Mercurial > repos > devteam > blast_datatypes

comparison tools/ncbi_blast_plus/ncbi_blastx_wrapper.xml @ 2:45ba7c750bc8 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
This update should have no functional effect. Renamed files (since xml.py will be inaccurate once BLAST databases are added in future update).
author peterjc
date Thu, 20 Sep 2012 10:12:43 -0400
parents
children
comparison
equal deleted inserted replaced
1:10dce68b584b 2:45ba7c750bc8
1 <tool id="ncbi_blastx_wrapper" name="NCBI BLAST+ blastx" version="0.0.13">
2 <description>Search protein 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>blastx -version</version_command>
6 <command>
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 blastx
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 $adv_opts.filter_query
28 $adv_opts.strand
29 -matrix $adv_opts.matrix
30 ## Need int(str(...)) because $adv_opts.max_hits is an InputValueWrapper object not a string
31 ## Note -max_target_seqs overrides -num_descriptions and -num_alignments
32 #if (str($adv_opts.max_hits) and int(str($adv_opts.max_hits)) > 0):
33 -max_target_seqs $adv_opts.max_hits
34 #end if
35 #if (str($adv_opts.word_size) and int(str($adv_opts.word_size)) > 0):
36 -word_size $adv_opts.word_size
37 #end if
38 $adv_opts.ungapped
39 $adv_opts.parse_deflines
40 ## End of advanced options:
41 #end if
42 </command>
43 <stdio>
44 <exit_code range="1:" />
45 <exit_code range="://0" />
46 </stdio>
47 <inputs>
48 <param name="query" type="data" format="fasta" label="Nucleotide query sequence(s)"/>
49 <conditional name="db_opts">
50 <param name="db_opts_selector" type="select" label="Subject database/sequences">
51 <option value="db" selected="True">BLAST Database</option>
52 <option value="file">FASTA file (pairwise e-values)</option>
53 </param>
54 <when value="db">
55 <param name="database" type="select" label="Protein BLAST database">
56 <options from_file="blastdb_p.loc">
57 <column name="value" index="0"/>
58 <column name="name" index="1"/>
59 <column name="path" index="2"/>
60 </options>
61 </param>
62 <param name="subject" type="hidden" value="" />
63 </when>
64 <when value="file">
65 <param name="database" type="hidden" value="" />
66 <param name="subject" type="data" format="fasta" label="Protein FASTA file to use as database"/>
67 </when>
68 </conditional>
69 <param name="query_gencode" type="select" label="Query genetic code">
70 <!-- See http://www.ncbi.nlm.nih.gov/Taxonomy/Utils/wprintgc.cgi for details -->
71 <option value="1" select="True">1. Standard</option>
72 <option value="2">2. Vertebrate Mitochondrial</option>
73 <option value="3">3. Yeast Mitochondrial</option>
74 <option value="4">4. Mold, Protozoan, and Coelenterate Mitochondrial Code and the Mycoplasma/Spiroplasma Code</option>
75 <option value="5">5. Invertebrate Mitochondrial</option>
76 <option value="6">6. Ciliate, Dasycladacean and Hexamita Nuclear Code</option>
77 <option value="9">9. Echinoderm Mitochondrial</option>
78 <option value="10">10. Euplotid Nuclear</option>
79 <option value="11">11. Bacteria and Archaea</option>
80 <option value="12">12. Alternative Yeast Nuclear</option>
81 <option value="13">13. Ascidian Mitochondrial</option>
82 <option value="14">14. Flatworm Mitochondrial</option>
83 <option value="15">15. Blepharisma Macronuclear</option>
84 <option value="16">16. Chlorophycean Mitochondrial Code</option>
85 <option value="21">21. Trematode Mitochondrial Code</option>
86 <option value="22">22. Scenedesmus obliquus mitochondrial Code</option>
87 <option value="23">23. Thraustochytrium Mitochondrial Code</option>
88 <option value="24">24. Pterobranchia mitochondrial code</option>
89 </param>
90 <param name="evalue_cutoff" type="float" size="15" value="0.001" label="Set expectation value cutoff" />
91 <param name="out_format" type="select" label="Output format">
92 <option value="6" selected="True">Tabular (standard 12 columns)</option>
93 <option value="ext">Tabular (extended 24 columns)</option>
94 <option value="5">BLAST XML</option>
95 <option value="0">Pairwise text</option>
96 <option value="0 -html">Pairwise HTML</option>
97 <option value="2">Query-anchored text</option>
98 <option value="2 -html">Query-anchored HTML</option>
99 <option value="4">Flat query-anchored text</option>
100 <option value="4 -html">Flat query-anchored HTML</option>
101 <!--
102 <option value="-outfmt 11">BLAST archive format (ASN.1)</option>
103 -->
