def bidsmri2project(directory, args):
#Parse dataset_description.json file in BIDS directory
if (os.path.isdir(os.path.join(directory))):
try:
with open(os.path.join(directory,
'dataset_description.json')) as data_file:
dataset = json.load(data_file)
except OSError:
logging.critical(
"Cannot find dataset_description.json file which is required in the BIDS spec"
)
exit("-1")
else:
logging.critical("Error: BIDS directory %s does not exist!" %
os.path.join(directory))
exit("-1")
#create project / nidm-exp doc
project = Project()
#add various attributes if they exist in BIDS dataset
for key in dataset:
#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]})
#add absolute location of BIDS directory on disk for later finding of files which are stored relatively in NIDM document
project.add_attributes({Constants.PROV['Location']: directory})
#get BIDS layout
bids_layout = BIDSLayout(directory)
#create empty dictinary for sessions where key is subject id and used later to link scans to same session as demographics
session = {}
participant = {}
#Parse participants.tsv file in BIDS directory and create study and acquisition objects
if os.path.isfile(os.path.join(directory, 'participants.tsv')):
with open(os.path.join(directory, 'participants.tsv')) as csvfile:
participants_data = csv.DictReader(csvfile, delimiter='\t')
#logic to map variables to terms.#########################################################################################################
#first iterate over variables in dataframe and check which ones are already mapped as BIDS constants and which are not. For those that are not
#we want to use the variable-term mapping functions to help the user do the mapping
#iterate over columns
mapping_list = []
column_to_terms = {}
for field in participants_data.fieldnames:
#column is not in BIDS_Constants
if not (field in BIDS_Constants.participants):
#add column to list for column_to_terms mapping
mapping_list.append(field)
#do variable-term mappings
if ((args.json_map != False) or (args.key != None)):
#if user didn't supply a json mapping file but we're doing some variable-term mapping create an empty one for column_to_terms to use
if args.json_map == False:
#defaults to participants.json because here we're mapping the participants.tsv file variables to terms
# if participants.json file doesn't exist then run without json mapping file
if not os.path.isfile(
os.path.join(directory, 'participants.json')):
#maps variables in CSV file to terms
temp = DataFrame(columns=mapping_list)
column_to_terms, cde = map_variables_to_terms(
directory=directory,
assessment_name='participants.tsv',
df=temp,
apikey=args.key,
output_file=os.path.join(directory,
'participants.json'))
else:
#maps variables in CSV file to terms
temp = DataFrame(columns=mapping_list)
column_to_terms, cde = map_variables_to_terms(
directory=directory,
assessment_name='participants.tsv',
df=temp,
apikey=args.key,
output_file=os.path.join(directory,
'participants.json'),
json_file=os.path.join(directory,
'participants.json'))
else:
#maps variables in CSV file to terms
temp = DataFrame(columns=mapping_list)
column_to_terms, cde = map_variables_to_terms(
directory=directory,
assessment_name='participants.tsv',
df=temp,
apikey=args.key,
output_file=os.path.join(directory,
'participants.json'),
json_file=args.json_map)
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
temp = row['participant_id'].split("-")
#for ambiguity in BIDS datasets. Sometimes participant_id is sub-XXXX and othertimes it's just XXXX
if len(temp) > 1:
subjid = temp[1]
else:
subjid = temp[0]
logging.info(subjid)
session[subjid] = Session(project)
#add acquisition object
acq = AssessmentAcquisition(session=session[subjid])
acq_entity = AssessmentObject(acquisition=acq)
participant[subjid] = {}
participant[subjid]['person'] = acq.add_person(
attributes=({
Constants.NIDM_SUBJECTID: row['participant_id']
}))
#add qualified association of participant with acquisition activity
acq.add_qualified_association(
person=participant[subjid]['person'],
role=Constants.NIDM_PARTICIPANT)
print(acq)
for key, value in row.items():
if not value:
continue
#for variables in participants.tsv file who have term mappings in BIDS_Constants.py use those, add to json_map so we don't have to map these if user
#supplied arguments to map variables
if key in BIDS_Constants.participants:
#if this was the participant_id, we already handled it above creating agent / qualified association
if not (BIDS_Constants.participants[key]
== Constants.NIDM_SUBJECTID):
acq_entity.add_attributes(
{BIDS_Constants.participants[key]: value})
#else if user added -mapvars flag to command line then we'll use the variable-> term mapping procedures to help user map variables to terms (also used
# in CSV2NIDM.py)
else:
# WIP: trying to add new support for CDEs...
add_attributes_with_cde(prov_object=acq_entity,
cde=cde,
row_variable=key,
value=value)
# if key in column_to_terms:
# acq_entity.add_attributes({QualifiedName(provNamespace(Core.safe_string(None,string=str(key)), column_to_terms[key]["url"]), ""):value})
#else:
# acq_entity.add_attributes({Constants.BIDS[key.replace(" ", "_")]:value})
#create acquisition objects for each scan for each subject
#loop through all subjects in dataset
for subject_id in bids_layout.get_subjects():
logging.info("Converting subject: %s" % subject_id)
#skip .git directories...added to support datalad datasets
if subject_id.startswith("."):
continue
#check if there's a session number. If so, store it in the session activity
session_dirs = bids_layout.get(target='session',
subject=subject_id,
return_type='dir')
#if session_dirs has entries then get any metadata about session and store in session activity
#bids_layout.get(subject=subject_id,type='session',extensions='.tsv')
#bids_layout.get(subject=subject_id,type='scans',extensions='.tsv')
#bids_layout.get(extensions='.tsv',return_type='obj')
#check whether sessions have been created (i.e. was there a participants.tsv file? If not, create here
if not (subject_id in session):
session[subject_id] = Session(project)
for file_tpl in bids_layout.get(subject=subject_id,
extensions=['.nii', '.nii.gz']):
#create an acquisition activity
acq = MRAcquisition(session[subject_id])
#check whether participant (i.e. agent) for this subject already exists (i.e. if participants.tsv file exists) else create one
if not (subject_id in participant):
participant[subject_id] = {}
participant[subject_id]['person'] = acq.add_person(
attributes=({
Constants.NIDM_SUBJECTID: subject_id
}))
#add qualified association with person
acq.add_qualified_association(
person=participant[subject_id]['person'],
role=Constants.NIDM_PARTICIPANT)
if file_tpl.entities['datatype'] == 'anat':
#do something with anatomicals
acq_obj = MRObject(acq)
#add image contrast type
if file_tpl.entities['suffix'] in BIDS_Constants.scans:
acq_obj.add_attributes({
Constants.NIDM_IMAGE_CONTRAST_TYPE:
BIDS_Constants.scans[file_tpl.entities['suffix']]
})
else:
logging.info(
"WARNING: No matching image contrast type found in BIDS_Constants.py for %s"
% file_tpl.entities['suffix'])
#add image usage type
if file_tpl.entities['datatype'] in BIDS_Constants.scans:
acq_obj.add_attributes({
Constants.NIDM_IMAGE_USAGE_TYPE:
BIDS_Constants.scans[file_tpl.entities['datatype']]
})
else:
logging.info(
"WARNING: No matching image usage type found in BIDS_Constants.py for %s"
% file_tpl.entities['datatype'])
#add file link
#make relative link to
acq_obj.add_attributes({
Constants.NIDM_FILENAME:
getRelPathToBIDS(join(file_tpl.dirname, file_tpl.filename),
directory)
})
#WIP: add absolute location of BIDS directory on disk for later finding of files
acq_obj.add_attributes({Constants.PROV['Location']: directory})
#add sha512 sum
if isfile(join(directory, file_tpl.dirname,
file_tpl.filename)):
acq_obj.add_attributes({
Constants.CRYPTO_SHA512:
getsha512(
join(directory, file_tpl.dirname,
file_tpl.filename))
})
else:
logging.info(
"WARNINGL file %s doesn't exist! No SHA512 sum stored in NIDM files..."
% join(directory, file_tpl.dirname, file_tpl.filename))
#get associated JSON file if exists
#There is T1w.json file with information
json_data = (bids_layout.get(
suffix=file_tpl.entities['suffix'],
subject=subject_id))[0].metadata
if len(json_data.info) > 0:
for key in json_data.info.items():
if key in BIDS_Constants.json_keys:
if type(json_data.info[key]) is list:
acq_obj.add_attributes({
BIDS_Constants.json_keys[key.replace(
" ", "_")]:
''.join(
str(e) for e in json_data.info[key])
})
else:
acq_obj.add_attributes({
BIDS_Constants.json_keys[key.replace(
" ", "_")]:
json_data.info[key]
})
#Parse T1w.json file in BIDS directory to add the attributes contained inside
if (os.path.isdir(os.path.join(directory))):
try:
with open(os.path.join(directory,
'T1w.json')) as data_file:
dataset = json.load(data_file)
except OSError:
logging.critical(
"Cannot find T1w.json file which is required in the BIDS spec"
)
exit("-1")
else:
logging.critical(
"Error: BIDS directory %s does not exist!" %
os.path.join(directory))
exit("-1")
#add various attributes if they exist in BIDS dataset
for key in dataset:
#if key from T1w.json file is mapped to term in BIDS_Constants.py then add to NIDM object
if key in BIDS_Constants.json_keys:
if type(dataset[key]) is list:
acq_obj.add_attributes({
BIDS_Constants.json_keys[key]:
"".join(dataset[key])
})
else:
acq_obj.add_attributes(
{BIDS_Constants.json_keys[key]: dataset[key]})
elif file_tpl.entities['datatype'] == 'func':
#do something with functionals
acq_obj = MRObject(acq)
#add image contrast type
if file_tpl.entities['suffix'] in BIDS_Constants.scans:
acq_obj.add_attributes({
Constants.NIDM_IMAGE_CONTRAST_TYPE:
BIDS_Constants.scans[file_tpl.entities['suffix']]
})
else:
logging.info(
"WARNING: No matching image contrast type found in BIDS_Constants.py for %s"
% file_tpl.entities['suffix'])
#add image usage type
if file_tpl.entities['datatype'] in BIDS_Constants.scans:
acq_obj.add_attributes({
Constants.NIDM_IMAGE_USAGE_TYPE:
BIDS_Constants.scans[file_tpl.entities['datatype']]
})
else:
logging.info(
"WARNING: No matching image usage type found in BIDS_Constants.py for %s"
% file_tpl.entities['datatype'])
#make relative link to
acq_obj.add_attributes({
Constants.NIDM_FILENAME:
getRelPathToBIDS(join(file_tpl.dirname, file_tpl.filename),
directory)
})
#WIP: add absolute location of BIDS directory on disk for later finding of files
acq_obj.add_attributes({Constants.PROV['Location']: directory})
#add sha512 sum
if isfile(join(directory, file_tpl.dirname,
file_tpl.filename)):
acq_obj.add_attributes({
Constants.CRYPTO_SHA512:
getsha512(
join(directory, file_tpl.dirname,
file_tpl.filename))
})
else:
logging.info(
"WARNINGL file %s doesn't exist! No SHA512 sum stored in NIDM files..."
