diff data_manager/hisat_index_builder.xml @ 0:8082f04de7ae draft default tip

planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/data_manager/hisat_index_builder.xml	Fri Nov 06 14:17:24 2015 -0500
@@ -0,0 +1,67 @@
+<tool id="hisat_index_builder_data_manager" name="HISAT index" tool_type="manage_data" version="1.0.0">
+    <description>builder</description>
+    <requirements>
+        <requirement type="package" version="0.1.6">hisat</requirement>
+    </requirements>
+    <stdio>
+        <exit_code range=":-1" />
+        <exit_code range="1:" />
+    </stdio>
+    <command interpreter="python">hisat_index_builder.py "${out_file}" --fasta_filename "${all_fasta_source.fields.path}" --fasta_dbkey "${all_fasta_source.fields.dbkey}" --fasta_description "${all_fasta_source.fields.name}" --data_table_name "hisat_indexes"</command>
+    <inputs>
+        <param label="Source FASTA Sequence" name="all_fasta_source" type="select">
+            <options from_data_table="all_fasta" />
+        </param>
+        <param label="Name of sequence" name="sequence_name" type="text" value="" />
+        <param label="ID for sequence" name="sequence_id" type="text" value="" />
+    </inputs>
+    <outputs>
+        <data format="data_manager_json" name="out_file" />
+    </outputs>
+    <help>
+<![CDATA[
+.. class:: infomark
+
+**Notice:** If you leave name, description, or id blank, it will be generated automatically. 
+
+What is HISAT?
+--------------
+
+`HISAT <http://ccb.jhu.edu/software/hisat>`__ is a fast and sensitive
+spliced alignment program. As part of HISAT, we have developed a new
+indexing scheme based on the Burrows-Wheeler transform
+(`BWT <http://en.wikipedia.org/wiki/Burrows-Wheeler_transform>`__) and
+the `FM index <http://en.wikipedia.org/wiki/FM-index>`__, called
+hierarchical indexing, that employs two types of indexes: (1) one global
+FM index representing the whole genome, and (2) many separate local FM
+indexes for small regions collectively covering the genome. Our
+hierarchical index for the human genome (about 3 billion bp) includes
+~48,000 local FM indexes, each representing a genomic region of
+~64,000bp. As the basis for non-gapped alignment, the FM index is
+extremely fast with a low memory footprint, as demonstrated by
+`Bowtie <http://bowtie-bio.sf.net>`__. In addition, HISAT provides
+several alignment strategies specifically designed for mapping different
+types of RNA-seq reads. All these together, HISAT enables extremely fast
+and sensitive alignment of reads, in particular those spanning two exons
+or more. As a result, HISAT is much faster >50 times than
+`TopHat2 <http://ccb.jhu.edu/software/tophat>`__ with better alignment
+quality. Although it uses a large number of indexes, the memory
+requirement of HISAT is still modest, approximately 4.3 GB for human.
+HISAT uses the `Bowtie2 <http://bowtie-bio.sf.net/bowtie2>`__
+implementation to handle most of the operations on the FM index. In
+addition to spliced alignment, HISAT handles reads involving indels and
+supports a paired-end alignment mode. Multiple processors can be used
+simultaneously to achieve greater alignment speed. HISAT outputs
+alignments in `SAM <http://samtools.sourceforge.net/SAM1.pdf>`__ format,
+enabling interoperation with a large number of other tools (e.g.
+`SAMtools <http://samtools.sourceforge.net>`__,
+`GATK <http://www.broadinstitute.org/gsa/wiki/index.php/The_Genome_Analysis_Toolkit>`__)
+that use SAM. HISAT is distributed under the `GPLv3
+license <http://www.gnu.org/licenses/gpl-3.0.html>`__, and it runs on
+the command line under Linux, Mac OS X and Windows.
+]]>
+    </help>
+    <citations>
+        <citation type="doi">10.1038/nmeth.3317</citation>
+    </citations>
+</tool>