Mercurial > repos > bebatut > sortmerna

changeset 16:1a4662c2d6db draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/rna_tools/sortmerna commit 044a991b45c9135339daf138929887cd8e93a1bf-dirty
author bebatut
date Mon, 12 Jun 2017 06:20:50 -0400
parents baab049d3aff
children 715c75d6d784
files macros.xml readme.md sortmerna.xml tool-data/rRNA_databases.loc.sample tool_dependencies.xml
diffstat 5 files changed, 63 insertions(+), 106 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/macros.xml	Mon Jun 12 06:20:50 2017 -0400
@@ -0,0 +1,4 @@
+<?xml version="1.0" ?>
+<macros>
+    <token name="@VERSION@">2.1b</token>
+</macros>
\ No newline at end of file
--- a/readme.md	Wed Feb 10 04:02:18 2016 -0500
+++ b/readme.md	Mon Jun 12 06:20:50 2017 -0400
@@ -15,6 +15,8 @@
 
 .. _`Galaxy Tool Shed`:  https://testtoolshed.g2.bx.psu.edu/view/bgruening/sortmerna
 
+To install the databases, we recommend to use the dedicated data manager available in the `Galaxy Tool Shed`
+
 
 =======
 History
--- a/sortmerna.xml	Wed Feb 10 04:02:18 2016 -0500
+++ b/sortmerna.xml	Mon Jun 12 06:20:50 2017 -0400
@@ -1,7 +1,10 @@
-<tool id="bg_sortmerna" name="Filter with SortMeRNA" version="2.1.0">
+<tool id="bg_sortmerna" name="Filter with SortMeRNA" version="@VERSION@.4">
     <description>Fast and accurate filtering of ribosomal RNAs in metatranscriptomic data</description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
     <requirements>
-        <requirement type="package" version="2.0">sortmerna</requirement>
+        <requirement type="package" version="@VERSION@">sortmerna</requirement>
     </requirements>
     <stdio>
         <regex match="This program builds a Burst trie on an input rRNA database"
@@ -35,14 +38,14 @@
         ## databases path is not directly accessible, must match by hand with LOC file contents
         #set $data_table = dict([(_[0], _[2]) for _ in $databases_type.input_databases.input.options.tool_data_table.data])
         #for $db in $databases_type.input_databases.value
-            #set $ref += $sep + $data_table[$db] + ',' + $os.path.splitext($data_table[$db])[0] + '-reindexed'
+            #set $ref += $sep + $databases_type.input_databases.path + '.fasta,' + $databases_type.input_databases.path + '-reindexed'
             #set $sep = ':'
         #end for
     #else:
         ## databases path is not directly accessible, must match by hand with LOC file contents
         #set $data_table = dict([(_[0], _[2]) for _ in $databases_type.input_databases.input.options.tool_data_table.data])
         #for $db in $databases_type.input_databases.value
-            #set $ref += $sep + $data_table[$db] + ',' + $os.path.splitext($data_table[$db])[0]
+            #set $ref += $sep + $databases_type.input_databases.path + '.fasta,' + $databases_type.input_databases.path
             #set $sep = ':'
         #end for
     #end if
@@ -75,7 +78,9 @@
     	#if $aligned_sam.aligned_sam_selector == '--sam'
         	$aligned_sam.sq
     	#end if
-    	$aligned_blast
+    	#if $aligned_blast.aligned_blast_selector == '--blast'
+        	--blast "$aligned_blast.aligned_blast_format"
+    	#end if
 
