comparison ncbi_blastp_wrapper.xml @ 2:ab1a8640f817 draft

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_blastp_wrapper" name="NCBI BLAST+ blastp" version="0.0.12">
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 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 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 <inputs>
44 <param name="query" type="data" format="fasta" label="Protein 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="Protein BLAST database">
52 <options from_file="blastdb_p.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="Protein FASTA file to use as database"/>
63 </when>
64 </conditional>
65 <param name="blast_type" type="select" display="radio" label="Type of BLAST">
66 <option value="blastp">blastp</option>
67 <option value="blastp-short">blastp-short</option>
68 </param>
69 <param name="evalue_cutoff" type="float" size="15" value="0.001" label="Set expectation value cutoff" />
70 <param name="out_format" type="select" label="Output format">
71 <option value="6" selected="True">Tabular (standard 12 columns)</option>
72 <option value="ext">Tabular (extended 24 columns)</option>
73 <option value="5">BLAST XML</option>
74 <option value="0">Pairwise text</option>
75 <option value="0 -html">Pairwise HTML</option>
76 <option value="2">Query-anchored text</option>
77 <option value="2 -html">Query-anchored HTML</option>
78 <option value="4">Flat query-anchored text</option>
79 <option value="4 -html">Flat query-anchored HTML</option>
80 <!--
81 <option value="-outfmt 11">BLAST archive format (ASN.1)</option>
82 -->
83 </param>
84 <conditional name="adv_opts">
85 <param name="adv_opts_selector" type="select" label="Advanced Options">
86 <option value="basic" selected="True">Hide Advanced Options</option>
87 <option value="advanced">Show Advanced Options</option>
88 </param>
89 <when value="basic" />
90 <when value="advanced">
91 <!-- Could use a select (yes, no, other) where other allows setting 'window locut hicut' -->
92 <param name="filter_query" type="boolean" label="Filter out low complexity regions (with SEG)" truevalue="-seg yes" falsevalue="-seg no" checked="false" />
93 <param name="matrix" type="select" label="Scoring matrix">
94 <option value="BLOSUM90">BLOSUM90</option>
95 <option value="BLOSUM80">BLOSUM80</option>
96 <option value="BLOSUM62" selected="true">BLOSUM62 (default)</option>
97 <option value="BLOSUM50">BLOSUM50</option>
98 <option value="BLOSUM45">BLOSUM45</option>
99 <option value="PAM250">PAM250</option>
100 <option value="PAM70">PAM70</option>
101 <option value="PAM30">PAM30</option>
102 </param>
103 <!-- Why doesn't optional override a validator? I want to accept an empty string OR a non-negative integer -->
104 <param name="max_hits" type="integer" value="0" label="Maximum hits to show" help="Use zero for default limits">
105 <validator type="in_range" min="0" />
106 </param>
107 <!-- I'd like word_size to be optional, with minimum 2 for blastp -->
108 <param name="word_size" type="integer" value="0" label="Word size for wordfinder algorithm" help="Use zero for default, otherwise minimum 2.">
109 <validator type="in_range" min="0" />
110 </param>
111 <!--
112 Can't use '-ungapped' on its own, error back is:
113 Composition-adjusted searched are not supported with an ungapped search, please add -comp_based_stats F or do a gapped search
114 Tried using '-ungapped -comp_based_stats F' and blastp crashed with 'Attempt to access NULL pointer.'
115 <param name="ungapped" type="boolean" label="Perform ungapped alignment only?" truevalue="-ungapped -comp_based_stats F" falsevalue="" checked="false" />
116 -->
117 <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"/>
118 </when>
119 </conditional>
120 </inputs>
121 <outputs>
122 <data name="output1" format="tabular" label="${blast_type.value_label} on ${db_opts.db_opts_selector}">
123 <change_format>
124 <when input="out_format" value="0" format="txt"/>
125 <when input="out_format" value="0 -html" format="html"/>
126 <when input="out_format" value="2" format="txt"/>
127 <when input="out_format" value="2 -html" format="html"/>
128 <when input="out_format" value="4" format="txt"/>
129 <when input="out_format" value="4 -html" format="html"/>
130 <when input="out_format" value="5" format="blastxml"/>
131 </change_format>
132 </data>
133 </outputs>
134 <requirements>
135 <requirement type="binary">blastp</requirement>
136 </requirements>
137 <tests>
138 <test>
139 <param name="query" value="four_human_proteins.fasta" ftype="fasta" />
140 <param name="db_opts_selector" value="file" />
141 <param name="subject" value="rhodopsin_proteins.fasta" ftype="fasta" />
142 <param name="database" value="" />
143 <param name="evalue_cutoff" value="1e-8" />
144 <param name="blast_type" value="blastp" />
145 <param name="out_format" value="5" />
146 <param name="adv_opts_selector" value="advanced" />
147 <param name="filter_query" value="False" />
148 <param name="matrix" value="BLOSUM62" />
149 <param name="max_hits" value="0" />
150 <param name="word_size" value="0" />
151 <param name="parse_deflines" value="True" />
152 <output name="output1" file="blastp_four_human_vs_rhodopsin.xml" ftype="blastxml" />
153 </test>
154 <test>
155 <param name="query" value="four_human_proteins.fasta" ftype="fasta" />
156 <param name="db_opts_selector" value="file" />
