# HG changeset patch
# User tomnl
# Date 1486139137 18000
# Node ID 5990ad11314551d7bd579340580005f5a35d7ccc
Uploaded
diff -r 000000000000 -r 5990ad113145 nmrml2isa-galaxy/.gitignore
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/nmrml2isa-galaxy/.gitignore Fri Feb 03 11:25:37 2017 -0500
@@ -0,0 +1,7 @@
+*.pyc
+.idea
+*.egg-info
+.egg
+*~
+*.
+.DS_Store
diff -r 000000000000 -r 5990ad113145 nmrml2isa-galaxy/.travis.yml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/nmrml2isa-galaxy/.travis.yml Fri Feb 03 11:25:37 2017 -0500
@@ -0,0 +1,16 @@
+language: python
+
+before_install:
+ - sudo apt-get install -y python-virtualenv
+ - virtualenv planemo-venv
+ - . planemo-venv/bin/activate
+ - pip install --upgrade pip setuptools
+ - pip install planemo
+ - planemo conda_init
+
+install:
+ - planemo conda_install ${TRAVIS_BUILD_DIR}/galaxy/nmrml2isa/
+
+script:
+ - planemo test --install_galaxy --no_cache_galaxy --conda_dependency_resolution ${TRAVIS_BUILD_DIR}/galaxy/nmrml2isa/ --galaxy_branch "dev"
+
diff -r 000000000000 -r 5990ad113145 nmrml2isa-galaxy/README.md
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/nmrml2isa-galaxy/README.md Fri Feb 03 11:25:37 2017 -0500
@@ -0,0 +1,32 @@
+nmrml2isa for galaxy
+===============
+
+[](http://bioconda.github.io/recipes/nmrml2isa/README.html) [](https://travis-ci.org/ISA-tools/nmrml2isa-galaxy)
+
+This is a Galaxy wrapper for the nmrml2isa python package tool.
+
+- Full documentation: http://2isa.readthedocs.io/en/latest/
+- Python PyPi package: https://pypi.python.org/pypi/mzml2isa/
+- Github code: https://github.com/ISA-tools/mzml2isa
+
+nmrml2isa is a program that allows you to convert metabolomic studies in .mzML format to the open ISA-Tab standard supported by the MetaboLights database.
+
+Installation
+===============
+
+The recommended installation is by means of the toolshed (https://toolshed.g2.bx.psu.edu/). Dependencies should be installed automatically when using Galaxy version >= 16.10.
+
+The dependencies are dealt with Bioconda. To ensure that Bioconda is working check to make sure the following settings are in the config/galaxy.ini file.
+
+```
+# dependencies before each job runs.
+conda_auto_install = True
+# Set to True to instruct Galaxy to install Conda from the web automatically
+# if it cannot find a local copy and conda_exec is not configured.
+conda_auto_init = True
+```
+
+
+Licence
+===============
+GNU General Public License v3 (GPLv3)
diff -r 000000000000 -r 5990ad113145 nmrml2isa-galaxy/galaxy/nmrml2isa/README.rst
diff -r 000000000000 -r 5990ad113145 nmrml2isa-galaxy/galaxy/nmrml2isa/nmrml2isa.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/nmrml2isa-galaxy/galaxy/nmrml2isa/nmrml2isa.xml Fri Feb 03 11:25:37 2017 -0500
@@ -0,0 +1,256 @@
+
+ Parser to get meta information from nmrML files and create an ISA-Tab structure
+
+
+ nmrml2isa_macros.xml
+
+
+
i_Investigation.txt
s_test.txt
\ No newline at end of file
diff -r 000000000000 -r 5990ad113145 nmrml2isa-galaxy/galaxy/nmrml2isa/test-data/metabolomics_study/test/s_test.txt
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/nmrml2isa-galaxy/galaxy/nmrml2isa/test-data/metabolomics_study/test/s_test.txt Fri Feb 03 11:25:37 2017 -0500
@@ -0,0 +1,4 @@
+"Source Name" "Characteristics[Organism]" "Term Source REF" "Term Accession Number" "Characteristics[Organism variant]" "Term Source REF" "Term Accession Number" "Characteristics[Organism part]" "Term Source REF" "Term Accession Number" "Protocol REF" "Sample Name"
+"" "" "" "" "" "" "" "" "" "" "Sample collection" "ADG10003u_007"
+"" "" "" "" "" "" "" "" "" "" "Sample collection" "ADG10003u_008"
