<tool id="paralyzer" name="PARalyzer" version="1.5">

    <description>A method to map interaction sites between RNA-binding proteins
      and their targets</description>

    <requirements>
        <!-- conda dependency -->
        <requirement type="package" version="1.5">paralyzer</requirement>
        <requirement type="package" version="324">ucsc-fatotwobit</requirement>
    </requirements>

    <command>
<![CDATA[
    #if $refGenomeSource.genomeSource == "history":
        faToTwoBit '$refGenomeSource.ownFile' ownFile.2bit
        &&
    #end if

    ## execute paralyzer
    ## note the 2nd argument is the memory parameter
    ## the parameter can be override in job_conf.xml e.g.
    ## <env id="_JAVA_OPTIONS">-Xmx12G</env>
    PARalyzer 2G $input_ini

]]>
    </command>
    <inputs>
        <param name="input_sam" type="data"
            format="sam" label="Alignment"
            help="The sam file containing alignment of the read data."/>

        <param name="collapse" type="boolean" truevalue="=COLLAPSED"
          falsevalue="" checked="True"
          label="Incorporate the read copy number"
          help="If reads were collapse before alignment and you want
          to incorporate the read copy number, please select Yes,
          otherwise select No" />

        <!-- Genome source. -->
        <conditional name="refGenomeSource">
            <param name="genomeSource" type="select"
                label="Will you select a reference genome from your
                history or use a built-in genome?"
                help="The version of genome against which the reads were aligned.">
                <option value="2bit" selected="True">
                    Use a built-in genome</option>
                <option value="history">
                    Use a genome from my current history</option>
            </param>
            <when value="2bit">
            <param name="builtin" type="select"
                label="Select a reference genome">
                <options from_data_table="lastz_seqs">
                    <filter type="sort_by" column="1" />
                    <validator type="no_options"
                    message="A built-in reference genome is not available
                    for the build associated with the selected input file"/>
                </options>
            </param>
            </when>
            <when value="history">
                <param name="ownFile" type="data" format="fasta"
                label="Select the reference genome" />
            </when>
        </conditional>

        <conditional name="methods">
          <param name="choice" type="select"
              label="Please select one of the approaches"
              help="">
              <option value="EXTEND_BY_READ">
                EXTEND_BY_READ
              </option>
              <option value="HAFFNER_APPROACH">
                HAFFNER_APPROACH
              </option>
              <option value="ADDITIONAL_NUCLEOTIDES_BEYOND_SIGNAL">
                ADDITIONAL_NUCLEOTIDES_BEYOND_SIGNAL
              </option>
          </param>
          <when value="EXTEND_BY_READ" />
          <when value="HAFFNER_APPROACH" />
          <when value="ADDITIONAL_NUCLEOTIDES_BEYOND_SIGNAL">
            <param name="max_num" type="integer"
                value="0" label="The maximum number"
                help="
                The maximum number of reads to extend beyond the positive
                signal in each direction (default 0) the cluster is defined
                ">
                <validator type="in_range"
                    message="Minimum allowed value is 0" min="0"/>
            </param>
          </when>
        </conditional>

        <conditional name="conversion">
            <param name="selection" type="select"
                label="Conversion"
                help="Please specify characters">
              <option value="default">Use defaults: T to C</option>
              <option value="custom">Specify other characters</option>
            </param>
            <when value="default" />
            <when value="custom">
                <param name="character_from" type="text"
                    size="1" value="T" label="Character from"
                    help="Character representing the modified ribonucleotide
                    (default 'T')">
                </param>
                <param name="character_to" type="text"
                    size="1" value="C" label="Character to"
                    help="Character representing what the modified ribonucleotide
                    is read as by rTranscriptase (default 'C')">
                </param>
            </when>
        </conditional>

