annotate bowtie2_macros.xml @ 19:97d1923c8c4b draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/bowtie2 commit a579dc125a63383d0a5f826cf5975c0035e8c35a

<macros>
    <!-- Import this at the top of your command block and then
         define rg_auto_name. -->
    <token name="@define_read_group_helpers@">
#def identifier_or_name($input1)
    #if hasattr($input1, 'element_identifier')
        #return $input1.element_identifier
    #else
        #return $input1.name.rstrip('.gz').rstrip('.fastq').rstrip('.fq').rstrip('.bz2')
    #end if
#end def

#def clean(name)
    #import re
    #set $name_clean = re.sub('[^\w\-_\.]', '_', $name)
    #return $name_clean
#end def

#def read_group_name_default($input1, $input2=None)
    #if $input2 is None
        #return $clean($identifier_or_name($input1))
    #else
        #import itertools
        #set $input_name1 = $clean($identifier_or_name($input1))
        #set $input_name2 = $clean($identifier_or_name($input2))
        #set $common_prefix = ''.join([c[0] for c in itertools.takewhile(lambda x: all(x[0] == y for y in x), itertools.izip(*[$input_name1, $input_name2]))])
        #if len($common_prefix) > 3
            #return $common_prefix
        #else
            #return $input_name1
        #end if
    #end if
#end def

#def format_read_group(prefix, value, quote='', arg='')
    #if $value
        #return $arg + $quote + $prefix + $value + $quote
    #else
        #return ''
    #end if
#end def

#def rg_param(name)
    #if $varExists("rg")
        #return $rg.get($name, None)
    #else
        #return $getVar($name, None)
    #end if
#end def

#set $use_rg = True
    </token>
    <!-- preconditions use_rg and rg_auto_name have been
         defined.
    -->
    <token name="@set_read_group_vars@">
#if $use_rg
    #if $rg_param('read_group_id_conditional') is None
        #set $rg_id = $rg_auto_name
    #elif $rg_param('read_group_id_conditional').do_auto_name
        #set $rg_id = $rg_auto_name
    #else
        #set $rg_id = str($rg_param('read_group_id_conditional').ID)
    #end if

    #if $rg_param('read_group_sm_conditional') is None
        #set $rg_sm = ''
    #elif $rg_param('read_group_sm_conditional').do_auto_name
        #set $rg_sm = $rg_auto_name
    #else
        #set $rg_sm = str($rg_param('read_group_sm_conditional').SM)
    #end if

    #if $rg_param('PL')
        #set $rg_pl = str($rg_param('PL'))
    #else
        #set $rg_pl = ''
    #end if

    #if $rg_param('read_group_lb_conditional') is None
        #set $rg_lb = ''
    #elif $rg_param('read_group_lb_conditional').do_auto_name
        #set $rg_lb = $rg_auto_name
    #else
        #set $rg_lb = str($rg_param('read_group_lb_conditional').LB)
    #end if

    #if $rg_param('CN')
        #set $rg_cn = str($rg_param('CN'))
    #else
        #set $rg_cn = ''
    #end if

    #if $rg_param("DS")
        #set $rg_ds = str($rg_param("DS"))
    #else
        #set $rg_ds = ''
    #end if

    #if $rg_param("DT")
        #set $rg_dt = str($rg_param("DT"))
    #else
        #set $rg_dt = ''
    #end if

    #if $rg_param("FO")
        #set $rg_fo = str($rg_param("FO"))
    #else
        #set $rg_fo = ''
    #end if

    #if $rg_param("KS")
        #set $rg_ks = str($rg_param("KS"))
    #else
        #set $rg_ks = ''
    #end if

    #if $rg_param("PG")
        #set $rg_pg = str($rg_param("PG"))
    #else
        #set $rg_pg = ''
    #end if

    #if $rg_param("PI") != None
        #set $rg_pi = str($rg_param("PI"))
    #else
        #set $rg_pi = ''
    #end if

