def test_GetParticipantIDs():
kwargs = {
Constants.NIDM_PROJECT_NAME: "FBIRN_PhaseII",
Constants.NIDM_PROJECT_IDENTIFIER: 9610,
Constants.NIDM_PROJECT_DESCRIPTION: "Test investigation"
}
project = Project(uuid="_123456", attributes=kwargs)
session = Session(uuid="_13579", project=project)
acq = Acquisition(uuid="_15793", session=session)
acq2 = Acquisition(uuid="_15795", session=session)
person = acq.add_person(attributes=({Constants.NIDM_SUBJECTID: "9999"}))
acq.add_qualified_association(person=person,
role=Constants.NIDM_PARTICIPANT)
person2 = acq2.add_person(attributes=({Constants.NIDM_SUBJECTID: "8888"}))
acq2.add_qualified_association(person=person2,
role=Constants.NIDM_PARTICIPANT)
#save a turtle file
with open("test.ttl", 'w') as f:
f.write(project.serializeTurtle())
participant_list = Query.GetParticipantIDs(["test.ttl"])
remove("test.ttl")
assert (participant_list['ID'].str.contains('9999').any())
assert (participant_list['ID'].str.contains('8888').any())
def main(argv):
#create new nidm-experiment document with project
kwargs={Constants.NIDM_PROJECT_NAME:"FBIRN_PhaseII",Constants.NIDM_PROJECT_IDENTIFIER:9610,Constants.NIDM_PROJECT_DESCRIPTION:"Test investigation"}
project = Project(attributes=kwargs)
#test add string attribute with existing namespace
#nidm_doc.addLiteralAttribute("nidm","isFun","ForMe")
project.add_attributes({Constants.NIDM["isFun"]:"ForMe"})
#test adding string attribute with new namespace/term
project.addLiteralAttribute("fred","notFound","in namespaces","www.fred.org/")
#test add float attribute
project.addLiteralAttribute("nidm", "float", float(2.34))
#test adding attributes in bulk with mix of existing and new namespaces
#nidm_doc.addAttributesWithNamespaces(nidm_doc.getProject(),[{"prefix":"nidm", "uri":nidm_doc.namespaces["nidm"], "term":"score", "value":int(15)}, \
# {"prefix":"dave", "uri":"http://www.davidkeator.com/", "term":"isAwesome", "value":"15"}, \
# {"prefix":"nidm", "uri":nidm_doc.namespaces["nidm"], "term":"value", "value":float(2.34)}])
#nidm_doc.addAttributes(nidm_doc.getProject(),{"nidm:test":int(15), "ncit:isTerminology":"15","ncit:joker":float(1)})
#test add PI to investigation
project_PI = project.add_person(role=Constants.NIDM_PI, attributes={Constants.NIDM_FAMILY_NAME:"Keator", Constants.NIDM_GIVEN_NAME:"David"})
#test add session to graph and associate with project
session = Session(project)
project.add_sessions(session)
#test add acquisition activity to graph and associate with session
acq_act = Acquisition(session=session)
#test add acquisition object entity to graph associated with participant role NIDM_PARTICIPANT
acq_entity = MRAcquisitionObject(acquisition=acq_act)
acq_entity.add_person(role=Constants.NIDM_PARTICIPANT,attributes={Constants.NIDM_GIVEN_NAME:"George"})
#save a turtle file
with open("test.ttl",'w') as f:
f.write (project.serializeTurtle())
#save a DOT graph as PDF
project.save_DotGraph("test.png",format="png")
def makeTestFile(filename, params):
global test_person_uuid, test_p2_subject_uuids
nidm_project_name = params.get('NIDM_PROJECT_NAME',
False) or "Project_name_sample"
nidm_project_identifier = params.get('NIDM_PROJECT_IDENTIFIER',
False) or 9610
nidm_project2_identifier = params.get('NIDM_PROJECT_IDENTIFIER',
False) or 550
nidm_project_description = params.get(
'NIDM_PROJECT_DESCRIPTION', False) or "1234356 Test investigation"
