Mercurial > repos > galaxyp > blast_plus_remote_blastp

comparison blast_plus_remote_blastp.xml @ 5:22a767177ac9 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/peterjc/galaxy_blast/tree/master/tools/ncbi_blast_plus commit 8cb8939dadaad8e804e35128cfb7b2560eb4d9b4
author galaxyp
date Fri, 20 Jan 2017 16:00:56 -0500
parents
children e9975de58321
comparison
equal deleted inserted replaced
4:a51980bc0ffe 5:22a767177ac9
1 <tool id="blast_plus_remote_blastp" name="NCBI BLAST+ remote blastp" version="2.6.0">
2 <description>Search protein database with protein query sequence(s)</description>
3 <!-- If job splitting is enabled, break up the query file into parts -->
4 <!--
5 <parallelism method="multi" split_inputs="query" split_mode="to_size" split_size="500" merge_outputs="output1" />
6 -->
7 <requirements>
8 <requirement type="binary">blastp</requirement>
9 <requirement type="package" version="2.6.0">blast</requirement>
10 </requirements>
11 <stdio>
12 <exit_code range="1" level="fatal" description="Bad input dataset or BLAST options" />
13 <exit_code range="2" level="fatal" description="Error in BLAST database" />
14 <exit_code range="3" level="fatal" description="Error in BLAST engine" />
15 <exit_code range="4" level="fatal" description="Out of Memory" />
16 <exit_code range="5:" level="fatal" description="Unknown Error" />
17 </stdio>
18 <version_command>blastp -version</version_command>
19 <command>
20 ## The command is a Cheetah template which allows some Python based syntax.
21 ## Lines starting hash hash are comments. Galaxy will turn newlines into spaces
22 blastp
23 -query "$query"
24 #if $db_opts.db_opts_selector == "db":
25 -db "${db_opts.database.fields.path}"
26 #elif $db_opts.db_opts_selector == "histdb":
27 -db "${os.path.join($db_opts.histdb.extra_files_path,'blastdb')}"
28 #elif $db_opts.db_opts_selector == "remote":
29 -db $db_opts.database
30 -remote
31 #set $txids = []
32 #set $ntxids = []
33 #for $i, $org in enumerate($db_opts.taxid_repeat):
34 #if $org.exclude:
35 #set $ntxids = $ntxids + ["txid" + $org.taxid.__str__]
36 #else
37 #set $txids = $txids + ["txid" + $org.taxid.__str__]
38 #end if
39 #end for
40 #if (len($txids) + len($ntxids)) > 0:
41 #set $entrez_query = ''
42 #if len($txids) > 0:
43 #set $entrez_query = $entrez_query + '(' + ' OR '.join($txids) + ')'
44 #end if
45 #if len($ntxids) > 0:
46 #set $entrez_query = $entrez_query + ' NOT (' + ' OR '.join($ntxids) + ')'
47 #end if
48 -entrez_query '$entrez_query'
49 #end if
50 #else:
51 -subject "$db_opts.subject"
52 #end if
53 -task $blast_type
54 -evalue $evalue_cutoff
55 -out blast_output
56 ##Set the extended list here so if/when we add things, saved workflows are not affected
57 #if str($fmt_opt.out_format)=="text":
58 -outfmt "$fmt_opt.outfmt" $fmt_opt.html $fmt_opt.show_gis
59 #if $fmt_opt.num_descriptions.__str__.strip() != '':
60 -num_descriptions $fmt_opt.num_descriptions
61 #end if
62 #if $fmt_opt.num_alignments.__str__.strip() != '':
63 -num_alignments $fmt_opt.num_alignments
64 #end if
65 #elif str($fmt_opt.out_format)=="cols":
66 #set cols = (str($fmt_opt.std_cols)+","+str($fmt_opt.ext_cols)+","+str($fmt_opt.ids_cols)+","+str($fmt_opt.misc_cols)+","+str($fmt_opt.tax_cols)).replace("None", "").replace(",,", ",").replace(",", " ").strip()
67 -outfmt "6 $cols"
68 #if $fmt_opt.max_target_seqs.__str__.strip() != '':
69 -max_target_seqs $fmt_opt.max_target_seqs
70 #end if
71 #else:
72 -outfmt "$fmt_opt.outfmt"
73 #if $fmt_opt.max_target_seqs.__str__.strip() != '':
74 -max_target_seqs $fmt_opt.max_target_seqs
75 #end if
76 #end if
77 #if $db_opts.db_opts_selector != "remote":
78 -num_threads 8
79 #end if
80 #if $adv_opts.adv_opts_selector=="advanced":
81 $adv_opts.filter_query
82 -matrix $adv_opts.scoring.matrix
83 $adv_opts.scoring.gap_costs
84
85 #if $adv_opts.word_size.__str__.strip() != '':
86 -word_size $adv_opts.word_size
87 #end if
88
89 #if $adv_opts.window_size.__str__.strip() != '':
90 -window_size $adv_opts.window_size
91 #end if
92
93 #if $adv_opts.threshold.__str__.strip() != '':
94 -threshold $adv_opts.threshold
95 #end if
96
97 #if $adv_opts.comp_based_stats.__str__.strip() != '':
98 -comp_based_stats $adv_opts.comp_based_stats
99 #end if
100