    #if $rg_param("PU")
        #set $rg_pu = str($rg_param("PU"))
    #else
        #set $rg_pu = ''
    #end if
#end if
    </token>
    <token name="@set_use_rg_var@">
#set $use_rg = str($rg.rg_selector) != "do_not_set"
    </token>
    <xml name="read_group_auto_name_conditional">
        <param name="do_auto_name" type="boolean" label="Auto-assign" help="Use dataset name or collection information to automatically assign this value" checked="false" />
        <when value="true">
        </when>
        <when value="false">
            <yield />
        </when>
    </xml>
    <xml name="read_group_id_param">
        <param name="ID" type="text" value="" label="Read group identifier (ID)" help="This value must be unique among multiple samples in your experiment" optional="false">
            <validator type="empty_field" />
        </param>
    </xml>
    <xml name="read_group_id_conditional">
        <conditional name="read_group_id_conditional">
            <expand macro="read_group_auto_name_conditional">
                <expand macro="read_group_id_param" />
            </expand>
        </conditional>
    </xml>
    <xml name="read_group_sm_param">
        <param name="SM" type="text" value="" label="Read group sample name (SM)" help="This value should be descriptive. Use pool name where a pool is being sequenced" />
    </xml>
    <xml name="read_group_sm_conditional">
        <conditional name="read_group_sm_conditional">
            <expand macro="read_group_auto_name_conditional">
                <expand macro="read_group_sm_param" />
            </expand>
        </conditional>
    </xml>
    <!-- Above SM param is optional (for SAM/BAM spec, this is required
         as per Picard.
    -->
    <xml name="read_group_sm_param_required">
        <param name="SM" type="text" value="" label="Read group sample name (SM)" optional="false" help="This value should be descriptive. Use pool name where a pool is being sequenced">
            <validator type="empty_field" />
        </param>
    </xml>
    <xml name="read_group_sm_required_conditional">
        <conditional name="read_group_sm_conditional">
            <expand macro="read_group_auto_name_conditional">
                <expand macro="read_group_sm_param" />
            </expand>
        </conditional>
    </xml>
    <xml name="read_group_pl_param">
        <param name="PL" type="select" label="Platform/technology used to produce the reads (PL)">
            <option value="CAPILLARY">CAPILLARY</option>
            <option value="LS454">LS454</option>
            <option selected="True" value="ILLUMINA">ILLUMINA</option>
            <option value="SOLID">SOLID</option>
            <option value="HELICOS">HELICOS</option>
            <option value="IONTORRENT">IONTORRENT</option>
            <option value="PACBIO">PACBIO</option>
        </param>
    </xml>
    <xml name="read_group_lb_param">
        <param name="LB" type="text" label="Library name (LB)" optional="true" />
    </xml>
    <xml name="read_group_lb_conditional">
        <conditional name="read_group_lb_conditional">
            <expand macro="read_group_auto_name_conditional">
                <expand macro="read_group_lb_param" />
            </expand>
        </conditional>
    </xml>
    <xml name="read_group_lb_required_param">
        <param name="LB" type="text" label="Library name (LB)" optional="false">
            <validator type="empty_field" />
        </param>
    </xml>
    <xml name="read_group_lb_required_conditional">
        <conditional name="read_group_lb_conditional">
            <expand macro="read_group_auto_name_conditional">
                <expand macro="read_group_lb_required_param" />
            </expand>
        </conditional>
    </xml>
    <xml name="read_group_cn_param">
        <param name="CN" type="text" label="Sequencing center that produced the read (CN)" />
    </xml>
    <xml name="read_group_ds_param">
        <param name="DS" type="text" label="Description (DS)" />
    </xml>
    <xml name="read_group_dt_param">
        <param name="DT" type="text" label="Date that run was produced (DT)" help="ISO8601 format date or date/time, like YYYY-MM-DD" />
    </xml>
    <xml name="read_group_fo_param">
        <param name="FO" type="text" optional="true" label="Flow order (FO)" help="The array of nucleotide bases that correspond to the nucleotides used for each flow of each read. Multi-base flows are encoded in IUPAC format, and non-nucleotide flows by various other characters. Format: /\*|[ACMGRSVTWYHKDBN]+/">
