Mercurial > repos > devteam > ncbi_blast_plus

comparison ncbi_tblastn_wrapper.xml @ 0:d375502056f1 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author devteam
date Fri, 17 Aug 2012 09:11:43 -0400
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:d375502056f1
1 <tool id="ncbi_tblastn_wrapper" name="NCBI BLAST+ tblastn" version="0.0.11">
2 <description>Search translated nucleotide database with protein query sequence(s)</description>
3 <!-- If job splitting is enabled, break up the query file into four -->
4 <parallelism method="multi" split_inputs="query" split_mode="number_of_parts" split_size="4" shared_inputs="subject" merge_outputs="output1"></parallelism>
5 <version_command>tblastn -version</version_command>
6 <command interpreter="python">hide_stderr.py
7 ## The command is a Cheetah template which allows some Python based syntax.
8 ## Lines starting hash hash are comments. Galaxy will turn newlines into spaces
9 tblastn
10 -query "$query"
11 #if $db_opts.db_opts_selector == "db":
12 -db "${db_opts.database.fields.path}"
13 #else:
14 -subject "$db_opts.subject"
15 #end if
16 -evalue $evalue_cutoff
17 -out $output1
18 ##Set the extended list here so if/when we add things, saved workflows are not affected
19 #if str($out_format)=="ext":
20 -outfmt "6 std sallseqid score nident positive gaps ppos qframe sframe qseq sseq qlen slen"
21 #else:
22 -outfmt $out_format
23 #end if
24 -num_threads 8
25 #if $adv_opts.adv_opts_selector=="advanced":
26 $adv_opts.filter_query
27 -matrix $adv_opts.matrix
28 ## Need int(str(...)) because $adv_opts.max_hits is an InputValueWrapper object not a string
29 ## Note -max_target_seqs overrides -num_descriptions and -num_alignments
30 #if (str($adv_opts.max_hits) and int(str($adv_opts.max_hits)) > 0):
31 -max_target_seqs $adv_opts.max_hits
32 #end if
33 #if (str($adv_opts.word_size) and int(str($adv_opts.word_size)) > 0):
34 -word_size $adv_opts.word_size
35 #end if
36 ##Ungapped disabled for now - see comments below
37 ##$adv_opts.ungapped
38 $adv_opts.parse_deflines
39 ## End of advanced options:
40 #end if
41 </command>
42 <inputs>
43 <param name="query" type="data" format="fasta" label="Protein query sequence(s)"/>
44 <conditional name="db_opts">
45 <param name="db_opts_selector" type="select" label="Subject database/sequences">
46 <option value="db" selected="True">BLAST Database</option>
47 <option value="file">FASTA file</option>
48 </param>
49 <when value="db">
50 <param name="database" type="select" label="Nucleotide BLAST database">
51 <options from_file="blastdb.loc">
52 <column name="value" index="0"/>
53 <column name="name" index="1"/>
54 <column name="path" index="2"/>
55 </options>
56 </param>
57 <param name="subject" type="hidden" value="" />
58 </when>
59 <when value="file">
60 <param name="database" type="hidden" value="" />
61 <param name="subject" type="data" format="fasta" label="Nucleotide FASTA file to use as database"/>
62 </when>
63 </conditional>
64 <param name="evalue_cutoff" type="float" size="15" value="0.001" label="Set expectation value cutoff" />
65 <param name="out_format" type="select" label="Output format">
66 <option value="6" selected="True">Tabular (standard 12 columns)</option>
67 <option value="ext">Tabular (extended 24 columns)</option>
68 <option value="5">BLAST XML</option>
69 <option value="0">Pairwise text</option>
70 <option value="0 -html">Pairwise HTML</option>
71 <option value="2">Query-anchored text</option>
72 <option value="2 -html">Query-anchored HTML</option>
73 <option value="4">Flat query-anchored text</option>
74 <option value="4 -html">Flat query-anchored HTML</option>
75 <!--
76 <option value="-outfmt 11">BLAST archive format (ASN.1)</option>
77 -->
78 </param>
79 <conditional name="adv_opts">
80 <param name="adv_opts_selector" type="select" label="Advanced Options">
81 <option value="basic" selected="True">Hide Advanced Options</option>
82 <option value="advanced">Show Advanced Options</option>
83 </param>
84 <when value="basic" />
85 <when value="advanced">
86 <!-- Could use a select (yes, no, other) where other allows setting 'window locut hicut' -->
87 <param name="filter_query" type="boolean" label="Filter out low complexity regions (with SEG)" truevalue="-seg yes" falsevalue="-seg no" checked="true" />
88 <param name="matrix" type="select" label="Scoring matrix">
89 <option value="BLOSUM90">BLOSUM90</option>
90 <option value="BLOSUM80">BLOSUM80</option>
91 <option value="BLOSUM62" selected="true">BLOSUM62 (default)</option>
92 <option value="BLOSUM50">BLOSUM50</option>
93 <option value="BLOSUM45">BLOSUM45</option>
94 <option value="PAM250">PAM250</option>
95 <option value="PAM70">PAM70</option>
96 <option value="PAM30">PAM30</option>
97 </param>
98 <!-- Why doesn't optional override a validator? I want to accept an empty string OR a non-negative integer -->
99 <param name="max_hits" type="integer" value="0" label="Maximum hits to show" help="Use zero for default limits">
100 <validator type="in_range" min="0" />
101 </param>
102 <!-- I'd like word_size to be optional, with minimum 2 for blastp -->
103 <param name="word_size" type="integer" value="0" label="Word size for wordfinder algorithm" help="Use zero for default, otherwise minimum 2.">
104 <validator type="in_range" min="0" />
105 </param>
106 <!--
107 Can't use '-ungapped' on its own, error back is:
108 Composition-adjusted searched are not supported with an ungapped search, please add -comp_based_stats F or do a gapped search
