Mercurial > repos > devteam > blast_datatypes

comparison tools/ncbi_blast_plus/ncbi_blastn_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_blastn_wrapper" name="NCBI BLAST+ blastn" version="0.0.13">
2 <description>Search nucleotide database with 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>blastn -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 blastn
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 -task $blast_type
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 ## Need int(str(...)) because $adv_opts.max_hits is an InputValueWrapper object not a string
30 ## Note -max_target_seqs overrides -num_descriptions and -num_alignments
31 #if (str($adv_opts.max_hits) and int(str($adv_opts.max_hits)) > 0):
32 -max_target_seqs $adv_opts.max_hits
33 #end if
34 #if (str($adv_opts.word_size) and int(str($adv_opts.word_size)) > 0):
35 -word_size $adv_opts.word_size
36 #end if
37 $adv_opts.ungapped
38 $adv_opts.parse_deflines
39 ## End of advanced options:
40 #end if
41 </command>
42 <stdio>
43 <exit_code range="1:" />
44 <exit_code range="://0" />
45 </stdio>
46 <inputs>
47 <param name="query" type="data" format="fasta" label="Nucleotide query sequence(s)"/>
48 <conditional name="db_opts">
49 <param name="db_opts_selector" type="select" label="Subject database/sequences">
50 <option value="db" selected="True">BLAST Database</option>
51 <option value="file">FASTA file (pairwise e-values)</option>
52 </param>
53 <when value="db">
54 <param name="database" type="select" label="Nucleotide BLAST database">
55 <options from_file="blastdb.loc">
56 <column name="value" index="0"/>
57 <column name="name" index="1"/>
58 <column name="path" index="2"/>
59 </options>
60 </param>
61 <param name="subject" type="hidden" value="" />
62 </when>
63 <when value="file">
64 <param name="database" type="hidden" value="" />
65 <param name="subject" type="data" format="fasta" label="Nucleotide FASTA file to use as database"/>
66 </when>
67 </conditional>
68 <param name="blast_type" type="select" display="radio" label="Type of BLAST">
69 <option value="megablast">megablast</option>
70 <option value="blastn">blastn</option>
71 <option value="blastn-short">blastn-short</option>
72 <option value="dc-megablast">dc-megablast</option>
73 <!-- Using BLAST 2.2.24+ this gives an error:
74 BLAST engine error: Program type 'vecscreen' not supported
75 <option value="vecscreen">vecscreen</option>
76 -->
77 </param>
78 <param name="evalue_cutoff" type="float" size="15" value="0.001" label="Set expectation value cutoff" />
79 <param name="out_format" type="select" label="Output format">
80 <option value="6" selected="True">Tabular (standard 12 columns)</option>
81 <option value="ext">Tabular (extended 24 columns)</option>
82 <option value="5">BLAST XML</option>
83 <option value="0">Pairwise text</option>
84 <option value="0 -html">Pairwise HTML</option>
85 <option value="2">Query-anchored text</option>
86 <option value="2 -html">Query-anchored HTML</option>
87 <option value="4">Flat query-anchored text</option>
88 <option value="4 -html">Flat query-anchored HTML</option>
89 <!--
90 <option value="-outfmt 11">BLAST archive format (ASN.1)</option>
91 -->
92 </param>
93 <conditional name="adv_opts">
94 <param name="adv_opts_selector" type="select" label="Advanced Options">
95 <option value="basic" selected="True">Hide Advanced Options</option>
96 <option value="advanced">Show Advanced Options</option>
97 </param>
98 <when value="basic" />
99 <when value="advanced">
100 <!-- Could use a select (yes, no, other) where other allows setting 'level window linker' -->
101 <param name="filter_query" type="boolean" label="Filter out low complexity regions (with DUST)" truevalue="-dust yes" falsevalue="-dust no" checked="true" />
102 <param name="strand" type="select" label="Query strand(s) to search against database/subject">
103 <option value="-strand both">Both</option>
104 <option value="-strand plus">Plus (forward)</option>
105 <option value="-strand minus">Minus (reverse complement)</option>
106 </param>
107 <!-- Why doesn't optional override a validator? I want to accept an empty string OR a non-negative integer -->
108 <param name="max_hits" type="integer" value="0" label="Maximum hits to show" help="Use zero for default limits">
109 <validator type="in_range" min="0" />
110 </param>
111 <!-- I'd like word_size to be optional, with minimum 4 for blastn -->
