Merge pull request #137 from davebx/hisat

Add HISAT wrapper and data manager.

data_managers/data_manager_hisat_index_builder/.shed.yml

@@ -0,0 +1,35 @@
+categories:
+- Data Managers
+description: HISAT is a fast and sensitive spliced alignment program.
+long_description: |
+  As part of HISAT, we have developed a new indexing scheme based on
+  the Burrows-Wheeler transform (BWT) and the 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. 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
+  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
+  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 processor
+  can be used simultaneously to achieve greater alignment speed.
+  HISAT outputs alignments in SAM format, enabling interoperation
+  with a large number of other tools (e.g. SAMtools, GATK) that use
+  SAM. HISAT is distributed under the GPLv3 license, and it runs on
+  the command line under Linux, Mac OS X and Windows.
+  
+  http://ccb.jhu.edu/software/hisat/index.shtml
+name: data_manager_hisat_index_builder
+owner: devteam
+remote_repository_url: https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_hisat_index_builder
+type: unrestricted

data_managers/data_manager_hisat_index_builder/data_manager/hisat_index_builder.py

@@ -0,0 +1,76 @@
+#!/usr/bin/env python
+# Based heavily on the Bowtie 2 data manager wrapper script by Dan Blankenberg
+
+import sys
+import os
+import optparse
+import subprocess
+
+from json import loads, dumps
+
+
+DEFAULT_DATA_TABLE_NAME = "hisat_indexes"
+
+def get_id_name( params, dbkey, fasta_description=None):
+    #TODO: ensure sequence_id is unique and does not already appear in location file
+    sequence_id = params['param_dict']['sequence_id']
+    if not sequence_id:
+        sequence_id = dbkey
+
+    sequence_name = params['param_dict']['sequence_name']
+    if not sequence_name:
+        sequence_name = fasta_description
+        if not sequence_name:
+            sequence_name = dbkey
+    return sequence_id, sequence_name
+
+def build_hisat_index( data_manager_dict, fasta_filename, params, target_directory, dbkey, sequence_id, sequence_name, data_table_name=DEFAULT_DATA_TABLE_NAME ):
+    #TODO: allow multiple FASTA input files
+    fasta_base_name = os.path.split( fasta_filename )[-1]
+    sym_linked_fasta_filename = os.path.join( target_directory, fasta_base_name )
+    os.symlink( fasta_filename, sym_linked_fasta_filename )
+    args = [ 'hisat-build', sym_linked_fasta_filename, sequence_id ]
+    proc = subprocess.Popen( args=args, shell=False, cwd=target_directory )
+    return_code = proc.wait()
+    if return_code:
+        print >> sys.stderr, "Error building index."
+        sys.exit( return_code )
+    data_table_entry = dict( value=sequence_id, dbkey=dbkey, name=sequence_name, path=sequence_id )
+    _add_data_table_entry( data_manager_dict, data_table_name, data_table_entry )
+
+def _add_data_table_entry( data_manager_dict, data_table_name, data_table_entry ):
+    data_manager_dict['data_tables'] = data_manager_dict.get( 'data_tables', {} )
+    data_manager_dict['data_tables'][ data_table_name ] = data_manager_dict['data_tables'].get( data_table_name, [] )
+    data_manager_dict['data_tables'][ data_table_name ].append( data_table_entry )
+    return data_manager_dict
+
+def main():
+    #Parse Command Line
+    parser = optparse.OptionParser()
+    parser.add_option( '-f', '--fasta_filename', dest='fasta_filename', action='store', type="string", default=None, help='fasta_filename' )
+    parser.add_option( '-d', '--fasta_dbkey', dest='fasta_dbkey', action='store', type="string", default=None, help='fasta_dbkey' )
+    parser.add_option( '-t', '--fasta_description', dest='fasta_description', action='store', type="string", default=None, help='fasta_description' )
+    parser.add_option( '-n', '--data_table_name', dest='data_table_name', action='store', type="string", default=None, help='data_table_name' )
+    (options, args) = parser.parse_args()
+
+    filename = args[0]
+
+    params = loads( open( filename ).read() )
+    target_directory = params[ 'output_data' ][0]['extra_files_path']
+    os.mkdir( target_directory )
+    data_manager_dict = {}
+
+    dbkey = options.fasta_dbkey
+
+    if dbkey in [ None, '', '?' ]:
+        raise Exception( '"%s" is not a valid dbkey. You must specify a valid dbkey.' % ( dbkey ) )
+
+    sequence_id, sequence_name = get_id_name( params, dbkey=dbkey, fasta_description=options.fasta_description )
+
+    #build the index
+    build_hisat_index( data_manager_dict, options.fasta_filename, params, target_directory, dbkey, sequence_id, sequence_name, data_table_name=options.data_table_name or DEFAULT_DATA_TABLE_NAME )
+
+    #save info to json file
+    open( filename, 'wb' ).write( dumps( data_manager_dict ) )
+
+if __name__ == "__main__": main()

