def build_schema(self):
schema = super(CellResource,self).build_schema()
schema['fields'] = get_detail_schema(Cell(),['cell'])
return schema
def main(path):
"""
Read in the Cell
"""
sheet_name = 'HMS-LINCS cell line metadata'
sheet = iu.readtable([path, sheet_name, 1]) # Note, skipping the header row by default
properties = ('model_field','required','default','converter')
column_definitions = {
'Facility ID':('facility_id',True,None, lambda x: x[x.index('HMSL')+4:]),
'CL_Name':('name',True),
'CL_LINCS_ID':'lincs_id',
'CL_Alternate_Name':'alternative_names',
'CL_Alternate_ID':'alternate_id',
'CL_Center_Specific_ID':'center_specific_id',
'MGH_ID':('mgh_id',False,None,lambda x:util.convertdata(x,int)),
'Assay':'assay',
'CL_Organism':'organism',
'CL_Organ':'organ',
'CL_Tissue':'tissue',
'CL_Cell_Type':'cell_type',
'CL_Cell_Type_Detail':'cell_type_detail',
'CL_Donor_Sex': 'donor_sex',
'CL_Donor_Age': ('donor_age_years',False,None,lambda x:util.convertdata(x,int)),
'CL_Donor_Ethnicity': 'donor_ethnicity',
'CL_Donor_Health_Status': 'donor_health_status',
'CL_Disease':'disease',
'CL_Disease_Detail':'disease_detail',
'CL_Growth_Properties':'growth_properties',
'CL_Genetic_Modification':'genetic_modification',
'CL_Related_Projects':'related_projects',
'CL_Recommended_Culture_Conditions':'recommended_culture_conditions',
'CL_Verification_Reference_Profile':'verification_reference_profile',
'CL_Known_Mutations':'mutations_known',
'CL_Mutations_Citations':'mutations_citations',
'CL_Molecular_Features': 'molecular_features',
'CL_Relevant_Citations': 'relevant_citations',
'CL_Reference_Source': 'reference_source',
'CL_Reference_Source_ID': 'reference_source_id',
'Reference Source URL': 'reference_source_url',
'Usage Note': 'usage_note',
'Date Data Received':('date_data_received',False,None,util.date_converter),
'Date Loaded': ('date_loaded',False,None,util.date_converter),
'Date Publicly Available': ('date_publicly_available',False,None,util.date_converter),
'Most Recent Update': ('date_updated',False,None,util.date_converter),
'Is Restricted':('is_restricted',False,False,util.bool_converter)}
# convert the labels to fleshed out dict's, with strategies for optional, default and converter
column_definitions = util.fill_in_column_definitions(properties,column_definitions)
# create a dict mapping the column ordinal to the proper column definition dict
cols = util.find_columns(column_definitions, sheet.labels, all_sheet_columns_required=False)
rows = 0
logger.debug(str(('cols: ' , cols)))
for row in sheet:
r = util.make_row(row)
initializer = {}
for i,value in enumerate(r):
if i not in cols: continue
properties = cols[i]
logger.debug(str(('read col: ', i, ', ', properties)))
required = properties['required']
default = properties['default']
converter = properties['converter']
model_field = properties['model_field']
# Todo, refactor to a method
logger.debug(str(('raw value', value)))
if(converter != None):
value = converter(value)
if(value == None ):
if( default != None ):
value = default
if(value == None and required == True):
raise Exception('Field is required: %s, record: %d' % (properties['column_label'],rows))
logger.debug(str(('model_field: ' , model_field, ', value: ', value)))
initializer[model_field] = value
try:
logger.debug(str(('initializer: ', initializer)))
cell = Cell(**initializer)
cell.save()
logger.info(str(('cell created:', cell)))
rows += 1
# create a default batch - 0
CellBatch.objects.create(reagent=cell,batch_id=0)
except Exception, e:
print "Invalid Cell, name: ", r[0]
raise e
def main(path):
"""
Read in the Cell
"""
sheet_name = 'HMS-LINCS cell line metadata'
sheet = iu.readtable([path, sheet_name, 1]) # Note, skipping the header row by default
properties = ('model_field','required','default','converter')
column_definitions = {
'Facility ID':('facility_id',True,None, lambda x: x[x.index('HMSL')+4:]),
'CL_Name':('name',True),
'CL_ID':'cl_id',
'CL_Alternate_Name':'alternate_name',
'CL_Alternate_ID':'alternate_id',
'CL_Center_Name':'center_name',
'CL_Center_Specific_ID':'center_specific_id',
'MGH_ID':('mgh_id',False,None,lambda x:util.convertdata(x,int)),
'Assay':'assay',
'CL_Provider_Name':'provider_name',
'CL_Provider_Catalog_ID':'provider_catalog_id',
'CL_Batch_ID':'batch_id',
'CL_Organism':'organism',
'CL_Organ':'organ',
'CL_Tissue':'tissue',
'CL_Cell_Type':'cell_type',
'CL_Cell_Type_Detail':'cell_type_detail',
'CL_Disease':'disease',
'CL_Disease_Detail':'disease_detail',
'CL_Growth_Properties':'growth_properties',
'CL_Genetic_Modification':'genetic_modification',
'CL_Related_Projects':'related_projects',
'CL_Recommended_Culture_Conditions':'recommended_culture_conditions',
'CL_Verification_Profile':'verification_profile',
'CL_Verification_Reference_Profile':'verification_reference_profile',
'CL_Mutations_Reference':'mutations_reference',
'CL_Mutations_Explicit':'mutations_explicit',
'CL_Organism_Gender':'organism_gender',
'Date Data Received':('date_data_received',False,None,util.date_converter),
'Date Loaded': ('date_loaded',False,None,util.date_converter),
'Date Publicly Available': ('date_publicly_available',False,None,util.date_converter),