109 Tried using '-ungapped -comp_based_stats F' and tblastn crashed with 'Attempt to access NULL pointer.'
110 <param name="ungapped" type="boolean" label="Perform ungapped alignment only?" truevalue="-ungapped -comp_based_stats F" falsevalue="" checked="false" />
111 -->
112 <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"/>
113 </when>
114 </conditional>
115 </inputs>
116 <outputs>
117 <data name="output1" format="tabular" label="tblastn on ${db_opts.db_opts_selector}">
118 <change_format>
119 <when input="out_format" value="0" format="txt"/>
120 <when input="out_format" value="0 -html" format="html"/>
121 <when input="out_format" value="2" format="txt"/>
122 <when input="out_format" value="2 -html" format="html"/>
123 <when input="out_format" value="4" format="txt"/>
124 <when input="out_format" value="4 -html" format="html"/>
125 <when input="out_format" value="5" format="blastxml"/>
126 </change_format>
127 </data>
128 </outputs>
129 <requirements>
130 <requirement type="package" version="2.2.26+">blast+</requirement>
131 </requirements>
132 <tests>
133 <test>
134 <param name="query" value="four_human_proteins.fasta" ftype="fasta" />
135 <param name="db_opts_selector" value="file" />
136 <param name="subject" value="rhodopsin_nucs.fasta" ftype="fasta" />
137 <param name="database" value="" />
138 <param name="evalue_cutoff" value="1e-10" />
139 <param name="out_format" value="5" />
140 <param name="adv_opts_selector" value="advanced" />
141 <param name="filter_query" value="false" />
142 <param name="matrix" value="BLOSUM80" />
143 <param name="max_hits" value="0" />
144 <param name="word_size" value="0" />
145 <param name="parse_deflines" value="false" />
146 <output name="output1" file="tblastn_four_human_vs_rhodopsin.xml" ftype="blastxml" />
147 </test>
148 <test>
149 <param name="query" value="four_human_proteins.fasta" ftype="fasta" />
150 <param name="db_opts_selector" value="file" />
151 <param name="subject" value="rhodopsin_nucs.fasta" ftype="fasta" />
152 <param name="database" value="" />
153 <param name="evalue_cutoff" value="1e-10" />
154 <param name="out_format" value="ext" />
155 <param name="adv_opts_selector" value="advanced" />
156 <param name="filter_query" value="false" />
157 <param name="matrix" value="BLOSUM80" />
158 <param name="max_hits" value="0" />
159 <param name="word_size" value="0" />
160 <param name="parse_deflines" value="false" />
161 <output name="output1" file="tblastn_four_human_vs_rhodopsin_ext.tabular" ftype="tabular" />
162 </test>
163 <test>
164 <param name="query" value="four_human_proteins.fasta" ftype="fasta" />
165 <param name="db_opts_selector" value="file" />
166 <param name="subject" value="rhodopsin_nucs.fasta" ftype="fasta" />
167 <param name="database" value="" />
168 <param name="evalue_cutoff" value="1e-10" />
169 <param name="out_format" value="6" />
170 <param name="adv_opts_selector" value="advanced" />
171 <param name="filter_query" value="false" />
172 <param name="matrix" value="BLOSUM80" />
173 <param name="max_hits" value="0" />
174 <param name="word_size" value="0" />
175 <param name="parse_deflines" value="false" />
176 <output name="output1" file="tblastn_four_human_vs_rhodopsin.tabular" ftype="tabular" />
177 </test>
178 <test>
179 <!-- Same as above, but parse deflines - on BLAST 2.2.25+ makes no difference -->
180 <param name="query" value="four_human_proteins.fasta" ftype="fasta" />
181 <param name="db_opts_selector" value="file" />
182 <param name="subject" value="rhodopsin_nucs.fasta" ftype="fasta" />
183 <param name="database" value="" />
184 <param name="evalue_cutoff" value="1e-10" />
185 <param name="out_format" value="6" />
186 <param name="adv_opts_selector" value="advanced" />
187 <param name="filter_query" value="false" />
188 <param name="matrix" value="BLOSUM80" />
189 <param name="max_hits" value="0" />
190 <param name="word_size" value="0" />
191 <param name="parse_deflines" value="true" />
192 <output name="output1" file="tblastn_four_human_vs_rhodopsin.tabular" ftype="tabular" />
193 </test>
194 <test>
