="Any taxonomic rank can be used, and only reference sequences matching one of the specified taxon ids will be searched against.">
|
|
193 <option value="no" selected="True">No</option>
|
|
194 <option value="list">List of taxids entered manually</option>
|
|
195 <option value="file">List of taxids from single column tabular file</option>
|
|
196 </param>
|
|
197 <when value="no"/>
|
|
198 <when value="list">
|
|
199 <param name="taxonlist" argument="--taxonlist" type="text" value="" label="Comma separated list of taxon ids" help="">
|
|
200 <validator type="regex" message="Taxonlist needs to be a comma separated list of integers">[0-9,]*</validator>
|
|
201 </param>
|
|
202 </when>
|
|
203 <when value="file">
|
|
204 <param name="taxonlistfile" argument="--taxonlist" type="data" format="tabular" label="Keep alignments within the given percentage range of the top alignment score for a quer" help="" />
|
|
205 </when>
|
|
206 </conditional>
|
|
207 <conditional name="sens_cond">
|
|
208 <param name='sensitivity' type="select" label="Sensitivity Mode" help="Choose one of the sensitivity modes. The default mode is mainly designed for short read alignment, i.e. finding significant matches of >50 bits on 30-40aa fragments. The sensitive mode is a lot more sensitive than the default and generally recommended for aligning longer sequences. The more sensitive mode provides even more sensitivity. More sensitivity may increase computation time.">
|
|
209 <option value="--fast">Fast (--fast)</option>
|
|
210 <option value="" selected="True">Default</option>
|
|
211 <option value="--mid-sensitive">Mid Sensitive (--mid-sensitive)</option>
|
|
212 <option value="--sensitive">Sensitive (--sensitive)</option>
|
|
213 <option value="--more-sensitive">More Sensitive (--more-sensitive)</option>
|
|
214 <option value="--very-sensitive">Very Sensitive (--very-sensitive)</option>
|
|
215 <option value="--ultra-sensitive">Ultra Sensitive (--ultra-sensitive)</option>
|
|
216 </param>
|
|
217 <when value="--fast">
|
|
218 <expand macro="block_size_low_sens"/>
|
|
219 </when>
|
|
220 <when value="">
|
|
221 <expand macro="block_size_low_sens"/>
|
|
222 </when>
|
|
223 <when value="--mid-sensitive">
|
|
224 <expand macro="block_size_low_sens"/>
|
|
225 </when>
|
|
226 <when value="--sensitive">
|
|
227 <expand macro="block_size_low_sens"/>
|
|
228 </when>
|
|
229 <when value="--more-sensitive">
|
|
230 <expand macro="block_size_low_sens"/>
|
|
231 </when>
|
|
232 <when value="--very-sensitive">
|
|
233 <expand macro="block_size_hi_sens"/>
|
|
234 </when>
|
|
235 <when value="--ultra-sensitive">
|
|
236 <expand macro="block_size_hi_sens"/>
|
|
237 </when>
|
|
238 </conditional>
|
|
239 <param argument="--matrix" type="select" label="Scoring matrix" help="In parentheses are the supported values for (gap open)/(gap extend). In brackets are default gap penalties">
|
|
240 <option value="BLOSUM45">BLOSUM45 ((10-13)/3; (12-16)/2; (16-19)/1) [14/2]</option>
|
|
241 <option value="BLOSUM50">BLOSUM50 ((9-13)/3; (12-16)/2; (15-19)/1) [13/2]</option>
|
|
242 <option value="BLOSUM62" selected="True">BLOSUM62 ((6-11)/2; (9-13)/1) [11/1]</option>
|
|
243 <option value="BLOSUM80">BLOSUM80 ((6-9)/2; 13/2; 25/2; (9-11)/1) [10/1]</option>
|
|
244 <option value="BLOSUM90">BLOSUM90 ((6-9)/2; (9-11)/1) [10/1]</option>
|
|
245 <option value="PAM250">PAM250 ((11-15)/3; (13-17)/2; (17-21)/1) [14/2]</option>
|
|
246 <option value="PAM70">PAM70 ((6-8)/2; (9-11)/1) [10/1]</option>
|
|
247 <option value="PAM30">PAM30 ((5-7)/2; (8-10)/1) [9/1]</option>
|
|
248 </param>
|
|
249 <param argument="--gapopen" type="integer" optional="True" value="" label="Gap open penalty" help="Leave empty for default (see scoring matrix)" />
|
|
250 <param argument="--gapextend" type="integer" optional="True" value="" label="Gap extension penalty" help="Leave empty for default (see scoring matrix)" />
|
|
251 <param argument="--masking" type="select" label="Masking algorithm" help="DIAMOND by default applies the tantan repeat masking algorithm to the query and target sequences as described in (Frith, 2011).
