comparison snpEff_create_db.xml @ 17:65ae79bddc69 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpeff commit 5ab504d384299d8c2ed496650f1f9e4a887cd102

16:c9ecd2a96ecf

<tool id="snpEff_build_gb" name="SnpEff build:" version="@wrapper_version@.galaxy3">
    <description> database from Genbank or GFF record</description>
    <macros>
        <import>snpEff_macros.xml</import>
    </macros>
    <requirements>

        <requirement type="package" version="5.32">libmagic</requirement>
    </requirements>
    <expand macro="stdio" />
    <expand macro="version_command" />
    <command><![CDATA[

        #if str( $input_type.input_type_selector ) == "gb":
            #if str( $input_type.fasta ) == "yes":
                python3 '$__tool_directory__/gbk2fa.py' '${input_type.input_gbk}' '${output_fasta}'
                #if $input_type.remove_version:
                    '${input_type.remove_version}'

                ln -s '${input_type.input_fasta}' '${snpeff_output.files_path}'/'${genome_version}'/sequences.fa.gz &&
            #end if
            ln -s '${input_type.input_gff}' '${snpeff_output.files_path}'/'${genome_version}'/genes.gff &&
        #end if

        snpEff @java_options@ build -v
        -configOption '${genome_version}'.genome='${genome_version}'
        -configOption '${genome_version}'.codonTable='${codon_table}'
        #if str( $input_type.input_type_selector ) == "gb":
            -genbank
        #elif str( $input_type.input_type_selector ) == "gff":

        echo "${genome_version}.genome : ${genome_version}" >> '${snpeff_output.files_path}'/snpEff.config &&
        echo "${genome_version}.codonTable : ${codon_table}" >> '${snpeff_output.files_path}'/snpEff.config

    ]]></command>
    <inputs>
        <param name="genome_version" type="text" value="" label="Name for the database" help="for E. coli K12 you may want to use 'EcK12' etc.">
            <validator type="regex" message="A genome version name is required">\S+</validator>
        </param>
        <conditional name="input_type">
            <param name="input_type_selector" type="select" display="radio" label="Input annotations are in" help="Specify format for annotations you are using to create SnpEff database">
                <option value="gb" selected="true">GenBank</option>
                <option value="gff">GFF</option>

                <param name="input_gbk" type="data" format="genbank,genbank.gz" label="Genbank dataset to build database from" help="This Genbank file will be used to generate snpEff database"/>
                <param name="fasta" type="select" display="radio" label="Parse Genbank into Fasta" help="This will generate an additional dataset containing all sequences from Genbank file in FASTA format">
                        <option value="yes" selected="true">Yes</option>
                        <option value="no">No</option>
                </param>
                <param type="boolean" name="remove_version" truevalue="--remove_version" falsevalue="" checked="true" label="Remove sequence version label?" help="Genbank sequences have vesion numbers such as B000564.2. This option removes them leaving only B000564" argument="--remove_version"/>
            </when>
            <when value="gff"> 
                <param name="input_gff" type="data" format="gff3" label="GFF dataset to build database from" help="This GFF file will be used to generate snpEff database"/>
                <param name="input_fasta" type="data" format="fasta,fasta.gz" label="Genome in FASTA format" help="This dataset is required for generating SnpEff database. See help section below."/>
            </when>
        </conditional>
        <param name="codon_table" type="select" label="Select genetic code for this sequence" help="If this sequence uses non-standard genetic code, select one from these options">

            <option value="Scenedesmus_obliquus_Mitochondrial">Scenedesmus_obliquus_Mitochondrial</option>
            <option value="Thraustochytrium_Mitochondrial">Thraustochytrium_Mitochondrial</option>
        </param>
    </inputs>
    <outputs>
        <data name="snpeff_output" format="snpeffdb" label="@snpeff_version@ database for ${genome_version}"/>
        <data name="output_fasta" format="fasta" label="Fasta sequences for ${genome_version}">
            <filter>input_type['input_type_selector'] == 'gb'</filter>
            <filter>input_type['fasta'] == 'yes'</filter>
        </data>
    </outputs>

        </test>
    </tests>
    <help><![CDATA[
**What it does**

This tool uses `"snpEff build -genbank"` or `"snpEff build -gff3"` commands to create a snpEff database. 