+"" "" "" "" "" "" "" "" "" "" "Sample collection" "ADG10003u_009"
diff -r 000000000000 -r 5990ad113145 nmrml2isa-galaxy/galaxy/nmrml2isa/tool-data/get_status_ont.py
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/nmrml2isa-galaxy/galaxy/nmrml2isa/tool-data/get_status_ont.py Fri Feb 03 11:25:37 2017 -0500
@@ -0,0 +1,51 @@
+import sys
+import os
+import json
+import urllib.error
+import urllib.request as rq
+from urllib.parse import quote
+import csv
+
+###############################################################################
+# Python3 script to get tab seperated maf_index.loc files for drop down menus
+###############################################################################
+# Code modified from mzm2isa-qt python package developed by Martin Larralde
+# https://github.com/althonos/mzml2isa-qt/scrapers.py
+
+
+def get_ont_loc(jsonSourceUrl, sparName, ontoClass, filepth):
+ onto = json.loads(rq.urlopen(jsonSourceUrl).read().decode('utf-8'))
+ info = []
+ for x in onto:
+ if '@type' in x:
+ if ontoClass in x['@type']:
+ info.append(x)
+ info = [ (x['http://www.w3.org/2000/01/rdf-schema#label'],x['@id']) for x in info ]
+
+ ontd = {x[0]['@value'].capitalize():y for (x,y) in info}
+
+ with open(filepth, 'w') as f:
+ writer = csv.writer(f, delimiter='\t', quoting=csv.QUOTE_ALL)
+ writer.writerow(["name", "link"])
+ for key, value in ontd.items():
+ writer.writerow([key, value])
+
+ return ontd
+
+#-------------------------------
+# publication status ontology
+#-------------------------------
+jsonSourceUrl = "http://www.sparontologies.net/ontologies/pso/source.json"
+sparName = "pso"
+ontoClass = "http://purl.org/spar/pso/PublicationStatus"
+get_ont_loc(jsonSourceUrl, sparName, ontoClass, './pub_status.loc')
+
+#-------------------------------
+# Job role ontology
+#-------------------------------
+jsonSourceUrl = "http://www.sparontologies.net/ontologies/pro/source.json"
+sparName = "pro"
+ontoClass = "http://purl.org/spar/pro/PublishingRole"
+get_ont_loc(jsonSourceUrl, sparName, ontoClass, './pub_role.loc')
+
+
diff -r 000000000000 -r 5990ad113145 nmrml2isa-galaxy/galaxy/nmrml2isa/wrapper.py
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/nmrml2isa-galaxy/galaxy/nmrml2isa/wrapper.py Fri Feb 03 11:25:37 2017 -0500
@@ -0,0 +1,229 @@
+#!/usr/bin/env python
+
+import sys
+import json
+import os
+import argparse
+import textwrap
+import csv
+import inspect
+
+
+def ontology_lookup(name, table):
+ # takes in ontology name and source (e.g. loc file) and outputs the associated accesion number
+ filename = inspect.getframeinfo(inspect.currentframe()).filename
+ path = os.path.dirname(os.path.abspath(filename))
+
+ # check if correct table
+ if table=="role":
+ tablepth = os.path.join(path, 'pub_role.loc')
+ elif table=="status":
+ tablepth = os.path.join(path, 'pub_status.loc')
+ else:
+ print "Table not recognised"
+ return ""
+
+ with open(tablepth, "rb") as csvfile:
+ reader = csv.reader(csvfile, delimiter='\t')
+ ont_dict = dict((k, v) for k, v in reader)
+ try:
+ print ont_dict[name]
+ return ont_dict[name]
+ except KeyError:
+ return ""
+
+
+
+def main():
+
+ p = argparse.ArgumentParser(prog='PROG',
+ formatter_class=argparse.RawDescriptionHelpFormatter,
+ description='''nmrml2isa''',
+ epilog=textwrap.dedent('''\
+ -------------------------------------------------------------------------
+ '''))
+
+
+ p.add_argument('-inputzip', dest='inputzip', required=True)
+ p.add_argument('-out_dir', dest='out_dir', required=True)
+ p.add_argument('-html_file', dest='html_file', required=True)
+ p.add_argument('-study_title', dest='study_title', required=True)
+
+ p.add_argument('-jsontxt', dest='jsontxt', required=False, nargs='?')
