# HG changeset patch
# User sanbi-uwc
# Date 1497845298 14400
# Node ID 3e14eda348d378a80c878f37a3eb9bfcb4ac21cf
planemo upload for repository https://github.com/sanbi-sa/tools-sanbi-uwc commit 0245b4efed8ced6d06d76f1249a47d2178285385
diff -r 000000000000 -r 3e14eda348d3 vcf2neo.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/vcf2neo.xml Mon Jun 19 00:08:18 2017 -0400
@@ -0,0 +1,54 @@
+
+
+ Parses VCF files and SnpEff annotation and build a
+ Neo4j Graph database.
+
+ py2neo
+ vcf2neo
+
+ '${outputDb}'
+ ]]>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
diff -r 000000000000 -r 3e14eda348d3 vcf2neo_wrapper.py
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/vcf2neo_wrapper.py Mon Jun 19 00:08:18 2017 -0400
@@ -0,0 +1,51 @@
+#!/usr/bin/env python
+
+from __future__ import print_function
+import argparse
+import os
+import shlex
+import subprocess
+import uuid
+import sys
+
+parser = argparse.ArgumentParser(
+ description="Call vcf2neo on VCF inputs from Galaxy")
+
+parser.add_argument('--vcf_dataset_names', nargs='+',
+ help='Names of VCF datasets')
+parser.add_argument('--neo4j_db_path', help='Neo4j database directory')
+parser.add_argument('--user', help='Email of Galaxy user running this tool')
+parser.add_argument('--variantset_name',
+ help='Name for the VariantSet containing all the variants')
+parser.add_argument('--vcf_files',
+ help='VCF format variant file', nargs='+')
+
+args = parser.parse_args()
+
+os.mkdir(args.variantset_name)
+
+print("VCF names:", len(args.vcf_dataset_names), args.vcf_dataset_names, file=sys.stderr)
+print("VCF files:", len(args.vcf_files), args.vcf_files, file=sys.stderr)
+for i, vcf_file in enumerate(args.vcf_files):
+ print("XXXX I:", i, vcf_file, file=sys.stderr)
+ callset_name = args.vcf_dataset_names[i]
+ os.symlink(vcf_file, os.path.join(args.variantset_name,
+ callset_name) + '.vcf')
+# Usage: vcf2neo init [OPTIONS] VCF_DIR OWNER [HISTORY_ID] [OUTPUT_DIR]
+#
+# Copy reference database and load VCF to Neo4j Graph database. :param
+# vcf_dir: :param refdb_dir: :param d: :return:
+#
+# Options:
+# -d / -D Run Neo4j docker container.
+# --help Show this message and exit.
+
+history_id = str(uuid.uuid4())
+cmd_str = ('vcf2neo init -d ' +
+ '{input_vcf_dir} {email} {history_id} {neo4j_db_path}'.format(
+ input_vcf_dir=args.variantset_name,
+ email=args.user,
+ history_id=history_id,
+ neo4j_db_path=args.neo4j_db_path))
+cmd = shlex.split(cmd_str)
+subprocess.check_call(cmd)
diff -r 000000000000 -r 3e14eda348d3 write_db_summary.py
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/write_db_summary.py Mon Jun 19 00:08:18 2017 -0400
@@ -0,0 +1,27 @@
+#!/usr/bin/env python
+from __future__ import print_function
+
+import argparse
+import os
+import os.path
+
+parser = argparse.ArgumentParser(
+ description="Write HTML summary from neostore datatype")
+parser.add_argument('basepath')
+parser.add_argument('label')
+
+args = parser.parse_args()
+
+output = """Files for Composite Dataset ({})
+ This composite dataset is composed of
+ the following files:\n""".format(args.label)
+db_path = args.basepath + '/neo4jdb/databases/graph.db'
+for filename in os.listdir(db_path):
+ if filename.startswith('.'):
+ continue
+ path = db_path + '/' + filename
+ if os.path.isdir(path):
+ continue
+ output += "- {}
\n".format(filename)
+output += '
\b'
+print(output)