          <validator type="regex" message="Invalid flow order">\*|[ACMGRSVTWYHKDBN]+$</validator>
        </param>
    </xml>
    <xml name="read_group_ks_param">
        <param name="KS" type="text" label="The array of nucleotide bases that correspond to the key sequence of each read (KS)" />
    </xml>
    <xml name="read_group_pg_param">
        <param name="PG" type="text" label="Programs used for processing the read group (PG)" />
    </xml>
    <xml name="read_group_pi_param">
        <param name="PI" type="integer" optional="true" label="Predicted median insert size (PI)" />
    </xml>
    <xml name="read_group_pu_param">
        <param name="PU" type="text" label="Platform unit (PU)" help="Unique identifier (e.g. flowcell-barcode.lane for Illumina or slide for SOLiD)" optional="True" />
    </xml>
    <xml name="read_group_pu_required_param">
        <param name="PU" type="text" label="Platform unit (PU)" help="Unique identifier (e.g. flowcell-barcode.lane for Illumina or slide for SOLiD)" optional="False" />
    </xml>
    <!-- Only ID is required - all groups available -->
    <xml name="read_group_inputs_spec">
        <expand macro="read_group_id_conditional" />
        <expand macro="read_group_sm_conditional" />
        <expand macro="read_group_pl_param" />
        <expand macro="read_group_lb_conditional" />
        <expand macro="read_group_cn_param" />
        <expand macro="read_group_ds_param" />
        <expand macro="read_group_dt_param" />
        <expand macro="read_group_fo_param" />
        <expand macro="read_group_ks_param" />
        <expand macro="read_group_pg_param" />
        <expand macro="read_group_pi_param" />
        <expand macro="read_group_pu_param" />
    </xml>
    <!-- ID, SM, LB, PU, PL all required - not ks, pg, or fo params. -->
    <xml name="read_group_inputs_picard">
        <expand macro="read_group_id_conditional" />
        <expand macro="read_group_sm_required_conditional" />
        <expand macro="read_group_lb_required_conditional" />
        <expand macro="read_group_pl_param" />
        <expand macro="read_group_pu_required_param" />
        <expand macro="read_group_cn_param" />
        <expand macro="read_group_ds_param" />
        <expand macro="read_group_pi_param" />
        <expand macro="read_group_dt_param" />
    </xml>
    <xml name="read_group_conditional">
        <conditional name="rg">
            <param name="rg_selector" type="select" label="Set read groups information?" help="Specifying read group information can greatly simplify your downstream analyses by allowing combining multiple datasets.">
                <option value="set">Set read groups (SAM/BAM specification)</option>
                <option value="set_picard">Set read groups (Picard style)</option>
                <option value="set_id_auto">Automatically assign ID using name of history item(s)</option>
                <option value="do_not_set" selected="True">Do not set</option>
            </param>
            <when value="set_picard">
                <expand macro="read_group_inputs_picard" />
            </when>
            <when value="set">
                <expand macro="read_group_inputs_spec" />
            </when>
            <when value="set_id_auto">
            </when>
            <when value="do_not_set">
            </when>
        </conditional>
    </xml>
    <xml name="paired_end_options">
        <conditional name="paired_options">
            <param name="paired_options_selector" type="select" label="Do you want to set paired-end options?" help="See &quot;Alignment Options&quot; section of Help below for information">
                <option value="no" selected="True">No</option>
                <option value="yes">Yes</option>
            </param>
            <when value="yes">
                <param argument="-I" type="integer" value="0" min="0" label="Set the minimum fragment length for valid paired-end alignments"
                       help="E.g. if `-I 60` is specified and a paired-end alignment consists of two 20-bp alignments in the appropriate orientation with a 20-bp gap between them, that alignment is considered valid (as long as `-X` is also satisfied).  A 19-bp gap would not be valid in that case.  If trimming options `-3` or `-5` are also used, the `-I` constraint is applied with respect to the untrimmed mates. The larger the difference between `-I` and `-X`, the slower Bowtie 2 will run.  This is because larger differences bewteen `-I` and `-X` require that Bowtie 2 scan a larger window to determine if a concordant alignment exists. For typical fragment length ranges (200 to 400 nucleotides), Bowtie 2 is very efficient. Default=0"/>