101 ##Ungapped disabled for now - see comments below
102 ##$adv_opts.ungapped
103 $adv_opts.use_sw_tback
104 $adv_opts.parse_deflines
105 ## End of advanced options:
106 #end if
107 </command>
108 <inputs>
109 <param name="query" type="data" format="fasta" label="Protein query sequence(s)"/>
110 <conditional name="db_opts">
111 <param name="db_opts_selector" type="select" label="Subject database/sequences">
112 <option value="db" selected="True">Local BLAST Database</option>
113 <option value="histdb">BLAST database from your history</option>
114 <option value="file">Local FASTA file</option>
115 <option value="remote">NCBI Remote Database</option>
116 </param>
117 <when value="db">
118 <param name="database" type="select" label="Protein BLAST database">
119 <options from_file="blastdb_p.loc">
120 <column name="value" index="0"/>
121 <column name="name" index="1"/>
122 <column name="path" index="2"/>
123 </options>
124 </param>
125 <param name="subject" type="hidden" value="" />
126 </when>
127 <when value="histdb">
128 <param name="database" type="hidden" value="" />
129 <param name="histdb" type="data" format="blastdbp" label="Protein BLAST database" />
130 <param name="subject" type="hidden" value="" />
131 </when>
132 <when value="file">
133 <param name="database" type="hidden" value="" />
134 <param name="subject" type="data" format="fasta" label="Protein FASTA file to use as database"/>
135 </when>
136 <when value="remote">
137 <param name="database" type="select" label="Protein BLAST database">
138 <option value="nr" selected="True">Non-redundant protein sequences (nr)</option>
139 <option value="refseq_protein">Reference proteins (refseq_protein)</option>
140 <option value="swissprot">UniProtKB/Swiss-Prot(swissprot)</option>
141 <option value="pat">Patented protein sequences(pat)</option>
142 <option value="pdb">Protein Data Bank proteins(pdb)</option>
143 <option value="env_nr">Metagenomic proteins(env_nr)</option>
144 </param>
145 <repeat name="taxid_repeat" title="Search Organism Restriction" min="0">
146 <param name="taxid" type="integer" value="" label="NCBI Taxon ID" help="For example: Human is 9606 (see: http://www.ncbi.nlm.nih.gov/taxonomy ) ">
147 <validator type="in_range" min="0" />
148 </param>
149 <param name="exclude" type="boolean" checked="false" label="Exclude this NCBI Taxon ID" help=""/>
150 </repeat>
151 </when>
152 </conditional>
153 <param name="blast_type" type="select" display="radio" label="Type of BLAST">
154 <option value="blastp">blastp - Traditional BLASTP to compare a protein query to a protein database</option>
155 <option value="blastp-fast">blastp-fast - Use longer words for seeding, faster but less accurate</option>
156 <option value="blastp-short">blastp-short - BLASTP optimized for queries shorter than 30 residues</option>
157 </param>
158 <param name="evalue_cutoff" type="float" size="15" value="0.001" label="Set expectation value cutoff" />
159 <conditional name="fmt_opt">
160 <param name="out_format" type="select" label="Output format">
161 <option value="tabular" selected="True">Tabular</option>
162 <option value="cols">Tabular (select which columns)</option>
163 <option value="blastxml">BLAST XML</option>
164 <option value="text">Text Report</option>
165 </param>
166 <when value="tabular">
167 <param name="outfmt" type="select" label="Tabular columns">
168 <option value="6" selected="True">Tabular (standard 12 columns)</option>
169 <option value="7">Tabular (standard 12 columns) with comments</option>
170 <option value="6 std sallseqid score nident positive gaps ppos qframe sframe qseq sseq qlen slen">Tabular (extended 24 columns)</option>
171 <option value="6 std sallseqid score nident positive gaps ppos qframe sframe qseq sseq qlen slen salltitles">Tabular (extended 25 columns)</option>
172 </param>
173 <param name="max_target_seqs" type="integer" value="500" optional="true" label="Maximum hits to show" help="Use zero for default limits">
174 <validator type="in_range" min="0" />
175 </param>
176 </when>
177 <when value="cols">
178 <param name="std_cols" type="select" multiple="true" display="checkboxes" label="Standard columns">
179 <option selected="true" value="qseqid">qseqid = Query Seq-id (ID of your sequence)</option>
