Add HyPhy CLN tool wrapper

tools/hyphy/hyphy_cln.xml

@@ -0,0 +1,83 @@
+<tool id="hyphy_cln" name="HyPhy-CLN" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
+    <description>Clean and normalize alignment</description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="bio_tools"/>
+    <expand macro="requirements"/>
+    <command detect_errors="exit_code"><![CDATA[
+        @SYMLINK_FILES_NO_TREE@
+        @HYPHYMP@ cln
+            --alignment input.${input_file.extension}
+            --code '$gencodeid'
+            --filtering-method '$filtering_method'
+            --output '$output_file'
+    ]]></command>
+    <inputs>
+        <param name="input_file" type="data" format="fasta,fasta.gz,nex,nexus,phylip,mega" label="Input alignment file" help="An in-frame codon alignment in one of the formats supported by HyPhy (FASTA, NEXUS, PHYLIP, or MEGA)" />
+        <expand macro="gencode"/>
+        <param argument="--filtering-method" type="select" label="Filter duplicates/gaps" help="How to filter duplicates and gaps">
+            <option value="No/No" selected="true">Keep all sequences and sites</option>
+            <option value="No/Yes">Keep all sequences, filter sites with nothing but gaps</option>
+            <option value="Yes/No">Filter duplicate sequences but keep all sites</option>
+            <option value="Yes/Yes">Filter duplicate sequences and sites with nothing but gaps</option>
+            <option value="Disallow stops">Filter duplicate sequences and all sequences that have stop codons</option>
+        </param>
+    </inputs>
+    <outputs>
+        <data name="output_file" format="fasta" label="${tool.name} on ${on_string}: Cleaned alignment" />
+    </outputs>
+    <tests>
+        <test>
+            <param name="input_file" value="conv-in1.fa"/>
+            <param name="filtering_method" value="No/No"/>
+            <output name="output_file">
+                <assert_contents>
+                    <has_text text=">epi_isl_1041406_hCoV_19_USA_NY_PRL_2021_02_08_05H12_2021" />
+                </assert_contents>
+            </output>
+        </test>
+        <test>
+            <param name="input_file" value="cln-stop-codons.fa"/>
+            <param name="filtering_method" value="Disallow stops"/>
+            <output name="output_file">
+                <assert_contents>
+                    <has_text text=">GoodSeq" />
+                    <has_text text="ATGGCGACC" />
+                    <has_text text=">StopSeq" />
+                    <has_text text="ATG---GCG" />
+                    <not_has_text text=">GoodSeqDup" />
+                </assert_contents>
+            </output>
+        </test>
+    </tests>
+    <help><![CDATA[
+HyPhy-CLN: Clean and Normalize Alignment
+========================================
+
+**What does this tool do?**
+
+This tool reads a sequence alignment and 'normalizes' it by cleaning sequence identifiers, removing duplicates, and/or removing gaps. It ensures the alignment is in a format suitable for other HyPhy analyses.
+
+**Options**
+
+*   **Genetic Code**: The genetic code to use for the alignment.
+*   **Filter duplicates/gaps**:
+
+    *   **Keep all sequences and sites**: No filtering is performed.
+    *   **Keep all sequences, filter sites with nothing but gaps**: Removes sites (columns) that contain only gaps.
+    *   **Filter duplicate sequences but keep all sites**: Removes duplicate sequences (identical sequences with different names or same names).
+    *   **Filter duplicate sequences and sites with nothing but gaps**: Removes both duplicate sequences and gap-only sites.
+    *   **Filter duplicate sequences and mask sequences that have stop codons**: Removes duplicates and replaces any stop codons with gaps.
+
+**Input**
+
+*   A FASTA, NEXUS, PHYLIP, or MEGA sequence alignment.
+
+**Output**
+
+*   A cleaned FASTA alignment.
+
+    ]]></help>
+    <expand macro="citations" />
+</tool>

tools/hyphy/test-data/cln-stop-codons.fa

@@ -0,0 +1,6 @@
+>GoodSeq
+ATGGCGACC
+>StopSeq
+ATGTAGGCG
+>GoodSeqDup
+ATGGCGACC