annotate tools/ncbi_blast_plus/ncbi_blastx_wrapper.xml @ 13:623f727cdff1 draft

Uploaded v0.1.00, uses BLAST+ 2.2.29, allows custom column selection for tabular output - including taxonomy fields.

<tool id="ncbi_blastx_wrapper" name="NCBI BLAST+ blastx" version="0.1.00">
    <description>Search protein database with translated nucleotide query sequence(s)</description>
    <!-- If job splitting is enabled, break up the query file into parts -->
    <parallelism method="multi" split_inputs="query" split_mode="to_size" split_size="1000" merge_outputs="output1"></parallelism>
    <macros>
        <token name="@BINARY@">blastx</token>
        <import>ncbi_macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <command>
## The command is a Cheetah template which allows some Python based syntax.
## Lines starting hash hash are comments. Galaxy will turn newlines into spaces
blastx
-query "$query"
@BLAST_DB_SUBJECT@
-query_gencode $query_gencode
-evalue $evalue_cutoff
@BLAST_OUTPUT@
@THREADS@
#if $adv_opts.adv_opts_selector=="advanced":
$adv_opts.strand
-matrix $adv_opts.matrix
@ADVANCED_OPTIONS@
$adv_opts.ungapped
## End of advanced options:
#end if
    </command>

    <expand macro="stdio" />

    <inputs>
        <param name="query" type="data" format="fasta" label="Nucleotide query sequence(s)"/> 

        <expand macro="input_conditional_protein_db" />
        <expand macro="input_query_gencode" />
        <expand macro="input_evalue" />

        <expand macro="input_out_format" />
        <expand macro="advanced_options">
            <!-- Could use a select (yes, no, other) where other allows setting 'window locut hicut' -->
            <expand macro="input_filter_query_default_true" />
            <expand macro="input_strand" />
            <expand macro="input_scoring_matrix" />
            <expand macro="input_max_hits" />
            <expand macro="input_word_size" />
            <param name="ungapped" type="boolean" label="Perform ungapped alignment only?" truevalue="-ungapped" falsevalue="" checked="false" />
            <expand macro="input_parse_deflines" />
        </expand>
    </inputs>
    <outputs>
        <data name="output1" format="tabular" label="blastx $query.name vs @ON_DB_SUBJECT@">
            <expand macro="output_change_format" />
        </data>
    </outputs>
    <tests>
        <test>
            <param name="query" value="rhodopsin_nucs.fasta" ftype="fasta" />
            <param name="db_opts_selector" value="file" />
            <param name="subject" value="four_human_proteins.fasta" ftype="fasta" />
            <param name="database" value="" />
            <param name="evalue_cutoff" value="1e-10" />
            <param name="out_format" value="5" />
            <param name="adv_opts_selector" value="basic" />
            <output name="output1" file="blastx_rhodopsin_vs_four_human.xml" ftype="blastxml" />
        </test>
        <test>
            <param name="query" value="rhodopsin_nucs.fasta" ftype="fasta" />
            <param name="db_opts_selector" value="file" />
            <param name="subject" value="four_human_proteins.fasta" ftype="fasta" />
            <param name="database" value="" />
            <param name="evalue_cutoff" value="1e-10" />
            <param name="out_format" value="6" />
            <param name="adv_opts_selector" value="basic" />
            <output name="output1" file="blastx_rhodopsin_vs_four_human.tabular" ftype="tabular" />
        </test>
        <test>
            <param name="query" value="rhodopsin_nucs.fasta" ftype="fasta" />
            <param name="db_opts_selector" value="file" />
            <param name="subject" value="four_human_proteins.fasta" ftype="fasta" />
            <param name="database" value="" />
            <param name="evalue_cutoff" value="1e-10" />
            <param name="out_format" value="ext" />
            <param name="adv_opts_selector" value="basic" />
            <output name="output1" file="blastx_rhodopsin_vs_four_human_ext.tabular" ftype="tabular" />
        </test>
        <test>
            <param name="query" value="rhodopsin_nucs.fasta" ftype="fasta" />
            <param name="db_opts_selector" value="file" />
            <param name="subject" value="four_human_proteins.fasta" ftype="fasta" />
            <param name="database" value="" />
            <param name="evalue_cutoff" value="1e-10" />
            <param name="out_format" value="cols" />
            <param name="std_cols" value="qseqid,sseqid,pident,length,mismatch,gapopen,qstart,qend,sstart,send,evalue,bitscore" />
            <param name="ext_cols" value="sallseqid,score,nident,positive,gaps,ppos,qframe,sframe,qseq,sseq,qlen,slen,salltitles" />
            <param name="ids_cols" value="qgi,qacc,qaccver,sallseqid,sgi,sallgi,sacc,saccver,sallacc,stitle" />
            <param name="misc_cols" value="sstrand,frames,btop,qcovs,qcovhsp" />
            <param name="tax_cols" value="staxids,sscinames,scomnames,sblastnames,sskingdoms" />
            <param name="adv_opts_selector" value="basic" />
            <output name="output1" file="blastx_rhodopsin_vs_four_human_all.tabular" ftype="tabular" />
        </test>
    </tests>
    <help>
    
@SEARCH_TIME_WARNING@

**What it does**

Search a *protein database* using a *translated nucleotide query*,
using the NCBI BLAST+ blastx command line tool.

@FASTA_WARNING@

-----

@OUTPUT_FORMAT@

-------

**References**

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

@REFERENCES@
    </help>
</tool>