+
+ p.add_argument('--s_submission_date', dest='s_submission_date', required=False, default="", nargs='?')
+ p.add_argument('--s_release_date', dest='s_release_date', required=False, default="", nargs='?')
+ p.add_argument('--s_description', dest='s_description', required=False, default="", nargs='?')
+ p.add_argument('--s_pubmed', dest='s_pubmed', required=False, default="", nargs='?')
+ p.add_argument('--s_pub_doi', dest='s_pub_doi', required=False, default="", nargs='?')
+ p.add_argument('--s_pub_status', dest='s_pub_status', required=False, default="", nargs='?')
+ p.add_argument('--s_pub_author', dest='s_pub_author', required=False, default="", nargs='?')
+ p.add_argument('--s_pub_title', dest='s_pub_title', required=False, default="", nargs='?')
+ p.add_argument('--s_first_name', dest='s_first_name', required=False, default="", nargs='?')
+ p.add_argument('--s_mid_initials', dest='s_mid_initials', required=False, default="", nargs='?')
+ p.add_argument('--s_last_name', dest='s_last_name', required=False, default="", nargs='?')
+ p.add_argument('--s_telephone', dest='s_telephone', required=False, default="", nargs='?')
+ p.add_argument('--s_fax', dest='s_fax', required=False, default="", nargs='?')
+ p.add_argument('--s_affiliation', dest='s_affiliation', required=False, default="", nargs='?')
+ p.add_argument('--s_role', dest='s_role', required=False, default="", nargs='?')
+ p.add_argument('--s_mail', dest='s_mail', required=False, default="", nargs='?')
+ p.add_argument('--s_address', dest='s_address', required=False, default="", nargs='?')
+ p.add_argument('--i_submission_date', dest='i_submission_date', required=False, default="", nargs='?')
+ p.add_argument('--i_release_date', dest='i_release_date', required=False, default="", nargs='?')
+ p.add_argument('--i_description', dest='i_description', required=False, default="", nargs='?')
+ p.add_argument('--i_pubmed', dest='i_pubmed', required=False, default="", nargs='?')
+ p.add_argument('--i_pub_doi', dest='i_pub_doi', required=False, default="", nargs='?')
+ p.add_argument('--i_pub_title', dest='i_pub_title', required=False, default="", nargs='?')
+ p.add_argument('--i_pub_status', dest='i_pub_status', required=False, default="", nargs='?')
+ p.add_argument('--i_pub_author', dest='i_pub_author', required=False, default="", nargs='?')
+ p.add_argument('--i_first_name', dest='i_first_name', required=False, default="", nargs='?')
+ p.add_argument('--i_mid_initials', dest='i_mid_initials', required=False, default="", nargs='?')
+ p.add_argument('--i_last_name', dest='i_last_name', required=False, default="", nargs='?')
+ p.add_argument('--i_telephone', dest='i_telephone', required=False, default="", nargs='?')
+ p.add_argument('--i_fax', dest='i_fax', required=False, default="", nargs='?')
+ p.add_argument('--i_affiliation', dest='i_affiliation', required=False, default="", nargs='?')
+ p.add_argument('--i_role', dest='i_role', required=False, default="", nargs='?')
+ p.add_argument('--i_mail', dest='i_mail', required=False, default="", nargs='?')
+ p.add_argument('--i_address', dest='i_address', required=False, default="", nargs='?')
+ p.add_argument('--organism_text', dest='organism_text', required=False, default="", nargs='?')
+ p.add_argument('--organism_ref', dest='organism_ref', required=False, default="", nargs='?')
+ p.add_argument('--organism_iri', dest='organism_iri', required=False, default="", nargs='?')
+ p.add_argument('--organism_part_text', dest='organism_part_text', required=False, default="", nargs='?')
+ p.add_argument('--organism_part_ref', dest='organism_part_ref', required=False, default="", nargs='?')
+ p.add_argument('--organism_part_iri', dest='organism_part_iri', required=False, default="", nargs='?')
