comparison nextalign.xml @ 14:4d93e708218c draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/nextclade commit 2c63aeec74c260ccd9b2cdbbe1869bef2f3d5cda

13:e5ed60c823a7

        <requirement type="package" version="@TOOL_VERSION@">nextalign</requirement>
    </requirements>
    <version_command>nextalign --version-detailed</version_command>
    <command detect_errors="exit_code"><![CDATA[
@REF_FASTA@
ln -s '$sequences' sequences.fasta &&
nextalign
    --sequences sequences.fasta
    --reference reference.fa
    --output-fasta '$output_fasta'
#if $output_insertions:
    --output-insertions '$output_csv'
#end if
#if $translation.translation_select == "yes":
    --genes '${translation.genes}'
    --genemap '${translation.genemap}'
#end if
    --min-length '${min_length}'
    --penalty-gap-extend '${penalty_gap_extend}'
    --penalty-gap-open '${penalty_gap_open}'
    --penalty-gap-open-in-frame '${penalty_gap_open_in_frame}'
    --penalty-gap-open-out-of-frame '${penalty_gap_open_out_of_frame}'
    --penalty-mismatch '${penalty_mismatch}'
    --score-match '${score_match}'
    --max-indel '${max_indel}'
    --nuc-seed-length '${nuc_seed_length}'
    --nuc-min-seeds '${nuc_min_seeds}'
    --nuc-seed-spacing '${nuc_seed_spacing}'
    --nuc-mismatches-allowed '${nuc_mismatches_allowed}'
    ]]></command>
    <inputs>
        <expand macro="reference"/>
        <param argument="--sequences" type="data" format="fasta" label="FASTA file with input sequences"/>
        <param argument="--output-insertions" type="boolean" checked="true" label="Output insertion sequences?" help="Outputs stripped insertions relative to reference as CSV"/>
        <conditional name="translation">
            <param name="translation_select" type="select" label="Translate annotated genes based on GFF and gene list?">
                <option value="yes">Translate annotated genes</option>
                <option value="no">Don't translate genes</option>

                            <add value="." />
                            <add value="," />
                        </valid>
                    </sanitizer>
                </param>
                <param argument="--genemap" type="data" format="gtf" label="GTF file containing custom gene map"/> <!-- TODO - make sure they need GFF and not GTF or GFF3 -->
            </when>
            <when value="no"/>
        </conditional>
        <param argument="--min-length" type="integer" value="100" min="0"
            label="Minimum length of nucleotide sequence to consider for alignment"

            label="Score for encouraging aligned nucelotides or aminoacids with matching state."
            help="Note that this is redundantly parameterized with mismatch penalty." />
        <param argument="--max-indel" type="integer" value="400" min="0"
            label="Maximum length of insertions or deletions allowed to proceed with alignment."
            help="Alignments with long indels are slow to compute and require substantial memory in the current implementation. Alignment of sequences with indels that are longer than this value will not be attempted and a warning will be emitted." />
        <param argument="--nuc-seed-length" type="integer" value="21" min="1"
            label="Seed length for nucleotide alignment."
            help="Seeds should be long enough to be unique, but short enough to match with high probability." />
        <param argument="--nuc-min-seeds" type="integer" value="10" min="1"
            label="Minimum number of seeds to search for during nucleotide alignment."
            help="Relevant for short sequences. In long sequences, the number of seeds is determined by nucleotide seed spacing. This should be a positive integer." />
        <param argument="--nuc-seed-spacing" type="integer" value="100" min="0"
            label="Spacing between seeds during nucleotide alignment." />
        <param argument="--nuc-mismatches-allowed" type="integer" value="3" min="0"
            label="Maximum number of mismatching nucleotides."
            help="Maximum number of mismatching nucleotides allowed for a seed to be considered a match." />
    </inputs>
    <outputs>
        <data name="output_fasta" format="fasta" label="${tool.name} on ${on_string} (FASTA)"/>

