--- /dev/null
+"""Create a track hub
+"""
+
+#!/usr/bin/env python
+from ConfigParser import SafeConfigParser
+import fnmatch
+from glob import glob
+import json
+import logging
+import netrc
+from optparse import OptionParser, OptionGroup
+import os
+from pprint import pprint, pformat
+import shlex
+from StringIO import StringIO
+import stat
+import sys
+import time
+import types
+import urllib
+import urllib2
+import urlparse
+from zipfile import ZipFile
+
+import RDF
+
+if not 'DJANGO_SETTINGS_MODULE' in os.environ:
+ os.environ['DJANGO_SETTINGS_MODULE'] = 'htsworkflow.settings'
+
+
+from htsworkflow.util import api
+from htsworkflow.util.rdfhelp import \
+ dafTermOntology, \
+ fromTypedNode, \
+ get_model, \
+ get_serializer, \
+ load_into_model, \
+ sparql_query, \
+ submissionOntology
+from htsworkflow.submission.daf import get_submission_uri
+from htsworkflow.submission.results import ResultMap
+from htsworkflow.submission.trackhub import TrackHubSubmission
+from htsworkflow.submission.condorfastq import CondorFastqExtract
+
+logger = logging.getLogger(__name__)
+
+def main(cmdline=None):
+ parser = make_parser()
+ opts, args = parser.parse_args(cmdline)
+ submission_uri = None
+
+ if opts.debug:
+ logging.basicConfig(level = logging.DEBUG )
+ elif opts.verbose:
+ logging.basicConfig(level = logging.INFO )
+ else:
+ logging.basicConfig(level = logging.WARNING )
+
+ apidata = api.make_auth_from_opts(opts, parser)
+
+ model = get_model(opts.model, opts.db_path)
+ mapper = None
+ if opts.name:
+ mapper = TrackHubSubmission(opts.name, model, host=opts.host)
+ submission_uri = get_submission_uri(opts.name)
+
+
+ if opts.load_rdf is not None:
+ if submission_uri is None:
+ parser.error("Please specify the submission name")
+ load_into_model(model, 'turtle', opts.load_rdf, submission_uri)
+
+ results = ResultMap()
+ for a in args:
+ if os.path.exists(a):
+ results.add_results_from_file(a)
+ else:
+ logger.warn("File %s doesn't exist.", a)
+
+ if opts.make_tree_from is not None:
+ results.make_tree_from(opts.make_tree_from)
+
+ if opts.fastq:
+ logger.info("Building fastq extraction scripts")
+ flowcells = os.path.join(opts.sequence, 'flowcells')
+ extractor = CondorFastqExtract(opts.host, flowcells,
+ model=opts.model,
+ force=opts.force)
+ extractor.create_scripts(results)
+
+ if opts.scan_submission:
+ if opts.name is None:
+ parser.error("Please define a submission name")
+ mapper.scan_submission_dirs(results)
+
+ if opts.make_hub:
+ mapper.make_hub(results)
+
+ if opts.sparql:
+ sparql_query(model, opts.sparql)
+
+ if opts.print_rdf:
+ writer = get_serializer()
+ print writer.serialize_model_to_string(model)
+
+
+def make_parser():
+ parser = OptionParser()
+
+ model = OptionGroup(parser, 'model')
+ model.add_option('--name', help="Set submission name")
+ model.add_option('--db-path', default=None,
+ help="set rdf database path")
+ model.add_option('--model', default=None,
+ help="Load model database")
+ model.add_option('--load-rdf', default=None,
+ help="load rdf statements into model")
+ model.add_option('--sparql', default=None, help="execute sparql query")
+ model.add_option('--print-rdf', action="store_true", default=False,
+ help="print ending model state")
+ parser.add_option_group(model)
+ # commands
+ commands = OptionGroup(parser, 'commands')
+ commands.add_option('--make-tree-from',
+ help="create directories & link data files",
+ default=None)
+ commands.add_option('--fastq', default=False, action="store_true",
+ help="generate scripts for making fastq files")
+ commands.add_option('--scan-submission', default=False, action="store_true",
+ help="Import metadata for submission into our model")
+ commands.add_option('--make-hub', help='make the hub file', default=False,
+ action="store_true")
+
+ parser.add_option_group(commands)
+
+ parser.add_option('--force', default=False, action="store_true",
+ help="Force regenerating fastqs")
+ parser.add_option('--daf', default=None, help='specify daf name')
+ parser.add_option('--library-url', default=None,
+ help="specify an alternate source for library information")
+ # debugging
+ parser.add_option('--verbose', default=False, action="store_true",
+ help='verbose logging')
+ parser.add_option('--debug', default=False, action="store_true",