------

.. class:: infomark

**Working with Genbank files**

Using Genbank data for creating databases has several advantages:

 #. Genbank files contain annotations (such as locations of genes) together with sequences. This ensures that these two are in sync with each other. 
 #. When you are analyzing small genomes (or not so small) it is much more convenient to create a database on the fly and use it.

 .. class:: warningmark

 SnpEff errors out on highly fragmented genomes containing multiple scaffolds. This is because a single gene may be split between multiple scaffolds causing SnpEff to crash. If this is happening use GFF route described below. 

-------

**Genbank usage scenario**

Suppose you have a series of Illumina reads from an experiment involving *E. coli* K-12 MG1655. You want to map these reads to the reference genome of K-12 MG1655, call variants, and annotate them using snpEff. This tool enables you to follow the following analysis steps:

 #. Go to `NCBI <http://www.ncbi.nlm.nih.gov>`_ page for K-12 MG1655 genome (note that all NCBI genomes have similar list of files associated with them).
 #. Copy URL for file with extension `gbff.gz` 
 #. Paste the URL into upload tool and set datatype to `genbank.gz`.
 #. Use this tool to generate a snpEff database and FASTA sequences from the dataset you've uploaded during the previous step.
 #. Use your Illumina reads to map against FASTA dataset generated in the previous step using BWA-MEM.
 #. Call variants using **Freebayes**.
 #. Annotate vcf output of Freebayes with **SnpEff eff** using database generated at step 2 (using *Custom* option for **Genome source** parameter).

The GFF file contains coordinates of various features, but does not contain underlying sequences. This is why a FASTA file needs to be provided as well.

------

**GFF usage scenario**   

The following example also uses *E. coli* K-12 MG1655:

#. Go to `NCBI <http://www.ncbi.nlm.nih.gov>`_ page for K-12 MG1655 genome.
#. Copy URLs for files with `gff.gz` and `fna.gz` extensions. The first file contains annotations in GFF3 format. The second file contains entire genome as a FASTA record.
#. Paste URLs into upload tool and set datatypes to `gff3` and `fasta.gz` for annotations and genome, respectively.
#. Use this tool to generate a snpEff database from the GFF dataset.
#. Map your reads against the FASTA dataset and continue as described in the above example.


@snpeff_in_galaxy_info@
@external_documentation@
]]>
    </help>
    <expand macro="citations" />
</tool>

17:65ae79bddc69

<tool id="snpEff_build_gb" name="SnpEff build:" version="@WRAPPER_VERSION@.galaxy3">
    <description> database from Genbank or GFF record</description>
    <macros>
        <import>snpEff_macros.xml</import>
    </macros>
    <requirements>

        <requirement type="package" version="5.32">libmagic</requirement>
    </requirements>
    <expand macro="stdio" />
    <expand macro="version_command" />
    <command><![CDATA[
        #if str( $input_type.input_type_selector ) == "gb":
            #if str( $input_type.fasta ) == "yes":
                python3 '$__tool_directory__/gbk2fa.py' '${input_type.input_gbk}' '${output_fasta}'
                #if $input_type.remove_version:
                    '${input_type.remove_version}'

                ln -s '${input_type.input_fasta}' '${snpeff_output.files_path}'/'${genome_version}'/sequences.fa.gz &&
            #end if
            ln -s '${input_type.input_gff}' '${snpeff_output.files_path}'/'${genome_version}'/genes.gff &&
        #end if

        snpEff @JAVA_OPTIONS@ build -v
        -configOption '${genome_version}'.genome='${genome_version}'
        -configOption '${genome_version}'.codonTable='${codon_table}'
        #if str( $input_type.input_type_selector ) == "gb":
            -genbank
        #elif str( $input_type.input_type_selector ) == "gff":

        echo "${genome_version}.genome : ${genome_version}" >> '${snpeff_output.files_path}'/snpEff.config &&
        echo "${genome_version}.codonTable : ${codon_table}" >> '${snpeff_output.files_path}'/snpEff.config

    ]]></command>
    <inputs>
        <param name="genome_version" type="text" value="" label="Name for the database" help="For E. coli K12 you may want to use 'EcK12' etc.">
            <validator type="empty_field" message="A genome version name is required" />
        </param>
        <conditional name="input_type">
            <param name="input_type_selector" type="select" display="radio" label="Input annotations are in" help="Specify format for annotations you are using to create SnpEff database">
                <option value="gb" selected="true">GenBank</option>
                <option value="gff">GFF</option>

