annotate tools/ncbi_blast_plus/ncbi_macros.xml @ 11:4c4a0da938ff draft

Uploaded v0.0.22, now wraps BLAST+ 2.2.28 allowing extended tabular output to include the hit descriptions as column 25. Supports $GALAXY_SLOTS. Includes more tests and heavy use of macros.

<macros>
    <xml name="output_change_format">
        <change_format>
            <when input="out_format" value="0" format="txt"/>
            <when input="out_format" value="0 -html" format="html"/>
            <when input="out_format" value="2" format="txt"/>
            <when input="out_format" value="2 -html" format="html"/>
            <when input="out_format" value="4" format="txt"/>
            <when input="out_format" value="4 -html" format="html"/>
            <when input="out_format" value="5" format="blastxml"/>
        </change_format>
    </xml>
    <xml name="input_out_format">
        <param name="out_format" type="select" label="Output format">
            <option value="6">Tabular (standard 12 columns)</option>
            <option value="ext" selected="True">Tabular (extended 25 columns)</option>
            <option value="5">BLAST XML</option>
            <option value="0">Pairwise text</option>
            <option value="0 -html">Pairwise HTML</option>
            <option value="2">Query-anchored text</option>
            <option value="2 -html">Query-anchored HTML</option>
            <option value="4">Flat query-anchored text</option>
            <option value="4 -html">Flat query-anchored HTML</option>
            <!--
            <option value="-outfmt 11">BLAST archive format (ASN.1)</option>
            -->
        </param>
    </xml>
    <xml name="input_scoring_matrix">
        <param name="matrix" type="select" label="Scoring matrix">
            <option value="BLOSUM90">BLOSUM90</option>
            <option value="BLOSUM80">BLOSUM80</option>
            <option value="BLOSUM62" selected="true">BLOSUM62 (default)</option>
            <option value="BLOSUM50">BLOSUM50</option> 
            <option value="BLOSUM45">BLOSUM45</option>
            <option value="PAM250">PAM250</option>
            <option value="PAM70">PAM70</option>
            <option value="PAM30">PAM30</option>
        </param>
    </xml>
    <xml name="stdio">
        <stdio>
            <!-- Anything other than zero is an error -->
            <exit_code range="1:" />
            <exit_code range=":-1" />
            <!-- In case the return code has not been set propery check stderr too -->
            <regex match="Error:" />
            <regex match="Exception:" />
        </stdio>
    </xml>
    <xml name="input_query_gencode">
        <param name="query_gencode" type="select" label="Query genetic code">
            <!-- See http://www.ncbi.nlm.nih.gov/Taxonomy/Utils/wprintgc.cgi for details -->
            <option value="1" select="True">1. Standard</option>
            <option value="2">2. Vertebrate Mitochondrial</option>
            <option value="3">3. Yeast Mitochondrial</option>
            <option value="4">4. Mold, Protozoan, and Coelenterate Mitochondrial Code and the Mycoplasma/Spiroplasma Code</option>
            <option value="5">5. Invertebrate Mitochondrial</option>
            <option value="6">6. Ciliate, Dasycladacean and Hexamita Nuclear Code</option>
            <option value="9">9. Echinoderm Mitochondrial</option>
            <option value="10">10. Euplotid Nuclear</option>
            <option value="11">11. Bacteria and Archaea</option>
            <option value="12">12. Alternative Yeast Nuclear</option>
            <option value="13">13. Ascidian Mitochondrial</option>
            <option value="14">14. Flatworm Mitochondrial</option>
            <option value="15">15. Blepharisma Macronuclear</option>
            <option value="16">16. Chlorophycean Mitochondrial Code</option>
            <option value="21">21. Trematode Mitochondrial Code</option>
            <option value="22">22. Scenedesmus obliquus mitochondrial Code</option>
            <option value="23">23. Thraustochytrium Mitochondrial Code</option>
            <option value="24">24. Pterobranchia mitochondrial code</option>
        </param>
    </xml>
    <xml name="input_db_gencode">
        <param name="db_gencode" type="select" label="Database/subject genetic code">
            <!-- See http://www.ncbi.nlm.nih.gov/Taxonomy/Utils/wprintgc.cgi for details -->
            <option value="1" select="True">1. Standard</option>
            <option value="2">2. Vertebrate Mitochondrial</option>
            <option value="3">3. Yeast Mitochondrial</option>
            <option value="4">4. Mold, Protozoan, and Coelenterate Mitochondrial Code and the Mycoplasma/Spiroplasma Code</option>
            <option value="5">5. Invertebrate Mitochondrial</option>
            <option value="6">6. Ciliate, Dasycladacean and Hexamita Nuclear Code</option>
            <option value="9">9. Echinoderm Mitochondrial</option>
            <option value="10">10. Euplotid Nuclear</option>
            <option value="11">11. Bacteria and Archaea</option>
            <option value="12">12. Alternative Yeast Nuclear</option>
            <option value="13">13. Ascidian Mitochondrial</option>
