Mercurial > repos > devteam > ncbi_blast_plus

comparison ncbi_tblastx_wrapper.xml @ 2:ab1a8640f817 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded v0.0.12 again, without extra path
author peterjc
date Thu, 23 Aug 2012 07:32:06 -0400
parents
children
comparison
equal deleted inserted replaced
1:27d7e1deada4 2:ab1a8640f817
1 <tool id="ncbi_tblastx_wrapper" name="NCBI BLAST+ tblastx" version="0.0.12">
2 <description>Search translated nucleotide database with translated nucleotide query sequence(s)</description>
3 <!-- If job splitting is enabled, break up the query file into parts -->
4 <parallelism method="multi" split_inputs="query" split_mode="to_size" split_size="1000" shared_inputs="subject" merge_outputs="output1"></parallelism>
5 <version_command>tblastx -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 tblastx
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 -query_gencode $query_gencode
17 -evalue $evalue_cutoff
18 -out $output1
19 ##Set the extended list here so if/when we add things, saved workflows are not affected
20 #if str($out_format)=="ext":
21 -outfmt "6 std sallseqid score nident positive gaps ppos qframe sframe qseq sseq qlen slen"
22 #else:
23 -outfmt $out_format
24 #end if
25 -num_threads 8
26 #if $adv_opts.adv_opts_selector=="advanced":
27 -db_gencode $adv_opts.db_gencode
28 $adv_opts.filter_query
29 $adv_opts.strand
30 -matrix $adv_opts.matrix
31 ## Need int(str(...)) because $adv_opts.max_hits is an InputValueWrapper object not a string
32 ## Note -max_target_seqs overrides -num_descriptions and -num_alignments
33 #if (str($adv_opts.max_hits) and int(str($adv_opts.max_hits)) > 0):
34 -max_target_seqs $adv_opts.max_hits
35 #end if
36 #if (str($adv_opts.word_size) and int(str($adv_opts.word_size)) > 0):
37 -word_size $adv_opts.word_size
38 #end if
39 $adv_opts.parse_deflines
40 ## End of advanced options:
41 #end if
42 </command>
43 <inputs>
44 <param name="query" type="data" format="fasta" label="Nucleotide query sequence(s)"/>
45 <conditional name="db_opts">
46 <param name="db_opts_selector" type="select" label="Subject database/sequences">
47 <option value="db" selected="True">BLAST Database</option>
48 <option value="file">FASTA file (pairwise e-values)</option>
49 </param>
50 <when value="db">
51 <param name="database" type="select" label="Nucleotide BLAST database">
52 <options from_file="blastdb.loc">
53 <column name="value" index="0"/>
54 <column name="name" index="1"/>
55 <column name="path" index="2"/>
56 </options>
57 </param>
58 <param name="subject" type="hidden" value="" />
59 </when>
60 <when value="file">
61 <param name="database" type="hidden" value="" />
62 <param name="subject" type="data" format="fasta" label="Nucleotide FASTA file to use as database"/>
63 </when>
64 </conditional>
65 <param name="query_gencode" type="select" label="Query genetic code">
66 <!-- See http://www.ncbi.nlm.nih.gov/Taxonomy/Utils/wprintgc.cgi for details -->
67 <option value="1" select="True">1. Standard</option>
68 <option value="2">2. Vertebrate Mitochondrial</option>
69 <option value="3">3. Yeast Mitochondrial</option>
70 <option value="4">4. Mold, Protozoan, and Coelenterate Mitochondrial Code and the Mycoplasma/Spiroplasma Code</option>
71 <option value="5">5. Invertebrate Mitochondrial</option>
72 <option value="6">6. Ciliate, Dasycladacean and Hexamita Nuclear Code</option>
73 <option value="9">9. Echinoderm Mitochondrial</option>
74 <option value="10">10. Euplotid Nuclear</option>
75 <option value="11">11. Bacteria and Archaea</option>
76 <option value="12">12. Alternative Yeast Nuclear</option>
77 <option value="13">13. Ascidian Mitochondrial</option>
78 <option value="14">14. Flatworm Mitochondrial</option>
79 <option value="15">15. Blepharisma Macronuclear</option>
80 <option value="16">16. Chlorophycean Mitochondrial Code</option>
81 <option value="21">21. Trematode Mitochondrial Code</option>
82 <option value="22">22. Scenedesmus obliquus mitochondrial Code</option>
83 <option value="23">23. Thraustochytrium Mitochondrial Code</option>
84 <option value="24">24. Pterobranchia mitochondrial code</option>
