<tool id="teloscope" name="Teloscope" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
    <description>Assembly telomere annotation</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements"/>
    <version_command>teloscope -v</version_command>
    <command detect_errors="exit_code"><![CDATA[
        mkdir -p output &&
        teloscope
            --input-sequence '$input_sequence'
            --output output
            --canonical '$canonical'
            --patterns '$patterns'
            --window '$window'
            --step '$step'
            --threads "\${GALAXY_SLOTS:-2}"
            --terminal-limit '$terminal_limit'
            --max-match-distance '$max_match_distance'
            --max-block-distance '$max_block_distance'
            --min-block-length '$min_block_length'
            --min-block-density '$min_block_density'
            --edit-distance '$edit_distance'
            
            $out_win_repeats
            $out_gc
            $out_entropy
            $out_matches
            $out_its
            $ultra_fast
            $verbose
            > output/${input_sequence.name}.telo.report
    ]]></command>
    <inputs>
        <param argument="--input-sequence" type="data" format="fasta,fasta.gz" label="Input assembly"/>
        <param argument="--canonical" type="text" value="TTAGGG" label="Canonical telomeric pattern">
            <sanitizer>
                <valid initial="string.printable">
                    <remove value=" "/>
                    <remove value="\t"/>
                    <remove value="\r"/>
                    <remove value="\n"/>
                </valid>
            </sanitizer>
            <validator type="regex" message="Canonical must contain only A,C,G,T.">^[ACGTacgt]+$</validator>
        </param>

        <param argument="--patterns" type="text" value="TTAGGG,CCCTAA"
            label="Patterns to explore (comma-separated), IUPAC allowed">
            <validator type="regex"
                    message="Use IUPAC letters ACGTRYSWKMBDHVN; comma-separated.">^[ACGTRYSWKMBDHVNacgtryswkmbdhvn]+(?:,[ACGTRYSWKMBDHVNacgtryswkmbdhvn]+)*$</validator>
        </param>

        <param argument="--window" type="integer" min="100" value="1000" label="Sliding window size"/>
        <param argument="--step" type="integer" min="100" value="500" label="Sliding window step"/>
        <param argument="--terminal-limit" type="integer" min="10000" value="50000" label="Terminal limit (bp) in contigs"/>
        <param argument="--max-match-distance" type="integer" min="0" value="50" label="Maximum distance (bp) for merging matches"/>
        <param argument="--max-block-distance" type="integer" min="0" value="200" label="Maximum block distance for merging"/>
        <param argument="--min-block-length" type="integer" min="0" value="500" label="Minimum block length"/>
        <param argument="--min-block-density" type="float" min="0" max="1" value="0.5" label="Minimum block density (0–1)"/>
        <param argument="--edit-distance" type="integer" min="0" max="2" value="0" label="Edit distance for pattern matching (0–2)"/>

        <param argument="--out-win-repeats" type="boolean" truevalue="--out-win-repeats" falsevalue="" checked="false" label="Window repeat counts"/>
        <param argument="--out-gc" type="boolean" truevalue="--out-gc" falsevalue="" checked="false" label="Window GC"/>
        <param argument="--out-entropy" type="boolean" truevalue="--out-entropy" falsevalue="" checked="false" label="Window Shannon entropy"/>
        <param argument="--out-matches" type="boolean" truevalue="--out-matches" falsevalue="" checked="false" label="Canonical/NonCanonical Matches"/>
        <param argument="--out-its" type="boolean" truevalue="--out-its" falsevalue="" checked="false" label="Interstitial telomeres (ITSs)"/>
        <param argument="--ultra-fast" type="boolean" truevalue="--ultra-fast" falsevalue="" checked="true" label="Ultra-fast mode (terminal regions only)"/>
        <param argument="--verbose" type="boolean" truevalue="--verbose" falsevalue="" checked="false" label="Verbose output"/>
    </inputs>

    <outputs>
        <!-- BASIC OUTFILES -->
        <data name="terminal_telomeres" format="bed" from_work_dir="output/*_terminal_telomeres.bed" label="${tool.name} on ${on_string}: Terminal telomeres"/>
        <data name="telo_report" format="tabular" from_work_dir="output/*.telo.report" label="${tool.name} on ${on_string}: Summary report"/>