|
|
252 This masking procedure increases the specificity of alignments and serves to filter out spurious hits. Note that when using --comp-based-stats (2,3,4), tantan masking is disabled by default.">
|
|
253 <option value="0">Disabled</option>
|
|
254 <option value="1" selected="true">Tantan</option>
|
|
255 <option value="seg">SEG</option>
|
|
256 </param>
|
|
257 <conditional name="filter_score">
|
|
258 <param name="filter_score_select" type="select" label="Method to filter?" help="(--evalue/--min-score)">
|
|
259 <option value="evalue" selected="True">Maximum e-value to report alignments</option>
|
|
260 <option value="min-score">Minimum bit score to report alignments</option>
|
|
261 </param>
|
|
262 <when value="evalue">
|
|
263 <param argument="--evalue" type="float" value="0.001" label="Maximum expected value to keep an alignment" />
|
|
264 </when>
|
|
265 <when value="min-score">
|
|
266 <param name="min_score" argument="--min-score" type="integer" value="0" label="Minimum bit score to keep an alignment" help="(--min-score)" />
|
|
267 </when>
|
|
268 </conditional>
|
|
269 <param argument="--iterate" type="boolean" truevalue="--iterate" falsevalue="" checked="false"
|
|
270 label="Run multiple rounds of searches with increasing sensitivity" help="he query dataset will first be searched at a lower sensitivity setting, only searching those query sequences at
|
|
271 the target sensitivity that fail to produce a significant alignment at a lower sensitivity." />
|
|
272 <param argument="--algo" type="select" label="Algorithm for seed search" help="Double-indexed is the main algorithm of the program, designed for large input files but less efficient for small
|
|
273 query files. Query-indexed and improves performance for small query files. This mode will be automatically triggered based on the input. Contiguous-seed mode and further improves performance
|
|
274 for small query files. The modes differ slightly in their sensitivity, so results are not guaranteed to be 100% identical for different settings of this option.">
|
|
275 <option value="0">Doble-indexed (0)</option>
|
|
276 <option value="1">Query-indexed (1)</option>
|
|
277 <option value="ctg">Contiguous-seed mode (ctg)</option>
|
|
278 </param>
|
|
279 <expand macro="hit_filter_macro" />
|
|
280 <param argument="--global-ranking" type="integer" min="0" value="" optional="true"
|
|
281 label="Limit on the number of Smith Waterman extensions" help="Target sequences will be ranked according to their ungapped extension scores at seed hits, and gapped extensions will only
|
|
282 be computed for the best N targets for each query. Note that this option increases memory use." />
|
|
283 <param argument="--id" type="integer" value="0" label="Minimum identity percentage to report an alignment" help="Report only alignments above the given percentage of sequence identity" />
|
|
284 <param argument="--query-cover" type="integer" value="0" label="Minimum query cover percentage to report an alignment" help="Report only alignments above the given percentage of query cover" />
|
|
285 <param argument="--subject-cover" type="integer" value="0" label="Minimum subject cover percentage to report an alignment" help="Report only alignments above the given percentage of subject cover"/>
|
|
286 <section name="output_section" title="Output options">
|
|
287 <param argument="--max-hsps" type="integer" min="0" optional="true" label="Maximum number of HSPs"
|
|
288 help="The maximum number of HSPs (High-Scoring Segment Pairs) per target sequence to report for each query. The default policy is to report only the highest-scoring
|
|
289 HSP for each target, while disregarding alternative, lower-scoring HSPs that are contained in the same target." />
|
|
290 <expand macro="output_type_macro">
|
|
291 <!-- Taxonomy features are not supported for the DAA format (i.e.
