Repository 'stacks_cstacks'
hg clone https://toolshed.g2.bx.psu.edu/repos/iuc/stacks_cstacks

Changeset 8:759ba5c7faca (2017-04-27)
Previous changeset 7:c541e62d6c56 (2017-04-07) Next changeset 9:ff1f282d731e (2017-05-21)
Commit message:
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/stacks commit dc23703c260d004a28fe24a2a7c00cb4371bc32e
modified:
macros.xml
stacks_cstacks.xml
added:
test-data/demultiplexed/PopA_01.1.fq.gzip
test-data/denovo_map/popmap_cstacks.tsv
test-data/procrad/R1.fq.gzip
test-data/ustacks/ustacks.out
b
diff -r c541e62d6c56 -r 759ba5c7faca macros.xml
--- a/macros.xml Fri Apr 07 11:48:00 2017 -0400
+++ b/macros.xml Thu Apr 27 04:18:23 2017 -0400
[
@@ -2,14 +2,14 @@
 <macros>
     <xml name="requirements">
         <requirements>
-            <requirement type="package" version="1.42">stacks</requirement>
+            <requirement type="package" version="1.46">stacks</requirement>
             <requirement type="package" version="1.2.10">velvet</requirement>
-            <container type="docker">quay.io/biocontainers/stacks:1.42--2</container>
+            <requirement type="package" version="1.1">stacks_summary</requirement>
             <yield/>
         </requirements>
     </xml>
 
-    <token name="@WRAPPER_VERSION@">1.42</token>
+    <token name="@WRAPPER_VERSION@">1.46</token>
 
     <xml name="stdio">
         <stdio>
@@ -90,6 +90,7 @@
         <option value="bsaHI">bsaHI</option>
         <option value="hpaII">hpaII</option>
         <option value="ncoI">ncoI</option>
+        <option value="ApaLI">ApaLI</option>
     </xml>
 
     <xml name="cross_types">
@@ -100,6 +101,19 @@
         <option value="GEN">GEN (generic, unspecific to any map type)</option>
     </xml>
 
