root/galaxy-central/tools/ncbi_blast_plus/ncbi_blastp_wrapper.xml

リビジョン 2, 8.7 KB (コミッタ: hatakeyama, 14 年 前)

import galaxy-central

行番号 
1<tool id="ncbi_blastp_wrapper" name="NCBI BLAST+ blastp" version="0.0.1">
2    <description>Search protein database with protein query sequence(s)</description>
3    <command>
4## The command is a Cheetah template which allows some Python based syntax.
5## Lines starting hash hash are comments. Galaxy will turn newlines into spaces
6blastp
7-query "$query"
8#if $db_opts.db_opts_selector == "db":
9  -db "$db_opts.database"
10#else:
11  -subject "$db_opts.subject"
12#end if
13-task $blast_type
14-evalue $evalue_cutoff
15$adv_opts.filter_query
16$adv_opts.matrix
17-out $output1
18$out_format
19-num_threads 8
20## Need int(str(...)) because $adv_opts.max_hits is an InputValueWrapper object not a string
21## Note -max_target_seqs overrides -num_descriptions and -num_alignments
22#if (str($adv_opts.max_hits) and int(str($adv_opts.max_hits)) > 0):
23-max_target_seqs $adv_opts.max_hits
24#end if
25#if (str($adv_opts.word_size) and int(str($adv_opts.word_size)) > 0):
26-word_size $adv_opts.word_size
27#end if
28##Ungapped disabled for now - see comments below
29##$adv_opts.ungapped
30    </command>
31    <inputs>
32        <param name="query" type="data" format="fasta" label="Protein query sequence(s)"/>
33        <conditional name="db_opts">
34            <param name="db_opts_selector" type="select" label="Subject database/sequences">
35              <option value="db" selected="True">BLAST Database</option>
36              <option value="file">FASTA file</option>
37            </param>
38            <when value="db">
39                <param name="database" type="select" label="Protein BLAST database">
40                    <options from_file="blastdb_p.loc">
41                      <column name="name" index="0"/>
42                      <column name="value" index="1"/>
43                    </options>
44                </param>
45                <param name="subject" type="hidden" value="" />
46            </when>
47            <when value="file">
48                <param name="database" type="hidden" value="" />
49                <param name="subject" type="data" format="fasta" label="Protein FASTA file to use as database"/>
50            </when>
51        </conditional>
52        <param name="blast_type" type="select" display="radio" label="Type of BLAST">
53            <option value="blastp">blastp</option>
54            <option value="blastp-short">blastp-short</option>
55        </param>
56        <param name="evalue_cutoff" type="float" size="15" value="0.001" label="set expectation value cutoff" />
57        <param name="out_format" type="select" label="Output format">
58            <option value="-outfmt 6" selected="True">Tabular</option>
59            <option value="-outfmt 5">BLAST XML</option>
60            <option value="-outfmt 0">Pairwise text</option>
61            <option value="-outfmt 0 -html">Pairwise HTML</option>
62            <option value="-outfmt 2">Query-anchored text</option>
63            <option value="-outfmt 2 -html">Query-anchored HTML</option>
64            <option value="-outfmt 4">Flat query-anchored text</option>
65            <option value="-outfmt 4 -html">Flat query-anchored HTML</option>
66            <!--
67            <option value="-outfmt 11">BLAST archive format (ASN.1)</option>
68            -->
69        </param>
70        <conditional name="adv_opts">
71            <param name="adv_opts_selector" type="select" label="Advanced Options">
72              <option value="basic" selected="True">Hide Advanced Options</option>
73              <option value="advanced">Show Advanced Options</option>
74            </param>
75            <when value="basic">
76                <param name="filter_query" type="hidden" value="" />
77                <param name="matrix" type="hidden" value="" />
78                <param name="max_hits" type="hidden" value="" />
79                <param name="word_size" type="hidden" value="" />
80                <!--
81                Ungapped disabled for now, see comments below
82                <param name="ungapped" type="hidden" value="" />
83                -->
84            </when>
85            <when value="advanced">
86                <!-- Could use a select (yes, no, other) where other allows setting 'window locut hicut' -->
87                <param name="filter_query" type="boolean" label="Filter out low complexity regions (with SEG)" truevalue="-seg yes" falsevalue="-seg no" checked="true" />
88                <param name="matrix" type="select" label="Scoring matrix">