104 </param>
105 <conditional name="adv_opts">
106 <param name="adv_opts_selector" type="select" label="Advanced Options">
107 <option value="basic" selected="True">Hide Advanced Options</option>
108 <option value="advanced">Show Advanced Options</option>
109 </param>
110 <when value="basic" />
111 <when value="advanced">
112 <!-- Could use a select (yes, no, other) where other allows setting 'window locut hicut' -->
113 <param name="filter_query" type="boolean" label="Filter out low complexity regions (with SEG)" truevalue="-seg yes" falsevalue="-seg no" checked="true" />
114 <param name="strand" type="select" label="Query strand(s) to search against database/subject">
115 <option value="-strand both">Both</option>
116 <option value="-strand plus">Plus (forward)</option>
117 <option value="-strand minus">Minus (reverse complement)</option>
118 </param>
119 <param name="matrix" type="select" label="Scoring matrix">
120 <option value="BLOSUM90">BLOSUM90</option>
121 <option value="BLOSUM80">BLOSUM80</option>
122 <option value="BLOSUM62" selected="true">BLOSUM62 (default)</option>
123 <option value="BLOSUM50">BLOSUM50</option>
124 <option value="BLOSUM45">BLOSUM45</option>
125 <option value="PAM250">PAM250</option>
126 <option value="PAM70">PAM70</option>
127 <option value="PAM30">PAM30</option>
128 </param>
129 <!-- Why doesn't optional override a validator? I want to accept an empty string OR a non-negative integer -->
130 <param name="max_hits" type="integer" value="0" label="Maximum hits to show" help="Use zero for default limits">
131 <validator type="in_range" min="0" />
132 </param>
133 <!-- I'd like word_size to be optional, with minimum 2 for blastx -->
134 <param name="word_size" type="integer" value="0" label="Word size for wordfinder algorithm" help="Use zero for default, otherwise minimum 2.">
135 <validator type="in_range" min="0" />
136 </param>
137 <param name="ungapped" type="boolean" label="Perform ungapped alignment only?" truevalue="-ungapped" falsevalue="" checked="false" />
138 <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"/>
139 </when>
140 </conditional>
141 </inputs>
142 <outputs>
143 <data name="output1" format="tabular" label="blastx on ${db_opts.db_opts_selector}">
144 <change_format>
145 <when input="out_format" value="0" format="txt"/>
146 <when input="out_format" value="0 -html" format="html"/>
147 <when input="out_format" value="2" format="txt"/>
148 <when input="out_format" value="2 -html" format="html"/>
149 <when input="out_format" value="4" format="txt"/>
150 <when input="out_format" value="4 -html" format="html"/>
151 <when input="out_format" value="5" format="blastxml"/>
152 </change_format>
153 </data>
154 </outputs>
155 <requirements>
156 <requirement type="binary">blastx</requirement>
157 </requirements>
158 <tests>
159 <test>
160 <param name="query" value="rhodopsin_nucs.fasta" ftype="fasta" />
161 <param name="db_opts_selector" value="file" />
162 <param name="subject" value="four_human_proteins.fasta" ftype="fasta" />
163 <param name="database" value="" />
164 <param name="evalue_cutoff" value="1e-10" />
165 <param name="out_format" value="5" />
166 <param name="adv_opts_selector" value="basic" />
167 <output name="output1" file="blastx_rhodopsin_vs_four_human.xml" ftype="blastxml" />
168 </test>
169 <test>
170 <param name="query" value="rhodopsin_nucs.fasta" ftype="fasta" />
171 <param name="db_opts_selector" value="file" />
172 <param name="subject" value="four_human_proteins.fasta" ftype="fasta" />
173 <param name="database" value="" />
174 <param name="evalue_cutoff" value="1e-10" />
175 <param name="out_format" value="6" />
176 <param name="adv_opts_selector" value="basic" />
177 <output name="output1" file="blastx_rhodopsin_vs_four_human.tabular" ftype="tabular" />
178 </test>
179 <test>
180 <param name="query" value="rhodopsin_nucs.fasta" ftype="fasta" />
181 <param name="db_opts_selector" value="file" />
182 <param name="subject" value="four_human_proteins.fasta" ftype="fasta" />
183 <param name="database" value="" />
184 <param name="evalue_cutoff" value="1e-10" />
185 <param name="out_format" value="ext" />
186 <param name="adv_opts_selector" value="basic" />
187 <output name="output1" file="blastx_rhodopsin_vs_four_human_ext.tabular" ftype="tabular" />
188 </test>
189 </tests>
190 <help>
191
192 .. class:: warningmark
193
194 **Note**. Database searches may take a substantial amount of time.
