# HG changeset patch
# User iuc
# Date 1479852720 18000
# Node ID a7fb84abef45ba17c34a098e848a9264efb6f7d7
planemo upload for repository https://github.com/galaxyproject/tools-iuc/data_managers/data_manager_bwameth_index_builder commit 30192223eeb60f33a42046921351c6ba3c80c90c
diff -r 000000000000 -r a7fb84abef45 data_manager/bwameth_index_builder.py
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/data_manager/bwameth_index_builder.py Tue Nov 22 17:12:00 2016 -0500
@@ -0,0 +1,64 @@
+#!/usr/bin/env python
+# Based heavily on the HISAT2 data manager wrapper
+
+import argparse
+import os
+import subprocess
+import sys
+from json import dumps, loads
+
+DEFAULT_DATA_TABLE_NAME = "bwameth_indexes"
+
+
+def build_bwameth_index(data_manager_dict, params, args):
+ data_table_name = args.data_table_name
+ target_directory = params[ 'output_data' ][0]['extra_files_path']
+ if not os.path.exists( target_directory ):
+ os.mkdir( target_directory )
+ fasta_base_name = os.path.basename(args.fasta_filename)
+ sym_linked_fasta_filename = os.path.join(target_directory, fasta_base_name)
+ os.symlink(os.path.abspath(args.fasta_filename), sym_linked_fasta_filename)
+ cmd = ['bwameth.py', 'index', sym_linked_fasta_filename]
+ proc = subprocess.Popen(args=cmd, 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=args.dbKey, dbkey=args.dbkey, name=args.name, path=args.dbKey)
+ _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 = argparse.ArgumentParser()
+ parser.add_argument( '--output', default=None )
+ parser.add_argument( '--fasta_filename', default=None )
+ parser.add_argument( '--dbkey', default=None )
+ parser.add_argument( '--name', default=None )
+ parser.add_argument( '--description', default=None )
+ parser.add_argument( '--data_table_name', default=DEFAULT_DATA_TABLE_NAME )
+ args = parser.parse_args()
+
+ filename = args.output
+ params = loads(open(filename).read())
+ data_manager_dict = {}
+
+ if args.dbkey in [ None, '', '?' ]:
+ raise Exception('"%s" is not a valid dbkey. You must specify a valid dbkey.' % (args.dbkey))
+
+ # build the index
+ build_bwameth_index(data_manager_dict, params, args)
+
+ # save info to json file
+ open(filename, 'wb').write(dumps(data_manager_dict))
+
+
+if __name__ == "__main__":
+ main()
diff -r 000000000000 -r a7fb84abef45 data_manager/bwameth_index_builder.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/data_manager/bwameth_index_builder.xml Tue Nov 22 17:12:00 2016 -0500
@@ -0,0 +1,59 @@
+
+ builder
+
+ bwa
+ samtools
+ bwameth
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ @misc{1401.1129,
+ Author = {Brent S. Pedersen and Kenneth Eyring and Subhajyoti De and Ivana V. Yang and David A. Schwartz},
+ Title = {Fast and accurate alignment of long bisulfite-seq reads},
+ Year = {2014},
+ Eprint = {arXiv:1401.1129},
+ }
+
+
diff -r 000000000000 -r a7fb84abef45 data_manager_conf.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/data_manager_conf.xml Tue Nov 22 17:12:00 2016 -0500
@@ -0,0 +1,19 @@
+
+
+
+
+
+
+
+
diff -r 000000000000 -r a7fb84abef45 tool-data/all_fasta.loc.sample
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/all_fasta.loc.sample Tue Nov 22 17:12:00 2016 -0500
@@ -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):
+#
+#
+#
+#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.
+#
diff -r 000000000000 -r a7fb84abef45 tool-data/bwameth_indexes.loc.sample
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/bwameth_indexes.loc.sample Tue Nov 22 17:12:00 2016 -0500
@@ -0,0 +1,15 @@
+# This is a sample file distributed with Galaxy that is used to define a
+# list of bwa-meth indices, using three columns tab separated:
+#
+#
+#
+# An index can be created with the following command:
+#
+# bwameth.py index /some/path/genome.fa
+#
+# "/some/path/genome.fa" would then be the last column in the line
+# If this were for the mm10 mouse genome, the resulting entry would look like:
+#
+#mm9 mm9 Mouse (mm9) /some/path/genome.fa
+#
+#
diff -r 000000000000 -r a7fb84abef45 tool_data_table_conf.xml.sample
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_data_table_conf.xml.sample Tue Nov 22 17:12:00 2016 -0500
@@ -0,0 +1,13 @@
+
+
+
+
+ value, dbkey, name, path
+
+
+
+
+ value, dbkey, name, path
+
+
+
diff -r 000000000000 -r a7fb84abef45 tool_dependencies.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_dependencies.xml Tue Nov 22 17:12:00 2016 -0500
@@ -0,0 +1,12 @@
+
+
+
+
+
+
+
+
+
+
+
+