112 <param name="word_size" type="integer" value="0" label="Word size for wordfinder algorithm" help="Use zero for default, otherwise minimum 4.">
113 <validator type="in_range" min="0" />
114 </param>
115 <param name="ungapped" type="boolean" label="Perform ungapped alignment only?" truevalue="-ungapped" falsevalue="" checked="false" />
116 <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"/>
117 </when>
118 </conditional>
119 </inputs>
120 <outputs>
121 <data name="output1" format="tabular" label="${blast_type.value_label} on ${db_opts.db_opts_selector}">
122 <change_format>
123 <when input="out_format" value="0" format="txt"/>
124 <when input="out_format" value="0 -html" format="html"/>
125 <when input="out_format" value="2" format="txt"/>
126 <when input="out_format" value="2 -html" format="html"/>
127 <when input="out_format" value="4" format="txt"/>
128 <when input="out_format" value="4 -html" format="html"/>
129 <when input="out_format" value="5" format="blastxml"/>
130 </change_format>
131 </data>
132 </outputs>
133 <requirements>
134 <requirement type="binary">blastn</requirement>
135 </requirements>
136 <help>
137
138 .. class:: warningmark
139
140 **Note**. Database searches may take a substantial amount of time.
141 For large input datasets it is advisable to allow overnight processing.
142
143 -----
144
145 **What it does**
146
147 Search a *nucleotide database* using a *nucleotide query*,
148 using the NCBI BLAST+ blastn command line tool.
149 Algorithms include blastn, megablast, and discontiguous megablast.
150
151 -----
152
153 **Output format**
154
155 Because Galaxy focuses on processing tabular data, the default output of this
156 tool is tabular. The standard BLAST+ tabular output contains 12 columns:
157
158 ====== ========= ============================================
159 Column NCBI name Description
160 ------ --------- --------------------------------------------
161 1 qseqid Query Seq-id (ID of your sequence)
162 2 sseqid Subject Seq-id (ID of the database hit)
163 3 pident Percentage of identical matches
164 4 length Alignment length
165 5 mismatch Number of mismatches
166 6 gapopen Number of gap openings
167 7 qstart Start of alignment in query
168 8 qend End of alignment in query
169 9 sstart Start of alignment in subject (database hit)
170 10 send End of alignment in subject (database hit)
171 11 evalue Expectation value (E-value)
172 12 bitscore Bit score
173 ====== ========= ============================================
174
175 The BLAST+ tools can optionally output additional columns of information,
176 but this takes longer to calculate. Most (but not all) of these columns are
177 included by selecting the extended tabular output. The extra columns are
178 included *after* the standard 12 columns. This is so that you can write
179 workflow filtering steps that accept either the 12 or 24 column tabular
180 BLAST output.
181
182 ====== ============= ===========================================
183 Column NCBI name Description
184 ------ ------------- -------------------------------------------
185 13 sallseqid All subject Seq-id(s), separated by a ';'
186 14 score Raw score
187 15 nident Number of identical matches
188 16 positive Number of positive-scoring matches
189 17 gaps Total number of gaps
190 18 ppos Percentage of positive-scoring matches
191 19 qframe Query frame
192 20 sframe Subject frame
193 21 qseq Aligned part of query sequence
194 22 sseq Aligned part of subject sequence
195 23 qlen Query sequence length
196 24 slen Subject sequence length
197 ====== ============= ===========================================
198
199 The third option is BLAST XML output, which is designed to be parsed by
200 another program, and is understood by some Galaxy tools.
201
202 You can also choose several plain text or HTML output formats which are designed to be read by a person (not by another program).
203 The HTML versions use basic webpage formatting and can include links to the hits on the NCBI website.
204 The pairwise output (the default on the NCBI BLAST website) shows each match as a pairwise alignment with the query.
205 The two query anchored outputs show a multiple sequence alignment between the query and all the matches,
206 and differ in how insertions are shown (marked as insertions or with gap characters added to the other sequences).
207
208 -------
209
210 **References**
211
212 Zhang et al. A Greedy Algorithm for Aligning DNA Sequences. 2000. JCB: 203-214.
213
214 </help>
215 </tool>