89                    <option value="-matrix BLOSUM90">BLOSUM90</option>
90                    <option value="-matrix BLOSUM80">BLOSUM80</option>
91                    <option value="-matrix BLOSUM62" selected="true">BLOSUM62 (default)</option>
92                    <option value="-matrix BLOSUM50">BLOSUM50</option>
93                    <option value="-matrix BLOSUM45">BLOSUM45</option>
94                    <option value="-matrix PAM250">PAM250</option>
95                    <option value="-matrix PAM70">PAM70</option>
96                    <option value="-matrix PAM30">PAM30</option>
97                </param>
98                <!-- Why doesn't optional override a validator? I want to accept an empty string OR a non-negative integer -->
99                <param name="max_hits" type="integer" value="0" label="Maximum hits to show" help="Use zero for default limits">
100                    <validator type="in_range" min="0" />
101                </param>
102                <!-- I'd like word_size to be optional, with minimum 2 for blastp -->
103                <param name="word_size" type="integer" value="0" label="Word size for wordfinder algorithm" help="Use zero for default, otherwise minimum 2.">
104                    <validator type="in_range" min="0" />
105                </param>
106                <!--
107                Can't use '-ungapped' on its own, error back is:
108                Composition-adjusted searched are not supported with an ungapped search, please add -comp_based_stats F or do a gapped search
109                Tried using '-ungapped -comp_based_stats F' and blastp crashed with 'Attempt to access NULL pointer.'
110                <param name="ungapped" type="boolean" label="Perform ungapped alignment only?" truevalue="-ungapped -comp_based_stats F" falsevalue="" checked="false" />
111                -->
112            </when>
113        </conditional>
114    </inputs>
115    <outputs>
116        <data name="output1" format="tabular" label="${blast_type.value_label} on ${db_opts.db_opts_selector}">
117            <change_format>
118                <when input="out_format" value="-outfmt 0" format="txt"/>
119                <when input="out_format" value="-outfmt 0 -html" format="html"/>
120                <when input="out_format" value="-outfmt 2" format="txt"/>
121                <when input="out_format" value="-outfmt 2 -html" format="html"/>
122                <when input="out_format" value="-outfmt 4" format="txt"/>
123                <when input="out_format" value="-outfmt 4 -html" format="html"/>
124                <when input="out_format" value="-outfmt 5" format="blastxml"/>
125            </change_format>
126        </data>
127    </outputs>
128    <requirements>
129        <requirement type="binary">blastn</requirement>
130    </requirements>
131    <tests>
132    </tests>
133    <help>
134   
135.. class:: warningmark
136
137**Note**. Database searches may take substantial amount of time.
138For large input datasets it is advisable to allow overnight processing. 
139
140-----
141
142**What it does**
143
144Search a *protein database* using a *protein query*,
145using the NCBI BLAST+ blastp command line tool.
146
147-----
148
149**Output format**
150
151Because Galaxy focuses on processing tabular data, the default output of this tool is tabular. This contains 12 columns:
152
1531. Id of your sequence
1542. GI of the database hit
1553. % identity
1564. Alignment length
1575. # mismatches
1586. # gaps
1597. Start position in your sequence
1608. End position in your sequence
1619. Start position in database hit
16210. End position in database hit
16311. E-value
16412. Bit score
165
166The second option is BLAST XML output, which is designed to be parsed by another program, and is understood by other Galaxy tools.
167
168You can also choose several plain text or HTML output formats which are designed to be read by a person (not by another program).
169The HTML versions use basic webpage formatting and can include links to the hits on the NCBI website.
170The pairwise output (the default on the NCBI BLAST website) shows each match as a pairwise alignment with the query.
171The two query anchored outputs show a multiple sequence alignment between the query and all the matches,
172and differ in how insertions are shown (marked as insertions or with gap characters added to the other sequences).
173
174-------
175
176**References**
177
178Altschul et al. Gapped BLAST and PSI-BLAST: a new generation of protein database search programs. 1997. Nucleic Acids Res. 25:3389-3402.
179
180Schaffer 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.
181
182    </help>
183</tool>
Note: リポジトリブラウザについてのヘルプは TracBrowser を参照してください。