        <!-- OPTIONAL OUTFILES -->
        <data name="interstitial_telomeres" format="bed" from_work_dir="output/*_interstitial_telomeres.bed" label="${tool.name} on ${on_string}: Interstitial telomeres">
            <filter>out_its</filter>
        </data>
        <data name="canonical_matches" format="bed" from_work_dir="output/*_canonical_matches.bed" label="${tool.name} on ${on_string}: Canonical matches">
            <filter>out_matches</filter>
        </data>
        <data name="noncanonical_matches" format="bed" from_work_dir="output/*_noncanonical_matches.bed" label="${tool.name} on ${on_string}: Noncanonical matches">
            <filter>out_matches</filter>
        </data>
        <data name="window_metrics" format="bedgraph" from_work_dir="output/*_window_metrics.bedgraph" label="${tool.name} on ${on_string}: Window metrics">
            <filter>out_gc or out_entropy or out_win_repeats</filter>
        </data>
    </outputs>

    <tests>
        <!-- 1) Default (-u) : terminal telomeres + report -->
        <test expect_num_outputs="2">
            <param name="input_sequence" value="bTaeGut7_chr33_mat.fa.gz" ftype="fasta.gz"/>
            <param name="canonical" value="TTAGGG"/>
            <param name="patterns" value="TTAGGG,CCCTAA"/>
            <output name="terminal_telomeres">
                <assert_contents>
                    <!-- at least one BED-like line (match whole line to allow extra cols) -->
                    <has_line_matching expression="^\S+\t\d+\t\d+(?:\t.*)?$"/>
                </assert_contents>
            </output>
            <output name="telo_report">
                <assert_contents>
                    <has_line_matching expression="\+\+\+ Path Summary Report \+\+\+"/>
                    <has_line_matching expression="\+\+\+ Assembly Summary Report \+\+\+"/>
                    <has_line_matching expression="\+\+\+ Telomere Statistics \+\+\+"/>
                    <has_line_matching expression="\+\+\+ Chromosome Telomere Counts\+\+\+"/>
                    <has_line_matching expression="\+\+\+ Chromosome Telomere/Gap Completeness\+\+\+"/>
                </assert_contents>
            </output>
        </test>

        <!-- 2) Genome-wide (-g -e -r -m -i ; disable -u) -->
        <test expect_num_outputs="6">
            <param name="input_sequence" value="bTaeGut7_chr33_mat.fa.gz" ftype="fasta.gz"/>
            <param name="canonical" value="TTAGGG"/>
            <param name="patterns" value="TTAGGG,CCCTAA"/>
            <param name="out_gc" value="true"/>
            <param name="out_entropy" value="true"/>
            <param name="out_win_repeats" value="true"/>
            <param name="out_matches" value="true"/>
            <param name="out_its" value="true"/>
            <param name="ultra_fast" value="false"/>

            <output name="terminal_telomeres">
                <assert_contents>
                    <has_line_matching expression="^\S+\t\d+\t\d+(?:\t.*)?$"/>
                </assert_contents>
            </output>
            <output name="interstitial_telomeres">
                <assert_contents>
                    <has_line_matching expression="^\S+\t\d+\t\d+(?:\t.*)?$"/>
                </assert_contents>
            </output>
            <output name="canonical_matches">
                <assert_contents>
                    <!-- ensure at least one CCCTAA match line -->
                    <has_line_matching expression="^\S+\t\d+\t\d+\tCCCTAA(?:\s|$)"/>
                </assert_contents>
            </output>
            <output name="noncanonical_matches">
                <assert_contents>
                    <!-- expect an empty file -->
                    <has_n_lines n="0"/>
                </assert_contents>
            </output>
            <output name="window_metrics">
                <assert_contents>
                    <has_text text="track type=bedGraph"/>
                    <!-- first data window line -->
                    <has_line_matching expression="^\S+\t0\t1000\t.*"/>
                </assert_contents>
            </output>
            <output name="telo_report">
                <assert_contents>
                    <has_line_matching expression="\+\+\+ Path Summary Report \+\+\+"/>
                    <has_line_matching expression="\+\+\+ Assembly Summary Report \+\+\+"/>
                    <has_line_matching expression="\+\+\+ Telomere Statistics \+\+\+"/>
                    <has_line_matching expression="\+\+\+ Chromosome Telomere Counts\+\+\+"/>
                    <has_line_matching expression="\+\+\+ Chromosome Telomere/Gap Completeness\+\+\+"/>
                </assert_contents>
            </output>
        </test>