                <param argument="-X" type="integer" value="500" min="0" label="Set the maximum fragment length for valid paired-end alignments"
                       help="E.g. if `-X 100` is specified and a paired-end alignment consists of two 20-bp alignments in the proper orientation with a 60-bp gap between them, that alignment is considered valid (as long as `-I` is also satisfied).  A 61-bp gap would not be valid in that case.  If trimming options `-3` or `-5` are also used, the `-X` constraint is applied with respect to the untrimmed mates, not the trimmed mates; Default=500"/>
                <param name="fr_rf_ff" type="select" display="radio" label="Select the upstream/downstream mate orientations for a valid paired-end alignment against the forward reference strand"
                       help="--fr, --rf, or --ff; E.g., if `--fr` is specified and there is a candidate paired-end alignment where mate 1 appears upstream of the reverse complement of mate 2 and the fragment length constraints (`-I` and `-X`) are met, that alignment is valid.  Also, if mate 2 appears upstream of the reverse complement of mate 1 and all other constraints are met, that too is valid. `--rf` likewise requires that an upstream mate1 be reverse-complemented and a downstream mate2 be forward-oriented. `--ff` requires both an upstream mate 1 and a downstream mate 2 to be forward-oriented; Default=--fr (appropriate for Illumina's Paired-end Sequencing Assay)">
                    <option value="--fr" selected="True">--fr</option>
                    <option value="--rf">--rf</option>
                    <option value="--ff">--ff</option>
                </param>
                <param argument="--no-mixed" name="no_mixed" type="boolean" truevalue="--no-mixed" falsevalue="" checked="False" label="Disable no-mixed behavior" help="--no-mixed; By default, when `bowtie2` cannot find a concordant or discordant alignment for a pair, it then tries to find alignments for the individual mates; default=False"/>
                <param argument="--no-discordant" name="no_discordant" type="boolean" truevalue="--no-discordant" falsevalue="" checked="False" label="Disable no-discordant behavior" help="--no-discordant; By default, `bowtie2` looks for discordant alignments if it cannot find any concordant alignments. A discordant alignment is an alignment where both mates align uniquely, but that does not satisfy the paired-end constraints (`--fr`/`--rf`/`--ff`, `-I`, `-X`); default=False"/>
                <param argument="--dovetail" name="dovetail" type="boolean" truevalue="--dovetail" falsevalue="" checked="False" label="Allow mate dovetailing" help="--dovetail; If the mates `dovetail`, that is if one mate alignment extends past the beginning of the other such that the wrong mate begins upstream, consider that to be concordant. Default=False"/>
                <param argument="--no-contain" name="no_contain" type="boolean" truevalue="--no-contain" falsevalue="" checked="False" label="Disallow one mate alignment to contain another" help="--no-contain; If one mate alignment contains the other, consider that to be non-concordant. Default=False"/>
                <param argument="--no-overlap" name="no_overlap" type="boolean" truevalue="--no-overlap" falsevalue="" checked="False" label="Disallow mate alignments to overlap" help="--no-overlap; If one mate alignment overlaps the other at all, consider that to be non-concordant. Default=False"/>
            </when>
            <when value="no">
                <!-- do nothing -->
            </when>
        </conditional>
    </xml>
    <xml name="align_unalign">
        <param name="unaligned_file" type="boolean" truevalue="true" falsevalue="false" checked="False" label="Write unaligned reads (in fastq format) to separate file(s)" help="--un/--un-conc (possibly with -gz or -bz2); This triggers --un parameter for single reads and --un-conc for paired reads" />
        <param name="aligned_file" type="boolean" truevalue="true" falsevalue="false" checked="False" label="Write aligned reads (in fastq format) to separate file(s)" help="--al/--al-conc (possibly with -gz or -bz2); This triggers --al parameter for single reads and --al-conc for paired reads" />
    </xml>
</macros>