project_uuid = params.get('PROJECT_UUID', False) or "_proj1"
project_uuid2 = params.get('PROJECT2_UUID', False) or "_proj2"
session_uuid = params.get('SESSION_UUID', False) or "_ses1"
session_uuid2 = params.get('SESSION2_UUID', False) or "_ses2"
p1kwargs = {
Constants.NIDM_PROJECT_NAME: nidm_project_name,
Constants.NIDM_PROJECT_IDENTIFIER: nidm_project_identifier,
Constants.NIDM_PROJECT_DESCRIPTION: nidm_project_description
}
p2kwargs = {
Constants.NIDM_PROJECT_NAME: nidm_project_name,
Constants.NIDM_PROJECT_IDENTIFIER: nidm_project2_identifier,
Constants.NIDM_PROJECT_DESCRIPTION: nidm_project_description
}
project = Project(uuid=project_uuid, attributes=p1kwargs)
session = Session(uuid=session_uuid, project=project)
acq = Acquisition(uuid="_acq1", session=session)
acq2 = Acquisition(uuid="_acq2", session=session)
acq3 = Acquisition(uuid="_acq2", session=session)
person = acq.add_person(attributes=({Constants.NIDM_SUBJECTID: "a1_9999"}))
test_person_uuid = (str(person.identifier)).replace("niiri:", "")
acq.add_qualified_association(person=person,
role=Constants.NIDM_PARTICIPANT)
person2 = acq2.add_person(attributes=({
Constants.NIDM_SUBJECTID: "a1_8888"
}))
acq2.add_qualified_association(person=person2,
role=Constants.NIDM_PARTICIPANT)
person3 = acq3.add_person(attributes=({
Constants.NIDM_SUBJECTID: "a2_7777"
}))
acq2.add_qualified_association(person=person3,
role=Constants.NIDM_PARTICIPANT)
project2 = Project(uuid=project_uuid2, attributes=p2kwargs)
session2 = Session(uuid=session_uuid2, project=project2)
acq4 = Acquisition(uuid="_acq3", session=session2)
acq5 = Acquisition(uuid="_acq4", session=session2)
person4 = acq4.add_person(attributes=({
Constants.NIDM_SUBJECTID: "a3_6666"
}))
acq4.add_qualified_association(person=person4,
role=Constants.NIDM_PARTICIPANT)
person5 = acq5.add_person(attributes=({
Constants.NIDM_SUBJECTID: "a4_5555"
}))
acq5.add_qualified_association(person=person5,
role=Constants.NIDM_PARTICIPANT)
# now add some assessment instrument data
addData(
acq, {
Constants.NIDM_AGE: 9,
Constants.NIDM_HANDEDNESS: "R",
Constants.NIDM_DIAGNOSIS: "Anxiety"
})
addData(
acq2, {
Constants.NIDM_AGE: 8,
Constants.NIDM_HANDEDNESS: "L",
Constants.NIDM_DIAGNOSIS: "ADHD"
})
addData(
acq4, {
Constants.NIDM_AGE: 7,
Constants.NIDM_HANDEDNESS: "A",
Constants.NIDM_DIAGNOSIS: "Depression"
})
addData(
acq5, {
Constants.NIDM_AGE: 6,
Constants.NIDM_HANDEDNESS: "R",
Constants.NIDM_DIAGNOSIS: "Depression"
})
test_p2_subject_uuids.append(
(str(person4.identifier)).replace("niiri:", ""))
test_p2_subject_uuids.append(
(str(person5.identifier)).replace("niiri:", ""))
with open("a.ttl", 'w') as f:
f.write(project.graph.serialize(None, format='rdf', rdf_format='ttl'))
with open("b.ttl", 'w') as f:
f.write(project2.graph.serialize(None, format='rdf', rdf_format='ttl'))
#create empty graph
graph = Graph()
for nidm_file in ("a.ttl", "b.ttl"):
tmp = Graph()
graph = graph + tmp.parse(nidm_file,
format=util.guess_format(nidm_file))
graph.serialize(filename, format='turtle')
os.unlink("a.ttl")
os.unlink("b.ttl")
with open(filename, "r") as f:
x = f.read()
with open("./agent.ttl", "w") as f:
f.write(x)
def main(argv):
parser = ArgumentParser(
description=
'This program will convert a BIDS MRI dataset to a NIDM-Experiment \
RDF document. It will parse phenotype information and simply store variables/values \
and link to the associated json data dictionary file.')