            <option value="14">14. Flatworm Mitochondrial</option>
            <option value="15">15. Blepharisma Macronuclear</option>
            <option value="16">16. Chlorophycean Mitochondrial Code</option>
            <option value="21">21. Trematode Mitochondrial Code</option>
            <option value="22">22. Scenedesmus obliquus mitochondrial Code</option>
            <option value="23">23. Thraustochytrium Mitochondrial Code</option>
            <option value="24">24. Pterobranchia mitochondrial code</option>
        </param>
    </xml>
    <xml name="input_conditional_nucleotide_db">
        <conditional name="db_opts">
            <param name="db_opts_selector" type="select" label="Subject database/sequences">
              <option value="db" selected="True">Locally installed BLAST database</option>
              <option value="histdb">BLAST database from your history</option>
              <option value="file">FASTA file from your history (see warning note below)</option>
            </param>
            <when value="db">
                <param name="database" type="select" label="Nucleotide BLAST database">
                    <options from_file="blastdb.loc">
                      <column name="value" index="0"/>
                      <column name="name" index="1"/>
                      <column name="path" index="2"/>
                    </options>
                </param>
                <param name="histdb" type="hidden" value="" />
                <param name="subject" type="hidden" value="" /> 
            </when>
            <when value="histdb">
                <param name="database" type="hidden" value="" />
                <param name="histdb" type="data" format="blastdbn" label="Nucleotide BLAST database" />
                <param name="subject" type="hidden" value="" />
            </when>
            <when value="file">
                <param name="database" type="hidden" value="" />
                <param name="histdb" type="hidden" value="" />
                <param name="subject" type="data" format="fasta" label="Nucleotide FASTA file to use as database"/> 
            </when>
        </conditional>
    </xml>
    <xml name="input_conditional_protein_db">
        <conditional name="db_opts">
            <param name="db_opts_selector" type="select" label="Subject database/sequences">
              <option value="db" selected="True">Locally installed BLAST database</option>
              <option value="histdb">BLAST database from your history</option>
              <option value="file">FASTA file from your history (see warning note below)</option>
            </param>
            <when value="db">
                <param name="database" type="select" label="Protein BLAST database">
                    <options from_file="blastdb_p.loc">
                      <column name="value" index="0"/>
                      <column name="name" index="1"/>
                      <column name="path" index="2"/>
                    </options>
                </param>
                <param name="histdb" type="hidden" value="" />
                <param name="subject" type="hidden" value="" />
            </when>
            <when value="histdb">
                <param name="database" type="hidden" value="" />
                <param name="histdb" type="data" format="blastdbp" label="Protein BLAST database" />
                <param name="subject" type="hidden" value="" />
            </when>
            <when value="file">
                <param name="database" type="hidden" value="" />
                <param name="histdb" type="hidden" value="" />
                <param name="subject" type="data" format="fasta" label="Protein FASTA file to use as database"/> 
            </when>
        </conditional>
    </xml>
    <xml name="input_conditional_pssm">
        <conditional name="db_opts">
            <param name="db_opts_selector" type="select" label="Protein domain database (PSSM)">
              <option value="db" selected="True">Locally installed BLAST database</option>
              <!-- TODO - define new datatype
              <option value="histdb">BLAST protein domain database from your history</option>
              -->
            </param>
            <when value="db">
                <param name="database" type="select" label="Protein domain database">
                    <options from_file="blastdb_d.loc">
                      <column name="value" index="0"/>
                      <column name="name" index="1"/>
                      <column name="path" index="2"/>
                    </options>
                </param>
                <param name="histdb" type="hidden" value="" />
                <param name="subject" type="hidden" value="" />
            </when>
            <!-- TODO - define new datatype
            <when value="histdb">
                <param name="database" type="hidden" value="" />
                <param name="histdb" type="data" format="blastdbd" label="Protein domain database" />
                <param name="subject" type="hidden" value="" />
            </when>
            -->
        </conditional>
    </xml>
    <xml name="input_conditional_choose_db_type">