data_managers/data_manager_hisat_index_builder/data_manager/hisat_index_builder.xml

@@ -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>

data_managers/data_manager_hisat_index_builder/data_manager_conf.xml

@@ -0,0 +1,20 @@
+<?xml version="1.0"?>
+<data_managers>
+    <data_manager tool_file="data_manager/hisat_index_builder.xml" id="hisat_index_builder" version="0.0.1">
+        <data_table name="hisat_indexes">
+            <output>
+                <column name="value" />
+                <column name="dbkey" />
+                <column name="name" />
+                <column name="path" output_ref="out_file" >
+                    <move type="directory" relativize_symlinks="True">
+                        <!-- <source>${path}</source>--> <!-- out_file.extra_files_path is used as base by default --> <!-- if no source, eg for type=directory, then refers to base -->
+                        <target base="${GALAXY_DATA_MANAGER_DATA_PATH}">${dbkey}/hisat_index/${value}</target>
+                    </move>
+                    <value_translation>${GALAXY_DATA_MANAGER_DATA_PATH}/${dbkey}/hisat_index/${value}/${path}</value_translation>
+                    <value_translation type="function">abspath</value_translation>
+                </column>
+            </output>
+        </data_table>
+    </data_manager>
+</data_managers>

data_managers/data_manager_hisat_index_builder/tool-data/all_fasta.loc.sample

@@ -0,0 +1,18 @@
+#This file lists the locations and dbkeys of all the fasta files
+#under the "genome" directory (a directory that contains a directory
+#for each build). The script extract_fasta.py will generate the file
+#all_fasta.loc. This file has the format (white space characters are
+#TAB characters):
+#
+#<unique_build_id>	<dbkey>		<display_name>	<file_path>
+#
+#So, all_fasta.loc could look something like this:
+#
+#apiMel3	apiMel3	Honeybee (Apis mellifera): apiMel3		/path/to/genome/apiMel3/apiMel3.fa
+#hg19canon	hg19		Human (Homo sapiens): hg19 Canonical		/path/to/genome/hg19/hg19canon.fa
+#hg19full	hg19		Human (Homo sapiens): hg19 Full			/path/to/genome/hg19/hg19full.fa
+#
+#Your all_fasta.loc file should contain an entry for each individual
+#fasta file. So there will be multiple fasta files for each build,
+#such as with hg19 above.
+#

data_managers/data_manager_hisat_index_builder/tool-data/hisat_indexes.loc.sample

