<tool id="tetyper" name="TETyper" version="@TOOL_VERSION@+galaxy0">
    <description>Transposable Element Typer</description>
    <macros>
        <token name="@TOOL_VERSION@">1.1</token>
    </macros>
    <requirements>
        <requirement type="package" version="@TOOL_VERSION@">tetyper</requirement>
    </requirements>
    <command detect_errors="exit_code">
        <![CDATA[
        TETyper.py
            --threads \${GALAXY_SLOTS:-1}
            #if $collection_paired.selector == "paired"
                --fq1 '${collection_paired.forward_input}' --fq2 '${collection_paired.reverse_input}'
            #elif $collection_paired.selector == "collection":
                --fq1 '${collection_paired.input_pair.forward}' --fq2 '${collection_paired.input_pair.reverse}'
            #end if
            --ref '${reference}'
            --flank_len '${flank_length}'
            --min_reads '${min_reads}'
            --min_each_strand '${min_each_strand}'
            --min_mapped_len '${min_mapped_len}'
            --min_qual '${min_qual}'
            #if $snp_profiles
              --snp_profiles '${snp_profiles}'
            #end if
            #if $struct_profiles
              --struct_profiles '${struct_profiles}'
            #end if
            --outprefix output
        ]]>
    </command>
    <inputs>
        <conditional name="collection_paired">
            <param name="selector" type="select" label="Collection or paired reads" >
                <option value="collection">Collection</option>
                <option value="paired" selected="True">Paired</option>
            </param>
            <when value="collection">
                <param format="fastq,fastq.gz" name="input_pair" type="data_collection" collection_type="paired" label="Collection of paired reads" help="FASTQ datasets" />
            </when>
            <when value="paired">
                <param format="fastq,fastq.gz" name="forward_input" type="data" label="Forward strand" help="FASTQ dataset"/>
                <param format="fastq,fastq.gz" name="reverse_input" type="data" label="Reverse strand" help="FASTQ dataset"/>
            </when>
        </conditional>
        <param name="reference" type="data" format="fasta" label="Transposable Element Reference"/>
        <param name="flank_length" type="integer" min="4" value="5" max="16" label="Flank Length" help="Length of flanking region to extract."/>
        <param name="min_reads" type="integer" min="1" value="10" max="100" label="Minimum Reads" help="Minimum read number for including a specific flanking sequence."/>
        <param name="min_each_strand" type="integer" min="1" value="1" max="100" label="Minimum Reads (each strand)" help="Minimum read number for each strand for including a specific flanking sequence."/>
        <param name="min_mapped_len" type="integer" min="8" value="30" max="100" label="Minimum Mapped Length" help="Minimum length of mapping for a read to be used in determining flanking sequences. Higher values are more robust to spurious mapping. Lower values will recover more reads."/>
        <param name="min_qual" type="integer" min="0" value="10" max="100" label="Minimum quality" help="Minimum quality value across extracted flanking sequence." />
        <param name="snp_profiles" type="data" format="text" label="SNP Profiles" optional="true" />
        <param name="struct_profiles" type="data" format="text" label="Structural Variant Profiles" optional="true" />
        <param name="include_log" type="boolean" label="Include log in output"/>
    </inputs>
    <outputs>
        <data name="summary" format="tabular" from_work_dir="output_summary.txt" label="${tool.name} on ${on_string}: summary"/>
        <data name="snps" format="vcf" from_work_dir="output.vcf" label="${tool.name} on ${on_string}: SNPs"/>
        <data name="blast" format="tabular" from_work_dir="output_blast.txt" label="${tool.name} on ${on_string}: BLAST alignment"/>
        <data name="alignment" format="bam" from_work_dir="output.bam" label="${tool.name} on ${on_string}: BWA alignment"/>
        <data name="log" format="text" from_work_dir="output.log" label="${tool.name} on ${on_string}: log">
            <filter>include_log</filter>
        </data>
    </outputs>
    <tests>
        <test>
            <param name="reference" value="Tn4401b-1.fasta" />
            <conditional name="collection_paired">
                <param name="selector" value="paired" />
                <param name="forward_input" value="ERR1911133_Tn4401b-1_mapped_subsampled_1.fastq" />
                <param name="reverse_input" value="ERR1911133_Tn4401b-1_mapped_subsampled_2.fastq" />
            </conditional>
            <output name="summary" file="output_summary_1.txt" />
        </test>
        <test>
            <param name="reference" value="Tn4401b-1.fasta" />
            <conditional name="collection_paired">
                <param name="selector" value="paired" />
                <param name="forward_input" value="ERR1911133_Tn4401b-1_mapped_subsampled_1.fastq" />
                <param name="reverse_input" value="ERR1911133_Tn4401b-1_mapped_subsampled_2.fastq" />
            </conditional>
            <param name="snp_profiles" value="Tn4401b_snp_profiles.txt" />
            <param name="struct_profiles" value="Tn4401b_struct_profiles.txt" />
            <output name="summary" file="output_summary_2.txt" />
        </test>
    </tests>
    <help>
      <![CDATA[
**What it does**