            <conditional name="reference_source">
                <param name="reference_source_selector" value="history"/>
                <param name="ref_file" value="reference.fasta"/>
            </conditional>
            <param name="output_insertions" value="true"/>
            <param name="sequences" value="subsampled.fasta"/>
            <conditional name="translation">
                <param name="translation_select" value="yes"/>
                <param name="genes" value="E,M,N,ORF10,ORF14,ORF1a,ORF1b,ORF3a,ORF6,ORF7a,ORF7b,ORF8,ORF9b,S"/>
                <param name="genemap" value="genemap.gtf" ftype="gtf"/>
            </conditional>
            <output name="output_fasta" file="output.fasta" sort="true"/>
            <output name="output_csv" file="insertions.csv" sort="true"/>
            <output_collection name="translations" type="list" count="14">
                <element name="E" file="subsampled.gene.E.fasta" ftype="fasta" sort="true"/>
                <element name="M" file="subsampled.gene.M.fasta" ftype="fasta" sort="true"/>
                <element name="N" file="subsampled.gene.N.fasta" ftype="fasta" sort="true"/>
                <element name="ORF10" file="subsampled.gene.ORF10.fasta" ftype="fasta" sort="true"/>
                <element name="ORF14" file="subsampled.gene.ORF14.fasta" ftype="fasta" sort="true"/>
                <element name="ORF1a" file="subsampled.gene.ORF1a.fasta" ftype="fasta" sort="true"/>
                <element name="ORF1b" file="subsampled.gene.ORF1b.fasta" ftype="fasta" sort="true"/>
                <element name="ORF3a" file="subsampled.gene.ORF3a.fasta" ftype="fasta" sort="true"/>
                <element name="ORF6" file="subsampled.gene.ORF6.fasta" ftype="fasta" sort="true"/>
                <element name="ORF7a" file="subsampled.gene.ORF7a.fasta" ftype="fasta" sort="true"/>

            <conditional name="reference_source">
                <param name="reference_source_selector" value="history"/>
                <param name="ref_file" value="reference.fasta"/>
            </conditional>
            <param name="output_insertions" value="false"/>
            <param name="sequences" value="subsampled.fasta"/>
            <conditional name="translation">
                <param name="translation_select" value="no"/>
            </conditional>
            <output name="output_fasta" file="output.fasta" sort="true"/>
        </test>

            <conditional name="reference_source">
                <param name="reference_source_selector" value="cached"/>
                <param name="ref_file" value="reference_fasta"/>
            </conditional>
            <param name="output_insertions" value="false"/>
            <param name="sequences" value="subsampled.fasta"/>
            <conditional name="translation">
                <param name="translation_select" value="no"/>
            </conditional>
            <output name="output_fasta" file="output.fasta" sort="true"/>
        </test>

14:4d93e708218c

        <requirement type="package" version="@TOOL_VERSION@">nextalign</requirement>
    </requirements>
    <version_command>nextalign --version-detailed</version_command>
    <command detect_errors="exit_code"><![CDATA[
@REF_FASTA@
@QUERY_FASTA@
nextalign run
    --input-ref reference.fa
    --output-fasta '$output_fasta'
#if $output_insertions:
    --output-insertions '$output_csv'
#end if
#if $translation.translation_select == "yes":
    --genes '${translation.genes}'
    --genemap '${translation.genemap}'
    --output-translations 'sequences.gene.{gene}.fasta'
#end if
    --min-length ${min_length}
    --penalty-gap-extend ${penalty_gap_extend}
    --penalty-gap-open ${penalty_gap_open}
    --penalty-gap-open-in-frame ${penalty_gap_open_in_frame}
    --penalty-gap-open-out-of-frame ${penalty_gap_open_out_of_frame}
    --penalty-mismatch ${penalty_mismatch}
    --score-match ${score_match}
    --max-indel ${max_indel}
    --seed-length ${seed_length}
    --min-seeds ${min_seeds}
    --seed-spacing ${seed_spacing}
    --mismatches-allowed ${mismatches_allowed}
    $query
    ]]></command>
    <inputs>
        <expand macro="reference"/>
        <param name="input_fasta" type="data" format="fasta,fasta.gz" label="FASTA file with input sequences"/>
        <param argument="--output-insertions" type="boolean" checked="true" label="Output insertion sequences?" help="Outputs stripped insertions relative to reference as CSV"/>
        <conditional name="translation">
            <param name="translation_select" type="select" label="Translate annotated genes based on GFF and gene list?">
                <option value="yes">Translate annotated genes</option>
                <option value="no">Don't translate genes</option>

