<tool id="framebot" name="Framebot" version="0.1.0">
    <description> to coorect frameshift and classify nearest neighbor</description>

    <requirements>
        <requirement type="package" version="2.0.2">rdptools</requirement>
    </requirements>

    <stdio>
        <exit_code range="1:" />
    </stdio>

    <command><![CDATA[
        java -jar \${RDP_TOOLS_DIR}/FrameBot.jar framebot
            -a $alignment_mode
            -i $identity_cutoff
            -k $knn
            -l $length_cutoff
    
            #if $no_metric_search.no_metric_search_test
                -N 
                -e $no_metric_search.gap_ext_penalty
                -f $no_metric_search.frameshift_penalty
                -g $no_metric_search.gap_open_penalty
            #else
                -m $no_metric_search.max_radius
            #end if

            -o output
 
            #if str( $databases.databases_selector ) == 'history'
                $databases.databases_name
            #else
                #set $data_table = dict([(_[0], _[2]) for _ in $databases.databases_input.input.options.tool_data_table.data])
                $data_table[$databases.databases_input.value]
            #end if

            $framebot_input_sequence_file
    ]]></command>

    <inputs>
        <param name="framebot_input_sequence_file" type="data" format="fasta" 
            label="Input sequence file" help=""/>

        <conditional name="databases">
            <param name="databases_selector" type="select" label="Databases to query" help="">
                <option value="cached" selected="true">Public reference gene databases</option>
                <option value="history">Databases from your history</option>
            </param>
            <when value="cached">
                <param name="databases_input" label="Reference gene databases" type="select" display="radio">
                    <options from_data_table="framebot_ref_gene_databases" />
                    <validator type="no_options" message="Select at least one database"/>
                </param>
            </when>
            <when value="history">
                <param name="databases_name" type="data" format="fasta" label="Reference gene database"
                    multiple="false" help=""/>
            </when>
        </conditional>

        <param name="alignment_mode" type="select" display="radio" 
            label="Alignment mode" help="">
            <option value="glocal">Glocal</option>
            <option value="local">Local</option>
            <option value="global">Global</option>
        </param>

        <param name="identity_cutoff" type="float" min="0" max="1" value="0.4" 
            label="Percent identity cutoff" help=""/>

        <conditional name="no_metric_search">
            <param name="no_metric_search_test" type='boolean' checked="true" label="Disable 
                metric search?" help="Provide fasta file of seeds instead of 
                index file"/>
            <when value="true">
                <param name="gap_ext_penalty" type="integer" min="-10" max="0" 
                    value="-1" label="Gap extension penalty" help=""/>
                <param name="frameshift_penalty" type="integer" min="-20" max="0" 
                    value="-10" label="Frameshift penalty" help=""/>
                <param name="gap_open_penalty" type="integer" min="-20" max="0" 
                    value="-10" label="Gap opening penalty" help=""/>
            </when>
            <when value="false">
                <param name="max_radius" type="float" min="1" max="2147483647" 
                    value="100" label="Maximum radius" help=""/>
            </when>
        </conditional>
        
        <param name="knn" type="integer" min="0" max="100" value="10" 
            label="The top k closest protein targets" help=""/>
        <param name="length_cutoff" type="integer" min="0" max="100" value="80" 
            label="Length cutoff in number of amino acids" help=""/>
        
        <param name="transl_table" type="select" display="radio" label="Protein 
            translation table to use" help="NCBI Translation Tables">
            <option value="1">Standard Code</option>
            <option value="2">Vertebrate Mitochondrial Code</option>
            <option value="3">Yeast Mitochondrial Code</option>
            <option value="4">Mold, Protozoan, and Coelenterate Mitochondrial Code and the Mycoplasma/Spiroplasma Code</option>
            <option value="5">Invertebrate Mitochondrial Code</option>
            <option value="6">Ciliate, Dasycladacean and Hexamita Nuclear Code</option>
            <option value="9">Echinoderm and Flatworm Mitochondrial Code</option>
            <option value="10">Euplotid Nuclear Code</option>
            <option value="11" selected="true">Bacterial, Archaeal and Plant Plastid Code</option>
            <option value="12">Alternative Yeast Nuclear Code</option>
            <option value="13">Ascidian Mitochondrial Code</option>
            <option value="14">Alternative Flatworm Mitochondrial Code</option>
            <option value="16">Chlorophycean Mitochondrial Code</option>
            <option value="21">Trematode Mitochondrial Code</option>
            <option value="22">Scenedesmus obliquus Mitochondrial Code</option>
            <option value="23">Thraustochytrium Mitochondrial Code</option>
            <option value="24">Pterobranchia Mitochondrial Code</option>
            <option value="25">Candidate Division SR1 and Gracilibacteria Code</option>
        </param>
        
        <param name="word_size" type="integer" min="3" max="6" value="4" 
            label="Word size used to find closest protein target" help=""/>
    </inputs>