% join(directory, file_tpl.dirname, file_tpl.filename))
if 'run' in file_tpl.entities:
acq_obj.add_attributes({
BIDS_Constants.json_keys["run"]:
file_tpl.entities['run']
})
#get associated JSON file if exists
json_data = (bids_layout.get(
suffix=file_tpl.entities['suffix'],
subject=subject_id))[0].metadata
if len(json_data.info) > 0:
for key in json_data.info.items():
if key in BIDS_Constants.json_keys:
if type(json_data.info[key]) is list:
acq_obj.add_attributes({
BIDS_Constants.json_keys[key.replace(
" ", "_")]:
''.join(
str(e) for e in json_data.info[key])
})
else:
acq_obj.add_attributes({
BIDS_Constants.json_keys[key.replace(
" ", "_")]:
json_data.info[key]
})
#get associated events TSV file
if 'run' in file_tpl.entities:
events_file = bids_layout.get(
subject=subject_id,
extensions=['.tsv'],
modality=file_tpl.entities['datatype'],
task=file_tpl.entities['task'],
run=file_tpl.entities['run'])
else:
events_file = bids_layout.get(
subject=subject_id,
extensions=['.tsv'],
modality=file_tpl.entities['datatype'],
task=file_tpl.entities['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.NIDM_FILENAME:
getRelPathToBIDS(events_file[0].filename, directory)
})
#link it to appropriate MR acquisition entity
events_obj.wasAttributedTo(acq_obj)
#Parse task-rest_bold.json file in BIDS directory to add the attributes contained inside
if (os.path.isdir(os.path.join(directory))):
try:
with open(
os.path.join(
directory,
'task-rest_bold.json')) as data_file:
dataset = json.load(data_file)
except OSError:
logging.critical(
"Cannot find task-rest_bold.json file which is required in the BIDS spec"
)
exit("-1")
else:
logging.critical(
"Error: BIDS directory %s does not exist!" %
os.path.join(directory))
exit("-1")
#add various attributes if they exist in BIDS dataset
for key in dataset:
#if key from task-rest_bold.json file is mapped to term in BIDS_Constants.py then add to NIDM object
if key in BIDS_Constants.json_keys:
if type(dataset[key]) is list:
acq_obj.add_attributes({
BIDS_Constants.json_keys[key]:
",".join(map(str, dataset[key]))
})
else:
acq_obj.add_attributes(
{BIDS_Constants.json_keys[key]: dataset[key]})
elif file_tpl.entities['datatype'] == 'dwi':
#do stuff with with dwi scans...
acq_obj = MRObject(acq)
#add image contrast type
if file_tpl.entities['suffix'] in BIDS_Constants.scans:
acq_obj.add_attributes({
Constants.NIDM_IMAGE_CONTRAST_TYPE:
BIDS_Constants.scans[file_tpl.entities['suffix']]
})
else:
logging.info(
"WARNING: No matching image contrast type found in BIDS_Constants.py for %s"
% file_tpl.entities['suffix'])
#add image usage type
if file_tpl.entities['datatype'] in BIDS_Constants.scans:
acq_obj.add_attributes({
Constants.NIDM_IMAGE_USAGE_TYPE:
BIDS_Constants.scans["dti"]
})
else:
logging.info(
"WARNING: No matching image usage type found in BIDS_Constants.py for %s"
% file_tpl.entities['datatype'])
#make relative link to
acq_obj.add_attributes({
Constants.NIDM_FILENAME:
getRelPathToBIDS(join(file_tpl.dirname, file_tpl.filename),
directory)
})
#add sha512 sum
if isfile(join(directory, file_tpl.dirname,
file_tpl.filename)):
acq_obj.add_attributes({
Constants.CRYPTO_SHA512:
getsha512(
join(directory, file_tpl.dirname,
file_tpl.filename))
})
else:
logging.info(
"WARNINGL file %s doesn't exist! No SHA512 sum stored in NIDM files..."
% join(directory, file_tpl.dirname, 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(
suffix=file_tpl.entities['suffix'],
subject=subject_id))[0].metadata
if len(json_data.info) > 0:
for key in json_data.info.items():
if key in BIDS_Constants.json_keys:
if type(json_data.info[key]) is list:
acq_obj.add_attributes({
BIDS_Constants.json_keys[key.replace(
" ", "_")]:
''.join(
str(e) for e in json_data.info[key])
})
else:
acq_obj.add_attributes({
BIDS_Constants.json_keys[key.replace(
" ", "_")]:
json_data.info[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:
getRelPathToBIDS(
join(file_tpl.dirname,
bids_layout.get_bval(file_tpl.filename)),
directory)
})
#WIP: add absolute location of BIDS directory on disk for later finding of files
acq_obj_bval.add_attributes(
{Constants.PROV['Location']: directory})
#add sha512 sum
if isfile(join(directory, file_tpl.dirname,
file_tpl.filename)):
acq_obj_bval.add_attributes({
Constants.CRYPTO_SHA512:
getsha512(
join(directory, file_tpl.dirname,
file_tpl.filename))
})
else:
logging.info(
"WARNINGL file %s doesn't exist! No SHA512 sum stored in NIDM files..."