180 <option selected="true" value="sseqid">sseqid = Subject Seq-id (ID of the database hit)</option>
181 <option selected="true" value="pident">pident = Percentage of identical matches</option>
182 <option selected="true" value="length">length = Alignment length</option>
183 <option selected="true" value="mismatch">mismatch = Number of mismatches</option>
184 <option selected="true" value="gapopen">gapopen = Number of gap openings</option>
185 <option selected="true" value="qstart">qstart = Start of alignment in query</option>
186 <option selected="true" value="qend">qend = End of alignment in query</option>
187 <option selected="true" value="sstart">sstart = Start of alignment in subject (database hit)</option>
188 <option selected="true" value="send">send = End of alignment in subject (database hit)</option>
189 <option selected="true" value="evalue">evalue = Expectation value (E-value)</option>
190 <option selected="true" value="bitscore">bitscore = Bit score</option>
191 </param>
192 <param name="ext_cols" type="select" multiple="true" display="checkboxes" label="Extended columns">
193 <option value="sallseqid">sallseqid = All subject Seq-id(s), separated by a ';'</option>
194 <option value="score">score = Raw score</option>
195 <option value="nident">nident = Number of identical matches</option>
196 <option value="positive">positive = Number of positive-scoring matches</option>
197 <option value="gaps">gaps = Total number of gaps</option>
198 <option value="ppos">ppos = Percentage of positive-scoring matches</option>
199 <option value="qframe">qframe = Query frame</option>
200 <option value="sframe">sframe = Subject frame</option>
201 <option value="qseq">qseq = Aligned part of query sequence</option>
202 <option value="sseq">sseq = Aligned part of subject sequence</option>
203 <option value="qlen">qlen = Query sequence length</option>
204 <option value="slen">slen = Subject sequence length</option>
205 <option value="salltitles">salltitles = All subject title(s), separated by a '&lt;&gt;'</option>
206 </param>
207 <param name="ids_cols" type="select" multiple="true" display="checkboxes" label="Other identifier columns">
208 <option value="qgi">qgi = Query GI</option>
209 <option value="qacc">qacc = Query accesion</option>
210 <option value="qaccver">qaccver = Query accesion.version</option>
211 <option value="sallseqid">sallseqid = All subject Seq-id(s), separated by a ';'</option>
212 <option value="sgi">sgi = Subject GI</option>
213 <option value="sallgi">sallgi = All subject GIs</option>
214 <option value="sacc">sacc = Subject accession</option>
215 <option value="saccver">saccver = Subject accession.version</option>
216 <option value="sallacc">sallacc = All subject accessions</option>
217 <option value="stitle">stitle = Subject Title</option>
218 </param>
219 <param name="misc_cols" type="select" multiple="true" display="checkboxes" label="Miscellaneous columns">
220 <option value="sstrand">sstrand = Subject Strand</option>
221 <!-- Is it really worth including 'frames' given have 'qframe' and 'sframe'? -->
222 <option value="frames">frames = Query and subject frames separated by a '/'</option>
223 <option value="btop">btop = Blast traceback operations (BTOP)</option>
224 <option value="qcovs">qcovs = Query Coverage Per Subject</option>
225 <option value="qcovhsp">qcovhsp = Query Coverage Per HSP</option>
226 </param>
227 <param name="tax_cols" type="select" multiple="true" display="checkboxes" label="Taxonomy columns">
228 <option value="staxids">staxids = unique Subject Taxonomy ID(s), separated by a ';' (in numerical order)</option>
229 <!-- TODO, how to handle the taxonomy data file dependency? If missing these give N/A -->
230 <option value="sscinames">sscinames = unique Subject Scientific Name(s), separated by a ';'</option>
231 <option value="scomnames">scomnames = unique Subject Common Name(s), separated by a ';'</option>
232 <option value="sblastnames">sblastnames = unique Subject Blast Name(s), separated by a ';' (in alphabetical order)</option>
233 <option value="sskingdoms">sskingdoms = unique Subject Super Kingdom(s), separated by a ';' (in alphabetical order)</option>
234 </param>