|
|
292 can't be used in diamond view) -->
|
|
293 <option value="staxids">unique Subject Taxonomy ID(s), separated by a ';' (in numerical order)</option>
|
|
294 <option value="sskingdoms">Subject super kingdoms</option>
|
|
295 <option value="skingdoms">Subject kingdoms</option>
|
|
296 <option value="sphylums">Subject phylums</option>
|
|
297 </expand>
|
|
298 <param name="output_unal" type="select" optional="true" multiple="true" label="Output aligned/unaligned queries to separate file" help="">
|
|
299 <option value="--un">Output unaligned queries (--un)</option>
|
|
300 <option value="--al">Output alaligned queries (--al)</option>
|
|
301 </param>
|
|
302 </section>
|
|
303 <section name="advanced_section" title="Advanced options" expanded="false">
|
|
304 <param argument="--seed-cut" type="float" min="0" optional="true" label="Set a complexity cutoff for indexed seeds"/>
|
|
305 <param argument="--freq-masking" type="boolean" truevalue="--freq-masking" falsevalue="" checked="false" label="Enable masking seeds based on frequency" help="This option is incompatible with --sed-cut" />
|
|
306 <param argument="--motif-masking" type="select" label="Softmask abundant motifs" help="Enable or disable motif masking">
|
|
307 <option value="0">Disabled</option>
|
|
308 <option value="1">Enabled</option>
|
|
309 </param>
|
|
310 </section>
|
|
311 </inputs>
|
|
312 <outputs>
|
|
313 <expand macro="output_macro" />
|
|
314 <data format_source="query" name="unalqueries" label="${tool.name} on ${on_string}: unaligned queries">
|
|
315 <filter>output_section['output_unal'] and "--un" in output_section['output_unal']</filter>
|
|
316 </data>
|
|
317 <data format_source="query" name="alqueries" label="${tool.name} on ${on_string}: aligned queries">
|
|
318 <filter>output_section['output_unal'] and "--un" in output_section['output_unal']</filter>
|
|
319 </data>
|
|
320 </outputs>
|
40
|
321 <tests>
|
|
322 <!--Test 01-->
|
|
323 <test expect_num_outputs="3">
|
|
324 <conditional name="method_cond">
|
|
325 <param name="method_select" value="blastp" />
|
|
326 </conditional>
|
|
327 <param name="query" value="protein.fasta" ftype="fasta"/>
|
|
328 <conditional name="ref_db_source">
|
|
329 <param name="db_source" value="history"/>
|
|
330 <param name="reference_database" value="db-wtax.dmnd"/>
|
|
331 </conditional>
|
|
332 <section name="output_section">
|
|
333 <conditional name="output">
|
|
334 <param name="outfmt" value="6"/>
|
|
335 <!-- removed ,cigar from test: https://github.com/bbuchfink/diamond/issues/532 -->
|
|
336 <param name="fields" value="qseqid,sseqid,pident,length,mismatch,gapopen,qstart,qend,sstart,send,evalue,bitscore,scovhsp,sskingdoms,skingdoms,sphylums"/>
|
|
337 <param name="unal" value="true"/>
|
|
338 </conditional>
|
|
339 </section>
|
|
340 <conditional name="sens_cond">
|
|
341 <param name="sensitivity" value=""/>
|
|
342 </conditional>
|
|
343 <param name="matrix" value="BLOSUM62"/>
|
|
344 <param name="comp_based_stats" value="1"/>
|
|
345 <param name="masking" value="1"/>
|
|
346 <conditional name="hit_filter">
|
|
347 <param name="hit_filter_select" value="max"/>
|
|
348 <param name="max_target_seqs" value="25" />
|
|
349 </conditional>
|
|
350 <conditional name="filter_score">
|
|
351 <param name="filter_score_select" value="evalue"/>
|
|
352 <param name="evalue" value="0.001" />
|
|
353 </conditional>
|
|
354 <param name="id" value="0"/>
|
|
355 <param name="query_cover" value="0"/>
|
|
356 <conditional name="sens_cond">
|
|
357 <param name="block_size" value="2"/>
|
|
358 </conditional>
|
|
359 <param name="output_unal" value="--al,--un"/>