+    <token name="@CLEAN_EXT@">
+        <![CDATA[
+        #from os.path import splitext
+        #import re
+        #def clean_ext($identifier)
+            #while $identifier.endswith(('.1', '.fa', '.fq', '.fasta', '.fastq', '.gz', '.gzip', '.sam', '.bam'))
+                #set $identifier = splitext($identifier)[0]
+            #end while
+$identifier#slurp
+        #end def
+        ]]>
+    </token>
+
     <token name="@NORM_GENOTYPES_OUTPUT_LIGHT@">
         <![CDATA[
         ##¬†We need to do this as the output file names contains the value of an option (min progeny)
b
diff -r c541e62d6c56 -r 759ba5c7faca stacks_cstacks.xml
--- a/stacks_cstacks.xml Fri Apr 07 11:48:00 2017 -0400
+++ b/stacks_cstacks.xml Thu Apr 27 04:18:23 2017 -0400
[
b'@@ -13,28 +13,33 @@\n         &&\n \n         #set $samples = ""\n-        #for $input_file in $input_col:\n+        #for $input_file in $input_col\n             #set $filename = str($input_file.element_identifier)\n-            #if not filename.endswith(\'.tsv\'):\n+            #if not filename.endswith(\'.tsv\')\n                 #set $filename = $filename + ".tsv"\n             #end if\n-            #if not re.search(\'catalog\\.[a-z]+(\\.tsv)?$\', $filename):\n-                ln -s "${input_file}" "stacks_inputs/$filename" &&\n+            #if not re.search(\'catalog\\.[a-z]+(\\.tsv)?$\', $filename)\n+                ln -s \'${input_file}\' \'stacks_inputs/$filename\' &&\n \n-                #if $filename.endswith(\'.tags.tsv\'):\n-                    #set samples += " -s \\"stacks_inputs/" + $filename[:-9] + "\\""\n+                #if $filename.endswith(\'.tags.tsv\')\n+                    #set samples += " -s \'stacks_inputs/" + $filename[:-9] + "\'"\n                 #end if\n             #end if\n         #end for\n \n         cstacks\n \n+            ## Batch description\n+            -b 1\n+\n             -p \\${GALAXY_SLOTS:-1}\n \n-            $samples\n-\n-            ## Batch description\n-            -b 1\n+            #if $popmap\n+                -P stacks_inputs -M \'$popmap\'\n+            #else\n+                $samples\n+                -o stacks_outputs\n+            #end if\n \n             $g\n \n@@ -42,20 +47,29 @@\n \n             $include_multiple\n \n-            #if $gapped.use_gapped:\n+            #if $gapped.use_gapped == "yes"\n                 --gapped\n                 --max_gaps $gapped.max_gaps\n                 --min_aln_len $gapped.min_aln_len\n             #end if\n \n-            -o stacks_outputs\n+            2>&1 | tee cstacks.log\n \n-             > cstacks.log 2>&1\n+            #if $popmap\n+                ## When using a popmap, stacks write to the input dir\n+                && mv stacks_inputs/batch_1.catalog.*.tsv stacks_outputs/\n+            #end if\n+\n+            &&\n+\n+            stacks_summary.py --stacks-prog cstacks --res-dir stacks_outputs --logfile cstacks.log --summary stacks_outputs/summary.html\n     ]]></command>\n \n     <inputs>\n         <param name="input_col" format="tabular,txt" type="data_collection" collection_type="list" label="Output from previous Stacks pipeline steps (e.g. denovo_map, refmap, ustacks or pstacks)" />\n \n+        <param name="popmap" type="data" format="tabular,txt" label="Population map" help="If set, the catalog will be built from samples listed in this file" optional="true" argument="-M" />\n+\n         <param name="g" argument="-g" type="boolean" checked="false" truevalue="-g" falsevalue="" label="Base catalog matching on genomic location, not sequence identity" />\n \n         <param name="n" argument="-n" type="integer" value="1" label="Number of mismatches allowed between sample tags when building the catalog"/>\n@@ -63,9 +77,12 @@\n         <param name="include_multiple" argument="-m" type="boolean" checked="false" truevalue="-m" falsevalue="" label="Include tags in the catalog that match to more than one entry" />\n \n         <conditional name="gapped">\n-            <param name="use_gapped" argument="--gapped" type="boolean" checked="false" label="Perform gapped alignments between stacks" />\n-            <when value="false"></when>\n-            <when value="true">\n+            <param name="use_gapped" argument="--gapped" type="select" label="Perform gapped alignments between stacks">\n+                <option value="no" selected="true">No</option>\n+                <option value="yes">Yes</option>\n+            </param>\n+            <when value="no"/>\n+            <when value="yes">\n                 <param name="max_gaps" argument="--max_gaps" type="integer" value="2" label="Number of gaps allowed between stacks before merging"/>\n                 <param name="min_aln_len" argument="--min_aln_len" type="float" value="0.8" min="0.0" max="1.0" label="Minimum length of aligned sequence in a gapped alignment"/>\n             </when'..b'abel="Catalog model calls (snps) with ${tool.name} on ${on_string}" from_work_dir="stacks_outputs/batch_1.catalog.snps.tsv" />\n         <data format="tabular" name="catalogalleles" label="Catalog haplotypes (alleles) with ${tool.name} on ${on_string}" from_work_dir="stacks_outputs/batch_1.catalog.alleles.tsv" />\n@@ -103,6 +122,11 @@\n                     <has_text text="done." />\n                 </assert_contents>\n             </output>\n+            <output name="output_summary">\n+                <assert_contents>\n+                    <has_text text="Stacks Statistics" />\n+                </assert_contents>\n+            </output>\n \n             <!