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

Changeset 8:c209e3f3359b (2017-04-27)
Previous changeset 7:14396ffcb253 (2017-04-07) Next changeset 9:4ee074ca88fb (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_refmap.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 14396ffcb253 -r c209e3f3359b macros.xml
--- a/macros.xml Fri Apr 07 11:46:59 2017 -0400
+++ b/macros.xml Thu Apr 27 04:17:01 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 14396ffcb253 -r c209e3f3359b stacks_refmap.xml
--- a/stacks_refmap.xml Fri Apr 07 11:46:59 2017 -0400
+++ b/stacks_refmap.xml Thu Apr 27 04:17:01 2017 -0400
[
b'@@ -6,54 +6,42 @@\n     <expand macro="requirements"/>\n     <expand macro="stdio"/>\n     <command><![CDATA[\n-        #from os.path import splitext\n-        #import re\n+\n+        @CLEAN_EXT@\n \n-        #if str( $options_usage.rad_analysis_type ) == "genetic":\n-            #for $input_parent in $options_usage.parent_alignments:\n-                #if $input_parent.is_of_type(\'sam\'):\n-                    #set $data_path = splitext($input_parent.element_identifier)[0]\n-                    #set $data_path = re.sub(r\'\\.1$\', \'\', $data_path)\n-                    #set $data_path = $data_path + ".sam"\n-                #else:\n-                    #set $data_path = splitext($input_parent.element_identifier)[0]\n-                    #set $data_path = re.sub(r\'\\.1$\', \'\', $data_path)\n-                    #set $data_path = $data_path + ".bam"\n+        #if str( $options_usage.rad_analysis_type ) == "genetic"\n+            #for $input_parent in $options_usage.parent_alignments\n+                #if $input_parent.is_of_type(\'sam\')\n+                    #set $data_path = $clean_ext($input_parent.element_identifier) + ".sam"\n+                #else\n+                    #set $data_path = $clean_ext($input_parent.element_identifier) + ".bam"\n                 #end if\n \n-                ln -s "${input_parent}" "${data_path}" &&\n+                ln -s \'${input_parent}\' \'${data_path}\' &&\n             #end for\n \n-            #for $input_progeny in $options_usage.progeny_alignments:\n+            #for $input_progeny in $options_usage.progeny_alignments\n \n-                #if $input_progeny:\n-                    #if $input_progeny.is_of_type(\'sam\'):\n-                        #set $data_path = splitext($input_progeny.element_identifier)[0]\n-                        #set $data_path = re.sub(r\'\\.1$\', \'\', $data_path)\n-                        #set $data_path = $data_path + ".sam"\n-                    #else:\n-                        #set $data_path = splitext($input_progeny.element_identifier)[0]\n-                        #set $data_path = re.sub(r\'\\.1$\', \'\', $data_path)\n-                        #set $data_path = $data_path + ".bam"\n+                #if $input_progeny\n+                    #if $input_progeny.is_of_type(\'sam\')\n+                        #set $data_path = $clean_ext($input_progeny.element_identifier) + ".sam"\n+                    #else\n+                        #set $data_path = $clean_ext($input_progeny.element_identifier) + ".bam"\n                     #end if\n \n-                    ln -s "${input_progeny}" "${data_path}" &&\n+                    ln -s \'${input_progeny}\' \'${data_path}\' &&\n                 #end if\n             #end for\n-        #else:\n-            #for $input_indiv in $options_usage.individual_sample:\n+        #else\n+            #for $input_indiv in $options_usage.individual_sample\n \n-                #if $input_indiv.is_of_type(\'sam\'):\n-                    #set $data_path = splitext($input_indiv.element_identifier)[0]\n-                    #set $data_path = re.sub(r\'\\.1$\', \'\', $data_path)\n-                    #set $data_path = $data_path + ".sam"\n-                #else:\n-                    #set $data_path = splitext($input_indiv.element_identifier)[0]\n-                    #set $data_path = re.sub(r\'\\.1$\', \'\', $data_path)\n-                    #set $data_path = $data_path + ".bam"\n+                #if $input_indiv.is_of_type(\'sam\')\n+                    #set $data_path = $clean_ext($input_indiv.element_identifier) + ".sam"\n+                #else\n+                    #set $data_path = $clean_ext($input_indiv.element_identifier) + ".bam"\n                 #end if\n \n-                ln -s "${input_indiv}" "${data_path}" &&\n+                ln -s \'${input_indiv}\' \'${data_path}\' &&\n             #end for\n         #end if\n \n@@ -65,60 +53,48 @@\n \n             -T \\${GALAXY_SLOTS:-1}\n \n-            #if str( $options_usage.rad_analysis_type ) == "genetic":\n-                #for $input_parent in $options_usage.parent_alignments:\n-                    #if $input_p'..b'r) + ".bam"\n                     #end if\n \n-                    -s "${data_path}"\n+                    -s \'${data_path}\'\n                 #end for\n-                -O "$options_usage.popmap"\n+                -O \'$options_usage.popmap\'\n             #end if\n \n-            #if str($m):\n+            #if str($m)\n                 -m $m\n             #end if\n-            #if str($P):\n+            #if str($P)\n                 -P $P\n             #end if\n \n@@ -129,22 +105,29 @@\n             -S\n \n             ## snp_model\n-            #if str( $snp_options.select_model.model_type) == "bounded":\n+            #if str( $snp_options.select_model.model_type) == "bounded"\n                 --bound_low $snp_options.select_model.bound_low\n                 --bound_high $snp_options.select_model.bound_high\n                 --alpha $snp_options.select_model.alpha\n-            #else if str( $snp_options.select_model.model_type) == "snp":\n+            #else if str( $snp_options.select_model.model_type) == "snp"\n                 --alpha $snp_options.select_model.alpha\n             #end if\n \n             -o stacks_outputs\n \n-            #if str( $options_usage.rad_analysis_type ) == "genetic":\n+            #if str( $options_usage.rad_analysis_type ) == "genetic"\n                 @NORM_GENOTYPES_OUTPUT_LIGHT@\n             #end if\n \n             ## If input is in bam format, stacks will output gzipped files (no option to control this)\n             && if ls stacks_outputs/*.gz > /dev/null 2>&1; then gunzip stacks_outputs/*.gz; fi\n+\n+            &&\n+\n+            stacks_summary.py --stacks-prog ref_map.pl --res-dir stacks_outputs --logfile stacks_outputs/ref_map.log --summary stacks_outputs/summary.html\n+            #if str( $options_usage.rad_analysis_type ) == "population":\n+                --pop-map \'$options_usage.popmap\'\n+            #end if\n     ]]></command>\n \n     <inputs>\n@@ -178,6 +161,8 @@\n     <outputs>\n         <data format="txt" name="output_log" label="ref_map.log with ${tool.name} on ${on_string}" from_work_dir="stacks_outputs/ref_map.log" />\n \n+        <data format="html" name="output_summary" label="Summary from ${tool.name} on ${on_string}" from_work_dir="stacks_outputs/summary.html" />\n+\n         <data format="tabular" name="catalogtags" label="Catalog assembled loci (tags) with ${tool.name} on ${on_string}" from_work_dir="stacks_outputs/batch_1.catalog.tags.tsv" />\n         <data format="tabular" name="catalogsnps" label="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@@ -217,6 +202,11 @@\n                     <has_text text="ref_map.pl completed" />\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="catalogsnps">\n@@ -306,6 +296,11 @@\n                     <has_text text="ref_map.pl completed" />\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="catalogsnps">\n@@ -395,6 +390,11 @@\n                     <has_text text="ref_map.pl completed" />\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 14396ffcb253 -r c209e3f3359b test-data/demultiplexed/PopA_01.1.fq.gzip
b
Binary file test-data/demultiplexed/PopA_01.1.fq.gzip has changed
b
diff -r 14396ffcb253 -r c209e3f3359b 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 04:17:01 2017 -0400
b
@@ -0,0 +1,1 @@
+PopA_01 myPopA
b
diff -r 14396ffcb253 -r c209e3f3359b test-data/procrad/R1.fq.gzip
b
Binary file test-data/procrad/R1.fq.gzip has changed
b
diff -r 14396ffcb253 -r c209e3f3359b test-data/ustacks/ustacks.out
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/ustacks/ustacks.out Thu Apr 27 04:17:01 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.