changeset 20:ac69be28e786 draft

FlaiMapper: added wrapper for FASTA->GTF conversion

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/flaimapper-gtf-from-fasta.xml	Wed Mar 25 12:37:45 2015 -0400
@@ -0,0 +1,98 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<tool id="flaimapper" name="FlaiMapper" version="1.1.5.b">
+	<description>Extract GTF file from FASTA file (as FlaiMapper reference).</description>
+	<requirements>
+		<requirement type="package" version="0.8.2.1">pysam</requirement>
+		<requirement type="package" version="1.1.5">flaimapper</requirement>
+	</requirements>
+	
+	<version_command>flaimapper --version</version_command>
+	
+	<command>
+		gtf-from-fasta
+			 -o $output
+			 $fasta
+	</command>
+	
+	<inputs>
+		<param name="fasta" type="data" format="fasta" label="Fasta sequence corresponding to reference genome" help="" />
+	</inputs>
+	
+	<outputs>
+		<data format="gtf" name="output" label="${tool.name} on ${', '.join([ str(a.hid)+': '+a.name for a in $alignments ])}" />
+	</outputs>
+	
+	<help>
+FlaiMapper wrapper for Galaxy
+=============================
+
+https://github.com/yhoogstrate/flaimapper
+http://www.ncbi.nlm.nih.gov/pubmed/25338717
+http://dx.doi.org/10.1093/bioinformatics/btu696
+
+Fragment Location Annotation Identification Mapper
+
+FlaiMapper: computational annotation of small ncRNA-derived fragments using RNA-seq high-throughput data.
+
+Input formats
+-------------
+To make FlaiMapper compatible with both an entire reference genome as a
+separate ncRNA database, it requires an additional GTF file *(mask file)*.
+The major difference between an entire reference and a ncRNA database
+is that an entire reference usually contains multiple ncRNAs per sequence
+entry (chromosome). While for the ncRNA database, each entry should
+represent one single mature ncRNA.
+
+Therefore the mask file that represents to the FASTA file of a ncRNA
+database will only contain the start- and end positions of each entry.
+To generate this in an automated fashion, you can make use of this tool
+*as long as the FASTA file doesn't contain entire chromosomes* but
+mature ncRNA.
+
+An example input file is **ncRNAdb09**, available at the following URLs:
+https://raw.githubusercontent.com/yhoogstrate/flaimapper/master/share/annotations/ncRNA_annotation/ncrnadb09.fa *(reference file)*
+
+It should generate a GTF/GFF file (mask file) similar to the following URL:
+https://raw.githubusercontent.com/yhoogstrate/flaimapper/master/share/annotations/ncRNA_annotation/ncrnadb09.gtf *(mask file)*
+
+Installation
+------------
+
+The wrapper makes use of easy_install to install a python egg. Please
+ensure you have easy_install installed.
+
+License
+-------
+
+**flaimapper** and **wrapper**:
+
+GPL (>=3)
+
+**pysam**:
+
+The MIT License
+
+Contact
+-------
+
+The tool wrapper has been written by Youri Hoogstrate from the Erasmus
+Medical Center (Rotterdam, Netherlands).
+
+
+Development
+-----------
+
+* Repository-Maintainer: Youri Hoogstrate
+* Repository-Developers: Youri Hoogstrate
+
+* Repository-Development: https://bitbucket.org/EMCbioinf/galaxy-tool-shed-tools
+
+The tool wrapper has been written by Youri Hoogstrate from the Erasmus
+Medical Center (Rotterdam, Netherlands).
+
+	</help>
+	
+	<citations>
+		<citation type="doi">10.1093/bioinformatics/btu696</citation>
+	</citations>
+</tool>

--- a/flaimapper.xml	Fri Mar 20 11:14:32 2015 -0400
+++ b/flaimapper.xml	Wed Mar 25 12:37:45 2015 -0400
@@ -60,7 +60,7 @@
 - http://genome.ucsc.edu/FAQ/FAQformat.html#format3
 - http://www.ensembl.org/info/website/upload/gff.html
 
-The reference sequence should be provided in FASTSA format.
+The reference sequence should be provided in FASTA format.
 
 You can access **ncRNAdb09** at the following URLs:
 https://raw.githubusercontent.com/yhoogstrate/flaimapper/master/share/annotations/ncRNA_annotation/ncrnadb09.gtf *(mask file)*
@@ -112,19 +112,9 @@
 The tool wrapper has been written by Youri Hoogstrate from the Erasmus
 Medical Center (Rotterdam, Netherlands).
 
-References
-----------
-**FlaiMapper: computational annotation of small ncRNA-derived fragments using RNA-seq high-throughput data.**
-
-*Hoogstrat* - Bioinformatics. 2014 Apr 1;30(7):923-30.
-
-*Youri Hoogstrate, Guido Jenster, and Elena S. Martens-Uzunova* - Bioinformatics (2015) 31 (5): 665-673
-
-- http://www.ncbi.nlm.nih.gov/pubmed/25338717
-- http://dx.doi.org/10.1093/bioinformatics/btu696
 	</help>
 	
 	<citations>
 		<citation type="doi">10.1093/bioinformatics/btu696</citation>
 	</citations>
-</tool>
\ No newline at end of file
+</tool>