annotate gmql_operators_join.xml @ 0:a80c93182db3 draft default tip

planemo upload for repository https://github.com/lu-brn/gmql-galaxy commit 953ee36ceda5814dc9baa03427bc0eb4ee2e93bd-dirty

<macros>
    <import>gmql_queries_macros.xml</import>
    <xml name="join">
        <expand macro="input_var" name="input_var_anchor" label="Anchor Dataset" optional="false" />
        <expand macro="input_var" name="input_var_experiment" label="Experiment Dataset" optional="false" />
        <expand macro="output_var" />
        <section name="conditions_section" title="Join Conditions" expanded="true">
            <conditional name="conditions">
                <param name="c_type" type="select" label="Type of conditions" display="radio">
                    <option value="distance">Only on genomic distances</option>
                    <option value="attributes">Only on region attributes</option>
                    <option value="both">Both types</option>
                </param>
                <when value="distance">
                   <expand macro="genomic_predicate" />
                    <expand macro="output_opt"
                            help="Declare which region is given in output for each input pair of anchor and experiment
                           regions satisfying the equi predicate and the genomic predicate. The default output option is CAT.">
                        <option value="CAT" selected="true">CAT: Outputs the concatenation between regions that satisfy predicates</option>
                        <option value="INT">INT: Outputs overlapping part (intersection) that satisfy predicates</option>
                    </expand>
                </when>
                <when value="attributes">
                   <expand macro="equi_predicate" />
                    <expand macro="output_opt"
                           help="Declare which region is given in output for each input pair of anchor and experiment
                           regions satisfying the equi predicate and the genomic predicate. Some options are not allowed
                           with conditions only on the attributes (INT and CAT)."/>
                </when>
                <when value="both">
                    <expand macro="genomic_predicate"/>
                    <expand macro="equi_predicate"/>
                    <expand macro="output_opt"
                            help="Declare which region is given in output for each input pair of anchor and experiment
                           regions satisfying the equi predicate and the genomic predicate. The default output option is CAT.">
                        <option value="CAT" selected="true">CAT: Outputs the concatenation between regions that satisfy predicates </option>
                        <option value="INT">INT: Outputs overlapping part (intersection) that satisfy predicates</option>
                    </expand>
                </when>
            </conditional>
        </section>
        <section name="joinby" title="Condition on Samples Metadata" expanded="false"
                 help="This is used to select sample pairs satisfying certain conditions on their metadata
                 (e.g., regarding the same cell line or antibody target); it is expressed as a list of metadata
                 attributes whose names and values must match between samples in the Anchor dataset and the
                 Experiment Dataset in order for such samples to verify the condition and be considered for the join.">
            <repeat name="joinby_clause" title="Attributes to match" min="0" default="0">
                <expand macro="metajoin_attribute" name="j_att" optional="true">
                    <expand macro="metajoin_options"/>
                </expand>
            </repeat>
        </section>
        <expand macro="materialize_stm" />
    </xml>
    <xml name="equi_predicate">
        <repeat name="region_attributes" title="Add Region Attribute"
                min="1" default="1"
                help="Region attributes which must exist in anchor dataset region for the experiment region
                to be considered" >
            <param name="attribute" type="text" label="Region Attribute">
                <expand macro="text_val" />
            </param>
        </repeat>
    </xml>
    <xml name="genomic_predicate">
        <repeat name="distance_conditions" title="Conditions over genomic distances between samples regions"
                min="1" max="4" default="1"
                help="Genometric predicates are fundamental for JOIN commands: they allow the expression of a variety
                of distal conditions all based on the concept of genomic distance. The genomic distance is defined as
                the number of base pairs (i.e., nucleotides) between the closest opposite ends of two regions on to the
                same DNA strand, or when at least one of the two regions has unknown strand, and belonging to the same
                chromosome (it is not defined for regions on different chromosomes or different DNA strands).
                Further details in the GMQL online guide or in the above help section.">
            <conditional name="type_dc">
                <param label="Type" name="type_dc_value" type="select" display="radio">
                    <option value="dist">Distance</option>
                    <option value="stream">Direction</option>
                </param>
                <when value="dist">
                    <param name="dc" label="Condition" type="select"
                           help="The overall condition must contain at least one and at most four distal conditions.
                           There must be at least one less-equal distance or one less distance,
                           or a minimum distance clause (which can then be combined with other clauses) in order to
                           be well-formed and compile.">
                        <option value="MD">Minimum distance</option>
                        <option value="DL">Less distance</option>
                        <option value="DLE">Less or equal distance</option>
                        <option value="DG">Greater distance</option>
                        <option value="DGE">Greater or equal distance</option>
                    </param>
                    <param name="n" label="Value" type="integer" value="0"
                           help="In the GMQL framework, overlapping regions have negative distance while adjacent
                           regions have distance equal to 0"/>
                </when>
                <when value="stream">
                    <param name="ds" label="Direction" display="radio" type="select"
                           help="This requires that the rest of the predicate holds only on the upstream (downstream)
                           genome with respect to the anchor region." >
                        <option value="UP">Upstream</option>
                        <option value="DOWN">Downstream</option>
                    </param>
                </when>
            </conditional>
        </repeat>
    </xml>
    <xml name="output_opt" token_help="@HELP@">
        <param name="output_opt" type="select" label="Output options"
               help="@HELP@" >
            <option value="LEFT">LEFT: Outputs only anchor samples regions</option>
            <option value="LEFT_DISTINCT">LEFT_DISTINCT: Outputs only anchor regions and eliminate duplicates</option>
            <option value="RIGHT">RIGHT: Outpus only experiment samples regions</option>
            <option value="RIGHT_DISTINCT">RIGHT_DISTINCT: Outputs only experiment samples regions and eliminate duplicates</option>
            <option value="BOTH">BOTH: Outputs anchor samples regions, but it adds attributes of the relative experiments samples regions</option>
            <yield />
        </param>
    </xml>
</macros>