|
|
360 <output name="unalqueries">
|
|
361 <assert_contents>
|
|
362 <has_line line=">shuffled sequence that should go to unaligned"/>
|
|
363 </assert_contents>
|
|
364 </output>
|
|
365 <output name="alqueries">
|
|
366 <assert_contents>
|
|
367 <has_line line=">sequence more text"/>
|
|
368 </assert_contents>
|
|
369 </output>
|
|
370 <output name="blast_tabular" file="diamond_results.tabular"/>
|
|
371 </test>
|
|
372 <!--Test 02-->
|
|
373 <test expect_num_outputs="1">
|
|
374 <conditional name="method_cond">
|
|
375 <param name="method_select" value="blastp" />
|
|
376 </conditional>
|
|
377 <param name="query" value="protein.fasta" ftype="fasta"/>
|
|
378 <conditional name="ref_db_source">
|
|
379 <param name="db_source" value="history"/>
|
|
380 <param name="reference_database" value="db-wtax.dmnd"/>
|
|
381 </conditional>
|
|
382 <conditional name="tax_cond">
|
|
383 <param name="tax_select" value="list"/>
|
|
384 <param name="taxonlist" value="2" />
|
|
385 </conditional>
|
|
386 <section name="output_section">
|
|
387 <conditional name="output">
|
|
388 <param name="outfmt" value="6"/>
|
|
389 <param name="fields" value="qseqid,sseqid,pident,length,mismatch,gapopen,qstart,qend,sstart,send,evalue,bitscore"/>
|
|
390 </conditional>
|
|
391 </section>
|
|
392 <conditional name="sens_cond">
|
|
393 <param name="sensitivity" value=""/>
|
|
394 </conditional>
|
|
395 <param name="matrix" value="BLOSUM62"/>
|
|
396 <param name="comp_based_stats" value="1"/>
|
|
397 <param name="masking" value="1"/>
|
|
398 <conditional name="hit_filter">
|
|
399 <param name="hit_filter_select" value="max"/>
|
|
400 <param name="max_target_seqs" value="25" />
|
|
401 </conditional>
|
|
402 <conditional name="filter_score">
|
|
403 <param name="filter_score_select" value="evalue"/>
|
|
404 <param name="evalue" value="0.001" />
|
|
405 </conditional>
|
|
406 <param name="id" value="0"/>
|
|
407 <param name="query_cover" value="0"/>
|
|
408 <conditional name="sens_cond">
|
|
409 <param name="block_size" value="2"/>
|
|
410 </conditional>
|
|
411 <output name="blast_tabular" file="diamond_results.wtax.tabular"/>
|
|
412 </test>
|
|
413 <!--Test 03-->
|
|
414 <test expect_num_outputs="1">
|
|
415 <conditional name="method_cond">
|
|
416 <param name="method_select" value="blastx" />
|
|
417 <conditional name="frameshift_cond">
|
|
418 <param name="frameshift_select" value="yes"/>
|
|
419 </conditional>
|
|
420 </conditional>
|
|
421 <param name="query" value="nucleotide.fasta" ftype="fasta"/>
|
|
422 <conditional name="ref_db_source">
|
|
423 <param name="db_source" value="history"/>
|
|
424 <param name="reference_database" value="db.dmnd"/>
|
|
425 </conditional>
|
|
426 <section name="output_section">
|
|
427 <conditional name="output">
|
|
428 <param name="outfmt" value="0"/>
|
|
429 </conditional>
|
|
430 </section>
|
|
431 <conditional name="sens_cond">
|
|
432 <param name="sensitivity" value=""/>
|
|
433 </conditional>
|
|
434 <param name="matrix" value="BLOSUM62"/>
|
|
435 <param name="comp_based_stats" value="1"/>
|
|
436 <param name="masking" value="1"/>
|
|
437 <conditional name="hit_filter">
|
|
438 <param name="hit_filter_select" value="top"/>
|
|
439 <param name="top" value="10" />
|
|
440 </conditional>
|
|
441 <conditional name="filter_score">
|
|
442 <param name="filter_score_select" value="min-score"/>
|
|
443 <param name="min_score" value="1" />
|
|
444 </conditional>
|
|
445 <param name="id" value="0"/>
|
|
446 <param name="query_cover" value="0"/>
|
|
447 <conditional name="sens_cond">
|
|
448 <param name="block_size" value="2"/>
|
|