235 <param name="max_target_seqs" type="integer" value="500" optional="true" label="Maximum hits to show" help="Use zero for default limits">
236 <validator type="in_range" min="0" />
237 </param>
238 </when>
239 <when value="blastxml">
240 <param name="outfmt" type="hidden" value="5"/>
241 <param name="max_target_seqs" type="integer" value="500" optional="true" label="Maximum hits to show" help="Use zero for default limits">
242 <validator type="in_range" min="0" />
243 </param>
244 </when>
245 <when value="text">
246 <param name="outfmt" type="select" label="Text format">
247 <option value="0">Pairwise text</option>
248 <option value="1">Query-anchored text showing identitites</option>
249 <option value="2">Query-anchored text</option>
250 <option value="3">Flat query-anchored text showing identitites</option>
251 <option value="4">Flat query-anchored text</option>
252 </param>
253 <param name="html" type="boolean" label="Html" truevalue="-html" falsevalue="" checked="true" />
254 <param name="show_gis" type="boolean" label="NCBI-gis" truevalue="-show_gis" falsevalue="" checked="false"
255 help="Show the NCBI gis in the Subject def lines"/>
256 <param name="num_descriptions" type="integer" value="500" optional="true" label="Maximum Decriptions to show" help="Show one-line descriptions for this number of database sequences.">
257 <validator type="in_range" min="0" />
258 </param>
259 <param name="num_alignments" type="integer" value="250" optional="true" label="Maximum alignments to show" help="Show alignments for this number of database sequences.">
260 <validator type="in_range" min="0" />
261 </param>
262 </when>
263 </conditional>
264 <conditional name="adv_opts">
265 <param name="adv_opts_selector" type="select" label="Advanced Options">
266 <option value="basic" selected="True">Hide Advanced Options</option>
267 <option value="advanced">Show Advanced Options</option>
268 </param>
269 <when value="basic" />
270 <when value="advanced">
271 <param name="filter_query" type="boolean" label="Filter out low complexity regions (with SEG)" truevalue="-seg yes" falsevalue="-seg no" checked="false" />
272 <conditional name="scoring">
273 <param name="matrix" type="select" label="Scoring matrix">
274 <option value="BLOSUM90">BLOSUM90</option>
275 <option value="BLOSUM80">BLOSUM80</option>
276 <option value="BLOSUM62" selected="True">BLOSUM62 (default)</option>
277 <option value="BLOSUM50">BLOSUM50</option>
278 <option value="BLOSUM45">BLOSUM45</option>
279 <option value="PAM250">PAM250</option>
280 <option value="PAM70">PAM70</option>
281 <option value="PAM30">PAM30</option>
282 </param>
283 <when value="BLOSUM90">
284 <param name="gap_costs" type="select" label="Gap Costs">
285 <option value="">Use Defaults</option>
286 <option value="-gapopen 9 -gapextend 2">Existense: 9 Extension: 2</option>
287 <option value="-gapopen 8 -gapextend 2">Existense: 8 Extension: 2</option>
288 <option value="-gapopen 7 -gapextend 2">Existense: 7 Extension: 2</option>
289 <option value="-gapopen 6 -gapextend 2">Existense: 6 Extension: 2</option>
290 <option value="-gapopen 11 -gapextend 1">Existense: 11 Extension: 1</option>
291 <option value="-gapopen 10 -gapextend 1" selected="True">Existense: 10 Extension: 1 (default)</option>
292 <option value="-gapopen 9 -gapextend 1">Existense: 9 Extension: 1</option>
293 </param>
294
295 </when>
296 <when value="BLOSUM80">
297 <param name="gap_costs" type="select" label="Gap Costs">
298 <option value="">Use Defaults</option>
299 <option value="-gapopen 8 -gapextend 2">Existense: 8 Extension: 2</option>
300 <option value="-gapopen 7 -gapextend 2">Existense: 7 Extension: 2</option>
301 <option value="-gapopen 6 -gapextend 2">Existense: 6 Extension: 2</option>
302 <option value="-gapopen 11 -gapextend 1">Existense: 11 Extension: 1</option>
303 <option value="-gapopen 10 -gapextend 1" selected="True">Existense: 10 Extension: 1 (default)</option>
304 <option value="-gapopen 9 -gapextend 1">Existense: 9 Extension: 1</option>
305 </param>
306 </when>
307 <when value="BLOSUM62">
308 <param name="gap_costs" type="select" label="Gap Costs">
309 <option value="">Use Defaults</option>
310 <option value="-gapopen 11 -gapextend 2">Existense: 11 Extension: 2</option>