@@ -0,0 +1,37 @@
+# hisat_indexes.loc.sample
+# This is a *.loc.sample file distributed with Galaxy that enables tools
+# to use a directory of indexed data files. This one is for HISAT.
+# See the wiki: http://wiki.galaxyproject.org/Admin/NGS%20Local%20Setup
+# First create these data files and save them in your own data directory structure.
+# Then, create a hisat_indexes.loc file to use those indexes with tools.
+# Copy this file, save it with the same name (minus the .sample), 
+# follow the format examples, and store the result in this directory.
+# The file should include an one line entry for each index set.
+# The path points to the "basename" for the set, not a specific file.
+# It has four text columns seperated by TABS.
+#
+# <unique_build_id>	<dbkey>	<display_name>	<file_base_path>
+#
+# So, for example, if you had hg18 indexes stored in:
+#
+#    /depot/data2/galaxy/hg19/hisat/
+#
+# containing hg19 genome and hg19.*.bt2 files, such as:
+#    -rw-rw-r-- 1 james   james   914M Feb 10 18:56 hg19canon.fa
+#    -rw-rw-r-- 1 james   james   914M Feb 10 18:56 hg19canon.1.bt2
+#    -rw-rw-r-- 1 james   james   683M Feb 10 18:56 hg19canon.2.bt2
+#    -rw-rw-r-- 1 james   james   3.3K Feb 10 16:54 hg19canon.3.bt2
+#    -rw-rw-r-- 1 james   james   683M Feb 10 16:54 hg19canon.4.bt2
+#    -rw-rw-r-- 1 james   james   914M Feb 10 20:45 hg19canon.rev.1.bt2
+#    -rw-rw-r-- 1 james   james   683M Feb 10 20:45 hg19canon.rev.2.bt2
+#
+# then the hisat_indexes.loc entry could look like this:
+#
+#hg19	hg19	Human (hg19)	/depot/data2/galaxy/hg19/hisat/hg19canon
+#
+#More examples:
+#
+#mm10	mm10	Mouse (mm10)	/depot/data2/galaxy/mm10/hisat/mm10
+#dm3	dm3		D. melanogaster (dm3)	/depot/data2/galaxy/mm10/hisat/dm3
+#
+#

data_managers/data_manager_hisat_index_builder/tool_data_table_conf.xml.sample

@@ -0,0 +1,13 @@
+<!-- Use the file tool_data_table_conf.xml.oldlocstyle if you don't want to update your loc files as changed in revision 4550:535d276c92bc-->
+<tables>
+    <!-- Locations of all fasta files under genome directory -->
+    <table name="all_fasta" comment_char="#">
+        <columns>value, dbkey, name, path</columns>
+        <file path="tool-data/all_fasta.loc" />
+    </table>
+    <!-- Locations of indexes in the hisat mapper format -->
+    <table name="hisat_indexes" comment_char="#">
+        <columns>value, dbkey, name, path</columns>
+        <file path="tool-data/hisat_indexes.loc" />
+    </table>
+</tables>

data_managers/data_manager_hisat_index_builder/tool_dependencies.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0"?>
+<tool_dependency>
+    <package name="hisat" version="0.1.6">
+        <repository name="package_hisat_0_1_6" owner="iuc" />
+    </package>
+</tool_dependency>

tools/hisat/.shed.yml

@@ -0,0 +1,35 @@
+categories:
+- Assembly
+description: HISAT is a fast and sensitive spliced alignment program.
+long_description: |
+  As part of HISAT, we have developed a new indexing scheme based on
+  the Burrows-Wheeler transform (BWT) and the 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. 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
+  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
+  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 processor
+  can be used simultaneously to achieve greater alignment speed.
+  HISAT outputs alignments in SAM format, enabling interoperation
+  with a large number of other tools (e.g. SAMtools, GATK) that use
+  SAM. HISAT is distributed under the GPLv3 license, and it runs on
+  the command line under Linux, Mac OS X and Windows.
+  
+  http://ccb.jhu.edu/software/hisat/index.shtml
+name: hisat
+owner: devteam
+remote_repository_url: https://github.com/galaxyproject/tools-devteam/tree/master/tools/hisat
+type: unrestricted