85 </param>
86 <param name="evalue_cutoff" type="float" size="15" value="0.001" label="Set expectation value cutoff" />
87 <param name="out_format" type="select" label="Output format">
88 <option value="6" selected="True">Tabular (standard 12 columns)</option>
89 <option value="ext">Tabular (extended 24 columns)</option>
90 <option value="5">BLAST XML</option>
91 <option value="0">Pairwise text</option>
92 <option value="0 -html">Pairwise HTML</option>
93 <option value="2">Query-anchored text</option>
94 <option value="2 -html">Query-anchored HTML</option>
95 <option value="4">Flat query-anchored text</option>
96 <option value="4 -html">Flat query-anchored HTML</option>
97 <!--
98 <option value="-outfmt 11">BLAST archive format (ASN.1)</option>
99 -->
100 </param>
101 <conditional name="adv_opts">
102 <param name="adv_opts_selector" type="select" label="Advanced Options">
103 <option value="basic" selected="True">Hide Advanced Options</option>
104 <option value="advanced">Show Advanced Options</option>
105 </param>
106 <when value="basic" />
107 <when value="advanced">
108 <param name="db_gencode" type="select" label="Database/subject genetic code">
109 <!-- See http://www.ncbi.nlm.nih.gov/Taxonomy/Utils/wprintgc.cgi for details -->
110 <option value="1" select="True">1. Standard</option>
111 <option value="2">2. Vertebrate Mitochondrial</option>
112 <option value="3">3. Yeast Mitochondrial</option>
113 <option value="4">4. Mold, Protozoan, and Coelenterate Mitochondrial Code and the Mycoplasma/Spiroplasma Code</option>
114 <option value="5">5. Invertebrate Mitochondrial</option>
115 <option value="6">6. Ciliate, Dasycladacean and Hexamita Nuclear Code</option>
116 <option value="9">9. Echinoderm Mitochondrial</option>
117 <option value="10">10. Euplotid Nuclear</option>
118 <option value="11">11. Bacteria and Archaea</option>
119 <option value="12">12. Alternative Yeast Nuclear</option>
120 <option value="13">13. Ascidian Mitochondrial</option>
121 <option value="14">14. Flatworm Mitochondrial</option>
122 <option value="15">15. Blepharisma Macronuclear</option>
123 <option value="16">16. Chlorophycean Mitochondrial Code</option>
124 <option value="21">21. Trematode Mitochondrial Code</option>
125 <option value="22">22. Scenedesmus obliquus mitochondrial Code</option>
126 <option value="23">23. Thraustochytrium Mitochondrial Code</option>
127 <option value="24">24. Pterobranchia mitochondrial code</option>
128 </param>
129 <!-- Could use a select (yes, no, other) where other allows setting 'window locut hicut' -->
130 <param name="filter_query" type="boolean" label="Filter out low complexity regions (with SEG)" truevalue="-seg yes" falsevalue="-seg no" checked="true" />
131 <param name="strand" type="select" label="Query strand(s) to search against database/subject">
132 <option value="-strand both">Both</option>
133 <option value="-strand plus">Plus (forward)</option>
134 <option value="-strand minus">Minus (reverse complement)</option>
135 </param>
136 <param name="matrix" type="select" label="Scoring matrix">
137 <option value="BLOSUM90">BLOSUM90</option>
138 <option value="BLOSUM80">BLOSUM80</option>
139 <option value="BLOSUM62" selected="true">BLOSUM62 (default)</option>
140 <option value="BLOSUM50">BLOSUM50</option>
141 <option value="BLOSUM45">BLOSUM45</option>
142 <option value="PAM250">PAM250</option>
143 <option value="PAM70">PAM70</option>
144 <option value="PAM30">PAM30</option>
145 </param>
146 <!-- Why doesn't optional override a validator? I want to accept an empty string OR a non-negative integer -->
147 <param name="max_hits" type="integer" value="0" label="Maximum hits to show" help="Use zero for default limits">
148 <validator type="in_range" min="0" />
149 </param>
150 <!-- I'd like word_size to be optional, with minimum 2 for tblastx -->
151 <param name="word_size" type="integer" value="0" label="Word size for wordfinder algorithm" help="Use zero for default, otherwise minimum 2.">
152 <validator type="in_range" min="0" />
153 </param>
154 <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"/>