195 <param name="query" value="four_human_proteins.fasta" ftype="fasta" />
196 <param name="db_opts_selector" value="file" />
197 <param name="subject" value="rhodopsin_nucs.fasta" ftype="fasta" />
198 <param name="database" value="" />
199 <param name="evalue_cutoff" value="1e-10" />
200 <param name="out_format" value="0 -html" />
201 <param name="adv_opts_selector" value="advanced" />
202 <param name="filter_query" value="false" />
203 <param name="matrix" value="BLOSUM80" />
204 <param name="max_hits" value="0" />
205 <param name="word_size" value="0" />
206 <param name="parse_deflines" value="false" />
207 <output name="output1" file="tblastn_four_human_vs_rhodopsin.html" ftype="html" />
208 </test>
209 </tests>
210 <help>
211
212 .. class:: warningmark
213
214 **Note**. Database searches may take a substantial amount of time.
215 For large input datasets it is advisable to allow overnight processing.
216
217 -----
218
219 **What it does**
220
221 Search a *translated nucleotide database* using a *protein query*,
222 using the NCBI BLAST+ tblastn command line tool.
223
224 -----
225
226 **Output format**
227
228 Because Galaxy focuses on processing tabular data, the default output of this
229 tool is tabular. The standard BLAST+ tabular output contains 12 columns:
230
231 ====== ========= ============================================
232 Column NCBI name Description
233 ------ --------- --------------------------------------------
234 1 qseqid Query Seq-id (ID of your sequence)
235 2 sseqid Subject Seq-id (ID of the database hit)
236 3 pident Percentage of identical matches
237 4 length Alignment length
238 5 mismatch Number of mismatches
239 6 gapopen Number of gap openings
240 7 qstart Start of alignment in query
241 8 qend End of alignment in query
242 9 sstart Start of alignment in subject (database hit)
243 10 send End of alignment in subject (database hit)
244 11 evalue Expectation value (E-value)
245 12 bitscore Bit score
246 ====== ========= ============================================
247
248 The BLAST+ tools can optionally output additional columns of information,
249 but this takes longer to calculate. Most (but not all) of these columns are
250 included by selecting the extended tabular output. The extra columns are
251 included *after* the standard 12 columns. This is so that you can write
252 workflow filtering steps that accept either the 12 or 24 column tabular
253 BLAST output.
254
255 ====== ============= ===========================================
256 Column NCBI name Description
257 ------ ------------- -------------------------------------------
258 13 sallseqid All subject Seq-id(s), separated by a ';'
259 14 score Raw score
260 15 nident Number of identical matches
261 16 positive Number of positive-scoring matches
262 17 gaps Total number of gaps
263 18 ppos Percentage of positive-scoring matches
264 19 qframe Query frame
265 20 sframe Subject frame
266 21 qseq Aligned part of query sequence
267 22 sseq Aligned part of subject sequence
268 23 qlen Query sequence length
269 24 slen Subject sequence length
270 ====== ============= ===========================================
271
272 The third option is BLAST XML output, which is designed to be parsed by
273 another program, and is understood by some Galaxy tools.
274
275 You can also choose several plain text or HTML output formats which are designed to be read by a person (not by another program).
276 The HTML versions use basic webpage formatting and can include links to the hits on the NCBI website.
277 The pairwise output (the default on the NCBI BLAST website) shows each match as a pairwise alignment with the query.
278 The two query anchored outputs show a multiple sequence alignment between the query and all the matches,
279 and differ in how insertions are shown (marked as insertions or with gap characters added to the other sequences).
280
281 -------
282
283 **References**
284
285 Altschul et al. Gapped BLAST and PSI-BLAST: a new generation of protein database search programs. 1997. Nucleic Acids Res. 25:3389-3402.
286
287 </help>
288 </tool>