        <conditional name="db_opts">
            <param name="db_type" type="select" label="Type of BLAST database">
              <option value="nucl" selected="True">Nucleotide</option>
              <option value="prot">Protein</option>
            </param>
            <when value="nucl">
                <param name="database" type="select" label="Nucleotide BLAST database">
                    <options from_file="blastdb.loc">
                      <column name="value" index="0"/>
                      <column name="name" index="1"/>
                      <column name="path" index="2"/>
                    </options>
                </param>
            </when>
            <when value="prot">
                <param name="database" type="select" label="Protein BLAST database">
                    <options from_file="blastdb_p.loc">
                      <column name="value" index="0"/>
                      <column name="name" index="1"/>
                      <column name="path" index="2"/>
                    </options>
                </param>
            </when>
        </conditional>
    </xml>
    <xml name="input_parse_deflines">
        <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"/>
    </xml>
    <xml name="input_filter_query_default_false">
        <param name="filter_query" type="boolean" label="Filter out low complexity regions (with SEG)" truevalue="-seg yes" falsevalue="-seg no" checked="false" />
    </xml>
    <xml name="input_filter_query_default_true">
        <param name="filter_query" type="boolean" label="Filter out low complexity regions (with SEG)" truevalue="-seg yes" falsevalue="-seg no" checked="true" />
    </xml>
    <xml name="input_max_hits">
        <param name="max_hits" type="integer" value="0" label="Maximum hits to show" help="Use zero for default limits">
            <validator type="in_range" min="0" />
        </param>        
    </xml>
    <xml name="input_evalue">
        <param name="evalue_cutoff" type="float" size="15" value="0.001" label="Set expectation value cutoff" />
    </xml>
    <xml name="input_word_size">
        <param name="word_size" type="integer" value="0" label="Word size for wordfinder algorithm" help="Use zero for default, otherwise minimum 2.">
            <validator type="in_range" min="0" />
        </param>        
    </xml>
    <xml name="input_strand">
        <param name="strand" type="select" label="Query strand(s) to search against database/subject">
            <option value="-strand both">Both</option>
            <option value="-strand plus">Plus (forward)</option>
            <option value="-strand minus">Minus (reverse complement)</option>
        </param>
    </xml>
    <xml name="requirements">
        <requirements>
            <requirement type="binary">@BINARY@</requirement>
            <requirement type="package" version="2.2.28">blast+</requirement>
        </requirements>
        <version_command>@BINARY@ -version</version_command>
    </xml>
    <xml name="advanced_options">
        <conditional name="adv_opts">
            <param name="adv_opts_selector" type="select" label="Advanced Options">
              <option value="basic" selected="True">Hide Advanced Options</option>
              <option value="advanced">Show Advanced Options</option>
            </param>
            <when value="basic" />
            <when value="advanced">
                <yield />
            </when>
        </conditional>        
    </xml>
    <token name="@THREADS@">-num_threads "\${GALAXY_SLOTS:-8}"</token>
    <token name="@BLAST_DB_SUBJECT@">
#if $db_opts.db_opts_selector == "db":
  -db "${db_opts.database.fields.path}"
#elif $db_opts.db_opts_selector == "histdb":
  -db "${os.path.join($db_opts.histdb.extra_files_path,'blastdb')}"
#else:
  -subject "$db_opts.subject"
#end if
    </token>
    <token name="@BLAST_OUTPUT@">-out "$output1"
##Set the extended list here so when we add things, saved workflows are not affected
#if str($out_format)=="ext":
    -outfmt "6 std sallseqid score nident positive gaps ppos qframe sframe qseq sseq qlen slen salltitles"
#else:
    -outfmt $out_format
#end if
    </token>
    <token name="@ADVANCED_OPTIONS@">$adv_opts.filter_query
## Need int(str(...)) because $adv_opts.max_hits is an InputValueWrapper object not a string
## Note -max_target_seqs overrides -num_descriptions and -num_alignments
#if (str($adv_opts.max_hits) and int(str($adv_opts.max_hits)) > 0):
-max_target_seqs $adv_opts.max_hits
#end if
#if (str($adv_opts.word_size) and int(str($adv_opts.word_size)) > 0):
-word_size $adv_opts.word_size
#end if
$adv_opts.parse_deflines
    </token>
    <!-- @ON_DB_SUBJECT@ is for use with @BLAST_DB_SUBJECT@ -->
    <token name="@ON_DB_SUBJECT@">#if str($db_opts.db_opts_selector)=='db'
${db_opts.database}
#elif str($db_opts.db_opts_selector)=='histdb'
${db_opts.histdb.name}
#else
${db_opts.subject.name}
#end if</token>
    <token name="@REFERENCES@">
Peter J.A. Cock, Björn A. Grüning, Konrad Paszkiewicz and Leighton Pritchard (2013).
Galaxy tools and workflows for sequence analysis with applications
in molecular plant pathology. PeerJ 1:e167
http://dx.doi.org/10.7717/peerj.167