     	$log
 
@@ -115,8 +120,8 @@
             <when value="paired">
                 <param name="paired_type" type="select" display="radio" label="If one of the paired-end reads aligns and the other one does not">
                     <option value="">leave the reads split between aligned and rejected files</option>
-                    <option value="--paired-in">output both reads to aligned file (--paired-in)</option>
-                    <option value="--paired-out">output both reads to rejected file (--paired-out)</option>
+                    <option value="--paired_in">output both reads to aligned file (--paired_in)</option>
+                    <option value="--paired_out">output both reads to rejected file (--paired_out)</option>
                 </param>
             </when>
         </conditional>
@@ -179,14 +184,23 @@
             </when>
             <when value="" />
         </conditional>
-        <param name="aligned_blast" type="select" label="Include alignments in BLAST-like format">
-            <option value="--blast 0">pairwise (--blast 0)</option>
-            <option value="--blast 1">tabular BLAST -m 8 format (--blast 1)</option>
-            <option value="--blast 2">tabular + column for CIGAR (--blast 2)</option>
-            <option value="--blast 3">tabular + columns for CIGAR and query coverage (--blast 3)</option>
-            <option value="" selected="true">No</option>
-        </param>
-        <param name="log" type="boolean" checked="False" truevalue="--log" falsevalue="" label="Generate statistics file"
+        <conditional name="aligned_blast">
+            <param name="aligned_blast_selector" type="select" label="Include alignments in BLAST-like format?">
+                <option value="--blast">Yes</option>
+                <option value="" selected="true">No</option>
+            </param>
+            <when value="--blast">
+                <param name="aligned_blast_format" type="select" label="BLAST-like format?">
+                    <option value="0">pairwise (--blast '0')</option>
+                    <option value="1">tabular BLAST -m 8 format (--blast '1')</option>
+                    <option value="1 cigar">tabular + column for CIGAR (--blast '1 cigar')</option>
+                    <option value="1 cigar qcov">tabular + columns for CIGAR and query coverage (--blast '1 cigar qcov')</option>
+                    <option value="1 cigar qcov qstrand">tabular + columns for CIGAR, query coverage and strand (--blast '1 cigar qcov qstrand')</option>
+                </param>
+            </when>
+            <when value="" />
+        </conditional>
+        <param name="log" type="boolean" checked="false" truevalue="--log" falsevalue="" label="Generate statistics file"
                help="Generates statistics for the rRNA content of reads, as well as rRNA subunit distribution. (--log)">
         </param>
 	<conditional name="report">
@@ -247,9 +261,9 @@
         </data>
         <data format="tabular" name="output_blast" from_work_dir="aligned.blast"
             label="Alignments on ${on_string} (BLAST)">
-            <filter>aligned_blast</filter>
+            <filter>aligned_blast['aligned_blast_selector']</filter>
             <change_format>
-                <when input="aligned_blast" value="--blast 0" format="txt" />
+                <when input="aligned_blast.aligned_blast_format" value="0" format="txt" />
             </change_format>
         </data>
         <data format="txt" name="output_log" label="${tool.name} statistics (txt)" from_work_dir="aligned.log">
@@ -263,8 +277,20 @@
             <param name="strand_search" value="" />
             <param name="databases_selector" value="history" />
             <param name="database_name" value="ref_small.fasta" />
+            <param name="aligned_fastx_selector" value="--fastx" />
             <param name="other" value="True" />
+            <param name="aligned_sam_selector" value="--sam" />
+            <param name="aligned_blast_selector" value="--blast"/>
+            <param name="aligned_blast_format" value="1 cigar qcov" />
             <param name="log" value="" />
+            <param name="report_type" value="best" />
+            <param name="report_best_type" value="1" />
+            <param name="e_value" value="1"/>
+            <param name="match" value="2"/>
+            <param name="mismatch" value="-3" />
+            <param name="gap_open" value="5"/>
+            <param name="gap_ext" value="2"/>
+            <param name="ambiguous_letter" value="-3"/>
             <output name="output_fastx" file="sortmerna_wrapper_accept1.fastq" />
             <output name="output_other" file="sortmerna_wrapper_other1.fastq" />
             <output name="output_sam" file="sortmerna_wrapper_sam1.sam" lines_diff="2" />
@@ -275,8 +301,21 @@
             <param name="strand_search" value="" />
             <param name="databases_selector" value="history" />
             <param name="database_name" value="ref_small.fasta" />
+            <param name="aligned_fastx_selector" value="--fastx" />
             <param name="other" value="True" />
+            <param name="aligned_sam_selector" value="--sam" />
+            <param name="aligned_blast" value="" />
             <param name="log" value="" />
+            <param name="report_type" value="best" />
+            <param name="report_best_type" value="1" />
+            <param name="report_type" value="best" />
+            <param name="report_best_type" value="1" />
+            <param name="e_value" value="1"/>
+            <param name="match" value="2"/>
+            <param name="mismatch" value="-3" />
+            <param name="gap_open" value="5"/>
+            <param name="gap_ext" value="2"/>
+            <param name="ambiguous_letter" value="-3"/>
             <output name="output_fastx" file="sortmerna_wrapper_accept2.fasta" />
             <output name="output_other" file="sortmerna_wrapper_other2.fasta" />