    <outputs>
        <data format="txt" name="conserved_alignment_file" 
            from_work_dir="output_framebot.txt"
            label="Conserved alignments to the neared match of ${on_string} (Framebot)" />
        <data format="fasta" name="corr_nucl_output" 
            from_work_dir="output_corr_nucl.fasta"
            label="Frameshift-corrected nucleotide sequences of ${on_string} (Framebot)" />
         <data format="fasta" name="corr_prot_output" 
            from_work_dir="output_corr_prot.fasta"
            label="Frameshift-corrected protein sequences of ${on_string} (Framebot)" />
        
        <data format="txt" name="failed_alignment_file" 
            from_work_dir="output_failed_framebot.txt"
            label="Rejected alignments to the neared match of ${on_string} (Framebot)" />
        <data format="fasta" name="failed_nucl_output" 
            from_work_dir="output_failed_nucl.fasta"
            label="Non frameshift-corrected nucleotide sequences of ${on_string} (Framebot)" />
    </outputs>

    <tests>
        <test>
            <param name="framebot_input_sequence_file" value="framebot_input_sequence.fasta"/>
            <param name="databases_selector" value="cached" />
            <param name="databases_input" value="amoA_prot_ref" />
            <param name="alignment_mode" value="glocal" />
            <param name="denovo_abund_cutoff" value="10" />
            <param name="denovo_id_cutoff" value="0.7" />
            <param name="identity_cutoff" value="0.4" />
            <param name="no_metric_search_test" value="true" />
            <param name="gap_ext_penalty" value="-1" label="Gap extension penalty" help=""/>
            <param name="frameshift_penalty" value="-10" label="Frameshift penalty" help=""/>
            <param name="gap_open_penalty" value="-10" label="Gap opening penalty" help=""/>
            <param name="no_prefilter" value="false" />
            <param name="scoring_matrix" value="Blosum62"/>
            <param name="knn" value="10" />
            <param name="length_cutoff" value="80"/>
            <param name="transl_table" value="11"/>
            <param name="word_size" value="4"/>
            <param name="de_novo" value="false"/>

            <output name="conserved_alignment_file" file="framebot_conserved_alignment_file.txt"/>
            <output name="corr_nucl_output" file="framebot_corr_nucl_output.fasta"/>
            <output name="corr_prot_output" file="framebot_corr_prot_output.fasta"/>
            <output name="failed_alignment_file" file="framebot_failed_alignment_file.txt"/>
            <output name="failed_nucl_output" file="framebot_failed_nucl_output.fasta"/>
        </test>
    </tests>

    <help><![CDATA[

**What it does**

RDP FrameBot is a frameshift correction and nearest neighbor classification tool for use with high-throughput amplicon sequencing. It uses a dynamic programming algorithm to align each query DNA sequence against a set of target protein sequences, produces frameshift-corrected protein and DNA sequences and an optimal global or local protein alignment. 
More information on `Github repository <https://github.com/rdpstaff/Framebot>`_.

-----

**Input**

One protein reference fasta file or index file, and one DNA query fasta file are required. 

Several reference sets for a list of genes are available. 
But personal own set of reference sequences can be provide as representative of the gene of interest (`http://fungene.cme.msu.edu <http://fungene.cme.msu.edu>`_ is a good resource). 
The reference set must contain protein or DNA representative sequences of the gene target and should be compiled to have a good coverage of diversity of the gene family. FrameBot is significantly more accurate when the nearest target protein sequence (from the reference set) is at least 50% identical to the query read. Running FrameBot is computationally intensive in no-metric-search mode because it performs all-against-all comparisons between query DNA and the target protein sequences. Therefore we recommend limiting your reference set to 200 protein sequences for no-metric-search mode. The index metic-search mode gains more than 10-fold speedup by reducing the number of comparisons (see FrameBot citation). A larger DNA reference set can be used. 

-----

**Parameters**

The parameters are numerous in Framebot

    - The alignment mode: glocal, local or global
    - The minimum abundance for de-novo mode
    - The maxmimum aa identity cutoff for de-novo mode
    - The Percent identity cutoff
    - The top k closest protein targets
    - Length cutoff in number of amino acids
    - Disable metric search (provide fasta file of seeds instead of index file)
    - Result file name stem
    - Disable the pre-filtering step for non-metric search
    - Sequence quality data
    - Protein translation table to use
    - The word size used to find closest protein targets
    - ...

-----

**Output**

The framebot step produces five output files:

    - the alignment to the nearest match satisfying the minimum length and protein identity cutoff.
    - the frameshift-corrected nucleotide and protein sequences satisfying the minimum length and protein identity cutoff.
    - the alignment to the nearest match that failed the minimum length and protein identity cutoff.
    - a fasta file containing the nucleotide sequences that failed the minimum length and protein identity cutoff.

    ]]></help>

    <citations>
        <citation type="doi">10.1128/mBio.00592-13</citation>
    </citations>
</tool>