# HG changeset patch -- Bitbucket.org # Project galaxy-dist # URL http://bitbucket.org/galaxy/galaxy-dist/overview # User peterjc <p.j.a.cock@googlemail.com> # Date 1285090213 -3600 # Node ID dc68de280ac7f2ff2ff97068694a7ecded62ee0c # Parent e902e11cd57c7b5e4b0b43bdf0bde459535e8a0c Adding basic NCBI BLAST+ blastn wrapper with multiple output format support --- /dev/null +++ b/tools/ncbi_blast_plus/ncbi_blastn_wrapper.xml @@ -0,0 +1,117 @@ +<tool id="ncbi_blastn_wrapper" name="NCBI BLAST+ blastn" version="0.0.1"> + <description>Use NCBI BLAST+ tool to search a nucleotide database with nucleotide query sequence(s)</description> + <command> + blastn + -query "$query" + -db "$database" + -task $blast_type + -evalue $evalue_cutoff + -dust $filter_query + -out $output1 + -outfmt $out_format + </command> + <inputs> + <param name="query" type="data" format="fasta" label="Query sequence(s)"/> + <param name="database" type="select" display="radio" label="Nucelotide BLAST database"> + <options from_file="blastdb.loc"> + <column name="name" index="0"/> + <column name="value" index="1"/> + </options> + </param> + <param name="blast_type" type="select" display="radio" label="Type of BLAST"> + <option value="megablast">megablast</option> + <option value="blastn">blastn</option> + <option value="blastn-short">blastn-short</option> + <option value="dc-megablast">dc-megablast</option> + <option value="vecscreen">vecscreen</option> + </param> + <!-- TODO - integer, min 4, what default? + <param name="word_size" type="integer" label="using word size" help="Size of best perfect match"> + <option value="28">28</option> + <option value="16">16</option> + </param> + <param name="iden_cutoff" type="float" size="15" value="90.0" label="report hits above this identity" help="no cutoff if 0" /> + --> + <param name="evalue_cutoff" type="float" size="15" value="0.001" label="set expectation value cutoff" /> + <param name="filter_query" type="select" label="Filter out low complexity regions (with DUST)?"> + <option value="yes">Yes</option> + <option value="no">No</option> + </param> + <param name="out_format" type="select" label="Output format"> + <option value="6">Tabular</option> + <option value="5">BLAST XML</option> + <option value="0">Pairwise text</option> + <!-- + <option value="11">BLAST archive format (ASN.1)</option> + --> + </param> + </inputs> + <outputs> + <!-- TODO, can I get the caption rather than the value? e.g. 'NR' rather than a long path? --> + <data name="output1" format="tabular" label="${blast_type.value_label} on ${database.value_label}"> + <change_format> + <when input="out_format" value="0" format="txt"/> + </change_format> + <change_format> + <when input="out_format" value="5" format="blastxml"/> + </change_format> + </data> + </outputs> + <requirements> + <requirement type="binary">blastn</requirement> + </requirements> + <tests> + <test> + <param name="input_query" value="megablast_wrapper_test1.fa" ftype="fasta"/> + <!-- database needs to match the entry in the blastdb.loc file (first column), which includes the last update date if appropriate --> + <param name="database" value="phiX" /> + <param name="blast_type" value="megablast" /> + <!-- + <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="yes" /> + <param name="out_format" value="6" /> + <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 NCBI BLAST+ blastn tool (which include *megablast*). + +----- + +**Output format** + +The default Output of this tool is tabular, containing 12 columns: + +1. Id of your sequence +2. GI of the database hit +3. % identity +4. Alignment length +5. # mismatches +6. # gaps +7. Start position in your sequence +8. End position in your sequence +9. Start position in database hit +10. End position in database hit +11. E-value +12. Bit score + +------- + +**References** + +Zhang et al. A Greedy Algorithm for Aligning DNA Sequences. 2000. JCB: 203-214. + + </help> +</tool> --- a/tool_conf.xml.sample +++ b/tool_conf.xml.sample @@ -262,6 +262,9 @@ <tool file="sr_assembly/velveth.xml" /></section> --> + <section name="NCBI BLAST+" id="ncbi_blast_plus_tools"> + <tool file="ncbi_blast_plus/ncbi_blastn_wrapper.xml" /> + </section><section name="NGS: Mapping" id="solexa_tools"><tool file="sr_mapping/lastz_wrapper.xml" /><tool file="sr_mapping/lastz_paired_reads_wrapper.xml" />