'Most Recent Update': ('date_updated',False,None,util.date_converter),
'Is Restricted':('is_restricted',False,False,util.bool_converter)}
# convert the labels to fleshed out dict's, with strategies for optional, default and converter
column_definitions = util.fill_in_column_definitions(properties,column_definitions)
# create a dict mapping the column ordinal to the proper column definition dict
cols = util.find_columns(column_definitions, sheet.labels)
rows = 0
logger.debug(str(('cols: ' , cols)))
for row in sheet:
r = util.make_row(row)
initializer = {}
for i,value in enumerate(r):
if i not in cols: continue
properties = cols[i]
logger.debug(str(('read col: ', i, ', ', properties)))
required = properties['required']
default = properties['default']
converter = properties['converter']
model_field = properties['model_field']
# Todo, refactor to a method
logger.debug(str(('raw value', value)))
if(converter != None):
value = converter(value)
if(value == None ):
if( default != None ):
value = default
if(value == None and required == True):
raise Exception('Field is required: %s, record: %d' % (properties['column_label'],rows))
logger.debug(str(('model_field: ' , model_field, ', value: ', value)))
initializer[model_field] = value
try:
logger.debug(str(('initializer: ', initializer)))
cell = Cell(**initializer)
cell.save()
logger.info(str(('cell created:', cell)))
rows += 1
except Exception, e:
print "Invalid Cell, name: ", r[0]
raise e
def main(path, do_precursors_only):
"""
Read in the Cell
"""
sheet_name = 'HMS-LINCS cell line metadata'
sheet = iu.readtable([path, sheet_name, 1]) # allow for informational header row
properties = ('model_field','required','default','converter')
column_definitions = {
'Facility ID':('facility_id',True,None, lambda x: x[x.index('HMSL')+4:]),
'CL_Name':('name',True),
'CL_LINCS_ID':'lincs_id',
'CL_Alternate_Name':'alternative_names',
'CL_Alternate_ID':'alternative_id',
'Precursor_Cell':'precursor_facility_batch_id',
'CL_Organism':'organism',
'CL_Organ':'organ',
'CL_Tissue':'tissue',
'CL_Cell_Type':'cell_type',
'CL_Cell_Type_Detail':'cell_type_detail',
'CL_Donor_Sex': 'donor_sex',
'CL_Donor_Age': ('donor_age_years',False,None,lambda x:util.convertdata(x,int)),
'CL_Donor_Ethnicity': 'donor_ethnicity',
'CL_Donor_Health_Status': 'donor_health_status',
'CL_Disease':'disease',
'CL_Disease_Detail':'disease_detail',
'CL_Production_Details': 'production_details',
'CL_Genetic_Modification':'genetic_modification',
'CL_Known_Mutations':'mutations_known',
'CL_Mutation_Citations':'mutation_citations',
'CL_Verification_Reference_Profile':'verification_reference_profile',
'CL_Growth_Properties':'growth_properties',
'CL_Recommended_Culture_Conditions':'recommended_culture_conditions',
'CL_Relevant_Citations': 'relevant_citations',
'Usage Note': 'usage_note',
'CL_Reference_Source': 'reference_source',
'Reference Source URL': 'reference_source_url',
'Date Data Received':('date_data_received',False,None,util.date_converter),
'Date Loaded': ('date_loaded',False,None,util.date_converter),
'Date Publicly Available': ('date_publicly_available',False,None,util.date_converter),
'Most Recent Update': ('date_updated',False,None,util.date_converter),
'Is Restricted':('is_restricted',False,False,util.bool_converter)}
# convert the labels to fleshed out dict's, with strategies for optional, default and converter
column_definitions = util.fill_in_column_definitions(properties,column_definitions)
# create a dict mapping the column ordinal to the proper column definition dict
cols = util.find_columns(column_definitions, sheet.labels, all_sheet_columns_required=False)
rows = 0
precursor_map = {}
precursor_pattern = re.compile(r'HMSL(5\d{4})-(\d+)')
for row in sheet:
r = util.make_row(row)
initializer = {}
for i,value in enumerate(r):
if i not in cols: continue
properties = cols[i]
required = properties['required']
default = properties['default']
converter = properties['converter']
model_field = properties['model_field']
value = convertdata(value)
if value is not None:
if converter:
try:
value = converter(value)
except Exception:
logger.error('field parse error: %r, value: %r, row: %d',
properties['column_label'],value,rows+2)
raise
if value is None:
if default is not None:
value = default
if value is None and required:
raise Exception('Field is required: %s, record: %d'
% (properties['column_label'],rows))
logger.debug('model_field: %r, value: %r' , model_field, value)
initializer[model_field] = value
precursor_facility_batch_id = initializer.pop('precursor_facility_batch_id')
if precursor_facility_batch_id:
match = precursor_pattern.match(precursor_facility_batch_id)
if not match:
raise Exception('Invalid precursor pattern: needs: %s: %r, row: %d'
% (precursor_pattern, initializer, rows))
precursor_map[initializer['facility_id']] = (match.group(1),match.group(2))
if not do_precursors_only:
try:
logger.info('initializer: %r', initializer)
cell = Cell(**initializer)
cell.save()
logger.info(str(('cell created:', cell)))
# create a default batch - 0
CellBatch.objects.create(reagent=cell,batch_id=0)
except Exception, e:
print "Invalid Cell, name: ", r[0]
raise e
rows += 1