        <!-- optional parameters -->
        <conditional name="params">
            <param name="settingsType" type="select"
                label="Required parameters"
                help="You can use the default settings or
                set custom values for any of paralyzer's parameters.">
              <option value="default">Use defaults</option>
              <option value="custom">Full parameter list</option>
            </param>
            <when value="default" />
            <!-- Full/advanced params. -->
            <when value="custom">
                <param name="BANDWIDTH" type="integer"
                    value="3" label="BANDWIDTH"
                    help="Size of bandwidth for KDE calculation (default 3)">
                    <validator type="in_range"
                        message="Minimum allowed value is 1" min="1"/>
                </param>

                <param name="min_read_group" type="integer"
                    value="5" label="MINIMUM_READ_COUNT_PER_GROUP"
                    help="Minimum number of reads required to call a group (default 5)">
                    <validator type="in_range"
                        message="Minimum allowed value is 1" min="1"/>
                </param>

                <param name="min_read_cluster" type="integer"
                    value="2" label="MINIMUM_READ_COUNT_PER_CLUSTER"
                    help="Minimum number of reads required to call a cluster (default 2)">
                    <validator type="in_range"
                        message="Minimum allowed value is 1" min="1"/>
                </param>

                <param name="min_read_kde" type="integer"
                    value="3" label="MINIMUM_READ_COUNT_FOR_KDE"
                    help="Minimum read depth at a location to
                    make a KDE estimate (default 3)">
                    <validator type="in_range"
                        message="Minimum allowed value is 1" min="1"/>
                </param>

                <param name="min_read_cluster_inc" type="integer"
                    value="1" label="MINIMUM_READ_COUNT_FOR_CLUSTER_INCLUSION"
                    help="Minimum read depth for a location to be included
                    within a cluster (default 1)">
                    <validator type="in_range"
                        message="Minimum allowed value is 1" min="1"/>
                </param>

                <param name="min_cluster_size" type="integer"
                    value="11" label="MINIMUM_CLUSTER_SIZE"
                    help="Minimum length required for a cluster
                    to be reported (default 11)">
                    <validator type="in_range"
                        message="Minimum allowed value is 1" min="1"/>
                </param>

                <param name="min_conv_loc_cluster" type="integer"
                    value="2" label="MINIMUM_CONVERSION_LOCATIONS_FOR_CLUSTER"
                    help="Minimum number of separate locations to have a
                    reported conversion for a cluster to be
                    reported (default 2)">
                    <validator type="in_range"
                        message="Minimum allowed value is 1" min="1"/>
                </param>

                <param name="min_conv_cluster" type="integer"
                    value="2" label="MINIMUM_CONVERSION_COUNT_FOR_CLUSTER"
                    help="Minimum number of conversion events within a
                    region to report a cluster (default 2)">
                    <validator type="in_range"
                        message="Minimum allowed value is 1" min="1"/>
                </param>

                <param name="min_read_len" type="integer"
                    value="20" label="MINIMUM_READ_LENGTH"
                    help="Minimum length of mapped read to be included
                    in the analysis (default 20)">
                    <validator type="in_range"
                        message="Minimum allowed value is 1" min="1"/>
                </param>

                <param name="max_num_conv_mis" type="integer"
                    value="1" label="MAXIMUM_NUMBER_OF_NON_CONVERSION_MISMATCHES"
                    help="Maximum number of non-conversion mismatches of
                    a mapped read to be included in the analysis (default 1)">
                    <validator type="in_range"
                        message="Minimum allowed value is 1" min="1"/>
                </param>
            </when>  <!-- full -->
        </conditional>
    </inputs>
    <configfiles>
      <configfile name="input_ini">
## genome source
#if $refGenomeSource.genomeSource == "history":
GENOME_2BIT_FILE=ownFile.2bit
#else
GENOME_2BIT_FILE=$refGenomeSource.builtin.fields.path
#end if

