annotate tools/ncbi_blast_plus/ncbi_makeblastdb.xml @ 9:9dabbfd73c8a draft

Uploaded v0.0.19, adds wrappers for rpsblast and rpstblastn with new blastdb_d.loc file for their protein domain database. Also includes other minor improvements.

<tool id="ncbi_makeblastdb" name="NCBI BLAST+ makeblastdb" version="0.0.4">
  <description>Make BLAST database</description>
    <requirements>
        <requirement type="binary">makeblastdb</requirement>
        <requirement type="package" version="2.2.26+">blast+</requirement>
    </requirements>
    <version_command>makeblastdb -version</version_command>
    <command>
makeblastdb -out "${os.path.join($outfile.extra_files_path,'blastdb')}"
$parse_seqids
$hash_index
## Single call to -in with multiple filenames space separated with outer quotes
## (presumably any filenames with spaces would be a problem). Note this gives
## some extra spaces, e.g. -in " file1 file2 file3  " but BLAST seems happy:
-in "
#for $i in $in
${i.file} #end for
"
#if $title:
-title "$title"
#else:
##Would default to being based on the cryptic Galaxy filenames, which is unhelpful
-title "BLAST Database"
#end if
-dbtype $dbtype 
## #set $sep = '-mask_data '
## #for $i in $mask_data
## $sep${i.file}
## #set $set = ', '
## #end for 
## #set $sep = '-gi_mask -gi_mask_name '
## #for $i in $gi_mask
## $sep${i.file}
## #set $set = ', '
## #end for 
## #if $tax.select == 'id':
## -taxid $tax.id
## #else if $tax.select == 'map':
## -taxid_map $tax.map
## #end if
</command>
<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>
<inputs>
    <param name="dbtype" type="select" display="radio" label="Molecule type of input">
        <option value="prot">protein</option>
        <option value="nucl">nucleotide</option>
    </param>
    <!-- TODO Allow merging of existing BLAST databases (conditional on the database type)
    <repeat name="in" title="Blast or Fasta Database" min="1">
        <param name="file" type="data" format="fasta,blastdbn,blastdbp" label="Blast or Fasta database" />
    </repeat>
    -->
    <repeat name="in" title="FASTA file" min="1">
        <param name="file" type="data" format="fasta" />
    </repeat>
    <param name="title" type="text" value="" label="Title for BLAST database" help="This is the database name shown in BLAST search output" />
    <param name="parse_seqids" type="boolean" truevalue="-parse_seqids" falsevalue="" checked="False" label="Parse the sequence identifiers" help="This is only advised if your FASTA file follows the NCBI naming conventions using pipe '|' symbols" />
    <param name="hash_index" type="boolean" truevalue="-hash_index" falsevalue="" checked="true" label="Enable the creation of sequence hash values." help="These hash values can then be used to quickly determine if a given sequence data exists in this BLAST database." />

    <!-- SEQUENCE MASKING OPTIONS -->
    <!-- TODO
    <repeat name="mask_data" title="Provide one or more files containing masking data">
        <param name="file" type="data" format="asnb" label="File containing masking data" help="As produced by NCBI masking applications (e.g. dustmasker, segmasker, windowmasker)" />
    </repeat>
    <repeat name="gi_mask" title="Create GI indexed masking data">
        <param name="file" type="data" format="asnb" label="Masking data output file" />
    </repeat>
    -->

    <!-- TAXONOMY OPTIONS -->
    <!-- TODO
    <conditional name="tax">
        <param name="select" type="select" label="Taxonomy options">
            <option value="">Do not assign sequences to Taxonomy IDs</option>
            <option value="id">Assign all sequences to one Taxonomy ID</option>
            <option value="map">Supply text file mapping sequence IDs to taxnomy IDs</option>
        </param>
        <when value="">
        </when>
        <when value="id">
            <param name="id" type="integer" value="" label="NCBI taxonomy ID" help="Integer &gt;=0" />
        </when>
        <when value="map">
            <param name="file" type="data" format="txt" label="Seq ID : Tax ID mapping file" help="Format: SequenceId TaxonomyId" />
        </when>
    </conditional>
    -->
</inputs>
<outputs>
    <!-- If we only accepted one FASTA file, we could use its human name here... -->
    <data name="outfile" format="data" label="${dbtype.value_label} BLAST database from ${on_string}">
        <change_format>
                <when input="dbtype" value="nucl" format="blastdbn"/>
                <when input="dbtype" value="prot" format="blastdbp"/>
        </change_format>
    </data>
</outputs>
<help>
**What it does**

Make BLAST database from one or more FASTA files and/or BLAST databases.

This is a wrapper for the NCBI BLAST+ tool 'makeblastdb', which is the
replacement for the 'formatdb' tool in the NCBI 'legacy' BLAST suite.

<!--
Applying masks to an existing BLAST database will not change the original database; a new database will be created.
For this reason, it's best to apply all masks at once to minimize the number of unnecessary intermediate databases.
-->

**Documentation**

http://www.ncbi.nlm.nih.gov/books/NBK1763/
</help>
</tool>