+ help='debug logging')
+
+ api.add_auth_options(parser)
+
+ return parser
+
+if __name__ == "__main__":
+ main()
--- /dev/null
+import logging
+import os
+
+import RDF
+
+from htsworkflow.submission.submission import Submission
+
+from htsworkflow.util.rdfhelp import \
+ fromTypedNode, \
+ geoSoftNS, \
+ stripNamespace, \
+ submissionOntology
+
+from django.conf import settings
+from django.template import Context, loader
+
+LOGGER = logging.getLogger(__name__)
+
+class TrackHubSubmission(Submission):
+ def __init__(self, name, model, host):
+ super(TrackHubSubmission, self).__init__(name, model, host)
+
+ def make_hub(self, result_map):
+ samples = []
+ for lib_id, result_dir in result_map.items():
+ an_analysis = self.get_submission_node(result_dir)
+ metadata = self.get_sample_metadata(an_analysis)
+ if len(metadata) == 0:
+ errmsg = 'No metadata found for {0}'
+ LOGGER.error(errmsg.format(str(an_analysis),))
+ continue
+ elif len(metadata) > 1:
+ errmsg = 'Confused there are more than one sample for %s'
+ LOGGER.debug(errmsg % (str(an_analysis),))
+ metadata = metadata[0]
+ samples.append(metadata)
+
+ soft_template = loader.get_template('trackDb.txt')
+ context = Context({
+ 'samples': samples,
+ })
+ print str(soft_template.render(context))
+
+ def get_sample_metadata(self, analysis_node):
+ """Gather information for filling out sample section of a SOFT file
+ """
+ query_template = loader.get_template('trackhub_samples.sparql')
+
+ context = Context({
+ 'submission': str(analysis_node.uri),
+ 'submissionSet': str(self.submissionSetNS[''].uri),
+ })
+
+ results = self.execute_query(query_template, context)
+ return results
\ No newline at end of file
--- /dev/null
+PREFIX libraryOntology: <http://jumpgate.caltech.edu/wiki/LibraryOntology#>
+PREFIX submissionOntology: <http://jumpgate.caltech.edu/wiki/UcscSubmissionOntology#>
+PREFIX ucscDaf: <http://jumpgate.caltech.edu/wiki/UcscDaf#>
+PREFIX ncbiTaxon: <http://www.ncbi.nlm.nih.gov/Taxonomy/Browser/wwwtax.cgi?id=>
+PREFIX geoSoft: <http://www.ncbi.nlm.nih.gov/geo/info/soft2.html#>
+PREFIX cells: <http://encodewiki.ucsc.edu/EncodeDCC/index.php/Cell_lines#>
+
+select distinct ?name ?bam ?cell ?antibody ?sex ?control ?strain ?controlId ?library_id ?treatment ?protocol ?readType ?insertLength ?replicate ?mapAlgorithm ?species_name ?taxon_id ?extractMolecule ?growthProtocol ?extractProtocol ?dataProtocol ?tier ?experiment_type ?library_selection ?library_source ?input_quantity
+WHERE {
+ <{{submission}}> a submissionOntology:submission ;
+ submissionOntology:library ?library ;
+ submissionOntology:name ?name ;
+ ucscDaf:has_file ?file .
+ ?file ucscDaf:filename ?bam .
+ OPTIONAL { <{{submission}}> ucscDaf:control ?control }
+ OPTIONAL { <{{submission}}> ucscDaf:controlId ?controlId }
+ OPTIONAL { ?library libraryOntology:antibody ?antibody }
+ OPTIONAL { ?library libraryOntology:cell_line ?cell .
+ OPTIONAL { ?cell_line cells:cell ?cell .
+ OPTIONAL { ?cell_line cells:documents ?growthProtocol . }
+ OPTIONAL { ?cell_line cells:tier ?tier . } } }
+ OPTIONAL { ?library ucscDaf:sex ?sex }
+ OPTIONAL { ?library libraryOntology:library_id ?library_id }
+ OPTIONAL { ?library libraryOntology:replicate ?replicate }
+ OPTIONAL { ?library libraryOntology:species ?species_name .
+ ?species libraryOntology:species ?species_name ;
+ libraryOntology:taxon_id ?taxon_id . }
+ OPTIONAL { ?library libraryOntology:condition_term ?treatment }
+ OPTIONAL { ?library libraryOntology:experiment_type ?experiment_type }
+ OPTIONAL { ?library libraryOntology:librarySelection ?library_selection }
+ OPTIONAL { ?library libraryOntology:librarySource ?library_source }
+ OPTIONAL { <{{submissionSet}}> geoSoft:data_processing ?dataProtocol }
+ OPTIONAL { ?library libraryOntology:extractMolecule ?extractMolecule }
+ OPTIONAL { ?library libraryOntology:extractProtocol ?extractProtocol }
+ OPTIONAL { ?library ucscDaf:protocol ?protocol }
+ OPTIONAL { ?library ucscDaf:readType ?readType }
+ OPTIONAL { ?library ucscDaf:strain ?strain }
+ OPTIONAL { ?library libraryOntology:insert_size ?insertLength }
+ OPTIONAL { ?library libraryOntology:inputQuantity ?input_quantity }
+ OPTIONAL { ?library ucscDaf:mapAlgorithm ?mapAlgorithm }
+
+}
\ No newline at end of file
projects / htsworkflow.git / commitdiff