changeset 10:8da515fbc1bf draft

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/samtools/samtools_mpileup commit a18f79e7cfe15fd6e1a5f70533616c379e4e7c6a"
author iuc
date Tue, 21 Sep 2021 09:33:51 +0000
parents fa7ad9b89f4a
children 111f83918fe6
files macros.xml samtools_mpileup.xml
diffstat 2 files changed, 104 insertions(+), 36 deletions(-) [+]
line wrap: on
line diff
--- a/macros.xml	Mon Sep 03 13:10:02 2018 -0400
+++ b/macros.xml	Tue Sep 21 09:33:51 2021 +0000
@@ -7,6 +7,23 @@
     </xml>
     <token name="@TOOL_VERSION@">1.9</token>
     <token name="@FLAGS@">#set $flags = sum(map(int, str($filter).split(',')))</token>
+    <token name="@PREPARE_IDX@"><![CDATA[
+        ##prepare input and indices 
+        ln -s '$input' infile &&
+        #if $input.is_of_type('bam'):
+            #if str( $input.metadata.bam_index ) != "None":
+                ln -s '${input.metadata.bam_index}' infile.bai &&
+            #else:
+                samtools index infile infile.bai &&
+            #end if
+        #elif $input.is_of_type('cram'):
+            #if str( $input.metadata.cram_index ) != "None":
+                ln -s '${input.metadata.cram_index}' infile.crai &&
+            #else:
+                samtools index infile infile.crai &&
+            #end if
+        #end if
+    ]]></token>
     <token name="@PREPARE_IDX_MULTIPLE@"><![CDATA[
         ##prepare input and indices 
         #for $i, $bam in enumerate( $input_bams ):
@@ -26,20 +43,89 @@
             #end if
         #end for
     ]]></token>
+    <token name="@PREPARE_FASTA_IDX@"><![CDATA[
+        ##checks for reference data ($addref_cond.addref_select=="history" or =="cached")
+        ##and sets the -t/-T parameters accordingly:
+        ##- in case of history a symbolic link is used because samtools (view) will generate
+        ##  the index which might not be possible in the directory containing the fasta file
+        ##- in case of cached the absolute path is used which allows to read the cram file
+        ##  without specifying the reference
+        #if $addref_cond.addref_select == "history":
+            ln -s '${addref_cond.ref}' reference.fa &&
+            samtools faidx reference.fa &&
+            #set reffa="reference.fa"
+            #set reffai="reference.fa.fai"
+        #elif $addref_cond.addref_select == "cached":
+            #set reffa=str($addref_cond.ref.fields.path)
+            #set reffai=str($addref_cond.ref.fields.path)+".fai"
+        #else
+            #set reffa=None
+            #set reffai=None
+        #end if
+    ]]></token>
+    <token name="@ADDTHREADS@"><![CDATA[
+        ##compute the number of ADDITIONAL threads to be used by samtools (-@)
+        addthreads=\${GALAXY_SLOTS:-1} && (( addthreads-- )) &&
+    ]]></token>
+    <token name="@ADDMEMORY@"><![CDATA[
+        ##compute the number of memory available to samtools sort (-m)
+        ##use only 75% of available: https://github.com/samtools/samtools/issues/831
+        addmemory=\${GALAXY_MEMORY_MB_PER_SLOT:-768} && 
+        ((addmemory=addmemory*75/100)) &&
+    ]]></token>
+    <xml name="seed_input">
+       <param name="seed" type="integer" optional="True" label="Seed for random number generator" help="If empty a random seed is used." /> 
+    </xml>
     <xml name="flag_options">
-        <option value="1">read is paired</option>
-        <option value="2">read is mapped in a proper pair</option>
-        <option value="4">read is unmapped</option>
-        <option value="8">mate is unmapped</option>
-        <option value="16">read reverse strand</option>
-        <option value="32">mate reverse strand</option>
-        <option value="64">read is the first in a pair</option>
-        <option value="128">read is the second in a pair</option>
-        <option value="256">alignment or read is not primary</option>
-        <option value="512">read fails platform/vendor quality checks</option>
-        <option value="1024">read is a PCR or optical duplicate</option>
-        <option value="2048">supplementary alignment</option>
+        <option value="1">Read is paired</option>
+        <option value="2">Read is mapped in a proper pair</option>
+        <option value="4">Read is unmapped</option>
+        <option value="8">Mate is unmapped</option>
+        <option value="16">Read is mapped to the reverse strand of the reference</option>
