Merge branch 'master' of https://github.com/usegalaxy-au/tools-au

tools/cactus/.shed.yml

@@ -10,6 +10,8 @@ exclude:
   - README.md
   - tool_test_output.html
   - tool_test_output.json
+  - extras/*
+  - venv
 homepage_url: https://github.com/ComparativeGenomicsToolkit/cactus
 long_description: >
   Cactus is a reference-free whole-genome multiple alignment program

tools/cactus/cactus_cactus.xml

@@ -23,60 +23,26 @@
         ## Run cactus
 
         #if $aln_mode.aln_mode_select == 'intraspecies':
-            ## If we're doing a pangenome, we need to run the steps manually
-            cactus-minigraph 
-            --binariesMode local
-            --mapCores \${GALAXY_SLOTS:-4}
-            --maxMemory \${GALAXY_MEMORY_MB:-8192}M
-            --reference $aln_mode.ref_level
-            --workDir ./
-            ./jobStore
-            ./seqfile.txt
-            pangenome.gfa
-            &&
-            cactus-graphmap
-            --binariesMode local
-            --maxCores  \${GALAXY_SLOTS:-4}
-            --maxMemory \${GALAXY_MEMORY_MB:-8192}M
-            --outputFasta pangenome.gfa.fa
-            --reference $aln_mode.ref_level
-            --workDir ./
-            ./jobStore
-            ./seqfile.txt
-            pangenome.gfa
-            pangenome.paf 
-            &&
-            cactus-align
+            ## Run cactus-pangenome
+            cactus-pangenome 
             --binariesMode local
             --maxCores  \${GALAXY_SLOTS:-4}
-            --maxMemory \${GALAXY_MEMORY_MB:-8192}M
-            --outVG
-            --pangenome
-            --reference $aln_mode.ref_level
-            --workDir ./
-            ./jobStore
-            ./seqfile.txt
-            pangenome.paf 
-            alignment.hal
-            &&
-            cactus-graphmap-join
-            --binariesMode local
-            --giraffe
-            --maxCores  \${GALAXY_SLOTS:-4}
-            --maxMemory \${GALAXY_MEMORY_MB:-8192}M
+            --maxMemory \${GALAXY_MEMORY_MB:-8192}M    
+            --outDir ./
             --outName alignment
             --reference $aln_mode.ref_level
-            --vg alignment.vg
-            --outDir ./
             ./jobStore
+            seqfile.txt
         #else if $aln_mode.aln_mode_select == 'interspecies':
             ## Run cactus normally
             cactus 
             --binariesMode local 
             --maxCores  \${GALAXY_SLOTS:-4}
             --maxMemory \${GALAXY_MEMORY_MB:-8192}M
             --workDir ./
-            jobStore seqfile.txt alignment.hal 
+            jobStore
+            seqfile.txt
+            alignment.full.hal 
         #end if
 
     ]]></command>
@@ -111,12 +77,12 @@
             </param>
             <param name="fasta" type="data" format="fasta,fasta.gz" label="Genome Sequence" help="Input genome"/>
         </repeat>
-
         <!-- add an option for root -->
         <!-- root mr  -->
     </inputs>
     <outputs>
-        <data name="out_hal" format="h5" from_work_dir="alignment.hal" label="${tool.name} on ${on_string} (HAL file)" />
+        <data name="out_hal" format="h5" from_work_dir="alignment.full.hal" label="${tool.name} on ${on_string} (HAL file)">
+        </data>
         <data name="out_gfa" format="gfa2.gz" from_work_dir="alignment.gfa.gz" label="${tool.name} on ${on_string} (GFA file)" >
             <filter>aln_mode['aln_mode_select'] == 'intraspecies'</filter>
         </data>
@@ -182,7 +148,7 @@
             </repeat>
             <output name="out_hal">
                 <assert_contents>
-                    <has_size value="2088959" delta="200000" />
+                    <has_size value="565214" delta="65214" />
                 </assert_contents>
             </output>
             <output name="out_gfa">

tools/cactus/extras/README.md

@@ -0,0 +1,2 @@
+The Snakefile is for testing the cactus interface.
+Run the workflow with `snakemake --use-singularity` and inspect the output in `test_output`.