                <param name="input_gbk" type="data" format="genbank,genbank.gz" label="Genbank dataset to build database from" help="This Genbank file will be used to generate snpEff database"/>
                <param name="fasta" type="select" display="radio" label="Parse Genbank into Fasta" help="This will generate an additional dataset containing all sequences from Genbank file in FASTA format">
                        <option value="yes" selected="true">Yes</option>
                        <option value="no">No</option>
                </param>
                <param argument="--remove_version" type="boolean" truevalue="--remove_version" falsevalue="" checked="true" label="Remove sequence version label?" help="Genbank sequences have vesion numbers such as B000564.2. This option removes them leaving only B000564" />
            </when>
            <when value="gff">
                <param name="input_gff" type="data" format="gff3" label="GFF dataset to build database from" help="This GFF file will be used to generate snpEff database"/>
                <param name="input_fasta" type="data" format="fasta,fasta.gz" label="Genome in FASTA format" help="This dataset is required for generating SnpEff database. See help section below."/>
            </when>
        </conditional>
        <param name="codon_table" type="select" label="Select genetic code for this sequence" help="If this sequence uses non-standard genetic code, select one from these options">

            <option value="Scenedesmus_obliquus_Mitochondrial">Scenedesmus_obliquus_Mitochondrial</option>
            <option value="Thraustochytrium_Mitochondrial">Thraustochytrium_Mitochondrial</option>
        </param>
    </inputs>
    <outputs>
        <data name="snpeff_output" format="snpeffdb" label="@SNPEFF_VERSION@ database for ${genome_version}"/>
        <data name="output_fasta" format="fasta" label="Fasta sequences for ${genome_version}">
            <filter>input_type['input_type_selector'] == 'gb'</filter>
            <filter>input_type['fasta'] == 'yes'</filter>
        </data>
    </outputs>

        </test>
    </tests>
    <help><![CDATA[
**What it does**

This tool uses `"snpEff build -genbank"` or `"snpEff build -gff3"` commands to create a snpEff database.

------

.. class:: infomark

**Working with Genbank files**

Using Genbank data for creating databases has several advantages:

 #. Genbank files contain annotations (such as locations of genes) together with sequences. This ensures that these two are in sync with each other.
 #. When you are analyzing small genomes (or not so small) it is much more convenient to create a database on the fly and use it.

 .. class:: warningmark

 SnpEff errors out on highly fragmented genomes containing multiple scaffolds. This is because a single gene may be split between multiple scaffolds causing SnpEff to crash. If this is happening use GFF route described below.

-------

**Genbank usage scenario**

Suppose you have a series of Illumina reads from an experiment involving *E. coli* K-12 MG1655. You want to map these reads to the reference genome of K-12 MG1655, call variants, and annotate them using snpEff. This tool enables you to follow the following analysis steps:

 #. Go to `NCBI <http://www.ncbi.nlm.nih.gov>`_ page for K-12 MG1655 genome (note that all NCBI genomes have similar list of files associated with them).
 #. Copy URL for file with extension `gbff.gz`
 #. Paste the URL into upload tool and set datatype to `genbank.gz`.
 #. Use this tool to generate a snpEff database and FASTA sequences from the dataset you've uploaded during the previous step.
 #. Use your Illumina reads to map against FASTA dataset generated in the previous step using BWA-MEM.
 #. Call variants using **Freebayes**.
 #. Annotate vcf output of Freebayes with **SnpEff eff** using database generated at step 2 (using *Custom* option for **Genome source** parameter).

The GFF file contains coordinates of various features, but does not contain underlying sequences. This is why a FASTA file needs to be provided as well.

------

**GFF usage scenario**

The following example also uses *E. coli* K-12 MG1655:

#. Go to `NCBI <http://www.ncbi.nlm.nih.gov>`_ page for K-12 MG1655 genome.
#. Copy URLs for files with `gff.gz` and `fna.gz` extensions. The first file contains annotations in GFF3 format. The second file contains entire genome as a FASTA record.
#. Paste URLs into upload tool and set datatypes to `gff3` and `fasta.gz` for annotations and genome, respectively.
#. Use this tool to generate a snpEff database from the GFF dataset.
#. Map your reads against the FASTA dataset and continue as described in the above example.


@SNPEFF_IN_GALAXY_INFO@
@EXTERNAL_DOCUMENTATION@
]]>
    </help>
    <expand macro="citations" />
</tool>