annotate 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
author devteam
date Fri, 06 Nov 2015 14:17:24 -0500
parents
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
1 <tool id="hisat_index_builder_data_manager" name="HISAT index" tool_type="manage_data" version="1.0.0">
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
2 <description>builder</description>
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
3 <requirements>
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
4 <requirement type="package" version="0.1.6">hisat</requirement>
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
5 </requirements>
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
6 <stdio>
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
7 <exit_code range=":-1" />
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
8 <exit_code range="1:" />
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
9 </stdio>
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
10 <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>
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
11 <inputs>
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
12 <param label="Source FASTA Sequence" name="all_fasta_source" type="select">
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
13 <options from_data_table="all_fasta" />
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
14 </param>
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
15 <param label="Name of sequence" name="sequence_name" type="text" value="" />
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
16 <param label="ID for sequence" name="sequence_id" type="text" value="" />
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
17 </inputs>
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
18 <outputs>
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
19 <data format="data_manager_json" name="out_file" />
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
20 </outputs>
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
21 <help>
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
22 <![CDATA[
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
23 .. class:: infomark
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
24
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
25 **Notice:** If you leave name, description, or id blank, it will be generated automatically.
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
26
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
27 What is HISAT?
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
28 --------------
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
29
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
30 `HISAT <http://ccb.jhu.edu/software/hisat>`__ is a fast and sensitive
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
31 spliced alignment program. As part of HISAT, we have developed a new
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
32 indexing scheme based on the Burrows-Wheeler transform
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
33 (`BWT <http://en.wikipedia.org/wiki/Burrows-Wheeler_transform>`__) and
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
34 the `FM index <http://en.wikipedia.org/wiki/FM-index>`__, called
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
35 hierarchical indexing, that employs two types of indexes: (1) one global
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
36 FM index representing the whole genome, and (2) many separate local FM
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
37 indexes for small regions collectively covering the genome. Our
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
38 hierarchical index for the human genome (about 3 billion bp) includes
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
39 ~48,000 local FM indexes, each representing a genomic region of
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
40 ~64,000bp. As the basis for non-gapped alignment, the FM index is
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
41 extremely fast with a low memory footprint, as demonstrated by
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
42 `Bowtie <http://bowtie-bio.sf.net>`__. In addition, HISAT provides
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
43 several alignment strategies specifically designed for mapping different
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
44 types of RNA-seq reads. All these together, HISAT enables extremely fast
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
45 and sensitive alignment of reads, in particular those spanning two exons
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
46 or more. As a result, HISAT is much faster >50 times than
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
47 `TopHat2 <http://ccb.jhu.edu/software/tophat>`__ with better alignment
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
48 quality. Although it uses a large number of indexes, the memory
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
49 requirement of HISAT is still modest, approximately 4.3 GB for human.
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
50 HISAT uses the `Bowtie2 <http://bowtie-bio.sf.net/bowtie2>`__
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
51 implementation to handle most of the operations on the FM index. In
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
52 addition to spliced alignment, HISAT handles reads involving indels and
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
53 supports a paired-end alignment mode. Multiple processors can be used
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
54 simultaneously to achieve greater alignment speed. HISAT outputs
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
55 alignments in `SAM <http://samtools.sourceforge.net/SAM1.pdf>`__ format,
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
56 enabling interoperation with a large number of other tools (e.g.
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
57 `SAMtools <http://samtools.sourceforge.net>`__,
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
58 `GATK <http://www.broadinstitute.org/gsa/wiki/index.php/The_Genome_Analysis_Toolkit>`__)
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
59 that use SAM. HISAT is distributed under the `GPLv3
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
60 license <http://www.gnu.org/licenses/gpl-3.0.html>`__, and it runs on
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
61 the command line under Linux, Mac OS X and Windows.
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
62 ]]>
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
63 </help>
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
64 <citations>
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
65 <citation type="doi">10.1038/nmeth.3317</citation>
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
66 </citations>
8082f04de7ae planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder commit 86cf90107482cab1cb47fc0d42d6705f8077daa7
devteam
parents:
diff changeset
67 </tool>