tools/cactus/extras/Snakefile

@@ -0,0 +1,102 @@
+#!/usr/bin/env python3
+
+from pathlib import Path
+import tempfile
+
+cactus = 'docker://quay.io/comparative-genomics-toolkit/cactus:v2.5.1'
+
+data_dir = Path(Path().resolve().parent, 'test-data')
+outdir = Path('test_output')
+logdir = Path(outdir, 'logs')
+
+in_seqs = [Path(outdir, 'fastas', x) for x in [
+    'simCow_chr6.fasta',
+    'simDog_chr6.fasta',
+    'simHuman_chr6.fasta',
+    'simMouse_chr6.fasta',
+    'simRat_chr6.fasta']]
+
+rule target:
+    input:
+        Path(outdir, 'cactus_pangenome', 'alignment.full.hal'),
+        Path(outdir, 'cactus', 'alignment.hal'),
+
+
+with tempfile.TemporaryDirectory() as jobstore:
+    rule cactus_pangenome:
+        input:
+            fastas = in_seqs,
+            seqfile = Path(outdir, 'seqfile.txt')
+        output:
+            Path(outdir, 'cactus_pangenome', 'alignment.full.hal'),
+        params:
+            ref_level = 'simCow_chr6',
+            wd = Path(outdir, 'cactus_pangenome')
+        log:
+            Path(logdir, 'cactus_pangenome.log')
+        threads:
+            workflow.cores
+        container:
+            cactus
+        shell:
+            'cactus-pangenome '
+            '--binariesMode local '
+            '--maxCores  {threads} '
+            '--outDir {params.wd} '
+            '--outName alignment '
+            '--reference {params.ref_level} '
+            '{jobstore} '
+            '{input.seqfile} '
+            '&> {log}'
+
+with tempfile.TemporaryDirectory() as jobstore:
+    rule cactus:
+        input:
+            fastas = in_seqs,
+            seqfile = Path(outdir, 'seqfile.txt')
+        output:
+            Path(outdir, 'cactus', 'alignment.hal'),
+        params:
+            wd = Path(outdir, 'cactus'),
+            seqfile = lambda wildcards, input: Path(input.seqfile).resolve()
+        log:
+            Path(logdir, 'cactus.log').resolve()
+        threads:
+            workflow.cores
+        container:
+            cactus
+        shell:
+            'mkdir -p {params.wd} || exit 1 '
+            '&& '
+            'cd {params.wd} || exit 1 '
+            '&& '
+            'cactus '
+            '--binariesMode local '
+            '--maxCores  {threads} '
+            '{jobstore} '
+            '{params.seqfile} '
+            'alignment.hal '
+            '&> {log}'
+
+rule seqfile:
+    input:
+        in_seqs
+    output:
+        Path(outdir, 'seqfile.txt')
+    run:
+        with open(output[0], 'wt') as f:
+            for seq in input:
+                label = Path(seq).with_suffix('').name
+                filename = Path(seq).resolve()
+                f.write(f'{label} {filename}\n')
+
+rule fastas:
+    input:
+        lambda wildcards:
+            Path(data_dir, wildcards.filename)
+    output:
+        Path(outdir, 'fastas', '{filename}')
+    shell:
+        'cp {input} {output}'
+
+

tools/cactus/macros.xml

@@ -1,6 +1,6 @@
 <macros>
-    <token name="@TOOL_VERSION@">2.4.4</token>
-    <token name="@VERSION_SUFFIX@">0</token>
+    <token name="@TOOL_VERSION@">2.5.1</token>
+    <token name="@VERSION_SUFFIX@">1</token>
     <token name="@PROFILE@">20.09</token>
     <xml name="requirements">
         <requirements>

tools/cellranger/README

@@ -0,0 +1,11 @@
+This is the Galaxy Wrapper of CellRanger. Only three pipelines are wrappered: count, mkref and mkgtf.
+
+[See more information](https://support.10xgenomics.com/single-cell-gene-expression/software/pipelines/latest/what-is-cell-ranger)
+
+Setup Cellranger via command line
+
+[See more information](https://support.10xgenomics.com/single-cell-gene-expression/software/pipelines/latest/installation)
+
+Build Notes for Reference Packages
+
+[See more information](https://support.10xgenomics.com/single-cell-gene-expression/software/release-notes/build)