root/galaxy-central/tools/metag_tools/megablast_wrapper.xml @ 2

<tool id="megablast_wrapper" name="Megablast" version="1.0.5">
    <description> compare short reads against htgs, nt, and wgs databases</description>
    <command interpreter="python">
      megablast_wrapper.py 
       --db_build="$source_select"
       --input=$input_query
       --word_size=$word_size
       --identity_cutoff=$iden_cutoff
       --eval_cutoff=$evalue_cutoff 
       --filter_query=$filter_query
       --index_dir=${GALAXY_DATA_INDEX_DIR}
       --output=$output1
    </command>
    <inputs>
        <param name="input_query" type="data" format="fasta" label="Compare these sequences"/> 
        <param name="source_select" type="select" display="radio" label="against target database">
            <options from_file="blastdb.loc">
              <column name="name" index="0"/>
              <column name="value" index="0"/>
            </options>
        </param>
        <param name="word_size" type="select" label="using word size" help="Size of best perfect match">
            <option value="28">28</option>
            <option value="16">16</option>
        </param>
        <param name="iden_cutoff" type="float" size="15" value="90.0" label="report hits above this identity" help="no cutoff if 0" />
        <param name="evalue_cutoff" type="float" size="15" value="0.001" label="set expectation value cutoff" />
        <param name="filter_query" type="select" label="Filter out low complexity regions?">
            <option value="T">Yes</option>
            <option value="F">No</option>
        </param>
    </inputs>
    <outputs>
        <data name="output1" format="tabular"/>
    </outputs>
    <requirements>
        <requirement type="package">megablast</requirement>
    </requirements>
    <tests>
        <test>
            <param name="input_query" value="megablast_wrapper_test1.fa" ftype="fasta"/>
            <!-- source_select needs to match the entry in the blastdb.loc file, which includes the last update date if appropriate --> 
            <param name="source_select" value="phiX" />
            <param name="word_size" value="28" />
            <param name="iden_cutoff" value="99.0" />
            <param name="evalue_cutoff" value="10.0" />
            <param name="filter_query" value="T" />
            <output name="output1" file="megablast_wrapper_test1.out"/> 
        </test>
    </tests>
    <help>
    
.. class:: warningmark

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

-----

**What it does**

This tool runs **megablast** (for information about megablast, please see the reference below) a high performance nucleotide local aligner developed by Webb Miller and colleagues.

-----

**Output format**

Output of this tool contains 13 columns delimited by Tabs:

1. Id of your sequence 
2. GI of the database hit 
3. Length of the database hit
4. % identity
5. Alignment length
6. # mismatches
7. # gaps
8. Start position in your sequence
9. End position in your sequence
10. Start position in database hit
11. End position in database hit
12. E-value
13. Bit score

-------

**Reference**

Zhang et al. A Greedy Algorithm for Aligning DNA Sequences. 2000. JCB: 203-214.

    </help>
</tool>