PageRenderTime 15ms CodeModel.GetById 10ms app.highlight 2ms RepoModel.GetById 1ms app.codeStats 0ms

/tools/ncbi_blast_plus/ncbi_tblastx_wrapper.xml

https://bitbucket.org/cistrome/cistrome-harvard/
XML | 206 lines | 183 code | 17 blank | 6 comment | 0 complexity | 4d81acf373551d8160a748dfe252f661 MD5 | raw file
  1<tool id="ncbi_tblastx_wrapper" name="NCBI BLAST+ tblastx" version="0.0.11">
  2    <description>Search translated nucleotide database with translated nucleotide query sequence(s)</description>
  3    <version_command>tblastx -version</version_command>
  4    <command interpreter="python">hide_stderr.py
  5## The command is a Cheetah template which allows some Python based syntax.
  6## Lines starting hash hash are comments. Galaxy will turn newlines into spaces
  7tblastx
  8-query "$query"
  9#if $db_opts.db_opts_selector == "db":
 10  -db "${db_opts.database.fields.path}"
 11#else:
 12  -subject "$db_opts.subject"
 13#end if
 14-evalue $evalue_cutoff
 15-out $output1
 16##Set the extended list here so if/when we add things, saved workflows are not affected
 17#if str($out_format)=="ext":
 18    -outfmt "6 std sallseqid score nident positive gaps ppos qframe sframe qseq sseq qlen slen"
 19#else:
 20    -outfmt $out_format
 21#end if
 22-num_threads 8
 23#if $adv_opts.adv_opts_selector=="advanced":
 24$adv_opts.filter_query
 25$adv_opts.strand
 26-matrix $adv_opts.matrix
 27## Need int(str(...)) because $adv_opts.max_hits is an InputValueWrapper object not a string
 28## Note -max_target_seqs overrides -num_descriptions and -num_alignments
 29#if (str($adv_opts.max_hits) and int(str($adv_opts.max_hits)) > 0):
 30-max_target_seqs $adv_opts.max_hits
 31#end if
 32#if (str($adv_opts.word_size) and int(str($adv_opts.word_size)) > 0):
 33-word_size $adv_opts.word_size
 34#end if
 35$adv_opts.parse_deflines
 36## End of advanced options:
 37#end if
 38    </command>
 39    <inputs>
 40        <param name="query" type="data" format="fasta" label="Nucleotide query sequence(s)"/> 
 41        <conditional name="db_opts">
 42            <param name="db_opts_selector" type="select" label="Subject database/sequences">
 43              <option value="db" selected="True">BLAST Database</option>
 44              <option value="file">FASTA file</option>
 45            </param>
 46            <when value="db">
 47                <param name="database" type="select" label="Nucleotide BLAST database">
 48                    <options from_file="blastdb.loc">
 49                      <column name="value" index="0"/>
 50                      <column name="name" index="1"/>
 51                      <column name="path" index="2"/>
 52                    </options>
 53                </param>
 54                <param name="subject" type="hidden" value="" /> 
 55            </when>
 56            <when value="file">
 57                <param name="database" type="hidden" value="" /> 
 58                <param name="subject" type="data" format="fasta" label="Nucleotide FASTA file to use as database"/> 
 59            </when>
 60        </conditional>
 61        <param name="evalue_cutoff" type="float" size="15" value="0.001" label="Set expectation value cutoff" />
 62        <param name="out_format" type="select" label="Output format">
 63            <option value="6" selected="True">Tabular (standard 12 columns)</option>
 64            <option value="ext">Tabular (extended 24 columns)</option>
 65            <option value="5">BLAST XML</option>
 66            <option value="0">Pairwise text</option>
 67            <option value="0 -html">Pairwise HTML</option>
 68            <option value="2">Query-anchored text</option>
 69            <option value="2 -html">Query-anchored HTML</option>
 70            <option value="4">Flat query-anchored text</option>
 71            <option value="4 -html">Flat query-anchored HTML</option>
 72            <!--
 73            <option value="-outfmt 11">BLAST archive format (ASN.1)</option>
 74            -->
 75        </param>
 76        <conditional name="adv_opts">
 77            <param name="adv_opts_selector" type="select" label="Advanced Options">
 78              <option value="basic" selected="True">Hide Advanced Options</option>
 79              <option value="advanced">Show Advanced Options</option>
 80            </param>
 81            <when value="basic" />
 82            <when value="advanced">
 83                <!-- Could use a select (yes, no, other) where other allows setting 'window locut hicut' -->
 84                <param name="filter_query" type="boolean" label="Filter out low complexity regions (with SEG)" truevalue="-seg yes" falsevalue="-seg no" checked="true" />
 85                <param name="strand" type="select" label="Query strand(s) to search against database/subject">
 86                    <option value="-strand both">Both</option>
 87                    <option value="-strand plus">Plus (forward)</option>
 88                    <option value="-strand minus">Minus (reverse complement)</option>
 89                </param>
 90                <param name="matrix" type="select" label="Scoring matrix">
 91                    <option value="BLOSUM90">BLOSUM90</option>
 92                    <option value="BLOSUM80">BLOSUM80</option>
 93                    <option value="BLOSUM62" selected="true">BLOSUM62 (default)</option>
 94                    <option value="BLOSUM50">BLOSUM50</option> 
