comparison tools/ncbi_blast_plus/ncbi_makeblastdb.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.

10:70e7dcbf6573

<tool id="ncbi_makeblastdb" name="NCBI BLAST+ makeblastdb" version="0.0.5">
    <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

#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

                <when input="dbtype" value="prot" format="blastdbp" />
            </change_format>
        </data>
    </outputs>
    <tests>
    </tests>
    <help>
**What it does**

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

**References**

If you use this Galaxy tool in work leading to a scientific publication please
cite the following papers:

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
    </help>
</tool>

11:4c4a0da938ff

<tool id="ncbi_makeblastdb" name="NCBI BLAST+ makeblastdb" version="0.0.22">
    <description>Make BLAST database</description>
    <macros>
        <token name="@BINARY@">makeblastdb</token>
        <import>ncbi_macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <command interpreter="python">check_no_duplicates.py
##First check for duplicates (since BLAST+ 2.2.28 fails to do so)
##and abort (via the ampersand ampersand trick) if any are found.
#for $i in $in
"${i.file}"
#end for
&amp;&amp;
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

#else:
##Would default to being based on the cryptic Galaxy filenames, which is unhelpful
-title "BLAST Database"
#end if
-dbtype $dbtype 
#set $mask_string = ''
#set $sep = '-mask_data '
#for $i in $mask_data
#set $mask_string += $sep + str($i.file)
#set $sep = ','
#end for
$mask_string
## #set $gi_mask_string = ''
## #set $sep = '-gi_mask -gi_mask_name '
## #for $i in $gi_mask
## #set $gi_mask_string += $sep + str($i.file)
## #set $sep = ','
## #end for
## $gi_mask_string
## #if $tax.select == 'id':
## -taxid $tax.id
## #else if $tax.select == 'map':
## -taxid_map $tax.map
## #end if
## --------------------------------------------------------------------
## Capture the stdout log information to the primary file (plain text):
>> "$outfile"
    </command>
    <expand macro="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)
             NOTE Double check the new database would be self contained first
        <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>
        -->
        <!-- TODO Switch this to using <param ... multiple="true" /> instead of <repeat> block? -->
        <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 -->
        <repeat name="mask_data" title="Masking data file">
            <param name="mask_data_file" type="data" format="maskinfo-asn1,maskinfo-asn1-binary" label="ASN.1 file containing masking data" help="As produced by NCBI masking applications (e.g. dustmasker, segmasker, windowmasker)" />
        </repeat>
        <!-- TODO
        <repeat name="gi_mask" title="Create GI indexed masking data">
            <param name="gi_mask_file" type="data" format="asnb" label="Masking data output file" />
        </repeat>
        -->

        <!-- TAXONOMY OPTIONS -->
        <!-- TODO

                <when input="dbtype" value="prot" format="blastdbp" />
            </change_format>
        </data>
    </outputs>
    <tests>
        <!-- Note the (two line) PIN file is not reproducible run to run.
        -->
        <test>
            <param name="dbtype" value="prot" />
            <param name="file" value="four_human_proteins.fasta" ftype="fasta" />
            <param name="title" value="Just 4 human proteins" />
            <param name="parse_seqids" value="" />
            <param name="hash_index" value="true" />
            <output name="out_file" file="four_human_proteins.fasta.log" ftype="blastdbp" lines_diff="6">
                <extra_files type="file" value="four_human_proteins.fasta.phr" name="blastdb.phr" />
                <extra_files type="file" value="four_human_proteins.fasta.pin" name="blastdb.pin" lines_diff="2" />
                <extra_files type="file" value="four_human_proteins.fasta.psq" name="blastdb.psq" />
                <extra_files type="file" value="four_human_proteins.fasta.pog" name="blastdb.pog" />
                <extra_files type="file" value="four_human_proteins.fasta.phd" name="blastdb.phd" />
                <extra_files type="file" value="four_human_proteins.fasta.phi" name="blastdb.phi" />
                <extra_files type="file" value="four_human_proteins.fasta.psd" name="blastdb.psd" />
                <extra_files type="file" value="four_human_proteins.fasta.psi" name="blastdb.psi" />
            </output>
        </test>
    </tests>
    <help>
**What it does**

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

**References**

If you use this Galaxy tool in work leading to a scientific publication please
cite the following papers:

@REFERENCES@
    </help>
</tool>