        <!-- 3) Edit distance 1: more variants detected -->
        <test expect_num_outputs="2">
            <param name="input_sequence" value="bTaeGut7_chr33_mat.fa.gz" ftype="fasta.gz"/>
            <param name="canonical" value="TTAGGG"/>
            <param name="patterns" value="TTAGGG,CCCTAA"/>
            <param name="edit_distance" value="1"/>
            <output name="terminal_telomeres">
                <assert_contents>
                    <!-- p-arm telomere with extended start due to edit distance -->
                    <has_text text="chr33_mat&#9;442&#9;14354&#9;13912&#9;p&#9;"/>
                    <!-- q-arm telomere -->
                    <has_text text="chr33_mat&#9;4219967&#9;4246337&#9;26370&#9;q&#9;"/>
                </assert_contents>
            </output>
            <output name="telo_report">
                <assert_contents>
                    <has_line_matching expression="\+\+\+ Path Summary Report \+\+\+"/>
                </assert_contents>
            </output>
        </test>

        <!-- 4) Edit distance 2: maximum variants detected -->
        <test expect_num_outputs="2">
            <param name="input_sequence" value="bTaeGut7_chr33_mat.fa.gz" ftype="fasta.gz"/>
            <param name="canonical" value="TTAGGG"/>
            <param name="patterns" value="TTAGGG,CCCTAA"/>
            <param name="edit_distance" value="2"/>
            <output name="terminal_telomeres">
                <assert_contents>
                    <!-- p-arm telomere extends to position 1 with edit distance 2 -->
                    <has_text text="chr33_mat&#9;1&#9;14354&#9;14353&#9;p&#9;"/>
                    <!-- q-arm telomere -->
                    <has_text text="chr33_mat&#9;4219967&#9;4246337&#9;26370&#9;q&#9;"/>
                </assert_contents>
            </output>
            <output name="telo_report">
                <assert_contents>
                    <has_line_matching expression="\+\+\+ Path Summary Report \+\+\+"/>
                </assert_contents>
            </output>
        </test>
    </tests>
    
    <help><![CDATA[
        Description:
        Teloscope is a tool for telomere annotation in genome assemblies. 
        It scans for user-specified telomeric repeat patterns across assembly paths, contigs and windows.
        Teloscope annotates terminal and interstitial telomeres, canonical/noncanonical matches and genome-wide metrics such as GC content, Shannon entropy, and repeat counts.
        It generates a detailed telomere summary report for paths, telomere statistics, and chromosome labels to assess telomere completeness.
        Teloscope can be used for both complete and fragmented assemblies, providing valuable information for genome manual curation and analysis.

        Usage:
        Default (ultra-fast) scans terminal regions and reports terminal telomeres + a summary report.
        * ${input_sequence.name}_terminal_telomeres.bed
        * ${input_sequence.name}.telo.report

        Enabling window/match options (-g -e -r -m -i) performs a genome-wide scan and produces:
        * ${input_sequence.name}_terminal_telomeres.bed
        * ${input_sequence.name}_interstitial_telomeres.bed
        * ${input_sequence.name}_canonical_matches.bed
        * ${input_sequence.name}_noncanonical_matches.bed
        * ${input_sequence.name}_window_metrics.bedgraph
        * ${input_sequence.name}.telo.report

        Key parameters:
        - -c / --canonical: Canonical repeat (default TTAGGG). This is the vertebrate telomeric motif found at chromosome ends that binds to shelterin complex to form a telomere.
        - -p / --patterns: Variant patterns (comma-separated). These are additional telomeric repeat motifs to search for, besides the canonical repeat, it includes other variants that can be part of telomeres.
        - -w / -s: window size / step (defaults 1000/500).
        - -u / --ultra-fast: terminal scan only (default true); disabled automatically when -g/-e/-r/-m/-i are used.
        - -x / --edit-distance: Edit Hamming distance for pattern matching (0–2). Useful for identifying degenerate telomeric repeats (default 0).
    ]]></help>

    <expand macro="citations"/>
</tool>