annotate tools/ncbi_blast_plus/ncbi_rpstblastn_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_rpstblastn_wrapper" name="NCBI BLAST+ rpstblastn" version="0.1.00">
    <description>Search protein domain database (PSSMs) 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@">rpstblastn</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
rpstblastn
-query "$query"
#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')}"
#end if
-evalue $evalue_cutoff
@BLAST_OUTPUT@
## rpstblastn does not support multiple threads up to release 2.2.27+. Added in BLAST 2.2.28+.
##-num_threads 8
#if $adv_opts.adv_opts_selector=="advanced":
@ADVANCED_OPTIONS@
## 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_pssm" />

        <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_false" />
            <!-- Why doesn't optional override a validator? I want to accept an empty string OR a non-negative integer -->
            <expand macro="input_max_hits" />
            <expand macro="input_word_size" />
            <expand macro="input_parse_deflines" />
        </expand>
    </inputs>
    <outputs>
        <data name="output1" format="tabular" label="rpstblastn on ${on_string}">
            <expand macro="output_change_format" />
        </data>
    </outputs>
    <help>
    
@SEARCH_TIME_WARNING@

**What it does**

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

The protein domain databases use position-specific scoring matrices
(PSSMs) and are available for a number of domain collections including:

*CDD* - NCBI curarated meta-collection of domains, see
http://www.ncbi.nlm.nih.gov/Structure/cdd/cdd_help.shtml#NCBI_curated_domains

*Kog* - PSSMs from automatically aligned sequences and sequence
fragments classified in the KOGs resource, the eukaryotic 
counterpart to COGs, see http://www.ncbi.nlm.nih.gov/COG/new/

*Cog* - PSSMs from automatically aligned sequences and sequence
fragments classified in the COGs resource, which focuses primarily
on prokaryotes, see http://www.ncbi.nlm.nih.gov/COG/new/

*Pfam* - PSSMs from Pfam-A seed alignment database, see
http://pfam.sanger.ac.uk/

*Smart* - PSSMs from SMART domain alignment database, see
http://smart.embl-heidelberg.de/

*Tigr* - PSSMs from TIGRFAM database of protein families, see
http://www.jcvi.org/cms/research/projects/tigrfams/overview/

*Prk* - PSSms from automatically aligned stable clusters in the
Protein Clusters database, see
http://www.ncbi.nlm.nih.gov/proteinclusters?cmd=search&amp;db=proteinclusters

The exact list of domain databases offered will depend on how your
local Galaxy has been configured.

-----

@OUTPUT_FORMAT@

-------

**References**

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

@REFERENCES@
    </help>
</tool>