% join(directory, file_tpl.dirname, 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:
getRelPathToBIDS(
join(file_tpl.dirname,
bids_layout.get_bvec(file_tpl.filename)),
directory)
})
#WIP: add absolute location of BIDS directory on disk for later finding of files
acq_obj_bvec.add_attributes(
{Constants.PROV['Location']: directory})
if isfile(join(directory, file_tpl.dirname,
file_tpl.filename)):
#add sha512 sum
acq_obj_bvec.add_attributes({
Constants.CRYPTO_SHA512:
getsha512(
join(directory, file_tpl.dirname,
file_tpl.filename))
})
else:
logging.info(
"WARNINGL file %s doesn't exist! No SHA512 sum stored in NIDM files..."
% join(directory, file_tpl.dirname, file_tpl.filename))
#link bval and bvec acquisition object entities together or is their association with DWI scan...
#Added temporarily to support phenotype files
#for each *.tsv / *.json file pair in the phenotypes directory
#WIP: ADD VARIABLE -> TERM MAPPING HERE
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 = AssessmentAcquisition(session=session[subjid[1]])
#add qualified association with person
acq.add_qualified_association(
person=participant[subject_id]['person'],
role=Constants.NIDM_PARTICIPANT)
acq_entity = AssessmentObject(acquisition=acq)
for key, value in row.items():
if not value:
continue
#we're using participant_id in NIDM in agent so don't add to assessment as a triple.
#BIDS phenotype files seem to have an index column with no column header variable name so skip those
if ((not key == "participant_id") and (key != "")):
#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:
getRelPathToBIDS(tsv_file, directory)
})
#WIP: add absolute location of BIDS directory on disk for later finding of files
acq_entity.add_attributes(
{Constants.PROV['Location']: directory})
#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"]:
getRelPathToBIDS(data_dict, directory)
})
return project, cde
def addimagingsessions(bids_layout,subject_id,session,participant, directory,img_session=None):
'''
This function adds imaging acquistions to the NIDM file and deals with BIDS structures potentially having
separate ses-* directories or not
:param bids_layout:
:param subject_id:
:param session:
:param participant:
:param directory:
:param img_session:
:return:
'''
for file_tpl in bids_layout.get(subject=subject_id, session=img_session, extensions=['.nii', '.nii.gz']):
# create an acquisition activity
acq=MRAcquisition(session)
# check whether participant (i.e. agent) for this subject already exists (i.e. if participants.tsv file exists) else create one
if (not subject_id in participant) and (not subject_id.lstrip("0") in participant):
participant[subject_id] = {}
participant[subject_id]['person'] = acq.add_person(attributes=({Constants.NIDM_SUBJECTID:subject_id}))
acq.add_qualified_association(person=participant[subject_id]['person'],role=Constants.NIDM_PARTICIPANT)
# added to account for errors in BIDS datasets where participants.tsv may have no leading 0's but
# subject directories do. Since bidsmri2nidm starts with the participants.tsv file those are the IDs unless
# there's a subject directory and no entry in participants.tsv...
elif subject_id.lstrip("0") in participant:
# then link acquisition to the agent with participant ID without leading 00's
acq.add_qualified_association(person=participant[subject_id.lstrip("0")]['person'],role=Constants.NIDM_PARTICIPANT)
else:
# add qualified association with person
acq.add_qualified_association(person=participant[subject_id]['person'],role=Constants.NIDM_PARTICIPANT)
if file_tpl.entities['datatype']=='anat':
# do something with anatomicals
acq_obj = MRObject(acq)
# add image contrast type
if file_tpl.entities['suffix'] in BIDS_Constants.scans:
acq_obj.add_attributes({Constants.NIDM_IMAGE_CONTRAST_TYPE:BIDS_Constants.scans[file_tpl.entities['suffix']]})
else:
logging.info("WARNING: No matching image contrast type found in BIDS_Constants.py for %s" % file_tpl.entities['suffix'])
# add image usage type
if file_tpl.entities['datatype'] in BIDS_Constants.scans:
acq_obj.add_attributes({Constants.NIDM_IMAGE_USAGE_TYPE:BIDS_Constants.scans[file_tpl.entities['datatype']]})
else:
logging.info("WARNING: No matching image usage type found in BIDS_Constants.py for %s" % file_tpl.entities['datatype'])
# add file link
# make relative link to
acq_obj.add_attributes({Constants.NIDM_FILENAME:getRelPathToBIDS(join(file_tpl.dirname,file_tpl.filename), directory)})
# add git-annex info if exists
num_sources = addGitAnnexSources(obj=acq_obj,filepath=join(file_tpl.dirname,file_tpl.filename),bids_root=directory)
# if there aren't any git annex sources then just store the local directory information
if num_sources == 0:
# WIP: add absolute location of BIDS directory on disk for later finding of files
acq_obj.add_attributes({Constants.PROV['Location']:"file:/" + join(file_tpl.dirname,file_tpl.filename)})
