annotate eggnog_mapper_search.xml @ 13:844fa988236b draft

planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/eggnog_mapper/eggnog_mapper commit 468bd31b8858adbba2854f118e4cbe31f4cd68cb

<tool id="eggnog_mapper_search" name="eggNOG Mapper" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
    <description>search phase</description>
    <macros>
        <import>eggnog_macros.xml</import>
    </macros>
    <expand macro="requirements"/>
    <expand macro="version_command"/>
    <command detect_errors="aggressive"><![CDATA[
        emapper.py
        @DB_TOKEN@
        @ORTHO_SEARCH_TOKEN@

        $output_options.no_file_comments
        --output='results'
        --cpu "\${GALAXY_SLOTS:-4}"
        --scratch_dir \${TEMP:-\$_GALAXY_JOB_TMP_DIR}
        --temp_dir \${TEMP:-\$_GALAXY_JOB_TMP_DIR}
    ]]></command>
    <inputs>
        <expand macro="db_macro"/>
        <expand macro="ortho_search_macro"/>
        <expand macro="output_options_macro"/>
    </inputs>
    <outputs>
        <expand macro="ortho_search_output_macro"/>
    </outputs>
    <tests>
        <!-- test producing only seed orthologs-->
        <test expect_num_outputs="1">
            <param name="eggnog_data" value="@EGGNOG_DB_VERSION@"/>
            <conditional name="ortho_method">
                <param name="input" value="Nmar_0135.fa" ftype="fasta"/>
            </conditional>
            <section name="output_options">
                <param name="no_file_comments" value="true"/>
            </section>
            <expand macro="seed_orthologs_assertion"/>
            <expand macro="stdout_assertion"/>
        </test>
        
        <!-- test setting a diamond option-->
        <test expect_num_outputs="1">
            <param name="eggnog_data" value="@EGGNOG_DB_VERSION@"/> <!-- not passed in test, but required for test to work -->
            <conditional name="ortho_method">
                <param name="m" value="diamond" />
                <param name="input" value="Nmar_0135.fa" ftype="fasta"/>
                <param name="sensmode" value="fast" />
            </conditional>
            <section name="output_options">
                <param name="no_file_comments" value="true"/>
            </section>
            <expand macro="seed_orthologs_assertion"/>
            <expand macro="stdout_assertion">
                <has_text text="--sensmode fast"/>
            </expand>
        </test>
    </tests>
    <help><![CDATA[

eggnog-mapper
=============
Overview
--------

``eggnog-mapper`` is a tool for fast functional annotation of novel sequences (genes or proteins) using precomputed eggNOG-based orthology assignments.
Obvious examples include the annotation of novel genomes, transcriptomes or even metagenomic gene catalogs.
The use of orthology predictions for functional annotation is considered more precise than traditional homology searches,
as it avoids transferring annotations from paralogs (duplicate genes with a higher chance of being involved in functional divergence).

EggNOG-mapper is also available as a public online resource:  `<http://beta-eggnogdb.embl.de/#/app/emapper>`_.

Outputs
-------

@HELP_SEARCH_OUTPUTS@

**Recommentation for large input data**

EggNOG-mapper consists of two phases

1. finding seed orthologous sequences (compute intensive)
2. expanding annotations (IO intensive)

by default (i.e. if *Method to search seed orthologs* is not *Skip search stage...* and *Annotate seed orthologs* is *Yes*)
both phases are executed within one tool run. 

For large input FASTA datasets in can be favourable to split this in two separate
tool runs as follows:

1. Split the FASTA (e.g. 1M seqs per data set)
2. Run the search phase only (set *Annotate seed orthologs* to *No*) on the separate FASTA files.
3. Run the annotation phase (set *Method to search seed orthologs* to *Skip search stage...*)

See [also](https://github.com/eggnogdb/eggnog-mapper/wiki/eggNOG-mapper-v2.1.5-to-v2.1.8#Setting_up_large_annotation_jobs)

Another alternative is to use cached annotations (produced in a run with --md5 enabled).


    ]]></help>
    <expand macro="citations"/>
</tool>