+ p.add_argument('--organism_variant_text', dest='organism_variant_text', required=False, default="", nargs='?')
+ p.add_argument('--organism_variant_ref', dest='organism_variant_ref', required=False, default="", nargs='?')
+ p.add_argument('--organism_variant_iri', dest='organism_variant_iri', required=False, default="", nargs='?')
+
+ args = p.parse_args()
+
+ USERMETA = {'characteristics': {'organism': {'name': '', 'accession': '', 'ref': ''},
+ 'organism_variant': {'name': '', 'accession': '', 'ref': ''},
+ 'organism_part': {'name': '', 'accession': '', 'ref': ''},
+ },
+ 'investigation': {'identifier': '', 'title': 'Investigation', 'description': '',
+ 'submission_date': '', 'release_date': ''
+ },
+ 'investigation_publication': {'pubmed': '', 'doi': '', 'author_list': '', 'title': '',
+ 'status': {'name': '', 'accession': '', 'ref': 'PSO'},
+ },
+
+ 'study': {
+ 'title': '', 'description': '', 'submission_date': '', 'release_date': '',
+ },
+ 'study_publication': {'pubmed': '', 'doi': '', 'author_list': '', 'title': '',
+ 'status': {'name': '', 'accession': '', 'ref': 'PSO'},
+ },
+
+ 'description': {'sample_collect': '', 'extraction': '', 'chroma': '', 'mass_spec': '',
+ 'data_trans': '', 'metabo_id': ''
+ },
+
+ # Multiple Values Parameters
+ 'study_contacts': [
+ {'first_name': '', 'last_name': '', 'mid': '', 'email': '',
+ 'fax': '', 'phone': '', 'adress': '', 'affiliation': '',
+ 'roles': {'name': '', 'accession': '', 'ref': ''},
+ },
+ ],
+
+ 'investigation_contacts': [
+ {'first_name': '', 'last_name': '', 'mid': '', 'email': '',
+ 'fax': '', 'phone': '', 'adress': '', 'affiliation': '',
+ 'roles': {'name': '', 'accession': '', 'ref': ''},
+ },
+ ],
+
+ }
+
+ # check if using json file
+ if args.jsontxt and os.path.isfile(args.jsontxt):
+ with open(args.jsontxt, 'r') as f:
+ USERMETA = json.load(f)
+ else:
+
+ # Fill in USERMETA dictionary
+ USERMETA['characteristics']['organism']['value'] = args.organism_text
+ USERMETA['characteristics']['organism']['accession'] = args.organism_iri
+ USERMETA['characteristics']['organism']['ref'] = args.organism_ref
+
+ USERMETA['characteristics']['organism_variant']['value'] = args.organism_variant_text
+ USERMETA['characteristics']['organism_variant']['accession'] = args.organism_variant_iri
+ USERMETA['characteristics']['organism_variant']['ref'] = args.organism_variant_ref
+
+ USERMETA['characteristics']['organism_part']['value'] = args.organism_part_text
+ USERMETA['characteristics']['organism_part']['accession'] = args.organism_part_iri
+ USERMETA['characteristics']['organism_part']['ref'] = args.organism_part_ref
+
+ # USERMETA['investigation']['identifier'] = # uses study identifier
+ USERMETA['investigation']['description'] = args.i_description
+ USERMETA['investigation']['submission_date'] = args.i_submission_date
+ USERMETA['investigation']['release_date'] = args.i_release_date
+
+ USERMETA['investigation_publication']['pubmed'] = args.i_pubmed
+ USERMETA['investigation_publication']['author_list'] = args.i_pub_author
+ USERMETA['investigation_publication']['title'] = args.i_pub_title
+ USERMETA['investigation_publication']['doi'] = args.i_pub_doi
+ USERMETA['investigation_publication']['status']['name'] = args.i_pub_status
+ USERMETA['investigation_publication']['status']['accession'] = ontology_lookup(args.i_pub_status, 'status')
+
+ USERMETA['investigation_contacts'][0]['first_name'] = args.i_first_name
+ USERMETA['investigation_contacts'][0]['last_name'] = args.i_last_name