SAM_FILE=$input_sam$collapse

#if $methods.choice == "ADDITIONAL_NUCLEOTIDES_BEYOND_SIGNAL":
ADDITIONAL_NUCLEOTIDES_BEYOND_SIGNAL=$methods.max_num
#else:
$methods.choice
#end if

#if $conversion.selection == "custom":
CONVERSION=$conversion.character_from>$conversion.character_to
#end if

## required parameters
#if $params.settingsType == "custom":
BANDWIDTH=$params.BANDWIDTH
MINIMUM_READ_COUNT_PER_GROUP=$params.min_read_group
MINIMUM_READ_COUNT_PER_CLUSTER=$params.min_read_cluster
MINIMUM_READ_COUNT_FOR_KDE=$params.min_read_kde
MINIMUM_READ_COUNT_FOR_CLUSTER_INCLUSION=$params.min_read_cluster_inc
MINIMUM_CLUSTER_SIZE=$params.min_cluster_size
MINIMUM_CONVERSION_LOCATIONS_FOR_CLUSTER=$params.min_conv_loc_cluster
MINIMUM_CONVERSION_COUNT_FOR_CLUSTER=$params.min_conv_cluster
MINIMUM_READ_LENGTH=$params.min_read_len
MAXIMUM_NUMBER_OF_NON_CONVERSION_MISMATCHES=$params.max_num_conv_mis
#end if

OUTPUT_DISTRIBUTIONS_FILE=out.distribution
OUTPUT_GROUPS_FILE=out.groups
OUTPUT_CLUSTERS_FILE=out.clusters
      </configfile>
    </configfiles>
    <outputs>
        <data name="distribution" format="txt"
        from_work_dir="out.distribution"
        label="${tool.name} on ${on_string}: DISTRIBUTIONS"/>

        <data name="groups" format="txt"
        from_work_dir="out.groups"
        label="${tool.name} on ${on_string}: GROUPS"/>

        <data name="clusters" format="txt"
        from_work_dir="out.clusters"
        label="${tool.name} on ${on_string}: CLUSTERS"/>

        <!--
        <data name="PARalyzer_Utilized" format="sam"
        from_work_dir="out_PARalyzer_Utilized.sam"
        label="${tool.name} on ${on_string}: PARalyzer_Utilized.sam"/>
      -->
    </outputs>
    <tests>
        <test>
            <param name="input_sam" value="input.sam" ftype="sam" />
            <param name="genomeSource" value="history" />
            <param name="ownFile" value="input.fa" />
            <param name="choice" value="EXTEND_BY_READ" />
            <param name="selection" value="custom" />
            <param name="character_from" value="T" />
            <param name="character_to" value="C" />
            <param name="settingsType" value="custom" />
            <param name="$BANDWIDTH" value="3" />
            <param name="min_read_group" value="5" />
            <param name="min_read_cluster" value="2" />
            <param name="min_read_kde" value="3" />
            <param name="min_read_cluster_inc" value="1" />
            <param name="min_cluster_size" value="11" />
            <param name="min_conv_loc_cluster" value="2" />
            <param name="min_conv_cluster" value="2" />
            <param name="min_read_len" value="20" />
            <param name="max_num_conv_mis" value="1" />
            <output name="distribution" file="out.distribution"
            ftype="txt"/>
            <output name="groups" file="out.groups"
            ftype="txt"/>
            <output name="clusters" file="out.clusters"
            ftype="txt"/>
            <!--
            <output name="PARalyzer_Utilized" file="out_PARalyzer_Utilized.sam"
            ftype="sam"/>
            -->
        </test>
    </tests>
    <help>
<![CDATA[
.. class:: infomark

**What it does**

`paralyzer`_ is an algorithm to generate a high resolution
map of interaction sites between RNA-binding proteins and their targets. The
algorithm utilizes the deep sequencing reads generated by `PAR-CLIP`_
(Photoactivatable-Ribonucleoside-Enhanced Crosslinking and
Immunoprecipitation) protocol.The use of photoactivatable nucleotides in the
PAR-CLIP protocol results in more efficient crosslinking between the
RNA-binding protein and its target relative to other CLIP methods; in addition
a nucleotide substitution occurs at the site of crosslinking, providing for
single-nucleotide resolution binding information. PARalyzer utilizes this
nucleotide substition in a kernel density estimate classifier to generate
the high resolution set of Protein-RNA interaction sites.

