diff mapper.xml @ 2:ab8cd78709e1 draft

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/mirdeep2/mirdeep2_mapper commit b9d202134c3c6d0e5c398c3ae75e410067fcfc52
author rnateam
date Wed, 23 Nov 2016 16:32:13 -0500
parents 12fc62b7dc09
children a8d24f4b6d95
line wrap: on
line diff
--- a/mapper.xml	Thu Feb 12 09:46:55 2015 -0500
+++ b/mapper.xml	Wed Nov 23 16:32:13 2016 -0500
@@ -40,17 +40,19 @@
 
         #if $operation.collapse_map == "collapse_and_map" or $operation.collapse_map == "only_map"
             #if $operation.refGenomeSource.genomeSource == "history"
-                bowtie-build $operation.refGenomeSource.ownFile custom_bowtie_indices &&
+                bowtie-build '$operation.refGenomeSource.ownFile' custom_bowtie_indices &&
             #end if
         #end if
+
         mapper.pl 
     
-        $reads
+        '$reads'
         
         #if $reads.extension.startswith("fasta")
             -c
         #else if $reads.extension.startswith("fastq")
-            -e -h
+            -e
+            -h
         #end if
 
         $remove_non_canon
@@ -64,7 +66,7 @@
         -l $discard_short_reads
 
         #if $operation.collapse_map == "collapse_and_map" or $operation.collapse_map == "only_collapse"
-            -m -s $output_reads_collapsed
+            -m -s '$output_reads_collapsed'
         #end if
         
         #if $operation.collapse_map == "collapse_and_map" or $operation.collapse_map == "only_map"
@@ -73,14 +75,12 @@
             #if $operation.refGenomeSource.genomeSource == "history"
                 custom_bowtie_indices
             #else
-                $operation.refGenomeSource.index
+                '$operation.refGenomeSource.index.fields.path'
             #end if
-
             $operation.map_mismatch
-
             -r $operation.map_threshold
             
-            -t $output_mapping
+            -t '$output_mapping'
         #end if
 
         -v -n
@@ -95,7 +95,7 @@
         <regex match="Exception:" />
     </stdio>
     <inputs>
-        <param format="fastq, fasta" name="reads" type="data" optional="false" label="Deep sequencing reads" help="Reads in fastq or fasta format"/>
+        <param format="fastq, fasta" name="reads" type="data" optional="false" label="Deep sequencing reads" help="Reads in fastq or FASTA format"/>
         <param name="remove_non_canon" type="boolean" truevalue="-j" falsevalue="" checked="false" label="Remove reads with non-standard nucleotides" help="Remove all entries that have a sequence that contains letters other than a,c,g,t,u,n,A,C,G,T,U,N. (-j)"/>
         <param name="convert_rna_dna" type="boolean" truevalue="-i" falsevalue="" checked="false" label="Convert RNA to DNA alphabet (to map against genome)" help="(-i)"/>
 
@@ -181,23 +181,36 @@
     </tests>
     <help>
 <![CDATA[
-**What MiRDeep2 Mapper does**
+**What it does**
 
-The mapper module is designed as a tool to process deep sequencing reads and/or map them to the reference genome. 
-The module works in sequence space, and can process or map data that is in sequence fasta format. 
+The MiRDeep2 Mapper module is designed as a tool to process deep sequencing reads and/or map them to the reference genome. 
+The module works in sequence space, and can process or map data that is in sequence FASTA format. 
 A number of the functions of the mapper module are implemented specifically with Solexa/Illumina data in mind.
 
-**Example**
+**Input**
+
+Default input is a file in FASTA format, seq.txt or qseq.txt format. More input can be given depending on the options used. 
 
-Processing reads and mapping them to a genome.
+**Output**
+
+The output depends on the options used. Either a FASTA file with processed reads or an arf file with with mapped reads, or both, are output. 
+
+Arf format:
+Is a proprietary file format generated and processed by miRDeep2. It contains information of reads mapped to a reference genome. Each line in such a file contains 13 columns:
 
-The -c option designates that the input file is a fasta file. The -j options removes entries with
-non-canonical letters (letters other than a,c,g,t,u,n,A,C,G,T,U,N). The -k option clips adapters. The -l option discards reads shorter than 18 nts.
-The -m option collapses the reads. The -p option maps the processed reads against the previously indexed genome (cel_cluster). The -s option
-designates the name of the output file of processed reads and the -t option designates the name of the output file of the genome mappings. Last,
--v gives verbose output to the screen.
-
-    ``mapper.pl reads.fa -c -j -k TCGTATGCCGTCTTCTGCTTGT  -l 18 -m -p cel_cluster -s reads_collapsed.fa -t reads_collapsed_vs_genome.arf -v``
+1. read identifier
+2. length of read sequence
+3. start position in read sequence that is mapped
+4. end position in read sequence that is mapped
+5. read sequence
+6. identifier of the genome-part to which a read is mapped to. This is either a scaffold id or a chromosome name
+7. length of the genome sequence a read is mapped to
+8. start position in the genome where a read is mapped to
+9. end position in the genome where a read is mapped to
+10. genome sequence to which a read is mapped
+11. genome strand information. Plus means the read is aligned to the sense-strand of the genome. Minus means it is aligned to the antisense-strand of the genome.
+12. Number of mismatches in the read mapping
+13. Edit string that indicates matches by lowercase 'm' and mismatches by uppercase 'M'
 
 ]]>
     </help>