# add sha512 sum
if isfile(join(directory,file_tpl.dirname,file_tpl.filename)):
acq_obj.add_attributes({Constants.CRYPTO_SHA512:getsha512(join(directory,file_tpl.dirname,file_tpl.filename))})
else:
logging.info("WARNING file %s doesn't exist! No SHA512 sum stored in NIDM files..." %join(directory,file_tpl.dirname,file_tpl.filename))
# get associated JSON file if exists
# There is T1w.json file with information
json_data = (bids_layout.get(suffix=file_tpl.entities['suffix'],subject=subject_id))[0].metadata
if len(json_data.info)>0:
for key in json_data.info.items():
if key in BIDS_Constants.json_keys:
if type(json_data.info[key]) is list:
acq_obj.add_attributes({BIDS_Constants.json_keys[key.replace(" ", "_")]:''.join(str(e) for e in json_data.info[key])})
else:
acq_obj.add_attributes({BIDS_Constants.json_keys[key.replace(" ", "_")]:json_data.info[key]})
# Parse T1w.json file in BIDS directory to add the attributes contained inside
if (os.path.isdir(os.path.join(directory))):
try:
with open(os.path.join(directory,'T1w.json')) as data_file:
dataset = json.load(data_file)
except OSError:
logging.warning("Cannot find T1w.json file...looking for session-specific one")
try:
with open(os.path.join(directory,'ses-' + img_session + '_T1w.json')) as data_file:
dataset = json.load(data_file)
except OSError:
logging.warning("Cannot find session-specific T1w.json file which is required in the BIDS spec..continuing anyway")
dataset={}
else:
logging.critical("Error: BIDS directory %s does not exist!" %os.path.join(directory))
exit(-1)
# add various attributes if they exist in BIDS dataset
for key in dataset:
# if key from T1w.json file is mapped to term in BIDS_Constants.py then add to NIDM object
if key in BIDS_Constants.json_keys:
if type(dataset[key]) is list:
acq_obj.add_attributes({BIDS_Constants.json_keys[key]:"".join(dataset[key])})
else:
acq_obj.add_attributes({BIDS_Constants.json_keys[key]:dataset[key]})
elif file_tpl.entities['datatype'] == 'func':
# do something with functionals
acq_obj = MRObject(acq)
# add image contrast type
if file_tpl.entities['suffix'] in BIDS_Constants.scans:
acq_obj.add_attributes({Constants.NIDM_IMAGE_CONTRAST_TYPE:BIDS_Constants.scans[file_tpl.entities['suffix']]})
else:
logging.info("WARNING: No matching image contrast type found in BIDS_Constants.py for %s" % file_tpl.entities['suffix'])
# add image usage type
if file_tpl.entities['datatype'] in BIDS_Constants.scans:
acq_obj.add_attributes({Constants.NIDM_IMAGE_USAGE_TYPE:BIDS_Constants.scans[file_tpl.entities['datatype']]})
else:
logging.info("WARNING: No matching image usage type found in BIDS_Constants.py for %s" % file_tpl.entities['datatype'])
# make relative link to
acq_obj.add_attributes({Constants.NIDM_FILENAME:getRelPathToBIDS(join(file_tpl.dirname,file_tpl.filename), directory)})
# add git-annex/datalad info if exists
num_sources=addGitAnnexSources(obj=acq_obj,filepath=join(file_tpl.dirname,file_tpl.filename),bids_root=directory)
# if there aren't any git annex sources then just store the local directory information
if num_sources == 0:
# WIP: add absolute location of BIDS directory on disk for later finding of files
acq_obj.add_attributes({Constants.PROV['Location']:"file:/" + join(file_tpl.dirname,file_tpl.filename)})
# add sha512 sum
if isfile(join(directory,file_tpl.dirname,file_tpl.filename)):
acq_obj.add_attributes({Constants.CRYPTO_SHA512:getsha512(join(directory,file_tpl.dirname,file_tpl.filename))})
else:
logging.info("WARNINGL file %s doesn't exist! No SHA512 sum stored in NIDM files..." %join(directory,file_tpl.dirname,file_tpl.filename))
if 'run' in file_tpl.entities:
acq_obj.add_attributes({BIDS_Constants.json_keys["run"]:file_tpl.entities['run']})
# get associated JSON file if exists
json_data = (bids_layout.get(suffix=file_tpl.entities['suffix'],subject=subject_id))[0].metadata
if len(json_data.info)>0:
for key in json_data.info.items():
if key in BIDS_Constants.json_keys:
if type(json_data.info[key]) is list:
acq_obj.add_attributes({BIDS_Constants.json_keys[key.replace(" ", "_")]:''.join(str(e) for e in json_data.info[key])})
else:
acq_obj.add_attributes({BIDS_Constants.json_keys[key.replace(" ", "_")]:json_data.info[key]})
# get associated events TSV file
if 'run' in file_tpl.entities:
events_file = bids_layout.get(subject=subject_id, extensions=['.tsv'],modality=file_tpl.entities['datatype'],task=file_tpl.entities['task'],run=file_tpl.entities['run'])
else:
events_file = bids_layout.get(subject=subject_id, extensions=['.tsv'],modality=file_tpl.entities['datatype'],task=file_tpl.entities['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.NIDM_FILENAME:getRelPathToBIDS(events_file[0].filename, directory)})
#link it to appropriate MR acquisition entity
events_obj.wasAttributedTo(acq_obj)
