def annotate(self, ctx, input):
# ctx is the context object
# return variables are: jobid
#BEGIN annotate
''' Compute probabilistic annotations from the specified genome object.
The input dictionary must contain the following keys:
genome: Name of genome object
genome_workspace: Workspace from which to grab the Genome object
probanno: Name of probanno object to output
probanno_workspace: Workspace to which to save the ProbAnno object
The following keys are optional:
verbose: Print lots of messages on the progress of the algorithm
@param ctx Current context object
@param input Dictionary with input parameters for function
@return Job ID of job started to compute annotation likelihoods
'''
input = self._checkInputArguments(ctx, input,
[ "genome", "genome_workspace", "probanno", "probanno_workspace"],
{ "verbose" : False }
)
# Make sure the static database files are ready.
self._checkDatabaseFiles(ctx)
# Set log level to INFO when verbose parameter is enabled.
if input['verbose']:
ctx.set_log_level(log.DEBUG)
# Make sure the Genome object is available.
wsClient = Workspace(self.config["workspace_url"], token=ctx['token'])
genomeIdentity = make_object_identity(input['genome_workspace'], input['genome'])
wsClient.get_object_info( [ genomeIdentity ], 0 )
# Create a user and job state client and authenticate as the user.
ujsClient = UserAndJobState(self.config['userandjobstate_url'], token=ctx['token'])
# Create a job to track running probabilistic annotation.
description = 'pa-annotate for genome %s to probanno %s for user %s' %(input['genome'], input['probanno'], ctx['user_id'])
progress = { 'ptype': 'task', 'max': 5 }
jobid = ujsClient.create_and_start_job(ctx['token'], 'initializing', description, progress, timestamp(3600))
ctx.log_info('Job '+jobid+' started for genome '+input['genome']+' to probanno '+input['probanno'])
# Run the job on the local machine.
if self.config["job_queue"] == "local":
# Create working directory for job and build file names.
jobDirectory = make_job_directory(self.config['work_folder_path'], jobid)
jobDataFilename = os.path.join(jobDirectory, 'jobdata.json')
outputFilename = os.path.join(jobDirectory, 'stdout.log')
errorFilename = os.path.join(jobDirectory, 'stderr.log')
# Save data required for running the job.
jobData = { 'id': jobid, 'input': input, 'context': ctx, 'config': self.config }
json.dump(jobData, open(jobDataFilename, "w"), indent=4)
# Start worker to run the job.
jobScript = os.path.join(os.environ['KB_TOP'], 'bin/pa-runjob')
cmdline = "nohup %s %s >%s 2>%s &" %(jobScript, jobDirectory, outputFilename, errorFilename)
status = os.system(cmdline)
ctx.log_info('Job %s is running on local host, status %d' %(jobid, status))
#END annotate
# At some point might do deeper type checking...
if not isinstance(jobid, basestring):
raise ValueError('Method annotate return value ' +
'jobid is not type basestring as required.')
# return the results
return [jobid]
def runAnnotate(self, job):
''' Run an annotate job to create a ProbAnno typed object.
A ProbAnno typed object is created in four steps: (1) extract amino acid
sequences from a Genome typed object to a fasta file, (2) run a BLAST search
using the amino acid sequences against the subsystem BLAST database,
(3) calculate annotation likelihood scores for each roleset implied by the
functions of proteins in subsystems, and (4) save the likelihood scores
to a ProbAnno typed object.
The Job dictionary contains three main sections: (1) input parameters to
the annotate() function, (2) context of server instance running the
annotate() function, and (3) config variables of server.
@param job Job dictionary created by server's annotate() function
@return Nothing (although job is marked as complete)
'''
# The input parameters and user context for annotate() were stored in the job data for the job.
input = job["input"]
if input['verbose']:
self.logger.set_log_level(log.DEBUG)
self.ctx = job["context"]
self.config = job['config']
# Create a DataParser object for working with the static database files.
self.dataParser = DataParser(self.config)
status = None
try:
# Make sure the database files are available.
self.dataParser.checkIfDatabaseFilesExist()
# Make sure the job directory exists.
workFolder = make_job_directory(self.config['work_folder_path'], job['id'])
# Create a user and job state client and authenticate as the user.
ujsClient = UserAndJobState(self.config['userandjobstate_url'], token=self.ctx['token'])
# Get the Genome object from the specified workspace.
try:
ujsClient.update_job_progress(job['id'], self.ctx['token'], 'getting genome object', 1, timestamp(3600))
except:
pass
wsClient = Workspace(self.config["workspace_url"], token=self.ctx['token'])
genomeObjectId = make_object_identity(input["genome_workspace"], input["genome"])
objectList = wsClient.get_objects( [ genomeObjectId ] )
genomeObject = objectList[0]
# Convert Genome object to fasta file.
try:
ujsClient.update_job_progress(job['id'], self.ctx['token'], 'converting Genome object to fasta file', 1, timestamp(3600))
except:
pass
fastaFile = self._genomeToFasta(input, genomeObject, workFolder)
# Run blast using the fasta file.
try:
ujsClient.update_job_progress(job['id'], self.ctx['token'], 'running blast', 1, timestamp(3600))
except:
pass
blastResultFile = self._runBlast(input, fastaFile, workFolder)
# Calculate roleset probabilities.
try:
ujsClient.update_job_progress(job['id'], self.ctx['token'], 'calculating roleset probabilities', 1, timestamp(300))
except:
pass
rolestringTuples = self._rolesetProbabilitiesMarble(input, blastResultFile, workFolder)
# Build ProbAnno object and store in the specified workspace.
try:
ujsClient.update_job_progress(job['id'], self.ctx['token'], 'building ProbAnno object', 1, timestamp(120))
except:
pass
output = self._buildProbAnnoObject(input, genomeObject, blastResultFile, rolestringTuples, workFolder, wsClient)
# Mark the job as done.
status = "done"
tb = None
self._log(log.INFO, 'Job '+job['id']+' finished for genome '+input['genome']+' to probanno '+input['probanno'])
except:
tb = traceback.format_exc()
sys.stderr.write('\n'+tb)
status = "failed"
self._log(log.ERR, 'Job '+job['id']+' failed for genome '+input['genome']+' to probanno '+input['probanno'])
# Mark the job as complete with the given status.
ujsClient.complete_job(job['id'], self.ctx['token'], status, tb, { })
# Remove the temporary work directory.
if self.logger.get_log_level() < log.DEBUG2 and status == 'done':
try:
shutil.rmtree(workFolder)
except OSError:
# For some reason deleting the directory was failing in production. Rather than have all jobs look like they failed
# I catch and log the exception here (since the user still gets the same result if the directory remains intact)
msg = 'Unable to delete temporary directory %s\n' %(workFolder)
sys.stderr.write('WARNING: '+msg)
self._log(log.WARNING, msg)
return
