# Example script to execute a NIST Workflow
from gov.nasa.jpl.edrn.labcas.labcas_client import LabcasClient
if __name__ == '__main__':
# submit workflow
# ./wmgr-client --url http://localhost:9001 --operation --sendEvent --eventName nist
# --metaData --key DatasetName Lab005_C_R03 --key LabNumber 005
# --key NormalizationMethod C --key RoundNumber 003 --key LeadPI Johns
# --key DataCollectionDate 20160101 --key SampleProcessingProtocols 'With water and ammonia'
# --key InstrumentationTechnologyCode NGS --key Manufacturer TexasInstruments
# --key ModelNumber XYZ123 --key DataProcessingProtocols 'Crunching data'
# --key OwnerGroup Lab005_OwnerPrincipal
labcasClient = LabcasClient()
workflowTasks = ['urn:edrn:NistInitTask',
'urn:edrn:NistConvertTask',
'urn:edrn:NistExecTask',
'urn:edrn:NistCrawlTask']
metadata = {'DatasetName':'Lab005_C_R03',
'LabNumber':'005',
'Method':'C',
'RoundNumber':'003',
'LeadPI':'Johns',
'DataCollectionDate':'20160101',
'NewVersion':'false' }
# upload dataset without changing the version
wInstId = labcasClient.executeWorkflow(workflowTasks, metadata)
# Python script for programmatic execution of the AF workflow
# (and consequent publishing of UnivColoLungImages)
from gov.nasa.jpl.edrn.labcas.labcas_client import LabcasClient
if __name__ == '__main__':
# upload these datasets
#dataset_names = ['UCHSC_1467', 'UCHSC_8798']
#dataset_names = ['UCHSC_1467']
dataset_names = ['UCHSC_8798']
product_type = 'University_of_Colorado_Lung_Image'
for dataset_name in dataset_names:
# submit workflow
# ./wmgr-client --url http://localhost:9001 --operation --sendEvent --eventName waf --metaData --key DatasetId UCHSC_1001
labcasClient = LabcasClient()
wInstId = labcasClient.executeWorkflow(['urn:edrn:WafInitTask',
'urn:edrn:WafCrawlTask'],
{ 'DatasetName':dataset_name },
)
# monitor workflow instance
labcasClient.waitForCompletion(wInstId)
# list all products for given product type
labcasClient.listProducts(product_type)
# Example script to execute the "labcas-test" workflow
from gov.nasa.jpl.edrn.labcas.labcas_client import LabcasClient
if __name__ == '__main__':
# submit workflow
# ./wmgr-client --url http://localhost:9001 --operation --sendEvent --eventName labcas-test --metaData --key experiment 11 --key species snakes
labcasClient = LabcasClient()
wInstId = labcasClient.executeWorkflow(['urn:edrn:LabcasTestInit','urn:edrn:LabcasTestTask'],
{'experiment':'11',
'species':'snakes' } )
# monitor workflow instance
labcasClient.waitForCompletion(wInstId)
# list all files of this product type
labcasClient.listProducts('LabCAS_Test_Product')
from gov.nasa.jpl.edrn.labcas.labcas_client import LabcasClient
if __name__ == '__main__':
# required input metadata
collection_name = 'My Data Collection'
collection_description = 'This is my precious data collection'
dataset_name = 'Best Dataset'
dataset_description = 'The Best Dataset of this collection'
owner_principal = 'uid=testuser,dc=edrn,dc=jpl,dc=nasa,dc=gov',
# NOTE: data must be uploaded to directory $LABCAS_STAGING/<product_type>/<dataset_id>
product_type = collection_name.replace(' ','_')
#dataset_id = dataset_name.replace(' ','_')
labcasClient = LabcasClient()
# print out workflow definition
#labcasClient.getWorkflowsByEvent("labcas-upload")
# or equivalently
labcasClient.getWorkflowById("urn:edrn:LabcasUploadWorkflow")
# required metadata fields
#./wmgr-client --url http://localhost:9001 --operation --sendEvent --eventName labcas-upload --metaData
# --key DatasetId mydata --key ProductType 'MyData' --key Description 'My own data'
# --key ProtocolId 1 --key LeadPI 'John Doe' --key ProtocolName 'GSTP1 Methylation' --key OrganSite Lung --key OwnerPrincipal EDRN_CANCER_GROUP
# --key DataCustodian 'Rich Smith' --key DataCustodianEmail '*****@*****.**' --key CollaborativeGroup 'Prostate and Urologic'
metadata = { # required metadata
'CollectionName':collection_name,
'CollectionDescription':collection_description,
'DatasetName': dataset_name,
# Example Python script to upload Hanash data
from gov.nasa.jpl.edrn.labcas.labcas_client import LabcasClient
if __name__ == '__main__':
# datasetId must match the directory name where the data is staged on the server: $LABCAS_STAGING/$datasetId
datasetId = 'FHCRCHanashAnnexinLamr'
labcasClient = LabcasClient()
# product type metadata (to be submitted as part of upload workflow)
metadata = {
# required
'DatasetName':'Autoantibody Biomarkers',
'ProtocolId':'138',
'ProtocolName':'Validation of Protein Markers for Lung Cancer Using CARET Sera and Proteomics Techniques',
'LeadPI':'Samir Hanash',
'DataCustodian':'Ji Qiu',
'DataCustodianEmail':'*****@*****.**',
'CollaborativeGroup':'Lung and Upper Aerodigestive',
'OwnerPrincipal':'/Samir/Hanash',
# optional
'OrganSite':'Lung',
'SiteName':'Fred Hutchinson Cancer Research Center (Biomarker Developmental Laboratories)',
'SiteShortName':'FHCRC',
'QAState':'Accepted',
'PubMedId':'http://www.ncbi.nlm.nih.gov/pubmed/18794547',
'DateDatasetFrozen':'2007/05/29',
}