 95                    <option value="BLOSUM45">BLOSUM45</option>
 96                    <option value="PAM250">PAM250</option>
 97                    <option value="PAM70">PAM70</option>
 98                    <option value="PAM30">PAM30</option>
 99                </param>
100                <!-- Why doesn't optional override a validator? I want to accept an empty string OR a non-negative integer -->
101                <param name="max_hits" type="integer" value="0" label="Maximum hits to show" help="Use zero for default limits">
102                    <validator type="in_range" min="0" />
103                </param>
104                <!-- I'd like word_size to be optional, with minimum 2 for tblastx -->
105                <param name="word_size" type="integer" value="0" label="Word size for wordfinder algorithm" help="Use zero for default, otherwise minimum 2.">
106                    <validator type="in_range" min="0" />
107                </param>
108                <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"/>
109            </when>
110        </conditional>
111    </inputs>
112    <outputs>
113        <data name="output1" format="tabular" label="tblastx on ${db_opts.db_opts_selector}">
114            <change_format>
115                <when input="out_format" value="0" format="txt"/>
116                <when input="out_format" value="0 -html" format="html"/>
117                <when input="out_format" value="2" format="txt"/>
118                <when input="out_format" value="2 -html" format="html"/>
119                <when input="out_format" value="4" format="txt"/>
120                <when input="out_format" value="4 -html" format="html"/>
121                <when input="out_format" value="5" format="blastxml"/>
122            </change_format>
123        </data>
124    </outputs>
125    <requirements>
126        <requirement type="binary">tblastx</requirement>
127    </requirements>
128    <help>
129    
130.. class:: warningmark
131
132**Note**. Database searches may take a substantial amount of time.
133For large input datasets it is advisable to allow overnight processing.  
134
135-----
136
137**What it does**
138
139Search a *translated nucleotide database* using a *protein query*,
140using the NCBI BLAST+ tblastx command line tool.
141
142-----
143
144**Output format**
145
146Because Galaxy focuses on processing tabular data, the default output of this
147tool is tabular. The standard BLAST+ tabular output contains 12 columns:
148
149====== ========= ============================================
150Column NCBI name Description
151------ --------- --------------------------------------------
152     1 qseqid    Query Seq-id (ID of your sequence)
153     2 sseqid    Subject Seq-id (ID of the database hit)
154     3 pident    Percentage of identical matches
155     4 length    Alignment length
156     5 mismatch  Number of mismatches
157     6 gapopen   Number of gap openings
158     7 qstart    Start of alignment in query
159     8 qend      End of alignment in query
160     9 sstart    Start of alignment in subject (database hit)
161    10 send      End of alignment in subject (database hit)
162    11 evalue    Expectation value (E-value)
163    12 bitscore  Bit score
164====== ========= ============================================
165
166The BLAST+ tools can optionally output additional columns of information,
167but this takes longer to calculate. Most (but not all) of these columns are
168included by selecting the extended tabular output. The extra columns are
169included *after* the standard 12 columns. This is so that you can write
170workflow filtering steps that accept either the 12 or 24 column tabular
171BLAST output.
172
173====== ============= ===========================================
174Column NCBI name     Description
175------ ------------- -------------------------------------------
176    13 sallseqid     All subject Seq-id(s), separated by a ';'
177    14 score         Raw score
178    15 nident        Number of identical matches
179    16 positive      Number of positive-scoring matches
180    17 gaps          Total number of gaps
181    18 ppos          Percentage of positive-scoring matches
182    19 qframe        Query frame
183    20 sframe        Subject frame
184    21 qseq          Aligned part of query sequence
185    22 sseq          Aligned part of subject sequence
186    23 qlen          Query sequence length
187    24 slen          Subject sequence length
188====== ============= ===========================================
189
190The third option is BLAST XML output, which is designed to be parsed by
191another program, and is understood by some Galaxy tools.
192
193You can also choose several plain text or HTML output formats which are designed to be read by a person (not by another program).
194The HTML versions use basic webpage formatting and can include links to the hits on the NCBI website.
195The pairwise output (the default on the NCBI BLAST website) shows each match as a pairwise alignment with the query.
196The two query anchored outputs show a multiple sequence alignment between the query and all the matches,
197and differ in how insertions are shown (marked as insertions or with gap characters added to the other sequences).
198
199-------
200
201**References**
202
203Altschul et al. Gapped BLAST and PSI-BLAST: a new generation of protein database search programs. 1997. Nucleic Acids Res. 25:3389-3402.
204
205    </help>
206</tool>