195 For large input datasets it is advisable to allow overnight processing.
196
197 -----
198
199 **What it does**
200
201 Search a *protein database* using a *translated nucleotide query*,
202 using the NCBI BLAST+ blastx command line tool.
203
204 -----
205
206 **Output format**
207
208 Because Galaxy focuses on processing tabular data, the default output of this
209 tool is tabular. The standard BLAST+ tabular output contains 12 columns:
210
211 ====== ========= ============================================
212 Column NCBI name Description
213 ------ --------- --------------------------------------------
214 1 qseqid Query Seq-id (ID of your sequence)
215 2 sseqid Subject Seq-id (ID of the database hit)
216 3 pident Percentage of identical matches
217 4 length Alignment length
218 5 mismatch Number of mismatches
219 6 gapopen Number of gap openings
220 7 qstart Start of alignment in query
221 8 qend End of alignment in query
222 9 sstart Start of alignment in subject (database hit)
223 10 send End of alignment in subject (database hit)
224 11 evalue Expectation value (E-value)
225 12 bitscore Bit score
226 ====== ========= ============================================
227
228 The BLAST+ tools can optionally output additional columns of information,
229 but this takes longer to calculate. Most (but not all) of these columns are
230 included by selecting the extended tabular output. The extra columns are
231 included *after* the standard 12 columns. This is so that you can write
232 workflow filtering steps that accept either the 12 or 24 column tabular
233 BLAST output.
234
235 ====== ============= ===========================================
236 Column NCBI name Description
237 ------ ------------- -------------------------------------------
238 13 sallseqid All subject Seq-id(s), separated by a ';'
239 14 score Raw score
240 15 nident Number of identical matches
241 16 positive Number of positive-scoring matches
242 17 gaps Total number of gaps
243 18 ppos Percentage of positive-scoring matches
244 19 qframe Query frame
245 20 sframe Subject frame
246 21 qseq Aligned part of query sequence
247 22 sseq Aligned part of subject sequence
248 23 qlen Query sequence length
249 24 slen Subject sequence length
250 ====== ============= ===========================================
251
252 The third option is BLAST XML output, which is designed to be parsed by
253 another program, and is understood by some Galaxy tools.
254
255 You can also choose several plain text or HTML output formats which are designed to be read by a person (not by another program).
256 The HTML versions use basic webpage formatting and can include links to the hits on the NCBI website.
257 The pairwise output (the default on the NCBI BLAST website) shows each match as a pairwise alignment with the query.
258 The two query anchored outputs show a multiple sequence alignment between the query and all the matches,
259 and differ in how insertions are shown (marked as insertions or with gap characters added to the other sequences).
260
261 -------
262
263 **References**
264
265 Altschul et al. Gapped BLAST and PSI-BLAST: a new generation of protein database search programs. 1997. Nucleic Acids Res. 25:3389-3402.
266
267 </help>
268 </tool>