# add source links for this file
# add git-annex/datalad info if exists
num_sources=addGitAnnexSources(obj=events_obj,filepath=events_file,bids_root=directory)
# if there aren't any git annex sources then just store the local directory information
if num_sources == 0:
# WIP: add absolute location of BIDS directory on disk for later finding of files
events_obj.add_attributes({Constants.PROV['Location']:"file:/" + events_file})
#Parse task-rest_bold.json file in BIDS directory to add the attributes contained inside
if (os.path.isdir(os.path.join(directory))):
try:
with open(os.path.join(directory,'task-rest_bold.json')) as data_file:
dataset = json.load(data_file)
except OSError:
logging.warning("Cannot find task-rest_bold.json file looking for session-specific one")
try:
with open(os.path.join(directory,'ses-' + img_session +'_task-rest_bold.json')) as data_file:
dataset = json.load(data_file)
except OSError:
logging.warning("Cannot find session-specific task-rest_bold.json file which is required in the BIDS spec..continuing anyway")
dataset={}
else:
logging.critical("Error: BIDS directory %s does not exist!" %os.path.join(directory))
exit(-1)
#add various attributes if they exist in BIDS dataset
for key in dataset:
#if key from task-rest_bold.json file is mapped to term in BIDS_Constants.py then add to NIDM object
if key in BIDS_Constants.json_keys:
if type(dataset[key]) is list:
acq_obj.add_attributes({BIDS_Constants.json_keys[key]:",".join(map(str,dataset[key]))})
else:
acq_obj.add_attributes({BIDS_Constants.json_keys[key]:dataset[key]})
elif file_tpl.entities['datatype'] == 'dwi':
#do stuff with with dwi scans...
acq_obj = MRObject(acq)
#add image contrast type
if file_tpl.entities['suffix'] in BIDS_Constants.scans:
acq_obj.add_attributes({Constants.NIDM_IMAGE_CONTRAST_TYPE:BIDS_Constants.scans[file_tpl.entities['suffix']]})
else:
logging.info("WARNING: No matching image contrast type found in BIDS_Constants.py for %s" % file_tpl.entities['suffix'])
#add image usage type
if file_tpl.entities['datatype'] in BIDS_Constants.scans:
acq_obj.add_attributes({Constants.NIDM_IMAGE_USAGE_TYPE:BIDS_Constants.scans["dti"]})
else:
logging.info("WARNING: No matching image usage type found in BIDS_Constants.py for %s" % file_tpl.entities['datatype'])
#make relative link to
acq_obj.add_attributes({Constants.NIDM_FILENAME:getRelPathToBIDS(join(file_tpl.dirname,file_tpl.filename), directory)})
#add sha512 sum
if isfile(join(directory,file_tpl.dirname,file_tpl.filename)):
acq_obj.add_attributes({Constants.CRYPTO_SHA512:getsha512(join(directory,file_tpl.dirname,file_tpl.filename))})
else:
logging.info("WARNING file %s doesn't exist! No SHA512 sum stored in NIDM files..." %join(directory,file_tpl.dirname,file_tpl.filename))
# add git-annex/datalad info if exists
num_sources = addGitAnnexSources(obj=acq_obj,filepath=join(file_tpl.dirname,file_tpl.filename),bids_root=directory)
if num_sources == 0:
acq_obj.add_attributes({Constants.PROV['Location']: "file:/" + join(file_tpl.dirname,file_tpl.filename)})
if 'run' in file_tpl.entities:
acq_obj.add_attributes({BIDS_Constants.json_keys["run"]:file_tpl.run})
#get associated JSON file if exists
json_data = (bids_layout.get(suffix=file_tpl.entities['suffix'],subject=subject_id))[0].metadata
if len(json_data.info)>0:
for key in json_data.info.items():
if key in BIDS_Constants.json_keys:
if type(json_data.info[key]) is list:
acq_obj.add_attributes({BIDS_Constants.json_keys[key.replace(" ", "_")]:''.join(str(e) for e in json_data.info[key])})
else:
acq_obj.add_attributes({BIDS_Constants.json_keys[key.replace(" ", "_")]:json_data.info[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:getRelPathToBIDS(join(file_tpl.dirname,bids_layout.get_bval(join(file_tpl.dirname,file_tpl.filename))),directory)})
# add git-annex/datalad info if exists
num_sources = addGitAnnexSources(obj=acq_obj_bval,filepath=join(file_tpl.dirname,bids_layout.get_bval(join(file_tpl.dirname,file_tpl.filename))),bids_root=directory)
if num_sources == 0:
# WIP: add absolute location of BIDS directory on disk for later finding of files
acq_obj_bval.add_attributes({Constants.PROV['Location']:"file:/" + join(file_tpl.dirname,bids_layout.get_bval(join(file_tpl.dirname,file_tpl.filename)))})
# add sha512 sum
if isfile(join(directory,file_tpl.dirname,file_tpl.filename)):
acq_obj_bval.add_attributes({Constants.CRYPTO_SHA512:getsha512(join(directory,file_tpl.dirname,file_tpl.filename))})
else:
logging.info("WARNING file %s doesn't exist! No SHA512 sum stored in NIDM files..." %join(directory,file_tpl.dirname,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:getRelPathToBIDS(join(file_tpl.dirname,bids_layout.get_bvec(join(file_tpl.dirname,file_tpl.filename))),directory)})
# add git-annex/datalad info if exists
num_sources = addGitAnnexSources(obj=acq_obj_bvec,filepath=join(file_tpl.dirname,bids_layout.get_bvec(join(file_tpl.dirname,file_tpl.filename))),bids_root=directory)