+ USERMETA['investigation_contacts'][0]['mid'] = args.i_mid_initials
+ USERMETA['investigation_contacts'][0]['email'] = args.i_mail
+ USERMETA['investigation_contacts'][0]['fax'] = args.i_fax
+ USERMETA['investigation_contacts'][0]['phone'] = args.i_telephone
+ USERMETA['investigation_contacts'][0]['adress'] = args.i_address
+ USERMETA['investigation_contacts'][0]['affiliation'] = args.i_affiliation
+ USERMETA['investigation_contacts'][0]['roles']['name'] = args.i_role
+ USERMETA['investigation_contacts'][0]['roles']['accession'] = ontology_lookup(args.i_role, 'role')
+
+ USERMETA['study']['title'] = args.study_title
+ USERMETA['study']['description'] = args.s_description
+ USERMETA['study']['submission_date'] = args.s_submission_date
+ USERMETA['study']['release_date'] = args.s_release_date
+
+ USERMETA['study_publication']['pubmed'] = args.s_pubmed
+ USERMETA['study_publication']['author_list'] = args.s_pub_author
+ USERMETA['study_publication']['title'] = args.s_pub_title
+ USERMETA['study_publication']['doi'] = args.s_pub_doi
+ USERMETA['study_publication']['status']['name'] = args.s_pub_status
+ USERMETA['study_publication']['status']['accession'] = ontology_lookup(args.s_pub_status, 'status')
+
+ USERMETA['study_contacts'][0]['first_name'] = args.s_first_name
+ USERMETA['study_contacts'][0]['last_name'] = args.s_last_name
+ USERMETA['study_contacts'][0]['mid'] = args.s_mid_initials
+ USERMETA['study_contacts'][0]['email'] = args.s_mail
+ USERMETA['study_contacts'][0]['fax'] = args.s_fax
+ USERMETA['study_contacts'][0]['phone'] = args.s_telephone
+ USERMETA['study_contacts'][0]['adress'] = args.s_address
+ USERMETA['study_contacts'][0]['affiliation'] = args.s_affiliation
+ USERMETA['study_contacts'][0]['roles']['name'] = args.s_role
+ USERMETA['study_contacts'][0]['roles']['accession'] = ontology_lookup(args.s_role, 'role')
+
+
+ try:
+ from nmrml2isa.parsing import full_parse
+ # import progressbar as pb
+ # parse the files
+ full_parse(args.inputzip, args.out_dir, args.study_title, usermeta=USERMETA, verbose=True)
+
+ except ImportError:
+ import tempfile
+ temp = tempfile.NamedTemporaryFile()
+ temp.write(json.dumps(USERMETA))
+ temp.seek(0)
+ os.system("nmrml2isa -i %s -o %s -s %s -m %s" % (args.inputzip, args.out_dir, args.study_title, temp.name))
+ temp.close()
+
+ html_code = 'a_%s_metabolite_profiling_NMR_spectroscopy.txt' \
+ '
i_Investigation.txt
' \
+ 's_test.txt
' % tuple([args.study_title] * 6)
+
+ with open(args.html_file, 'wb') as f:
+ f.write(html_code)
+
+
+
+if __name__ == "__main__":
+ main()
diff -r 000000000000 -r 5990ad113145 nmrml2isa-galaxy/test.sh
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/nmrml2isa-galaxy/test.sh Fri Feb 03 11:25:37 2017 -0500
@@ -0,0 +1,22 @@
+sudo apt-get install python-dev libxml2-dev libxslt1-dev zlib1g-dev
+sudo apt-get install -y python-virtualenv
+virtualenv planemo-venv
+. planemo-venv/bin/activate
+pip install --upgrade pip setuptools
+pip install planemo
+#planemo travis_before_install
+#. .travis/env.sh # source environment created by planemo
+export DOWNLOAD_CACHE=$HOME/download_cache
+mkdir $DOWNLOAD_CACHE
+#git clone https://github.com/ISA-tools/nmrml2isa-galaxy.git
+planemo dependency_script -r packages/package_nmrml2isa_0_4_22/
+. env.sh
+bash dep_install.sh
+planemo test --galaxy_root=../galaxy galaxy/nmrml2isa/
+rm env.sh
+rm dep_install.sh
+deactivate #exit virtualenv
+rm -r planemo-venv
+rm -r lib
+
+