311 <option value="-gapopen 10 -gapextend 2">Existense: 10 Extension: 2</option>
312 <option value="-gapopen 9 -gapextend 2">Existense: 9 Extension: 2</option>
313 <option value="-gapopen 8 -gapextend 2">Existense: 8 Extension: 2</option>
314 <option value="-gapopen 7 -gapextend 2">Existense: 7 Extension: 2</option>
315 <option value="-gapopen 6 -gapextend 2">Existense: 6 Extension: 2</option>
316 <option value="-gapopen 13 -gapextend 1">Existense: 13 Extension: 1</option>
317 <option value="-gapopen 12 -gapextend 1">Existense: 12 Extension: 1</option>
318 <option value="-gapopen 11 -gapextend 1" selected="True">Existense: 11 Extension: 1 (default)</option>
319 <option value="-gapopen 10 -gapextend 1">Existense: 10 Extension: 1</option>
320 <option value="-gapopen 9 -gapextend 1">Existense: 9 Extension: 1</option>
321 </param>
322
323 </when>
324 <when value="BLOSUM50">
325 <param name="gap_costs" type="select" label="Gap Costs">
326 <option value="">Use Defaults</option>
327 <option value="-gapopen 13 -gapextend 3">Existense: 13 Extension: 3</option>
328 <option value="-gapopen 12 -gapextend 3">Existense: 12 Extension: 3</option>
329 <option value="-gapopen 11 -gapextend 3">Existense: 11 Extension: 3</option>
330 <option value="-gapopen 10 -gapextend 3">Existense: 10 Extension: 3</option>
331 <option value="-gapopen 9 -gapextend 3">Existense: 9 Extension: 3</option>
332 <option value="-gapopen 16 -gapextend 2">Existense: 16 Extension: 2</option>
333 <option value="-gapopen 15 -gapextend 2">Existense: 15 Extension: 2</option>
334 <option value="-gapopen 14 -gapextend 2">Existense: 14 Extension: 2</option>
335 <option value="-gapopen 13 -gapextend 2" selected="True">Existense: 13 Extension: 2 (default)</option>
336 <option value="-gapopen 12 -gapextend 2">Existense: 12 Extension: 2</option>
337 <option value="-gapopen 19 -gapextend 1">Existense: 19 Extension: 1</option>
338 <option value="-gapopen 18 -gapextend 1">Existense: 18 Extension: 1</option>
339 <option value="-gapopen 17 -gapextend 1">Existense: 17 Extension: 1</option>
340 <option value="-gapopen 16 -gapextend 1">Existense: 16 Extension: 1</option>
341 <option value="-gapopen 15 -gapextend 1">Existense: 15 Extension: 1</option>
342 </param>
343
344 </when>
345 <when value="BLOSUM45">
346 <param name="gap_costs" type="select" label="Gap Costs">
347 <option value="">Use Defaults</option>
348 <option value="-gapopen 13 -gapextend 3">Existense: 13 Extension: 3</option>
349 <option value="-gapopen 12 -gapextend 3">Existense: 12 Extension: 3</option>
350 <option value="-gapopen 11 -gapextend 3">Existense: 11 Extension: 3</option>
351 <option value="-gapopen 10 -gapextend 3">Existense: 10 Extension: 3</option>
352 <option value="-gapopen 15 -gapextend 2" selected="True">Existense: 15 Extension: 2 (default)</option>
353 <option value="-gapopen 14 -gapextend 2">Existense: 14 Extension: 2</option>
354 <option value="-gapopen 13 -gapextend 2">Existense: 13 Extension: 2</option>
355 <option value="-gapopen 12 -gapextend 2">Existense: 12 Extension: 2</option>
356 <option value="-gapopen 19 -gapextend 1">Existense: 19 Extension: 1</option>
357 <option value="-gapopen 18 -gapextend 1">Existense: 18 Extension: 1</option>
358 <option value="-gapopen 17 -gapextend 1">Existense: 17 Extension: 1</option>
359 <option value="-gapopen 16 -gapextend 1">Existense: 16 Extension: 1</option>
360 </param>
361 </when>
362 <when value="PAM250">
363 <param name="gap_costs" type="select" label="Gap Costs">
364 <option value="">Use Defaults</option>
365 <option value="-gapopen 15 -gapextend 3">Existense: 15 Extension: 3</option>
366 <option value="-gapopen 14 -gapextend 3">Existense: 14 Extension: 3</option>
367 <option value="-gapopen 13 -gapextend 3">Existense: 13 Extension: 3</option>
368 <option value="-gapopen 12 -gapextend 3">Existense: 12 Extension: 3</option>
369 <option value="-gapopen 17 -gapextend 2">Existense: 17 Extension: 2</option>
370 <option value="-gapopen 16 -gapextend 2">Existense: 16 Extension: 2</option>
371 <option value="-gapopen 15 -gapextend 2">Existense: 15 Extension: 2</option>
372 <option value="-gapopen 14 -gapextend 2" selected="True">Existense: 14 Extension: 2 (default)</option>