-- catalog -->\n             <output name="catalogtags">\n@@ -138,13 +162,66 @@\n                     <element name="PopA_02.tags.tsv" ftype="tabular" value="genotypes/PopA_02.tags.tsv" />\n                </collection>\n             </param>\n-            <param name="gapped|use_gapped" value="true" />\n+            <param name="gapped|use_gapped" value="yes" />\n \n             <output name="output_log">\n                 <assert_contents>\n                     <has_text text="done." />\n                 </assert_contents>\n             </output>\n+            <output name="output_summary">\n+                <assert_contents>\n+                    <has_text text="Stacks Statistics" />\n+                </assert_contents>\n+            </output>\n+\n+            <!-- catalog -->\n+            <output name="catalogtags">\n+                <assert_contents>\n+                    <has_text text="catalog generated on" />\n+                </assert_contents>\n+            </output>\n+            <output name="catalogsnps">\n+                <assert_contents>\n+                    <has_text text="catalog generated on" />\n+                </assert_contents>\n+            </output>\n+            <output name="catalogalleles">\n+                <assert_contents>\n+                    <has_text text="catalog generated on" />\n+                </assert_contents>\n+            </output>\n+        </test>\n+\n+        <test>\n+            <param name="input_col">\n+                <collection type="list">\n+                    <element name="batch_1.catalog.alleles.tsv" ftype="tabular" value="genotypes/batch_1.catalog.alleles.tsv" />\n+                    <element name="batch_1.catalog.snps.tsv" ftype="tabular" value="genotypes/batch_1.catalog.snps.tsv" />\n+                    <element name="batch_1.catalog.tags.tsv" ftype="tabular" value="genotypes/batch_1.catalog.tags.tsv" />\n+                    <element name="PopA_01.alleles.tsv" ftype="tabular" value="genotypes/PopA_01.alleles.tsv" />\n+                    <element name="PopA_01.matches.tsv" ftype="tabular" value="genotypes/PopA_01.matches.tsv" />\n+                    <element name="PopA_01.snps.tsv" ftype="tabular" value="genotypes/PopA_01.snps.tsv" />\n+                    <element name="PopA_01.tags.tsv" ftype="tabular" value="genotypes/PopA_01.tags.tsv" />\n+                    <element name="PopA_02.alleles.tsv" ftype="tabular" value="genotypes/PopA_02.alleles.tsv" />\n+                    <element name="PopA_02.matches.tsv" ftype="tabular" value="genotypes/PopA_02.matches.tsv" />\n+                    <element name="PopA_02.snps.tsv" ftype="tabular" value="genotypes/PopA_02.snps.tsv" />\n+                    <element name="PopA_02.tags.tsv" ftype="tabular" value="genotypes/PopA_02.tags.tsv" />\n+               </collection>\n+            </param>\n+\n+            <param name="popmap" ftype="tabular" value="denovo_map/popmap_cstacks.tsv" />\n+\n+            <output name="output_log">\n+                <assert_contents>\n+                    <has_text text="done." />\n+                </assert_contents>\n+            </output>\n+            <output name="output_summary">\n+                <assert_contents>\n+                    <has_text text="Stacks Statistics" />\n+                </assert_contents>\n+            </output>\n \n             <!-- catalog -->\n             <output name="catalogtags">\n'
b
diff -r c541e62d6c56 -r 759ba5c7faca test-data/demultiplexed/PopA_01.1.fq.gzip
b
Binary file test-data/demultiplexed/PopA_01.1.fq.gzip has changed
b
diff -r c541e62d6c56 -r 759ba5c7faca test-data/denovo_map/popmap_cstacks.tsv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/denovo_map/popmap_cstacks.tsv Thu Apr 27 04:18:23 2017 -0400
b
@@ -0,0 +1,1 @@
+PopA_01 myPopA
b
diff -r c541e62d6c56 -r 759ba5c7faca test-data/procrad/R1.fq.gzip
b
Binary file test-data/procrad/R1.fq.gzip has changed
b
diff -r c541e62d6c56 -r 759ba5c7faca test-data/ustacks/ustacks.out
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/ustacks/ustacks.out Thu Apr 27 04:18:23 2017 -0400
b
@@ -0,0 +1,41 @@
+ustacks parameters selected:
+  Sample ID: 1
+  Min depth of coverage to create a stack: 2
+  Max distance allowed between stacks: 2
+  Max distance allowed to align secondary reads: 4
+  Max number of stacks allowed per de novo locus: 3
+  Deleveraging algorithm: disabled
+  Removal algorithm: enabled
+  Model type: SNP
+  Alpha significance level for model: 0.05
+  Gapped alignments: disabled
+Parsing stacks_inputs/PopA_01.fq
+Loading RAD-Tags...done
+Loaded 66 RAD-Tags.
+  Inserted 7 elements into the RAD-Tags hash map.
+  0 reads contained uncalled nucleotides that were modified.
+4 initial stacks were populated; 3 stacks were set aside as secondary reads.
+Initial coverage mean: 15.75; Std Dev: 7.46241; Max: 27
+Deleveraging trigger: 23; Removal trigger: 31
+Calculating distance for removing repetitive stacks.
+  Distance allowed between stacks: 1; searching with a k-mer length of 47 (48 k-mers per read); 1 k-mer hits required.
+Removing repetitive stacks.
+  Removed 0 stacks.
+  4 stacks remain for merging.
+Post-Repeat Removal, coverage depth Mean: 15.75; Std Dev: 7.46241; Max: 27
+Calculating distance between stacks...
+  Distance allowed between stacks: 2; searching with a k-mer length of 31 (64 k-mers per read); 2 k-mer hits required.
+Merging stacks, maximum allowed distance: 2 nucleotide(s)
+  4 stacks merged into 3 loci; deleveraged 0 loci; blacklisted 0 loci.
+After merging, coverage depth Mean: 21; Std Dev: 4.24264; Max: 27
+Merging remainder radtags
+  3 remainder sequences left to merge.
+  Distance allowed between stacks: 4; searching with a k-mer length of 17 (78 k-mers per read); 10 k-mer hits required.
+  Matched 3 remainder reads; unable to match 0 remainder reads.
+After remainders merged, coverage depth Mean: 22; Std Dev: 4.32049; Max: 28
+Calling final consensus sequences, invoking SNP-calling model...
+Number of utilized reads: 66
+Writing loci, SNPs, and alleles to 'stacks_outputs/'...
+  Refetching sequencing IDs from stacks_inputs/PopA_01.fq... read 66 sequence IDs.
+done.
+ustacks is done.