parser.add_argument('-d',
dest='directory',
required=True,
help="Path to BIDS dataset directory")
parser.add_argument('-o',
dest='outputfile',
default="nidm.ttl",
help="NIDM output turtle file")
args = parser.parse_args()
directory = args.directory
outputfile = args.outputfile
#importlib.reload(sys)
#sys.setdefaultencoding('utf8')
#Parse dataset_description.json file in BIDS directory
with open(os.path.join(directory,
'dataset_description.json')) as data_file:
dataset = json.load(data_file)
#print(dataset_data)
#create project / nidm-exp doc
project = Project()
#add various attributes if they exist in BIDS dataset
for key in dataset:
#print(key)
#if key from dataset_description file is mapped to term in BIDS_Constants.py then add to NIDM object
if key in BIDS_Constants.dataset_description:
if type(dataset[key]) is list:
project.add_attributes({
BIDS_Constants.dataset_description[key]:
"".join(dataset[key])
})
else:
project.add_attributes(
{BIDS_Constants.dataset_description[key]: dataset[key]})
#create empty dictinary for sessions where key is subject id and used later to link scans to same session as demographics
session = {}
#Parse participants.tsv file in BIDS directory and create study and acquisition objects
with open(os.path.join(directory, 'participants.tsv')) as csvfile:
participants_data = csv.DictReader(csvfile, delimiter='\t')
#print(participants_data.fieldnames)
for row in participants_data:
#create session object for subject to be used for participant metadata and image data
#parse subject id from "sub-XXXX" string
subjid = row['participant_id'].split("-")
session[subjid[1]] = Session(project)
#add acquisition object
acq = Acquisition(session=session[subjid[1]])
acq_entity = DemographicsAcquisitionObject(acquisition=acq)
participant = acq.add_person(role=Constants.NIDM_PARTICIPANT,
attributes=({
Constants.NIDM_SUBJECTID:
row['participant_id']
}))
for key, value in row.items():
#for now only convert variables in participants.tsv file who have term mappings in BIDS_Constants.py
if key in BIDS_Constants.participants:
acq_entity.add_attributes(
{BIDS_Constants.participants[key]: value})
#get BIDS layout
bids_layout = BIDSLayout(directory)
#create acquisition objects for each scan for each subject
#loop through all subjects in dataset
for subject_id in bids_layout.get_subjects():
#skip .git directories...added to support datalad datasets
if subject_id.startswith("."):
continue
for file_tpl in bids_layout.get(subject=subject_id,
extensions=['.nii', '.nii.gz']):
#create an acquisition activity
acq = Acquisition(session[subject_id])
#print(file_tpl.type)
if file_tpl.modality == 'anat':
#do something with anatomicals
acq_obj = MRAcquisitionObject(acq)
acq_obj.add_attributes(
{PROV_TYPE: BIDS_Constants.scans[file_tpl.modality]})
#add file link
#make relative link to
acq_obj.add_attributes(
{Constants.NIDM_FILENAME: file_tpl.filename})
#get associated JSON file if exists
json_data = bids_layout.get_metadata(file_tpl.filename)
if json_data:
for key in json_data:
if key in BIDS_Constants.json_keys:
if type(json_data[key]) is list:
acq_obj.add_attributes({
BIDS_Constants.json_keys[key]:
''.join(str(e) for e in json_data[key])
})
else:
acq_obj.add_attributes({
BIDS_Constants.json_keys[key]:
json_data[key]
})
elif file_tpl.modality == 'func':
#do something with functionals
acq_obj = MRAcquisitionObject(acq)
acq_obj.add_attributes(
{PROV_TYPE: BIDS_Constants.scans[file_tpl.modality]})
#add file link
acq_obj.add_attributes(
{Constants.NIDM_FILENAME: file_tpl.filename})
if 'run' in file_tpl._fields:
acq_obj.add_attributes(
{BIDS_Constants.json_keys["run"]: file_tpl.run})
#get associated JSON file if exists
json_data = bids_layout.get_metadata(file_tpl.filename)
if json_data:
for key in json_data:
if key in BIDS_Constants.json_keys:
if type(json_data[key]) is list:
acq_obj.add_attributes({
BIDS_Constants.json_keys[key]:
''.join(str(e) for e in json_data[key])
})
else:
acq_obj.add_attributes({
BIDS_Constants.json_keys[key]:
json_data[key]
})
#get associated events TSV file
if 'run' in file_tpl._fields:
events_file = bids_layout.get(subject=subject_id,
extensions=['.tsv'],
modality=file_tpl.modality,
task=file_tpl.task,
run=file_tpl.run)
else:
events_file = bids_layout.get(subject=subject_id,
extensions=['.tsv'],
modality=file_tpl.modality,
task=file_tpl.task)
#if there is an events file then this is task-based so create an acquisition object for the task file and link
if events_file:
#for now create acquisition object and link it to the associated scan
events_obj = AcquisitionObject(acq)
#add prov type, task name as prov:label, and link to filename of events file
events_obj.add_attributes({
PROV_TYPE:
Constants.NIDM_MRI_BOLD_EVENTS,
BIDS_Constants.json_keys["TaskName"]:
json_data["TaskName"],
Constants.NFO["filename"]:
events_file[0].filename
})
#link it to appropriate MR acquisition entity
events_obj.wasAttributedTo(acq_obj)
elif file_tpl.modality == 'dwi':
#do stuff with with dwi scans...
acq_obj = MRAcquisitionObject(acq)
acq_obj.add_attributes(
{PROV_TYPE: BIDS_Constants.scans[file_tpl.modality]})
#add file link
acq_obj.add_attributes(
{Constants.NIDM_FILENAME: file_tpl.filename})
if 'run' in file_tpl._fields:
acq_obj.add_attributes(
{BIDS_Constants.json_keys["run"]: file_tpl.run})
#get associated JSON file if exists
json_data = bids_layout.get_metadata(file_tpl.filename)
if json_data:
for key in json_data:
if key in BIDS_Constants.json_keys:
if type(json_data[key]) is list:
acq_obj.add_attributes({
BIDS_Constants.json_keys[key]:
''.join(str(e) for e in json_data[key])
})
else:
acq_obj.add_attributes({
BIDS_Constants.json_keys[key]:
json_data[key]
})
#for bval and bvec files, what to do with those?
#for now, create new generic acquisition objects, link the files, and associate with the one for the DWI scan?
acq_obj_bval = AcquisitionObject(acq)
acq_obj_bval.add_attributes(
{PROV_TYPE: BIDS_Constants.scans["bval"]})
#add file link to bval files
acq_obj_bval.add_attributes({
Constants.NIDM_FILENAME:
bids_layout.get_bval(file_tpl.filename)
})
acq_obj_bvec = AcquisitionObject(acq)
acq_obj_bvec.add_attributes(
{PROV_TYPE: BIDS_Constants.scans["bvec"]})
#add file link to bvec files
acq_obj_bvec.add_attributes({
Constants.NIDM_FILENAME:
bids_layout.get_bvec(file_tpl.filename)
})
#link bval and bvec acquisition object entities together or is their association with enclosing activity enough?