373 <option value="-gapopen 13 -gapextend 2">Existense: 13 Extension: 2</option>
374 <option value="-gapopen 21 -gapextend 1">Existense: 21 Extension: 1</option>
375 <option value="-gapopen 20 -gapextend 1">Existense: 20 Extension: 1</option>
376 <option value="-gapopen 19 -gapextend 1">Existense: 19 Extension: 1</option>
377 <option value="-gapopen 18 -gapextend 1">Existense: 18 Extension: 1</option>
378 <option value="-gapopen 17 -gapextend 1">Existense: 17 Extension: 1</option>
379 </param>
380
381 </when>
382 <when value="PAM70">
383 <param name="gap_costs" type="select" label="Gap Costs">
384 <option value="">Use Defaults</option>
385 <option value="-gapopen 8 -gapextend 2">Existense: 8 Extension: 2</option>
386 <option value="-gapopen 7 -gapextend 2">Existense: 7 Extension: 2</option>
387 <option value="-gapopen 6 -gapextend 2">Existense: 6 Extension: 2</option>
388 <option value="-gapopen 11 -gapextend 1">Existense: 11 Extension: 1</option>
389 <option value="-gapopen 10 -gapextend 1" selected="True">Existense: 10 Extension: 1 (default)</option>
390 <option value="-gapopen 9 -gapextend 1">Existense: 9 Extension: 1</option>
391 </param>
392
393 </when>
394 <when value="PAM30">
395 <param name="gap_costs" type="select" label="Gap Costs">
396 <option value="">Use Defaults</option>
397 <option value="-gapopen 7 -gapextend 2">Existense: 7 Extension: 2</option>
398 <option value="-gapopen 6 -gapextend 2">Existense: 6 Extension: 2</option>
399 <option value="-gapopen 5 -gapextend 2">Existense: 5 Extension: 2</option>
400 <option value="-gapopen 10 -gapextend 1">Existense: 10 Extension: 1</option>
401 <option value="-gapopen 9 -gapextend 1" selected="True">Existense: 9 Extension: 1 (default)</option>
402 <option value="-gapopen 8 -gapextend 1">Existense: 8 Extension: 1</option>
403 </param>
404 </when>
405 </conditional>
406
407 <param name="word_size" type="integer" value="" optional="true" label="Word size for wordfinder algorithm" help="Recommended: blastp 3, blastp-short 2">
408 <validator type="in_range" min="2" />
409 </param>
410 <param name="window_size" type="integer" value="" optional="true" label="Multiple hits window size, use 0 to specify 1-hit algorithm." help="Recommended: blastp 40, blastp-short 15">
411 <validator type="in_range" min="0" />
412 </param>
413 <param name="threshold" type="integer" value="" optional="true" label="Threshold: Minimum score to add a word to the BLAST lookup table." help="Recommended: blastp 11, blastp-short 16">
414 <validator type="in_range" min="1" />
415 </param>
416 <param name="comp_based_stats" type="select" optional="true" label="Use composition-based statistics"
417 help="Recommended: blastp: 2 blastp-short: 0">
418 <option value="">Leave Unspecified</option>
419 <option value="0">0 or F (No composition-based statistics)</option>
420 <option value="1">1 (Composition-based statistics as in NAR 29:2994-3005, 2001)</option>
421 <option value="2">2, T, or D (Composition-based score adjustment as in Bioinformatics 21:902-911, 2005, conditioned on sequence properties)</option>
422 <option value="3">3 (Composition-based score adjustment as in Bioinformatics 21:902-911, 2005, unconditionally)</option>
423 </param>
424
425 <param name="use_sw_tback" type="boolean" label="Compute locally optimal Smith-Waterman alignments?" truevalue="-use_sw_tback" falsevalue="" checked="false" />
426
427 <param name="parse_deflines" type="boolean" label="Should the query and subject defline(s) be parsed?" truevalue="-parse_deflines" falsevalue="" checked="false" help="This affects the formatting of the query/subject ID strings"/>
428 </when>
429 </conditional>
430 </inputs>
431 <outputs>
432 <data name="output_tabular" format="tabular" label="${blast_type} on ${db_opts.db_opts_selector} ${db_opts.database}" from_work_dir="blast_output">
433 <filter>fmt_opt['out_format'] in ("tabular","cols")</filter>
434 </data>
435 <data name="output_xml" format="blastxml" label="${blast_type} on ${db_opts.db_opts_selector} ${db_opts.database}" from_work_dir="blast_output">
436 <filter>fmt_opt['out_format'] == "blastxml"</filter>
437 </data>
438 <data name="output_txt" format="txt" label="${blast_type} on ${db_opts.db_opts_selector} ${db_opts.database}" from_work_dir="blast_output">