             <output name="output_sam" file="sortmerna_wrapper_sam2.sam" lines_diff="2" />
--- a/tool-data/rRNA_databases.loc.sample	Wed Feb 10 04:02:18 2016 -0500
+++ b/tool-data/rRNA_databases.loc.sample	Mon Jun 12 06:20:50 2017 -0400
@@ -1,30 +1,1 @@
-#This is a sample file distributed with Galaxy that is used to define a
-#list of public ribosomal databases for SortMeRNA, using the following format
-#(white space characters are TAB characters):
-#
-#<unique_id>	<database_caption>	<fasta_file_path>
-#
-#So, for example, if your database is rfam-5.8s-id98 and the path to your FASTA
-#file is /data/rRNA_databases/rfam-5.8s-id98.fasta, then the rRNA_databases.loc
-#entry would look like this:
-#
-#rfam-5.8s-id98	Rfam 5.8S eukarya	/data/rRNA_databases/rfam-5.8s-id98.fasta
-#
-#For each rRNA database, you need to create the index files using the
-#indexdb_rna program provided by SortMeRNA. You need to specify as index
-#basename the path of the FASTA file without extension. For example, for the
-#previous database the command is:
-#
-#  indexdb_rna --ref /data/rRNA_databases/rfam-5.8s-id98.fasta,/data/rRNA_databases/rfam-5.8s-id98
-#
-#Since SortMeRNA comes bundled with eight ribosomal databases, you can use them
-#by creating the actual index files as explained above and uncommenting the
-#following lines.
-#rfam-5.8s-id98	Rfam 5.8S eukarya	$SORTMERNADIR/rRNA_databases/rfam-5.8s-database-id98.fasta
-#rfam-5s-id98	Rfam 5S archaea/bacteria	$SORTMERNADIR/rRNA_databases/rfam-5s-database-id98.fasta
-#silva-arc-16s-id95	SILVA v.119 16S archaea	$SORTMERNADIR/rRNA_databases/silva-arc-16s-id95.fasta
-#silva-arc-23s-id98	SILVA v.119 23S archaea	$SORTMERNADIR/rRNA_databases/silva-arc-23s-id98.fasta
-#silva-bac-16s-id90	SILVA v.119 16S bacteria	$SORTMERNADIR/rRNA_databases/silva-bac-16s-id90.fasta
-#silva-bac-23s-id98	SILVA v.119 23S bacteria	$SORTMERNADIR/rRNA_databases/silva-bac-23s-id98.fasta
-#silva-euk-18s-id95	SILVA v.119 18S eukarya	$SORTMERNADIR/rRNA_databases/silva-euk-18s-id95.fasta
-#silva-euk-28s-id98	SILVA v.119 28S eukarya	$SORTMERNADIR/rRNA_databases/silva-euk-28s-id98.fasta
+#<unique_id>  <database_caption>  <fasta_file_path>
--- a/tool_dependencies.xml	Wed Feb 10 04:02:18 2016 -0500
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,59 +0,0 @@
-<?xml version="1.0"?>
-<tool_dependency>
-    <package name="sortmerna" version="2.0">
-        <install version="1.0">
-            <actions_group>
-                <actions architecture="x86_64" os="linux">
-                        <action type="download_by_url" target_filename="sortmerna-2.0.tar.gz">https://github.com/biocore/sortmerna/archive/2.0.tar.gz</action>
-                        <action type="shell_command"><![CDATA[
-                            ./build.sh --prefix=$INSTALL_DIR
-                        ]]>
-                        </action>
-                        <action type="change_directory">../</action>
-                        <action type="make_directory">$INSTALL_DIR/bin/</action>
-                        <action type="move_file">
-                            <source>sortmerna-2.0/sortmerna</source>
-                            <destination>$INSTALL_DIR/bin</destination>
-                        </action>
-                        <action type="move_file">
-                            <source>sortmerna-2.0/indexdb_rna</source>
-                            <destination>$INSTALL_DIR/bin</destination>
-                        </action>
-                        <action type="make_directory">$INSTALL_DIR/rRNA_databases/</action>
-                        <action type="move_directory_files">
-                            <source_directory>sortmerna-2.0/rRNA_databases/</source_directory>
-                            <destination_directory>$INSTALL_DIR/rRNA_databases/</destination_directory>
-                        </action>
-                        <action type="set_environment">
-                            <environment_variable name="SORTMERNADIR" action="set_to">$INSTALL_DIR/</environment_variable>
-                            <environment_variable name="PATH" action="prepend_to">$INSTALL_DIR/bin</environment_variable>
-                        </action>
-                    </actions>
-                <actions architecture="x86_64" os="darwin">
-                        <action type="download_by_url" target_filename="sortmerna-2.0.tar.gz">https://github.com/biocore/sortmerna/archive/2.0.tar.gz</action>
-                        <action type="shell_command"><![CDATA[
-                            export CC=gcc-mp-4.8 && export CXX=g++-mp-4.8 && ./configure && make && make install
-                        ]]>
-                        </action>
-                        <action type="change_directory">../</action>
-                        <action type="make_directory">$INSTALL_DIR/rRNA_databases/</action>
-                        <action type="move_directory_files">
-                            <source_directory>sortmerna-2.0/rRNA_databases/</source_directory>
-                            <destination_directory>$INSTALL_DIR/rRNA_databases/</destination_directory>
-                        </action>
-                        <action type="set_environment">
-                            <environment_variable name="SORTMERNADIR" action="set_to">$INSTALL_DIR/</environment_variable>
-                            <environment_variable name="PATH" action="prepend_to">$INSTALL_DIR/bin</environment_variable>
-                        </action>                
-                    </actions>
-                </actions_group>
-        </install>
-        <readme>
-        SortMeRNA requires g++ 4.8 or later. 
-
-        Note: the Clang compiler on Mac (distributed through Xcode) does not 
-        support multithreading. The user is recommended to install the original 
-        GCC compiler via MacPorts
-        </readme>
-    </package>
-</tool_dependency>