#Added temporarily to support phenotype files
#for each *.tsv / *.json file pair in the phenotypes directory
for tsv_file in glob.glob(os.path.join(directory, "phenotype",
"*.tsv")):
#for now, open the TSV file, extract the row for this subject, store it in an acquisition object and link to
#the associated JSON data dictionary file
with open(tsv_file) as phenofile:
pheno_data = csv.DictReader(phenofile, delimiter='\t')
for row in pheno_data:
subjid = row['participant_id'].split("-")
if not subjid[1] == subject_id:
continue
else:
#add acquisition object
acq = Acquisition(session=session[subjid[1]])
acq_entity = AssessmentAcquisitionObject(
acquisition=acq)
participant = acq.add_person(
role=Constants.NIDM_PARTICIPANT,
attributes=({
Constants.NIDM_SUBJECTID:
row['participant_id']
}))
for key, value in row.items():
if not key == "participant_id":
#for now we're using a placeholder namespace for BIDS and simply the variable names as the concept IDs..
acq_entity.add_attributes(
{Constants.BIDS[key]: value})
#link TSV file
acq_entity.add_attributes(
{Constants.NIDM_FILENAME: tsv_file})
#link associated JSON file if it exists
data_dict = os.path.join(
directory, "phenotype",
os.path.splitext(os.path.basename(tsv_file))[0] +
".json")
if os.path.isfile(data_dict):
acq_entity.add_attributes(
{Constants.BIDS["data_dictionary"]: data_dict})
#serialize graph
#print(project.graph.get_provn())
with open(outputfile, 'w') as f:
f.write(project.serializeTurtle())
#f.write(project.graph.get_provn())
#save a DOT graph as PNG
project.save_DotGraph(str(outputfile + ".png"), format="png")
def main(argv):
parser = ArgumentParser()
parser.add_argument('-d',
dest='directory',
required=True,
help="Path to BIDS dataset directory")
parser.add_argument('-o',
dest='outputfile',
default="nidm.ttl",
help="NIDM output turtle file")
args = parser.parse_args()
directory = args.directory
outputfile = args.outputfile
#Parse dataset_description.json file in BIDS directory
with open(directory + '/' + 'dataset_description.json') as data_file:
dataset = json.load(data_file)
#print(dataset_data)
#create project / nidm-exp doc
project = Project()
#add various attributes if they exist in BIDS dataset
for key in dataset:
#print(key)
#if key from dataset_description file is mapped to term in BIDS_Constants.py then add to NIDM object
if key in BIDS_Constants.dataset_description:
if type(dataset[key]) is list:
project.add_attributes({
BIDS_Constants.dataset_description[key]:
"".join(dataset[key])
})
else:
project.add_attributes(
{BIDS_Constants.dataset_description[key]: dataset[key]})
#create empty dictinary for sessions where key is subject id and used later to link scans to same session as demographics
session = {}
#Parse participants.tsv file in BIDS directory and create study and acquisition objects
with open(directory + '/' + 'participants.tsv') as csvfile:
participants_data = csv.DictReader(csvfile, delimiter='\t')
#print(participants_data.fieldnames)
for row in participants_data:
#create session object for subject to be used for participant metadata and image data
#parse subject id from "sub-XXXX" string
subjid = row['participant_id'].split("-")
session[subjid[1]] = Session(project)
#add acquisition object
acq = Acquisition(session=session[subjid[1]])
acq_entity = DemographicsAcquisitionObject(acquisition=acq)
participant = acq.add_person(role=Constants.NIDM_PARTICIPANT,
attributes=({
Constants.NIDM_SUBJECTID:
row['participant_id']
}))
for key, value in row.items():
#for now only convert variables in participants.tsv file who have term mappings in BIDS_Constants.py
if key in BIDS_Constants.participants:
acq_entity.add_attributes(
{BIDS_Constants.participants[key]: value})
#get BIDS layout
bids_layout = BIDSLayout(directory)
#create acquisition objects for each scan for each subject
#loop through all subjects in dataset