439 <filter>fmt_opt['out_format'] == "text" and not fmt_opt['html']</filter>
440 </data>
441 <data name="output_html" format="html" label="${blast_type} on ${db_opts.db_opts_selector} ${db_opts.database}" from_work_dir="blast_output">
442 <filter>fmt_opt['out_format'] == "text" and fmt_opt['html']</filter>
443 </data>
444 </outputs>
445 <tests>
446 <test>
447 <param name="query" value="four_human_proteins.fasta" ftype="fasta" />
448 <param name="db_opts_selector" value="file" />
449 <param name="subject" value="rhodopsin_proteins.fasta" ftype="fasta" />
450 <param name="database" value="" />
451 <param name="evalue_cutoff" value="1e-8" />
452 <param name="blast_type" value="blastp" />
453 <param name="out_format" value="blastxml" />
454 <param name="outfmt" value="5" />
455 <param name="adv_opts_selector" value="advanced" />
456 <param name="filter_query" value="False" />
457 <param name="matrix" value="BLOSUM62" />
458 <param name="max_target_seqs" value="" />
459 <param name="word_size" value="" />
460 <param name="parse_deflines" value="False" />
461 <output name="output_xml">
462 <assert_contents>
463 <has_text text="sp|Q9BS26|ERP44_HUMAN"/>
464 </assert_contents>
465 </output>
466 </test>
467 <test>
468 <param name="query" value="four_human_proteins.fasta" ftype="fasta" />
469 <param name="db_opts_selector" value="file" />
470 <param name="subject" value="rhodopsin_proteins.fasta" ftype="fasta" />
471 <param name="database" value="" />
472 <param name="evalue_cutoff" value="1e-8" />
473 <param name="blast_type" value="blastp" />
474 <param name="out_format" value="tabular" />
475 <param name="outfmt" value="6" />
476 <param name="adv_opts_selector" value="advanced" />
477 <param name="filter_query" value="False" />
478 <param name="matrix" value="BLOSUM62" />
479 <param name="max_target_seqs" value="" />
480 <param name="word_size" value="" />
481 <param name="parse_deflines" value="False" />
482 <output name="output_tabular">
483 <assert_contents>
484 <has_text_matching expression="sp.P08100.OPSD_HUMAN\tgi.283855846.gb.ADB45242.1.\t\d+.\d+\t\d+\t\d+\t0\t\d+\t\d+\t\d+\t\d+\t\S+\t\s*\d+" />
485 <has_text text="BAB21486.1"/>
486 </assert_contents>
487 </output>
488 </test>
489 <test>
490 <param name="query" value="four_human_proteins.fasta" ftype="fasta" />
491 <param name="db_opts_selector" value="file" />
492 <param name="subject" value="rhodopsin_proteins.fasta" ftype="fasta" />
493 <param name="database" value="" />
494 <param name="evalue_cutoff" value="1e-8" />
495 <param name="blast_type" value="blastp" />
496 <param name="out_format" value="tabular" />
497 <param name="outfmt" value="6 std sallseqid score nident positive gaps ppos qframe sframe qseq sseq qlen slen" />
498 <param name="adv_opts_selector" value="advanced" />
499 <param name="filter_query" value="False" />
500 <param name="matrix" value="BLOSUM62" />
501 <param name="max_target_seqs" value="" />
502 <param name="word_size" value="" />
503 <param name="parse_deflines" value="False" />
504 <output name="output_tabular">
505 <assert_contents>
506 <has_text_matching expression="sp.P08100.OPSD_HUMAN\tgi.283855846.gb.ADB45242.1.\t\d+.\d+\t\d+\t\d+\t\d+\t\d+\t\d+\t\d+\t\d+\t\S+\t\s*\d+\t\S+\t\d+\t\d+\t\d+\t\d+\t\S+\t\d+\t\d+\t\S+\t\S+\t\d+\t\d+" />
507 </assert_contents>
508 </output>
509 </test>
510 <test>
511 <param name="query" value="rhodopsin_proteins.fasta" ftype="fasta" />
512 <param name="db_opts_selector" value="file" />
513 <param name="subject" value="four_human_proteins.fasta" ftype="fasta" />
514 <param name="database" value="" />
515 <param name="evalue_cutoff" value="1e-8" />
516 <param name="blast_type" value="blastp" />
517 <param name="out_format" value="tabular" />
518 <param name="outfmt" value="6" />
519 <param name="adv_opts_selector" value="basic" />
520 <output name="output_tabular">
521 <assert_contents>
522 <has_text_matching expression="gi.283855846.gb.ADB45242.1.\tsp.P08100.OPSD_HUMAN\t\d+.\d+\t\d+\t\d+\t0\t\d+\t\d+\t\d+\t\d+\t\S+\t\s*\d+" />
523 <has_text text="BAB21486.1"/>
524 </assert_contents>
525 </output>
526 </test>
527 </tests>
528 <help>
529
530 .. class:: warningmark
531
532 **Note**. Database searches may take a substantial amount of time.