155 </when>
156 </conditional>
157 </inputs>
158 <outputs>
159 <data name="output1" format="tabular" label="tblastx on ${db_opts.db_opts_selector}">
160 <change_format>
161 <when input="out_format" value="0" format="txt"/>
162 <when input="out_format" value="0 -html" format="html"/>
163 <when input="out_format" value="2" format="txt"/>
164 <when input="out_format" value="2 -html" format="html"/>
165 <when input="out_format" value="4" format="txt"/>
166 <when input="out_format" value="4 -html" format="html"/>
167 <when input="out_format" value="5" format="blastxml"/>
168 </change_format>
169 </data>
170 </outputs>
171 <requirements>
172 <requirement type="binary">tblastx</requirement>
173 </requirements>
174 <help>
175
176 .. class:: warningmark
177
178 **Note**. Database searches may take a substantial amount of time.
179 For large input datasets it is advisable to allow overnight processing.
180
181 -----
182
183 **What it does**
184
185 Search a *translated nucleotide database* using a *protein query*,
186 using the NCBI BLAST+ tblastx command line tool.
187
188 -----
189
190 **Output format**
191
192 Because Galaxy focuses on processing tabular data, the default output of this
193 tool is tabular. The standard BLAST+ tabular output contains 12 columns:
194
195 ====== ========= ============================================
196 Column NCBI name Description
197 ------ --------- --------------------------------------------
198 1 qseqid Query Seq-id (ID of your sequence)
199 2 sseqid Subject Seq-id (ID of the database hit)
200 3 pident Percentage of identical matches
201 4 length Alignment length
202 5 mismatch Number of mismatches
203 6 gapopen Number of gap openings
204 7 qstart Start of alignment in query
205 8 qend End of alignment in query
206 9 sstart Start of alignment in subject (database hit)
207 10 send End of alignment in subject (database hit)
208 11 evalue Expectation value (E-value)
209 12 bitscore Bit score
210 ====== ========= ============================================
211
212 The BLAST+ tools can optionally output additional columns of information,
213 but this takes longer to calculate. Most (but not all) of these columns are
214 included by selecting the extended tabular output. The extra columns are
215 included *after* the standard 12 columns. This is so that you can write
216 workflow filtering steps that accept either the 12 or 24 column tabular
217 BLAST output.
218
219 ====== ============= ===========================================
220 Column NCBI name Description
221 ------ ------------- -------------------------------------------
222 13 sallseqid All subject Seq-id(s), separated by a ';'
223 14 score Raw score
224 15 nident Number of identical matches
225 16 positive Number of positive-scoring matches
226 17 gaps Total number of gaps
227 18 ppos Percentage of positive-scoring matches
228 19 qframe Query frame
229 20 sframe Subject frame
230 21 qseq Aligned part of query sequence
231 22 sseq Aligned part of subject sequence
232 23 qlen Query sequence length
233 24 slen Subject sequence length
234 ====== ============= ===========================================
235
236 The third option is BLAST XML output, which is designed to be parsed by
237 another program, and is understood by some Galaxy tools.
238
239 You can also choose several plain text or HTML output formats which are designed to be read by a person (not by another program).
240 The HTML versions use basic webpage formatting and can include links to the hits on the NCBI website.
241 The pairwise output (the default on the NCBI BLAST website) shows each match as a pairwise alignment with the query.
242 The two query anchored outputs show a multiple sequence alignment between the query and all the matches,
243 and differ in how insertions are shown (marked as insertions or with gap characters added to the other sequences).
244
245 -------
246
247 **References**
248
249 Altschul et al. Gapped BLAST and PSI-BLAST: a new generation of protein database search programs. 1997. Nucleic Acids Res. 25:3389-3402.
250
251 </help>
252 </tool>