.. _paralyzer: https://ohlerlab.mdc-berlin.de/software/PARalyzer_85/
.. _PAR-CLIP: http://www.ncbi.nlm.nih.gov/pubmed/20371350

.. class:: infomark

**Approaches**

``EXTEND_BY_READ``: including this line means that the cluster will be extended
beyond the signal to include a region such that it extends to
the end of any read that falls within the cluster and contained
a conversion, or until the minimum read depth
(MINIMUM_READ_COUNT_FOR_CLUSTER_INCLUSION parameter) is no longer met

``HAFNER_APPROACH``: identifies the location with the largest number of conversion
events and extends the cluster up to
( parameter ADDITIONAL_NUCLEOTIDES_BEYOND_SIGNAL)nt
in each direction from that point, or until the minimum
read depth (MINIMUM_READ_COUNT_FOR_CLUSTER_INCLUSION parameter) is no longer met

``ADDITIONAL_NUCLEOTIDES_BEYOND_SIGNAL``: the maximum number of reads to
extend beyond the positive signal in each direction (default 0)
the cluster is defined as the region where the conversion KDE is above
the background KDE and then extended up to #integer#, or until the minimum
read depth (MINIMUM_READ_COUNT_FOR_CLUSTER_INCLUSION parameter) is no longer met

.. class:: infomark

**Outputs**

DISTRIBUTIONS: contains the signal KDE, background KDE, read count & conversion for all locations within each group
  * The data will be in blocks of four lines for each group
  * groups on the reverse strand do not need to be reversed; the values always equal nucleotdies from GroupStart to GroupEnd, regardless of Strand
  * First Column = Chromosome = chromosome on which the group resides
  * Second Column = Strand = orientation in which the group resides
  * Third Column = GroupStart = beginning coordinate on the chromosome of the group
  * Fourth Column = GroupEnd = ending coordinate on the chromosome of the group
  * Fifth Column = GroupID = unique ID for the group
  * Sixth Column = Information = reports if the current line contains the Signal, Background, Conversion Percent, or ReadCount
  * All nucleotides that do not have any possibility of having a conversion event are given a value of -1
  * All Subsequent Columns: the values for each nucleotide from GroupStart until GroupEnd


GROUPS: a comma separated file containing the information about the resulting groups
  * Chromosome = chromosome on which the group resides
  * Strand = orientation in which the group resides
  * GroupStart = beginning coordinate on the chromosome of the group
  * GroupEnd = ending coordinate on the chromosome of the group
  * GroupID = unique ID for the group
  * ReadCount = number of reads within the group

CLUSTERS: a comma separated file containing the information about the resulting clusters
  * Chromosome = chromosome on which the cluster resides
  * Strand = orientation in which the cluster resides
  * ClusterStart = beginning coordinate on the chromosome of the cluster
  * ClusterEnd = ending coordinate on the chromosome of the cluster
  * ClusterID = unique ID for the cluster
  * ClusterSequence = sequence of the cluster
  * ReadCount = number of reads that overlap the cluster by at least 1 nucleotide
  * ModeLocation = coordinate of the location with the highest signal / (signal + background) value
  * ModeScore = score of the highest signal / (signal + background) value
  * ConversionLocationCount = number of unique location where at least 1 conversion occurred
  * ConversionEventCount = total number of conversions that occurred within the cluster
  * NonConversionEventCount = total number of possible conversion events that did not occur

]]></help>
    <citations>
        <citation type="doi">10.1186/gb-2011-12-8-r79</citation>
    </citations>
</tool>