449 </conditional>
|
|
450 <output name="blast_tabular" file="diamond_results.pairwise"/>
|
|
451 </test>
|
|
452 <!--Test 04-->
|
|
453 <test expect_num_outputs="1">
|
|
454 <conditional name="method_cond">
|
|
455 <param name="method_select" value="blastp" />
|
|
456 </conditional>
|
|
457 <param name="query" value="protein.fasta" ftype="fasta"/>
|
|
458 <conditional name="ref_db_source">
|
|
459 <param name="db_source" value="history"/>
|
|
460 <param name="reference_database" value="db-wtax.dmnd"/>
|
|
461 </conditional>
|
|
462 <section name="output_section">
|
|
463 <conditional name="output">
|
|
464 <param name="outfmt" value="100"/>
|
|
465 <param name="salltitles" value="false"/>
|
|
466 <param name="sallseqid" value="false"/>
|
|
467 </conditional>
|
|
468 </section>
|
|
469 <output name="daa_output" file="diamond_results.daa" compare="sim_size" delta="10"/>
|
|
470 </test>
|
|
471 <!--Test 05-->
|
|
472 <test expect_num_outputs="1">
|
|
473 <conditional name="method_cond">
|
|
474 <param name="method_select" value="blastx" />
|
|
475 <conditional name="frameshift_cond">
|
|
476 <param name="frameshift_select" value="yes"/>
|
|
477 </conditional>
|
|
478 </conditional>
|
|
479 <param name="query" value="nucleotide.fasta" ftype="fasta"/>
|
|
480 <conditional name="ref_db_source">
|
|
481 <param name="db_source" value="indexed"/>
|
|
482 <param name="index" value="testDb"/>
|
|
483 </conditional>
|
|
484 <section name="output_section">
|
|
485 <conditional name="output">
|
|
486 <param name="outfmt" value="0"/>
|
|
487 </conditional>
|
|
488 </section>
|
|
489 <conditional name="sens_cond">
|
|
490 <param name="sensitivity" value=""/>
|
|
491 </conditional>
|
|
492 <param name="matrix" value="BLOSUM62"/>
|
|
493 <param name="comp_based_stats" value="1"/>
|
|
494 <param name="masking" value="1"/>
|
|
495 <conditional name="hit_filter">
|
|
496 <param name="hit_filter_select" value="top"/>
|
|
497 <param name="top" value="10" />
|
|
498 </conditional>
|
|
499 <conditional name="filter_score">
|
|
500 <param name="filter_score_select" value="min-score"/>
|
|
501 <param name="min_score" value="1" />
|
|
502 </conditional>
|
|
503 <param name="id" value="0"/>
|
|
504 <param name="query_cover" value="0"/>
|
|
505 <conditional name="sens_cond">
|
|
506 <param name="block_size" value="2"/>
|
|
507 </conditional>
|
|
508 <output name="blast_tabular" file="diamond_results.pairwise"/>
|
|
509 </test>
|
|
510 <!-- Test 06 iterate option-->
|
|
511 <test expect_num_outputs="1">
|
|
512 <conditional name="method_cond">
|
|
513 <param name="method_select" value="blastx" />
|
|
514 </conditional>
|
|
515 <param name="query" value="nucleotide.fasta" ftype="fasta"/>
|
|
516 <conditional name="ref_db_source">
|
|
517 <param name="db_source" value="indexed"/>
|
|
518 <param name="index" value="testDb"/>
|
|
519 </conditional>
|
|
520 <param name="iterate" value="true"/>
|
|
521 <section name="output_section">
|
|
522 <conditional name="output">
|
|
523 <param name="outfmt" value="6"/>
|
|
524 <param name="fields" value="qseqid,sseqid,pident,length,mismatch,gapopen,qstart,qend,sstart,send,evalue,bitscore"/>
|
|
525 </conditional>
|
|
526 </section>
|
|
527 <output name="blast_tabular" file="diamond_results_iterate.tabular"/>
|
|
528 </test>
|
|
529 <!--Test 07 algo option-->
|
|
530 <test expect_num_outputs="1">
|
|
531 <conditional name="method_cond">
|
|
532 <param name="method_select" value="blastx" />
|
|
533 </conditional>
|
|
534 <param name="query" value="nucleotide.fasta" ftype="fasta"/>
|
|
535 <conditional name="ref_db_source">
|
|
536 <param name="db_source" value="indexed"/>