TETyper is designed for typing a specific transposable element (TE) of interest from paired-end sequencing data. It determines single nucleotide variants (SNVs) and deletions within the TE, as well as flanking sequences surrounding the TE.

**Input**

**SNP Profiles**: A tab-delimited file with the following columns:

1. Profile ID
2. Homozygous SNPs
3. Heterozygous SNPs

SNPs are represented in the format [REF][POSITION][ALT], and separated by pipe (`|`) characters. SNPs should be ordered by position. Valid alt-bases for heterozygous SNPs are: `M,R,W,S,Y,K`

For example:

::

  1	none	none
  2	C8015T	none
  3	C8015T|T9621C	none
  4	T7199A|C8015T|T9621C	none
  6	C7509G|T7917G	none
  N2	none	C8015Y
  N4	none	A5178R
  N5	none	C8015Y|T9663Y

**Structural Variant Profiles**: A tab-delimited file with the following columns:

1. Profile ID
2. Structural Variants

Structural Variants are represented in the format [START-POSITION]-[END-POSITION], and separated by pipe (`|`) characters.

For example:

::

  Tn4401b	none
  Tn4401a	7020-7118
  Tn4401h	6919-7106
  Tn4401_truncC	1-7127|9198-10006

**Output**

TETyper will produce a tab-seperated output file with the following outputs:

+--------------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
|  Column                  | Description                                                                                                                                                                                                                                      |
+==========================+==================================================================================================================================================================================================================================================+
|  Deletions               | A list of sequence ranges corresponding to regions of the reference classified as deletions for this sample, or "none" for no deletions.                                                                                                         |
+--------------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
|  Structural_variant      | If --struct_profiles is specified and the pattern of deletions above corresponds to one of these profiles, then the profile name is given, otherwise "unknown".                                                                                  |
+--------------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
|  SNPs_homozygous         | A list of homozygous SNPs identified, or "none".                                                                                                                                                                                                 |
+--------------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
|  SNPs_heterozygous       | A list of heterozygous SNPs identified, or "none".                                                                                                                                                                                               |
+--------------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
|  Heterozygous_SNP_counts | For each heterozygous SNP, the number of reads supporting the reference and alternative calls, or "none" if there are no heterozygous SNPs.                                                                                                      |
+--------------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
|  SNP_variant             | If --snp_profiles is specified and the pattern of homozygous and heterozygous SNPs corresponds to one of these profiles, then the profile name is given. Otherwise "unknown".                                                                    |
+--------------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
|  Combined_variant        | Single name combining Structural_variant and SNP_variant, separated by "-".                                                                                                                                                                      |
+--------------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
|  Left_flanks             | A list of distinct sequences passing quality filters that flank the start position of the reference.                                                                                                                                             |
+--------------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
|  Right_flanks            | A list of distinct sequences passing quality filters that flank the end position of the reference.                                                                                                                                               |
+--------------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
|  Left_flank_counts       | The number of high quality reads supporting each of the left flanking sequences.                                                                                                                                                                 |
+--------------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
|  Right_flank_counts      | The number of high quality reads supporting each of the right flanking sequences.                                                                                                                                                                |
+--------------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
|  X_Y_presence            | If --show_region is specified as --show_region X-Y, this column shows 1 if the entirety of that region is classified as present (i.e. no overlap with deleted regions), or 0 otherwise. If --show_region is unspecified, this column is omitted. |
+--------------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+

      ]]>
    </help>
    <citations>
        <citation type="doi">10.1099/mgen.0.000232</citation>
    </citations>
</tool>