diff dotPrep.xml @ 0:732267cab191 draft default tip

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/dotprep commit 6db87bb19217d256b13cd66810043b667d1c7638
author bgruening
date Wed, 03 Dec 2025 16:17:07 +0000
parents
children
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/dotPrep.xml	Wed Dec 03 16:17:07 2025 +0000
@@ -0,0 +1,87 @@
+<tool id="dotprep" name="dotPrep" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@" license="MIT">
+    <description>Apply unique anchor filtering and prepare Dot coordinates</description>
+        <macros>
+        <token name="@TOOL_VERSION@">1.0</token>
+        <token name="@VERSION_SUFFIX@">0</token>
+        <token name="@PROFILE@">25.0</token>
+    </macros>
+    <command detect_errors="exit_code"><![CDATA[
+        ln -s '$delta' input.delta.gz &&
+        python3 '$__tool_directory__/dotPrep.py'
+            --delta input.delta.gz
+            --out result
+            --unique-length $unique_length
+            --overview $overview
+    ]]></command>
+    <inputs>
+        <param name="delta" type="data" format="tabular" label="Delta file" help="Input delta file from alignment tool (e.g., MUMmer)"/>
+        <param name="unique_length" type="integer" value="10000" min="0" label="Unique sequence length threshold" help="The total length of unique sequence an alignment must have on the query side to be retained"/>
+        <param name="overview" type="integer" value="1000" min="1" label="Number of alignments for overview" help="The number of alignments to include in the coords.idx output file for Dot overview"/>
+    </inputs>
+    <outputs>
+        <data name="result" format="tabular" label="${tool.name} on ${on_string}: Output delta file" from_work_dir="result.uniqueAnchorFiltered*"/>
+        <data name="coords" format="tabular" label="${tool.name} on ${on_string}: filtered coords" from_work_dir="result.coords"/>
+        <data name="coords_idx" format="tabular" label="${tool.name} on ${on_string}: coords.idx" from_work_dir="result.coords.idx"/>
+    </outputs>
+    <tests>
+        <test expect_num_outputs="3">
+            <param name="delta" location="https://zenodo.org/records/17592326/files/input.res.uniqueAnchorFiltered_l10000.delta.gz"/>
+            <param name="unique_length" value="10000"/>
+            <param name="overview" value="1000"/>
+            <output name="result" location="https://zenodo.org/records/17592326/files/test_output.delta.gz" compare="sim_size"/>
+            <output name="coords" ftype="tabular">
+                <assert_contents>
+                    <has_n_lines n="21848"/>
+                    <has_line line="28999,29316,9912,10233,h1tg000718l"/>
+                    <has_line line="32087,32264,16943,17122,h1tg000718l"/>
+                    <has_line line="41139,41490,26157,26508,h1tg000718l"/>
+                </assert_contents>
+            </output>
+            <output name="coords_idx" ftype="tabular">
+                <assert_contents>
+                    <has_n_lines n="1840"/>
+                </assert_contents>
+            </output>
+        </test>
+    </tests>
+    <help><![CDATA[
+**What it does**
+
+This tool takes a delta file from genome alignment tools (such as MUMmer's nucmer), applies unique anchor filtering, and prepares coordinate input files for visualization with Dot.
+
+**Inputs**
+
+- **Delta file**: Output from alignment programs like MUMmer's nucmer
+- **Unique sequence length threshold**: Minimum total length of unique sequence an alignment must have on the query side to be retained (Default: 10000 bp)
+- **Number of alignments for overview**: Number of top alignments to include in the coords.idx file for Dot overview visualization (Default: 1000)
+
+**Outputs**
+
+- **Filtered coords file**: Coordinate file with unique anchor filtering applied
+- **coords.idx file**: Index file containing top alignments for Dot visualization overview
+
+**About Unique Anchor Filtering**
+
+The unique anchor filtering strategy identifies high-quality alignments by requiring a minimum amount of unique sequence. This helps filter out repetitive regions and focus on reliable anchoring points between sequences.
+
+**Aknowledgements**
+
+dotPrep is part of Assemblytics, developed by Maria Nattestad. For more information, please visit the [Assemblytics GitHub repository](https://github.com/MariaNattestad/dot/tree/master)
+
+    ]]></help>
+<citations>
+        <citation type="bibtex">
+            @misc{githubdotprep,
+            author = {MariaNattestad},
+            year = {2023},
+            title = {dotPrep},
+            publisher = {GitHub},
+            journal = {GitHub repository},
+            url = {https://github.com/MariaNattestad/dot/blob/master/DotPrep.py},
+        }</citation>
+    </citations>
+    <creator>
+        <person givenName="Saim" familyName="Momin" url="https://github.com/SaimMomin12" identifier="https://orcid.org/0009-0003-9935-828X"/>
+        <organization name="Galaxy Europe" url="https://galaxyproject.org/eu/"/>
+    </creator>
+</tool>
\ No newline at end of file