|
|
537 <param name="index" value="testDb"/>
|
|
538 </conditional>
|
|
539 <param name="algo" value="1"/>
|
|
540 <section name="output_section">
|
|
541 <conditional name="output">
|
|
542 <param name="outfmt" value="6"/>
|
|
543 <param name="fields" value="qseqid,sseqid,pident,length,mismatch,gapopen,qstart,qend,sstart,send,evalue,bitscore"/>
|
|
544 </conditional>
|
|
545 </section>
|
|
546 <output name="blast_tabular" file="diamond_results_algorithm.tabular"/>
|
|
547 </test>
|
|
548 <!--Test 08 global-ranking option-->
|
|
549 <test expect_num_outputs="1">
|
|
550 <conditional name="method_cond">
|
|
551 <param name="method_select" value="blastx" />
|
|
552 </conditional>
|
|
553 <param name="query" value="nucleotide.fasta" ftype="fasta"/>
|
|
554 <conditional name="ref_db_source">
|
|
555 <param name="db_source" value="indexed"/>
|
|
556 <param name="index" value="testDb"/>
|
|
557 </conditional>
|
|
558 <param name="global_ranking" value="10"/>
|
|
559 <section name="output_section">
|
|
560 <conditional name="output">
|
|
561 <param name="outfmt" value="6"/>
|
|
562 <param name="fields" value="qseqid,sseqid,pident,length,mismatch,gapopen,qstart,qend,sstart,send,evalue,bitscore"/>
|
|
563 </conditional>
|
|
564 </section>
|
|
565 <output name="blast_tabular" file="diamond_results_global_ranking.tabular"/>
|
|
566 </test>
|
|
567 <!--Test 09 max-hsps option-->
|
|
568 <test expect_num_outputs="1">
|
|
569 <conditional name="method_cond">
|
|
570 <param name="method_select" value="blastx" />
|
|
571 </conditional>
|
|
572 <param name="query" value="nucleotide.fasta" ftype="fasta"/>
|
|
573 <conditional name="ref_db_source">
|
|
574 <param name="db_source" value="indexed"/>
|
|
575 <param name="index" value="testDb"/>
|
|
576 </conditional>
|
|
577 <param name="max_hsps" value="10"/>
|
|
578 <section name="output_section">
|
|
579 <conditional name="output">
|
|
580 <param name="outfmt" value="6"/>
|
|
581 <param name="fields" value="qseqid,sseqid,pident,length,mismatch,gapopen,qstart,qend,sstart,send,evalue,bitscore"/>
|
|
582 </conditional>
|
|
583 </section>
|
|
584 <output name="blast_tabular" file="diamond_results_max_hsps.tabular"/>
|
|
585 </test>
|
|
586 <!--Test 10 seed-cut option-->
|
|
587 <test expect_num_outputs="1">
|
|
588 <conditional name="method_cond">
|
|
589 <param name="method_select" value="blastx" />
|
|
590 </conditional>
|
|
591 <param name="query" value="nucleotide.fasta" ftype="fasta"/>
|
|
592 <conditional name="ref_db_source">
|
|
593 <param name="db_source" value="indexed"/>
|
|
594 <param name="index" value="testDb"/>
|
|
595 </conditional>
|
|
596 <param name="seed_cut" value="100"/>
|
|
597 <section name="output_section">
|
|
598 <conditional name="output">
|
|
599 <param name="outfmt" value="6"/>
|
|
600 <param name="fields" value="qseqid,sseqid,pident,length,mismatch,gapopen,qstart,qend,sstart,send,evalue,bitscore"/>
|
|
601 </conditional>
|
|
602 </section>
|
|
603 <output name="blast_tabular" file="diamond_results_seed_cut.tabular"/>
|
|
604 </test>
|
|
605 <!--Test 11 freq-masking option-->
|
|
606 <test expect_num_outputs="1">
|
|
607 <conditional name="method_cond">
|
|
608 <param name="method_select" value="blastx" />
|
|
609 </conditional>
|
|
610 <param name="query" value="nucleotide.fasta" ftype="fasta"/>
|
|
611 <conditional name="ref_db_source">
|
|
612 <param name="db_source" value="indexed"/>
|
|
613 <param name="index" value="testDb"/>
|
|
614 </conditional>
|
|
615 <param name="freq_masking" value="true"/>
|
|
616 <section name="output_section">
|
|
617 <conditional name="output">
|
|
