Mercurial > repos > devteam > blast_datatypes

comparison tools/ncbi_blast_plus/ncbi_blastp_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_blastp_wrapper" name="NCBI BLAST+ blastp" version="0.0.13">
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 <parallelism method="multi" split_inputs="query" split_mode="to_size" split_size="1000" shared_inputs="subject" merge_outputs="output1"></parallelism>
5 <version_command>blastp -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 blastp
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 -matrix $adv_opts.matrix
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 $adv_opts.word_size
36 #end if
37 ##Ungapped disabled for now - see comments below
38 ##$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="Protein 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="blast_type" type="select" display="radio" label="Type of BLAST">
70 <option value="blastp">blastp</option>
71 <option value="blastp-short">blastp-short</option>
72 </param>
73 <param name="evalue_cutoff" type="float" size="15" value="0.001" label="Set expectation value cutoff" />
74 <param name="out_format" type="select" label="Output format">
75 <option value="6" selected="True">Tabular (standard 12 columns)</option>
76 <option value="ext">Tabular (extended 24 columns)</option>
77 <option value="5">BLAST XML</option>
78 <option value="0">Pairwise text</option>
79 <option value="0 -html">Pairwise HTML</option>
80 <option value="2">Query-anchored text</option>
81 <option value="2 -html">Query-anchored HTML</option>
82 <option value="4">Flat query-anchored text</option>
83 <option value="4 -html">Flat query-anchored HTML</option>
84 <!--
85 <option value="-outfmt 11">BLAST archive format (ASN.1)</option>
86 -->
87 </param>
88 <conditional name="adv_opts">
89 <param name="adv_opts_selector" type="select" label="Advanced Options">
90 <option value="basic" selected="True">Hide Advanced Options</option>
91 <option value="advanced">Show Advanced Options</option>
92 </param>
93 <when value="basic" />
94 <when value="advanced">
95 <!-- Could use a select (yes, no, other) where other allows setting 'window locut hicut' -->
96 <param name="filter_query" type="boolean" label="Filter out low complexity regions (with SEG)" truevalue="-seg yes" falsevalue="-seg no" checked="false" />
97 <param name="matrix" type="select" label="Scoring matrix">
98 <option value="BLOSUM90">BLOSUM90</option>
99 <option value="BLOSUM80">BLOSUM80</option>
100 <option value="BLOSUM62" selected="true">BLOSUM62 (default)</option>
101 <option value="BLOSUM50">BLOSUM50</option>
102 <option value="BLOSUM45">BLOSUM45</option>
103 <option value="PAM250">PAM250</option>
104 <option value="PAM70">PAM70</option>
105 <option value="PAM30">PAM30</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 2 for blastp -->
112 <param name="word_size" type="integer" value="0" label="Word size for wordfinder algorithm" help="Use zero for default, otherwise minimum 2.">
113 <validator type="in_range" min="0" />
114 </param>
115 <!--
116 Can't use '-ungapped' on its own, error back is:
117 Composition-adjusted searched are not supported with an ungapped search, please add -comp_based_stats F or do a gapped search
118 Tried using '-ungapped -comp_based_stats F' and blastp crashed with 'Attempt to access NULL pointer.'
119 <param name="ungapped" type="boolean" label="Perform ungapped alignment only?" truevalue="-ungapped -comp_based_stats F" falsevalue="" checked="false" />
120 -->
121 <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"/>
122 </when>
123 </conditional>
124 </inputs>
125 <outputs>
126 <data name="output1" format="tabular" label="${blast_type.value_label} on ${db_opts.db_opts_selector}">
127 <change_format>
128 <when input="out_format" value="0" format="txt"/>
129 <when input="out_format" value="0 -html" format="html"/>
130 <when input="out_format" value="2" format="txt"/>
131 <when input="out_format" value="2 -html" format="html"/>
132 <when input="out_format" value="4" format="txt"/>
133 <when input="out_format" value="4 -html" format="html"/>
134 <when input="out_format" value="5" format="blastxml"/>
135 </change_format>
136 </data>
137 </outputs>
138 <requirements>
139 <requirement type="binary">blastp</requirement>
140 </requirements>
141 <tests>
142 <test>
143 <param name="query" value="four_human_proteins.fasta" ftype="fasta" />
144 <param name="db_opts_selector" value="file" />
145 <param name="subject" value="rhodopsin_proteins.fasta" ftype="fasta" />
146 <param name="database" value="" />
147 <param name="evalue_cutoff" value="1e-8" />
148 <param name="blast_type" value="blastp" />
149 <param name="out_format" value="5" />
150 <param name="adv_opts_selector" value="advanced" />
151 <param name="filter_query" value="False" />
152 <param name="matrix" value="BLOSUM62" />
153 <param name="max_hits" value="0" />
154 <param name="word_size" value="0" />
155 <param name="parse_deflines" value="True" />
156 <output name="output1" file="blastp_four_human_vs_rhodopsin.xml" ftype="blastxml" />
157 </test>
158 <test>
159 <param name="query" value="four_human_proteins.fasta" ftype="fasta" />
160 <param name="db_opts_selector" value="file" />
161 <param name="subject" value="rhodopsin_proteins.fasta" ftype="fasta" />