533 For large input datasets it is advisable to allow overnight processing.
534
535 -----
536
537 **What it does**
538
539 Search a *protein database* using a *protein query*,
540 using the NCBI BLAST+ blastp command line tool.
541
542 The search can be performed using a local database, against a sequence supplied in a fasta file,
543 or the blast can be performed remotely at NCBI.
544
545 The remote operation allows searches to be targeted at specific organisms.
546
547 -----
548
549 **Output format**
550
551 Because Galaxy focuses on processing tabular data, the default output of this
552 tool is tabular. The standard BLAST+ tabular output contains 12 columns:
553
554 ====== ========= ============================================
555 Column NCBI name Description
556 ------ --------- --------------------------------------------
557 1 qseqid Query Seq-id (ID of your sequence)
558 2 sseqid Subject Seq-id (ID of the database hit)
559 3 pident Percentage of identical matches
560 4 length Alignment length
561 5 mismatch Number of mismatches
562 6 gapopen Number of gap openings
563 7 qstart Start of alignment in query
564 8 qend End of alignment in query
565 9 sstart Start of alignment in subject (database hit)
566 10 send End of alignment in subject (database hit)
567 11 evalue Expectation value (E-value)
568 12 bitscore Bit score
569 ====== ========= ============================================
570
571 The BLAST+ tools can optionally output additional columns of information,
572 but this takes longer to calculate. Most (but not all) of these columns are
573 included by selecting the extended tabular output. The extra columns are
574 included *after* the standard 12 columns. This is so that you can write
575 workflow filtering steps that accept either the 12 or 24 column tabular
576 BLAST output.
577
578 ====== ============= ===========================================
579 Column NCBI name Description
580 ------ ------------- -------------------------------------------
581 13 sallseqid All subject Seq-id(s), separated by a ';'
582 14 score Raw score
583 15 nident Number of identical matches
584 16 positive Number of positive-scoring matches
585 17 gaps Total number of gaps
586 18 ppos Percentage of positive-scoring matches
587 19 qframe Query frame
588 20 sframe Subject frame
589 21 qseq Aligned part of query sequence
590 22 sseq Aligned part of subject sequence
591 23 qlen Query sequence length
592 24 slen Subject sequence length
593 25 salltitles All subject title(s), separated by a '&lt;&gt;'
594 ====== ============= ===========================================
595
596 The third option is BLAST XML output, which is designed to be parsed by
597 another program, and is understood by some Galaxy tools.
598
599 You can also choose several plain text or HTML output formats which are designed to be read by a person (not by another program).
600 The HTML versions use basic webpage formatting and can include links to the hits on the NCBI website.
601 The pairwise output (the default on the NCBI BLAST website) shows each match as a pairwise alignment with the query.
602 The two query anchored outputs show a multiple sequence alignment between the query and all the matches,
603 and differ in how insertions are shown (marked as insertions or with gap characters added to the other sequences).
604
605 -------
606
607 **References**
608
609 Altschul et al. Gapped BLAST and PSI-BLAST: a new generation of protein database search programs. 1997. Nucleic Acids Res. 25:3389-3402.
610
611 Schaffer et al. Improving the accuracy of PSI-BLAST protein database searches with composition-based statistics and other refinements. 2001. Nucleic Acids Res. 29:2994-3005.
612
613 </help>
614 <citations>
615 <citation type="doi">10.1186/1471-2105-10-421</citation>
616 <citation type="doi">10.1186/s13742-015-0080-7</citation>
617 </citations>
618 </tool>