                            <add value="." />
                            <add value="," />
                        </valid>
                    </sanitizer>
                </param>
                <param argument="--genemap" type="data" format="gff3" label="GFF3 file containing custom gene map"/>
            </when>
            <when value="no"/>
        </conditional>
        <param argument="--min-length" type="integer" value="100" min="0"
            label="Minimum length of nucleotide sequence to consider for alignment"

            label="Score for encouraging aligned nucelotides or aminoacids with matching state."
            help="Note that this is redundantly parameterized with mismatch penalty." />
        <param argument="--max-indel" type="integer" value="400" min="0"
            label="Maximum length of insertions or deletions allowed to proceed with alignment."
            help="Alignments with long indels are slow to compute and require substantial memory in the current implementation. Alignment of sequences with indels that are longer than this value will not be attempted and a warning will be emitted." />
        <param argument="--seed-length" type="integer" value="21" min="1"
            label="Seed length for nucleotide alignment."
            help="Seeds should be long enough to be unique, but short enough to match with high probability." />
        <param argument="--min-seeds" type="integer" value="10" min="1"
            label="Minimum number of seeds to search for during nucleotide alignment."
            help="Relevant for short sequences. In long sequences, the number of seeds is determined by nucleotide seed spacing. This should be a positive integer." />
        <param argument="--seed-spacing" type="integer" value="100" min="0"
            label="Spacing between seeds during nucleotide alignment." />
        <param argument="--mismatches-allowed" type="integer" value="3" min="0"
            label="Maximum number of mismatching nucleotides."
            help="Maximum number of mismatching nucleotides allowed for a seed to be considered a match." />
    </inputs>
    <outputs>
        <data name="output_fasta" format="fasta" label="${tool.name} on ${on_string} (FASTA)"/>

            <conditional name="reference_source">
                <param name="reference_source_selector" value="history"/>
                <param name="ref_file" value="reference.fasta"/>
            </conditional>
            <param name="output_insertions" value="true"/>
            <param name="input_fasta" value="subsampled.fasta" ftype="fasta" />
            <conditional name="translation">
                <param name="translation_select" value="yes"/>
                <param name="genes" value="E,M,N,ORF1a,ORF1b,ORF3a,ORF6,ORF7a,ORF7b,ORF8,ORF9b,ORF10,S"/>
                <param name="genemap" value="genemap.gff3" ftype="gff3"/>
            </conditional>
            <output name="output_fasta" file="output.fasta" sort="true"/>
            <output name="output_csv" file="insertions.csv" sort="true"/>
            <output_collection name="translations" type="list" count="13">
                <element name="E" file="subsampled.gene.E.fasta" ftype="fasta" sort="true"/>
                <element name="M" file="subsampled.gene.M.fasta" ftype="fasta" sort="true"/>
                <element name="N" file="subsampled.gene.N.fasta" ftype="fasta" sort="true"/>
                <element name="ORF1a" file="subsampled.gene.ORF1a.fasta" ftype="fasta" sort="true"/>
                <element name="ORF1b" file="subsampled.gene.ORF1b.fasta" ftype="fasta" sort="true"/>
                <element name="ORF3a" file="subsampled.gene.ORF3a.fasta" ftype="fasta" sort="true"/>
                <element name="ORF6" file="subsampled.gene.ORF6.fasta" ftype="fasta" sort="true"/>
                <element name="ORF7a" file="subsampled.gene.ORF7a.fasta" ftype="fasta" sort="true"/>

            <conditional name="reference_source">
                <param name="reference_source_selector" value="history"/>
                <param name="ref_file" value="reference.fasta"/>
            </conditional>
            <param name="output_insertions" value="false"/>
            <param name="input_fasta" value="subsampled.fasta" ftype="fasta" />
            <conditional name="translation">
                <param name="translation_select" value="no"/>
            </conditional>
            <output name="output_fasta" file="output.fasta" sort="true"/>
        </test>

            <conditional name="reference_source">
                <param name="reference_source_selector" value="cached"/>
                <param name="ref_file" value="reference_fasta"/>
            </conditional>
            <param name="output_insertions" value="false"/>
            <param name="input_fasta" value="subsampled.fasta" ftype="fasta"/>
            <conditional name="translation">
                <param name="translation_select" value="no"/>
            </conditional>
            <output name="output_fasta" file="output.fasta" sort="true"/>
        </test>