Merge pull request galaxyproject#6592 from richard-burhans/add-halfdeep

adding HalfDeep

tools/halfdeep/.shed.yml

@@ -0,0 +1,10 @@
+categories:
+- Sequence Analysis
+description: "HalfDeep: Automated detection of intervals covered at half depth by sequenced reads."
+homepage_url: https://github.com/makovalab-psu/HalfDeep
+long_description: |
+    Automated detection of intervals covered at half depth by sequenced reads.
+name: halfdeep
+owner: iuc
+remote_repository_url: https://github.com/galaxyproject/tools-iuc/tree/main/tools/halfdeep
+type: unrestricted

tools/halfdeep/halfdeep.xml

@@ -0,0 +1,90 @@
+<tool id="halfdeep" name="HalfDeep" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
+    <description>identifies genomic regions with half-depth coverage based on sequencing read mappings.</description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="requirements"/>
+    <command detect_errors="exit_code"><![CDATA[
+        ##
+        ## Set up the directory structure expected by bam_depth.sh and halfdeep.sh
+        ## See: https://github.com/makovalab-psu/HalfDeep?tab=readme-ov-file#expected-directory-layout
+        ##
+        mkdir -p reads halfdeep/ref/mapped_reads &&
+        ##
+        ## reference
+        ##
+        ln -s '$ref' 'ref.$ref.ext' &&
+        #if not $mapped_reads
+            minimap2 -x map-pb -d ref.idx 'ref.$ref.ext' &&
+        #else
+            touch ref.idx &&
+        #end if
+        ##
+        ## reads
+        ##
+        #import re
+        #set $reads_base = re.sub('[^\w\-\s]', '_', str($reads.element_identifier))
+        ln -s '$reads' 'reads/${reads_base}.$reads.ext' &&
+        echo 'reads/${reads_base}.$reads.ext' >> input.fofn &&
+        ##
+        ## mapped reads
+        ##
+        #if $mapped_reads
+            ln -s '$mapped_reads' 'halfdeep/ref/mapped_reads/${reads_base}.bam' &&
+            ln -s '${reads_base}.bam' 'halfdeep/ref/mapped_reads/${reads_base}.sort.bam' &&
+            ln -s '$mapped_reads.metadata.bam_index' 'halfdeep/ref/mapped_reads/${reads_base}.sort.bam.bai' &&
+        #end if
+        ##
+        ## run bam_depth.sh
+        ##
+        bam_depth.sh 'ref.$ref.ext' 1 &&
+        ##
+        ## run halfdeep.sh
+        ##
+        halfdeep.sh 'ref.$ref.ext'
+    ]]></command>
+    <inputs>
+        <param name="ref" type="data" format="fasta,fasta.gz" label="Genome Assembly" help="A Genome Assembly in FASTA format."/>
+        <param name="reads" type="data" format="fastqsanger,fastqsanger.gz" label="Sequencing Reads" help="Sequencing Reads for the Genome Assembly in FASTQ format."/>
+         <param name="mapped_reads" type="data" format="bam" value="" optional="true" label="Aligned Reads" help="Alignments of the Sequencing Reads to the Genome Assembly in BAM format."/>
+    </inputs>
+    <outputs>
+        <data name="halfdeep_dat" format="bed" from_work_dir="halfdeep/ref/halfdeep.dat" label="HalfDeep on ${on_string}"/>
+    </outputs>
+    <tests>
+        <test expect_num_outputs="1">
+            <param name="ref" value="ref.fasta.gz" ftype="fasta.gz"/>
+            <param name="reads" value="reads.fasta.gz" ftype="fasta.gz"/>
+            <param name="mapped_reads" value="mapped_reads.bam" ftype="bam"/>
+            <output name="halfdeep_dat" file="halfdeep.bed" ftype="bed"/>
+        </test>
+        <test expect_num_outputs="1">
+            <param name="ref" value="ref.fasta.gz" ftype="fasta.gz"/>
+            <param name="reads" value="reads.fasta.gz" ftype="fasta.gz"/>
+            <output name="halfdeep_dat" file="halfdeep.bed" ftype="bed"/>
+        </test>
+    </tests>
+    <help><![CDATA[
+
+HalfDeep identifies genomic regions with half-depth coverage based on sequencing read mappings. These regions may reveal insights into heterogametic sex chromosomes, haplotype-specific variation, or potential assembly errors such as heterotypic duplications.
+
+Given the following inputs:
+
+1. A genome assembly in FASTA format.
+2. Reads in FASTQ format.
+3. Mapped reads in BAM format (optional)
+
+HalfDeep automates the following tasks:
+
+1. Mapping reads and merging individual mapping files.
+2. Calculating per-base read depth.
+3. Smoothing read coverage using a defined window with genodsp.
+4. Determining the percentile of read coverage.
+5. Identifying genomic regions with half-depth coverage based on a specified percentile threshold (e.g., 40–60%) and exporting them in BED file format
+
+HalfDeep produces the following output:
+
+1. HalfDeep: BED file containing regions of the genome assembly that are "covered at half depth"
+    ]]></help>
+    <expand macro="citations"/>
+</tool>

tools/halfdeep/macros.xml

@@ -0,0 +1,23 @@
+<macros>
+    <xml name="requirements">
+        <requirements>
+            <requirement type="package" version="@TOOL_VERSION@">halfdeep</requirement>
+        </requirements>
+    </xml>
+    <token name="@TOOL_VERSION@">0.1.0</token>
+    <token name="@VERSION_SUFFIX@">0</token>
+    <token name="@PROFILE@">21.05</token>
+    <xml name="citations">
+        <citations>
+            <citation type="bibtex">
+                @misc{github_halfdeep,
+                    author = {Makova Lab PSU},
+                    year = "2019",
+                    title = {HalfDeep},
+                    publisher = {GitHub},
+                    journal = {GitHub repository},
+                    url = {https://github.com/makovalab-psu/HalfDeep}
+            </citation>
+        </citations>
+    </xml>
+</macros>