if num_sources == 0:
#WIP: add absolute location of BIDS directory on disk for later finding of files
acq_obj_bvec.add_attributes({Constants.PROV['Location']:"file:/" + join(file_tpl.dirname,bids_layout.get_bvec(join(file_tpl.dirname,file_tpl.filename)))})
if isfile(join(directory,file_tpl.dirname,file_tpl.filename)):
#add sha512 sum
acq_obj_bvec.add_attributes({Constants.CRYPTO_SHA512:getsha512(join(directory,file_tpl.dirname,file_tpl.filename))})
else:
logging.info("WARNING file %s doesn't exist! No SHA512 sum stored in NIDM files..." %join(directory,file_tpl.dirname,file_tpl.filename))
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(attributes={Constants.NIDM_FAMILY_NAME:"Keator", Constants.NIDM_GIVEN_NAME:"David"})
#add qualified association of project PI to project activity
project.add_qualified_association(person=project_PI,role=Constants.NIDM_PI)
#test add session to graph and associate with project
session = Session(project)
session.add_attributes({Constants.NIDM:"test"})
#project.add_sessions(session)
#test add MR acquisition activity / entity to graph and associate with session
acq_act = MRAcquisition(session=session)
#test add acquisition object entity to graph associated with participant role NIDM_PARTICIPANT
acq_entity = MRObject(acquisition=acq_act)
#add person to graph
person = acq_act.add_person(attributes={Constants.NIDM_GIVEN_NAME:"George"})
#add qualified association of person with role NIDM_PARTICIPANT, and associated with acquistion activity
acq_act.add_qualified_association(person=person, role=Constants.NIDM_PARTICIPANT)
#test add Assessment acquisition activity / entity to graph and associate with session
acq_act = AssessmentAcquisition(session=session)
#test add acquisition object entity to graph associated with participant role NIDM_PARTICIPANT
acq_entity = AssessmentObject(acquisition=acq_act)
acq_entity.add_attributes({Constants.NIDM["Q1"]:"Q1 Answer",Constants.NIDM["Q2"]:"Q2 Answer" })
#associate person as participant
acq_act.add_qualified_association(person=person, role=Constants.NIDM_PARTICIPANT)
#test add DemographicsAssessment acquisition activity / entity to graph and associate with session
acq_act = AssessmentAcquisition(session=session)
#test add acquisition object entity to graph associated with participant role NIDM_PARTICIPANT
acq_entity = DemographicsObject(acquisition=acq_act)
#add new person to graph
person2 = acq_act.add_person(attributes={Constants.NIDM_FAMILY_NAME:"Doe", \
Constants.NIDM_GIVEN_NAME:"John"})
#associate person2 with assessment acquisition
acq_act.add_qualified_association(person=person2, role=Constants.NIDM_PARTICIPANT)
acq_entity.add_attributes({Constants.NIDM_AGE:60,Constants.NIDM_GENDER:"Male" })
#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 bidsmri2project(directory):
#Parse dataset_description.json file in BIDS directory
if (os.path.isdir(os.path.join(directory))):
with open(os.path.join(directory,
'dataset_description.json')) as data_file:
dataset = json.load(data_file)
else:
print("Error: BIDS directory %s does not exist!" %
os.path.join(directory))
exit("-1")
#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]})
#add absolute location of BIDS directory on disk for later finding of files which are stored relatively in NIDM document
project.add_attributes({Constants.PROV['Location']: directory})
#create empty dictinary for sessions where key is subject id and used later to link scans to same session as demographics
session = {}
participant = {}
#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 = AssessmentAcquisition(session=session[subjid[1]])
acq_entity = AssessmentObject(acquisition=acq)
participant[subjid[1]] = {}
participant[subjid[1]]['person'] = acq.add_person(
attributes=({
Constants.NIDM_SUBJECTID: row['participant_id']
}))
#add qualified association of participant with acquisition activity
acq.add_qualified_association(
person=participant[subjid[1]]['person'],
role=Constants.NIDM_PARTICIPANT)
for key, value in row.items():
#for variables in participants.tsv file who have term mappings in BIDS_Constants.py use those
if key in BIDS_Constants.participants:
#if this was the participant_id, we already handled it above creating agent / qualified association
if not (BIDS_Constants.participants[key]
== Constants.NIDM_SUBJECTID):
acq_entity.add_attributes(
{BIDS_Constants.participants[key]: value})
#else just put variables in bids namespace since we don't know what they mean
else:
#acq_entity.add_attributes({Constants.BIDS[quote(key)]:value})
acq_entity.add_attributes(
{Constants.BIDS[key.replace(" ", "_")]: 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():
print("Converting subject: %s" % subject_id)
#skip .git directories...added to support datalad datasets
if subject_id.startswith("."):
continue
#check if there's a session number. If so, store it in the session activity