for subject_id in bids_layout.get_subjects():
for file_tpl in bids_layout.get(subject=subject_id,
extensions=['.nii', '.nii.gz']):
#create an acquisition activity
acq = Acquisition(session[subject_id])
#print(file_tpl.type)
if file_tpl.modality == 'anat':
#do something with anatomicals
acq_obj = MRAcquisitionObject(acq)
acq_obj.add_attributes(
{PROV_TYPE: BIDS_Constants.scans[file_tpl.modality]})
#add file link
acq_obj.add_attributes(
{Constants.NFO["filename"]: file_tpl.filename})
#get associated JSON file if exists
for json_file in bids_layout.get(subject=subject_id,
extensions=['.json'],
modality=file_tpl.modality):
#open json file, grab key-value pairs, map them to terms and add to acquisition object
with open(json_file[0]) as data_file:
json_data = json.load(data_file)
for key in json_data:
if key in BIDS_Constants.json_keys:
if type(json_data[key]) is list:
project.add_attributes({
BIDS_Constants.json_keys[key]:
"".join(json_data[key])
})
else:
project.add_attributes({
BIDS_Constants.json_keys[key]:
json_data[key]
})
#if we want to do something further if T1w or t2, etc
#if file_tpl.type == 'T1w':
#elif file_tpl.type == 'inplaneT2':
elif file_tpl.modality == 'func':
#do something with functionals
acq_obj = MRAcquisitionObject(acq)
acq_obj.add_attributes(
{PROV_TYPE: BIDS_Constants.scans[file_tpl.modality]})
#add file link
acq_obj.add_attributes({
Constants.NFO["filename"]:
file_tpl.filename,
BIDS_Constants.json_keys["run"]:
file_tpl.run
})
#add attributes for task description keys from task JSON file
for task_desc in bids_layout.get(extensions=['.json'],
task=file_tpl.task):
with open(task_desc[0]) as data_file:
json_data = json.load(data_file)
for key in json_data:
if key in BIDS_Constants.json_keys:
acq_obj.add_attributes({
BIDS_Constants.json_keys[key]:
json_data[key]
})
#get associated events TSV file
events_file = bids_layout.get(subject=subject_id,
extensions=['.tsv'],
modality=file_tpl.modality,
task=file_tpl.task,
run=file_tpl.run)
#for now create acquisition object and link it to the associated scan
events_obj = AcquisitionObject(acq)
#add prov type, task name as prov:label, and link to filename of events file
events_obj.add_attributes({
PROV_TYPE:
Constants.NIDM_MRI_BOLD_EVENTS,
BIDS_Constants.json_keys["TaskName"]:
json_data["TaskName"],
Constants.NFO["filename"]:
events_file[0].filename
})
#link it to appropriate MR acquisition entity
events_obj.wasAttributedTo(acq_obj)
elif file_tpl.modality == 'dwi':
#do stuff with with dwi scans...
acq_obj = MRAcquisitionObject(acq)
acq_obj.add_attributes(
{PROV_TYPE: BIDS_Constants.scans[file_tpl.modality]})
#add file link
acq_obj.add_attributes({
Constants.NFO["filename"]:
file_tpl.filename,
BIDS_Constants.json_keys["run"]:
file_tpl.run
})
#add attributes for task description keys from task JSON file
for task_desc in bids_layout.get(extensions=['.json'],
task=file_tpl.task):
with open(task_desc[0]) as data_file:
json_data = json.load(data_file)
for key in json_data:
if key in BIDS_Constants.json_keys:
acq_obj.add_attributes({
BIDS_Constants.json_keys[key]:
json_data[key]
})
#for bval and bvec files, what to do with those?
#for now, create new generic acquisition objects, link the files, and associate with the one for the DWI scan?
acq_obj = AcquisitionObject(acq)
acq_obj.add_attributes(
{PROV_TYPE: BIDS_Constants.scans["bval"]})
for bval in bids_layout.get(extensions=['.bval'],
task=file_tpl.task):
#add file link
acq_obj.add_attributes(
{Constants.NFO["filename"]: bval.filename})
for bvec in bids_layout.get(extensions=['.bvec'],
task=file_tpl.task):
#add file link
acq_obj.add_attributes(
{Constants.NFO["filename"]: bvec.filename})
#serialize graph
#print(project.graph.get_provn())
with open(outputfile, 'w') as f:
f.write(project.serializeTurtle())
#f.write(project.graph.get_provn())
#save a DOT graph as PNG
project.save_DotGraph(str(outputfile + ".png"), format="png")