618 <param name="outfmt" value="6"/>
|
|
619 <param name="fields" value="qseqid,sseqid,pident,length,mismatch,gapopen,qstart,qend,sstart,send,evalue,bitscore"/>
|
|
620 </conditional>
|
|
621 </section>
|
|
622 <output name="blast_tabular" file="diamond_results_freq_masking.tabular"/>
|
|
623 </test>
|
|
624 <!--Test 12 motif-masking option-->
|
|
625 <test expect_num_outputs="1">
|
|
626 <conditional name="method_cond">
|
|
627 <param name="method_select" value="blastx" />
|
|
628 </conditional>
|
|
629 <param name="query" value="nucleotide.fasta" ftype="fasta"/>
|
|
630 <conditional name="ref_db_source">
|
|
631 <param name="db_source" value="indexed"/>
|
|
632 <param name="index" value="testDb"/>
|
|
633 </conditional>
|
|
634 <section name="advanced_section">
|
|
635 <param name="motif_masking" value="1"/>
|
|
636 </section>
|
|
637 <section name="output_section">
|
|
638 <conditional name="output">
|
|
639 <param name="outfmt" value="6"/>
|
|
640 <param name="fields" value="qseqid,sseqid,pident,length,mismatch,gapopen,qstart,qend,sstart,send,evalue,bitscore"/>
|
|
641 </conditional>
|
|
642 </section>
|
|
643 <output name="blast_tabular" file="diamond_results_motif_masking.tabular"/>
|
|
644 </test>
|
|
645 </tests>
|
39
|
646 <help>
|
|
647 <![CDATA[
|
|
648
|
|
649 **What it does**
|
|
650
|
|
651 DIAMOND_ is a new alignment tool for aligning short DNA sequencing reads to a protein reference database such as NCBI-NR.
|
|
652 On Illumina reads of length 100-150bp, in fast mode, DIAMOND is about 20,000 times faster than BLASTX, while reporting
|
|
653 about 80-90% of all matches that BLASTX finds, with an e-value of at most 1e-5. In sensitive mode, DIAMOND ist about 2,500
|
|
654 times faster than BLASTX, finding more than 94% of all matches.
|
|
655
|
|
656 The DIAMOND algorithm is designed for the alignment of large datasets. The algorithm is not efficient for a small number of query sequences or only a single one of them, and speed will be low. BLAST is recommended for small datasets.
|
|
657
|
|
658 .. _DIAMOND: http://ab.inf.uni-tuebingen.de/software/diamond/
|
|
659
|
|
660 **Input**
|
|
661
|
|
662 Input data is a large protein or nucleotide sequence file.
|
|
663
|
|
664
|
|
665 **Output**
|
|
666
|
|
667 Diamond gives you a tabular output file with 12 columns:
|
|
668
|
|
669 Column Description
|
|
670 1 Query Seq-id (ID of your sequence)
|
|
671 2 Subject Seq-id (ID of the database hit)
|
|
672 3 Percentage of identical matches
|
|
673 4 Alignment length
|
|
674 5 Number of mismatches
|
|
675 6 Number of gap openings
|
|
676 7 Start of alignment in query
|
|
677 8 End of alignment in query
|
|
678 9 Start of alignment in subject (database hit)
|
|
679 10 End of alignment in subject (database hit)
|
|
680 11 Expectation value (E-value)
|
|
681 12 Bit score
|
|
682
|
|
683
|
|
684 Supported values for gap open and gap extend parameters depending on the selected scoring matrix.
|
|
685
|
|
686 ======== ============================================
|
|
687 Matrix Supported values for (gap open)/(gap extend)
|
|
688 ======== ============================================
|
|
689 BLOSUM45 (10-13)/3; (12-16)/2; (16-19)/1
|
|
690 BLOSUM50 (9-13)/3; (12-16)/2; (15-19)/1
|
|
691 BLOSUM62 (6-11)/2; (9-13)/1
|
|
692 BLOSUM80 (6-9)/2; 13/2; 25/2; (9-11)/1
|
|
693 BLOSUM90 (6-9)/2; (9-11)/1
|
|
694 PAM250 (11-15)/3; (13-17)/2; (17-21)/1
|
|
695 PAM70 (6-8)/2; (9-11)/1
|
|
696 PAM30 (5-7)/2; (8-10)/1
|
|
697 ======== ============================================
|
|
698
|
|
699
|
|
700 ]]>
|
|
701 </help>
|
|
702 <expand macro="citations" />
|
|
703 </tool>
|