157 <param name="subject" value="rhodopsin_proteins.fasta" ftype="fasta" />
158 <param name="database" value="" />
159 <param name="evalue_cutoff" value="1e-8" />
160 <param name="blast_type" value="blastp" />
161 <param name="out_format" value="6" />
162 <param name="adv_opts_selector" value="advanced" />
163 <param name="filter_query" value="False" />
164 <param name="matrix" value="BLOSUM62" />
165 <param name="max_hits" value="0" />
166 <param name="word_size" value="0" />
167 <param name="parse_deflines" value="True" />
168 <output name="output1" file="blastp_four_human_vs_rhodopsin.tabular" ftype="tabular" />
169 </test>
170 <test>
171 <param name="query" value="four_human_proteins.fasta" ftype="fasta" />
172 <param name="db_opts_selector" value="file" />
173 <param name="subject" value="rhodopsin_proteins.fasta" ftype="fasta" />
174 <param name="database" value="" />
175 <param name="evalue_cutoff" value="1e-8" />
176 <param name="blast_type" value="blastp" />
177 <param name="out_format" value="ext" />
178 <param name="adv_opts_selector" value="advanced" />
179 <param name="filter_query" value="False" />
180 <param name="matrix" value="BLOSUM62" />
181 <param name="max_hits" value="0" />
182 <param name="word_size" value="0" />
183 <param name="parse_deflines" value="True" />
184 <output name="output1" file="blastp_four_human_vs_rhodopsin_ext.tabular" ftype="tabular" />
185 </test>
186 <test>
187 <param name="query" value="rhodopsin_proteins.fasta" ftype="fasta" />
188 <param name="db_opts_selector" value="file" />
189 <param name="subject" value="four_human_proteins.fasta" ftype="fasta" />
190 <param name="database" value="" />
191 <param name="evalue_cutoff" value="1e-8" />
192 <param name="blast_type" value="blastp" />
193 <param name="out_format" value="6" />
194 <param name="adv_opts_selector" value="basic" />
195 <output name="output1" file="blastp_rhodopsin_vs_four_human.tabular" ftype="tabular" />
196 </test>
197 </tests>
198 <help>
199
200 .. class:: warningmark
201
202 **Note**. Database searches may take a substantial amount of time.
203 For large input datasets it is advisable to allow overnight processing.
204
205 -----
206
207 **What it does**
208
209 Search a *protein database* using a *protein query*,
210 using the NCBI BLAST+ blastp command line tool.
211
212 -----
213
214 **Output format**
215
216 Because Galaxy focuses on processing tabular data, the default output of this
217 tool is tabular. The standard BLAST+ tabular output contains 12 columns:
218
219 ====== ========= ============================================
220 Column NCBI name Description
221 ------ --------- --------------------------------------------
222 1 qseqid Query Seq-id (ID of your sequence)
223 2 sseqid Subject Seq-id (ID of the database hit)
224 3 pident Percentage of identical matches
225 4 length Alignment length
226 5 mismatch Number of mismatches
227 6 gapopen Number of gap openings
228 7 qstart Start of alignment in query
229 8 qend End of alignment in query
230 9 sstart Start of alignment in subject (database hit)
231 10 send End of alignment in subject (database hit)
232 11 evalue Expectation value (E-value)
233 12 bitscore Bit score
234 ====== ========= ============================================
235
236 The BLAST+ tools can optionally output additional columns of information,
237 but this takes longer to calculate. Most (but not all) of these columns are
238 included by selecting the extended tabular output. The extra columns are
239 included *after* the standard 12 columns. This is so that you can write
240 workflow filtering steps that accept either the 12 or 24 column tabular
241 BLAST output.
242
243 ====== ============= ===========================================
244 Column NCBI name Description
245 ------ ------------- -------------------------------------------
246 13 sallseqid All subject Seq-id(s), separated by a ';'
247 14 score Raw score
248 15 nident Number of identical matches
249 16 positive Number of positive-scoring matches
250 17 gaps Total number of gaps
251 18 ppos Percentage of positive-scoring matches
252 19 qframe Query frame
253 20 sframe Subject frame
254 21 qseq Aligned part of query sequence
255 22 sseq Aligned part of subject sequence
256 23 qlen Query sequence length
257 24 slen Subject sequence length
258 ====== ============= ===========================================
259
260 The third option is BLAST XML output, which is designed to be parsed by
261 another program, and is understood by some Galaxy tools.
262
263 You can also choose several plain text or HTML output formats which are designed to be read by a person (not by another program).
264 The HTML versions use basic webpage formatting and can include links to the hits on the NCBI website.
265 The pairwise output (the default on the NCBI BLAST website) shows each match as a pairwise alignment with the query.
266 The two query anchored outputs show a multiple sequence alignment between the query and all the matches,
267 and differ in how insertions are shown (marked as insertions or with gap characters added to the other sequences).
268
269 -------
270
271 **References**
272
273 Altschul et al. Gapped BLAST and PSI-BLAST: a new generation of protein database search programs. 1997. Nucleic Acids Res. 25:3389-3402.
274
275 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.
276
277 </help>
278 </tool>