+        <option value="32">Mate is mapped to the reverse strand of the reference</option>
+        <option value="64">Read is the first in a pair</option>
+        <option value="128">Read is the second in a pair</option>
+        <option value="256">Alignment of the read is not primary</option>
+        <option value="512">Read fails platform/vendor quality checks</option>
+        <option value="1024">Read is a PCR or optical duplicate</option>
+        <option value="2048">Alignment is supplementary</option>
     </xml>
+
+    <!-- region specification macros and tokens for tools that allow the specification 
+         of region by bed file / space separated list of regions -->
+    <token name="@REGIONS_FILE@"><![CDATA[
+        #if $cond_region.select_region == 'tab':
+            -t '$cond_region.targetregions'
+        #end if
+    ]]></token>
+    <token name="@REGIONS_MANUAL@"><![CDATA[
+        #if $cond_region.select_region == 'text':
+            #for $i, $x in enumerate($cond_region.regions_repeat):
+               '${x.region}'
+            #end for
+        #end if
+    ]]></token>
+    <xml name="regions_macro">
+        <conditional name="cond_region">
+            <param name="select_region" type="select" label="Filter by regions" help="restricts output to only those alignments which overlap the specified region(s)">
+                <option value="no" selected="True">No</option>
+                <option value="text">Manualy specify regions</option>
+                <option value="tab">Regions from tabular file</option>
+            </param>
+            <when value="no"/>
+            <when value="text">
+                <repeat name="regions_repeat" min="1" default="1" title="Regions">
+                    <param name="region" type="text" label="region" help="format chr:from-to">
+                        <validator type="regex" message="Required format: CHR[:FROM[-TO]]; where CHR: string containing any character except quotes, whitespace and colon; FROM and TO: any integer">^[^\s'\":]+(:\d+(-\d+){0,1}){0,1}$</validator>
+                    </param>
+                </repeat>
+            </when>
+            <when value="tab">
+                <param name="targetregions" argument="-t/--target-regions" type="data" format="tabular" label="Target regions file" help="Do stats in these regions only. Tab-delimited file chr,from,to (1-based, inclusive)" />
+            </when>
+        </conditional>
+    </xml>
+
     <xml name="citations">
         <citations>
             <citation type="bibtex">
@@ -83,21 +169,4 @@
             <exit_code range="1:" level="fatal" description="Error" />
         </stdio>
     </xml>
-    <token name="@no-chrom-options@">
------
-
-.. class:: warningmark
-
-**No options available? How to re-detect metadata**
-
-If you see a &quot;No options available&quot; within the &quot;**Select references (chromosomes and contigs) you would like to restrict bam to**&quot; drop down, you need to re-detect metadata for the dataset you are trying to process. To do this follow these steps:
-
-1. Click on the **pencil** icon adjacent to the dataset in the history
-2. A new menu will appear in the center pane of the interface
-3. Click **Datatype** tab
-4. Set **New Type** to **BAM**
-5. Click **Save**
-
-The medatada will be re-detected and you will be able to see the list of reference sequences in the &quot;**Select references (chromosomes and contigs) you would like to restrict bam to**&quot; drop-down.
-    </token>
 </macros>
--- a/samtools_mpileup.xml	Mon Sep 03 13:10:02 2018 -0400
+++ b/samtools_mpileup.xml	Tue Sep 21 09:33:51 2021 +0000
@@ -12,16 +12,15 @@
     @PREPARE_IDX_MULTIPLE@
 
     #if $reference_source.reference_source_selector == "history":
-        ln -s '${reference_source.ref_file}' &&
-        samtools faidx `basename '${reference_source.ref_file}'` &&
+        #set ref_fa = 'ref.fa'
+        ln -s '${reference_source.ref_file}' 'ref.fa' &&
+        samtools faidx ref.fa &&
+    #else:
+        #set ref_fa = str( $reference_source.ref_file.fields.path )
     #end if
 
     samtools mpileup
-    #if $reference_source.reference_source_selector != "history":
-        -f '${reference_source.ref_file.fields.path}'
-    #else:
-        -f '${reference_source.ref_file}'
-    #end if
+        -f '$ref_fa'
     #for $i in range(len( $input_bams )):
         '${i}'
     #end for