Christiam Camacho et al. (2009).
BLAST+: architecture and applications.
BMC Bioinformatics. 15;10:421.
http://dx.doi.org/10.1186/1471-2105-10-421

This wrapper is available to install into other Galaxy Instances via the Galaxy
Tool Shed at http://toolshed.g2.bx.psu.edu/view/devteam/ncbi_blast_plus
    </token>
    <token name="@OUTPUT_FORMAT@">**Output format**

Because Galaxy focuses on processing tabular data, the default output of this
tool is tabular. The standard BLAST+ tabular output contains 12 columns:

====== ========= ============================================
Column NCBI name Description
------ --------- --------------------------------------------
     1 qseqid    Query Seq-id (ID of your sequence)
     2 sseqid    Subject Seq-id (ID of the database hit)
     3 pident    Percentage of identical matches
     4 length    Alignment length
     5 mismatch  Number of mismatches
     6 gapopen   Number of gap openings
     7 qstart    Start of alignment in query
     8 qend      End of alignment in query
     9 sstart    Start of alignment in subject (database hit)
    10 send      End of alignment in subject (database hit)
    11 evalue    Expectation value (E-value)
    12 bitscore  Bit score
====== ========= ============================================

The BLAST+ tools can optionally output additional columns of information,
but this takes longer to calculate. Most (but not all) of these columns are
included by selecting the extended tabular output. The extra columns are
included *after* the standard 12 columns. This is so that you can write
workflow filtering steps that accept either the 12 or 25 column tabular
BLAST output. Galaxy now uses this extended 25 column output by default.

====== ============= ===========================================
Column NCBI name     Description
------ ------------- -------------------------------------------
    13 sallseqid     All subject Seq-id(s), separated by ';'
    14 score         Raw score
    15 nident        Number of identical matches
    16 positive      Number of positive-scoring matches
    17 gaps          Total number of gaps
    18 ppos          Percentage of positive-scoring matches
    19 qframe        Query frame
    20 sframe        Subject frame
    21 qseq          Aligned part of query sequence
    22 sseq          Aligned part of subject sequence
    23 qlen          Query sequence length
    24 slen          Subject sequence length
    25 salltitles    All subject title(s), separated by '&lt;&gt;'
====== ============= ===========================================

The third option is BLAST XML output, which is designed to be parsed by
another program, and is understood by some Galaxy tools.

You can also choose several plain text or HTML output formats which are designed to be read by a person (not by another program).
The HTML versions use basic webpage formatting and can include links to the hits on the NCBI website.
The pairwise output (the default on the NCBI BLAST website) shows each match as a pairwise alignment with the query.
The two query anchored outputs show a multiple sequence alignment between the query and all the matches,
and differ in how insertions are shown (marked as insertions or with gap characters added to the other sequences).
    </token>
    <token name="@FASTA_WARNING@">.. class:: warningmark

You can also search against a FASTA file of subject (target)
sequences. This is *not* advised because it is slower (only one
CPU is used), but more importantly gives e-values for pairwise
searches (very small e-values which will look overly signficiant).
In most cases you should instead turn the other FASTA file into a
database first using *makeblastdb* and search against that.
    </token>
    <token name="@SEARCH_TIME_WARNING@">.. class:: warningmark

**Note**. Database searches may take a substantial amount of time.
For large input datasets it is advisable to allow overnight processing.  

-----
    </token>
</macros>