session_dirs = bids_layout.get(target='session',
subject=subject_id,
return_type='dir')
#if session_dirs has entries then get any metadata about session and store in session activity
#bids_layout.get(subject=subject_id,type='session',extensions='.tsv')
#bids_layout.get(subject=subject_id,type='scans',extensions='.tsv')
#bids_layout.get(extensions='.tsv',return_type='obj')
for file_tpl in bids_layout.get(subject=subject_id,
extensions=['.nii', '.nii.gz']):
#create an acquisition activity
acq = MRAcquisition(session[subject_id])
#add qualified association with person
acq.add_qualified_association(
person=participant[subject_id]['person'],
role=Constants.NIDM_PARTICIPANT)
#print(file_tpl.type)
if file_tpl.modality == 'anat':
#do something with anatomicals
acq_obj = MRObject(acq)
#add image contrast type
if file_tpl.type in BIDS_Constants.scans:
acq_obj.add_attributes({
Constants.NIDM_IMAGE_CONTRAST_TYPE:
BIDS_Constants.scans[file_tpl.type]
})
else:
print(
"WARNING: No matching image contrast type found in BIDS_Constants.py for %s"
% file_tpl.type)
#add image usage type
if file_tpl.modality in BIDS_Constants.scans:
acq_obj.add_attributes({
Constants.NIDM_IMAGE_USAGE_TYPE:
BIDS_Constants.scans[file_tpl.modality]
})
else:
print(
"WARNING: No matching image usage type found in BIDS_Constants.py for %s"
% file_tpl.modality)
#add file link
#make relative link to
acq_obj.add_attributes({
Constants.NIDM_FILENAME:
getRelPathToBIDS(file_tpl.filename, directory)
})
#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.replace(
" ", "_")]:
''.join(str(e) for e in json_data[key])
})
else:
acq_obj.add_attributes({
BIDS_Constants.json_keys[key.replace(
" ", "_")]:
json_data[key]
})
elif file_tpl.modality == 'func':
#do something with functionals
acq_obj = MRObject(acq)
#add image contrast type
if file_tpl.type in BIDS_Constants.scans:
acq_obj.add_attributes({
Constants.NIDM_IMAGE_CONTRAST_TYPE:
BIDS_Constants.scans[file_tpl.type]
})
else:
print(
"WARNING: No matching image contrast type found in BIDS_Constants.py for %s"
% file_tpl.type)
#add image usage type
if file_tpl.modality in BIDS_Constants.scans:
acq_obj.add_attributes({
Constants.NIDM_IMAGE_USAGE_TYPE:
BIDS_Constants.scans[file_tpl.modality]
})
else:
print(
"WARNING: No matching image usage type found in BIDS_Constants.py for %s"
% file_tpl.modality)
#add file link
acq_obj.add_attributes({
Constants.NIDM_FILENAME:
getRelPathToBIDS(file_tpl.filename, directory)
})
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.replace(
" ", "_")]:
''.join(str(e) for e in json_data[key])
})
else:
acq_obj.add_attributes({
BIDS_Constants.json_keys[key.replace(
" ", "_")]:
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.NIDM_FILENAME:
getRelPathToBIDS(events_file[0].filename, directory)
})
#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 = MRObject(acq)
#add image contrast type
if file_tpl.type in BIDS_Constants.scans:
acq_obj.add_attributes({
Constants.NIDM_IMAGE_CONTRAST_TYPE:
BIDS_Constants.scans[file_tpl.type]
})
else:
print(
"WARNING: No matching image contrast type found in BIDS_Constants.py for %s"
% file_tpl.type)
#add image usage type
if file_tpl.modality in BIDS_Constants.scans:
acq_obj.add_attributes({
Constants.NIDM_IMAGE_USAGE_TYPE:
BIDS_Constants.scans["dti"]
})
else:
print(
"WARNING: No matching image usage type found in BIDS_Constants.py for %s"
% file_tpl.modality)
#add file link
acq_obj.add_attributes({
Constants.NIDM_FILENAME:
getRelPathToBIDS(file_tpl.filename, directory)
})
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.replace(
" ", "_")]:
''.join(str(e) for e in json_data[key])
})
else:
acq_obj.add_attributes({
BIDS_Constants.json_keys[key.replace(
" ", "_")]:
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:
getRelPathToBIDS(bids_layout.get_bval(file_tpl.filename),
directory)
})
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:
getRelPathToBIDS(bids_layout.get_bvec(file_tpl.filename),
directory)
})
#link bval and bvec acquisition object entities together or is their association with DWI scan...
#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 = AssessmentAcquisition(session=session[subjid[1]])
#add qualified association with person
acq.add_qualified_association(
person=participant[subject_id]['person'],
role=Constants.NIDM_PARTICIPANT)
acq_entity = AssessmentObject(acquisition=acq)
for key, value in row.items():
#we're using participant_id in NIDM in agent so don't add to assessment as a triple.
#BIDS phenotype files seem to have an index column with no column header variable name so skip those
if ((not key == "participant_id") and (key != "")):
#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:
getRelPathToBIDS(tsv_file, directory)
})
#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"]:
getRelPathToBIDS(data_dict, directory)
})
return project