162 <param name="database" value="" />
163 <param name="evalue_cutoff" value="1e-8" />
164 <param name="blast_type" value="blastp" />
165 <param name="out_format" value="6" />
166 <param name="adv_opts_selector" value="advanced" />
167 <param name="filter_query" value="False" />
168 <param name="matrix" value="BLOSUM62" />
169 <param name="max_hits" value="0" />
170 <param name="word_size" value="0" />
171 <param name="parse_deflines" value="True" />
172 <output name="output1" file="blastp_four_human_vs_rhodopsin.tabular" ftype="tabular" />
173 </test>
174 <test>
175 <param name="query" value="four_human_proteins.fasta" ftype="fasta" />
176 <param name="db_opts_selector" value="file" />
177 <param name="subject" value="rhodopsin_proteins.fasta" ftype="fasta" />
178 <param name="database" value="" />
179 <param name="evalue_cutoff" value="1e-8" />
180 <param name="blast_type" value="blastp" />
181 <param name="out_format" value="ext" />
182 <param name="adv_opts_selector" value="advanced" />
183 <param name="filter_query" value="False" />
184 <param name="matrix" value="BLOSUM62" />
185 <param name="max_hits" value="0" />
186 <param name="word_size" value="0" />
187 <param name="parse_deflines" value="True" />
188 <output name="output1" file="blastp_four_human_vs_rhodopsin_ext.tabular" ftype="tabular" />
189 </test>
190 <test>
191 <param name="query" value="rhodopsin_proteins.fasta" ftype="fasta" />
192 <param name="db_opts_selector" value="file" />
193 <param name="subject" value="four_human_proteins.fasta" ftype="fasta" />
194 <param name="database" value="" />
195 <param name="evalue_cutoff" value="1e-8" />
196 <param name="blast_type" value="blastp" />
197 <param name="out_format" value="6" />
198 <param name="adv_opts_selector" value="basic" />
199 <output name="output1" file="blastp_rhodopsin_vs_four_human.tabular" ftype="tabular" />
200 </test>
201 </tests>
202 <help>
203
204 .. class:: warningmark
205
206 **Note**. Database searches may take a substantial amount of time.
207 For large input datasets it is advisable to allow overnight processing.
208
209 -----
210
211 **What it does**
212
213 Search a *protein database* using a *protein query*,
214 using the NCBI BLAST+ blastp command line tool.
215
216 -----
217
218 **Output format**
219
220 Because Galaxy focuses on processing tabular data, the default output of this
221 tool is tabular. The standard BLAST+ tabular output contains 12 columns:
222
223 ====== ========= ============================================
224 Column NCBI name Description
225 ------ --------- --------------------------------------------
226 1 qseqid Query Seq-id (ID of your sequence)
227 2 sseqid Subject Seq-id (ID of the database hit)
228 3 pident Percentage of identical matches
229 4 length Alignment length
230 5 mismatch Number of mismatches
231 6 gapopen Number of gap openings
232 7 qstart Start of alignment in query
233 8 qend End of alignment in query
234 9 sstart Start of alignment in subject (database hit)
235 10 send End of alignment in subject (database hit)
236 11 evalue Expectation value (E-value)
237 12 bitscore Bit score
238 ====== ========= ============================================
239
240 The BLAST+ tools can optionally output additional columns of information,
241 but this takes longer to calculate. Most (but not all) of these columns are
242 included by selecting the extended tabular output. The extra columns are
243 included *after* the standard 12 columns. This is so that you can write
244 workflow filtering steps that accept either the 12 or 24 column tabular
245 BLAST output.
246
247 ====== ============= ===========================================
248 Column NCBI name Description
249 ------ ------------- -------------------------------------------
250 13 sallseqid All subject Seq-id(s), separated by a ';'
251 14 score Raw score
252 15 nident Number of identical matches
253 16 positive Number of positive-scoring matches
254 17 gaps Total number of gaps
255 18 ppos Percentage of positive-scoring matches
256 19 qframe Query frame
257 20 sframe Subject frame
258 21 qseq Aligned part of query sequence
259 22 sseq Aligned part of subject sequence
260 23 qlen Query sequence length
261 24 slen Subject sequence length
262 ====== ============= ===========================================
263
264 The third option is BLAST XML output, which is designed to be parsed by
265 another program, and is understood by some Galaxy tools.
266
267 You can also choose several plain text or HTML output formats which are designed to be read by a person (not by another program).
268 The HTML versions use basic webpage formatting and can include links to the hits on the NCBI website.
269 The pairwise output (the default on the NCBI BLAST website) shows each match as a pairwise alignment with the query.
270 The two query anchored outputs show a multiple sequence alignment between the query and all the matches,
271 and differ in how insertions are shown (marked as insertions or with gap characters added to the other sequences).
272
273 -------
274
275 **References**
276
277 Altschul et al. Gapped BLAST and PSI-BLAST: a new generation of protein database search programs. 1997. Nucleic Acids Res. 25:3389-3402.
278
279 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.
280
281 </help>
282 </tool>