changeset 3:b5c3b1856370 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/samtools/samtools_phase commit ca0d1d44099fd21e0f8214102f4d8a2fd2d054d6
author iuc
date Mon, 29 Jul 2019 08:49:17 -0400
parents 6166013090c0
children 1e5880498f52
files macros.xml samtools_phase.xml test-data/empty_file.bam test-data/samtools_phase_out_2_chimera.bam
diffstat 4 files changed, 127 insertions(+), 24 deletions(-) [+]
line wrap: on
line diff
--- a/macros.xml	Tue May 09 11:18:03 2017 -0400
+++ b/macros.xml	Mon Jul 29 08:49:17 2019 -0400
@@ -1,11 +1,131 @@
 <macros>
     <xml name="requirements">
         <requirements>
-            <requirement type="package" version="1.3.1">samtools</requirement>
+            <requirement type="package" version="@TOOL_VERSION@">samtools</requirement>
             <yield/>
         </requirements>
     </xml>
-    <token name="@TOOL_VERSION@">1.3.1</token>
+    <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( $input_bams ):
+            ln -s '$bam' '${i}' &&
+            #if $bam.is_of_type('bam'):
+                #if str( $bam.metadata.bam_index ) != "None":
+                    ln -s '${bam.metadata.bam_index}' '${i}.bai' &&
+                #else:
+                    samtools index '${i}' '${i}.bai' &&
+                #end if
+            #elif $bam.is_of_type('cram'):
+                #if str( $bam.metadata.cram_index ) != "None":
+                    ln -s '${bam.metadata.cram_index}' '${i}.crai' &&
+                #else:
+                    samtools index '${i}' '${i}.crai' &&
+                #end if
+            #end if
+        #end for
+    ]]></token>
+    <token name="@PREPARE_FASTA_IDX@"><![CDATA[
+        ##checks for reference data ($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>
+    </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">
@@ -49,21 +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_phase.xml	Tue May 09 11:18:03 2017 -0400
+++ b/samtools_phase.xml	Mon Jul 29 08:49:17 2019 -0400
@@ -37,7 +37,7 @@
                 <param name="min_bq" argument="-Q" type="integer" value="13" label="Minimum base quality to be used in het calling" />
                 <param name="read_depth" argument="-D" type="integer" value="256" label="Read depth" />
                 <param name="ignore_chimeras" argument="-F" type="boolean" truevalue="-F" falsevalue="" checked="False" label="Do not attempt to fix chimeric reads" />
-                <param name="drop_ambiguous" argument="-A" type="boolean" truevalue="-A 1" falsevalue="" checked="False" label="Drop reads with ambiguous phase" />
+                <param name="drop_ambiguous" argument="-A" type="boolean" truevalue="-A" falsevalue="" checked="False" label="Drop reads with ambiguous phase" />
             </when>
         </conditional>
     </inputs>
@@ -45,7 +45,7 @@
         <data format="txt" name="phase_sets" />
         <data format="bam" from_work_dir="phase_wrapper.0.bam" name="phase0" label="${tool.name} on ${on_string}: Phase-0 reads" />
         <data format="bam" from_work_dir="phase_wrapper.1.bam" name="phase1" label="${tool.name} on ${on_string}: Phase-1 reads" />
-        <data format="bam" from_work_dir="phase_wrapper.chimeras.bam" name="chimera" label="${tool.name} on ${on_string}: Chimeric reads" />
+        <data format="bam" from_work_dir="phase_wrapper.chimera.bam" name="chimera" label="${tool.name} on ${on_string}: Chimeric reads" />
     </outputs>
     <tests>
         <test>
@@ -54,7 +54,7 @@
             <output name="phase_sets" file="samtools_phase_out_1_log.txt" ftype="txt" />
             <output name="phase0" file="samtools_phase_out_1_phase0.bam" ftype="bam" />
             <output name="phase1" file="samtools_phase_out_1_phase1.bam" ftype="bam" />
-            <output name="chimera" file="empty_file.bam" compare="contains" />
+            <output name="chimera" file="empty_file.bam" ftype="bam" />
         </test>
         <test>
             <param name="input_bam" value="samtools_phase_in_2.bam" /> 
@@ -68,7 +68,7 @@
             <output name="phase_sets" file="samtools_phase_out_2_log.txt" ftype="txt" />
             <output name="phase0" file="samtools_phase_out_2_phase0.bam" ftype="bam" />
             <output name="phase1" file="samtools_phase_out_2_phase1.bam" ftype="bam" />
-            <output name="chimera" file="empty_file.bam" compare="contains" />
+            <output name="chimera" file="samtools_phase_out_2_chimera.bam" />
         </test>
         <test>
             <param name="input_bam" value="samtools_phase_in_2.bam" /> 
@@ -82,7 +82,7 @@
             <output name="phase_sets" file="samtools_phase_out_3_log.txt" ftype="txt" />
             <output name="phase0" file="samtools_phase_out_3_phase0.bam" ftype="bam" />
             <output name="phase1" file="samtools_phase_out_3_phase1.bam" ftype="bam" />
-            <output name="chimera" file="empty_file.bam" compare="contains" />
+            <output name="chimera" file="empty_file.bam"/>
         </test>
     </tests>
     <help><![CDATA[
Binary file test-data/empty_file.bam has changed
Binary file test-data/samtools_phase_out_2_chimera.bam has changed