def read_metadata(path):
"""
Read in the DataSets, Datacolumns, and Data sheets. In the Data sheet, rows are DataRecords, and columns are DataPoints
"""
# Read in the DataSet
sheetname = 'Meta'
# Define the Column Names -> model fields mapping
labels = {'Lead Screener First': 'lead_screener_firstname',
'Lead Screener Last': 'lead_screener_lastname',
'Lead Screener Email': 'lead_screener_email',
'Lab Head First': 'lab_head_firstname',
'Lab Head Last': 'lab_head_lastname',
'Lab Head Email': 'lab_head_email',
'Title': 'title',
'Facility ID': 'facility_id',
'Summary': 'summary',
'Protocol': 'protocol',
'References': 'protocol_references'}
metaSheet = iu.readtable([path, sheetname]) # Note, skipping the header row by default
metaData = {}
for row in metaSheet:
rowAsUnicode = util.make_row(row)
for key,value in labels.items():
if re.match(key, rowAsUnicode[0], re.M|re.I):
if key == 'Facility ID':
metaData[value] = util.convertdata(rowAsUnicode[1],int)
else:
metaData[value] = rowAsUnicode[1]
assert len(metaData) == len(labels), 'Meta data sheet does not contain the necessary keys, expected: %s, read: %s' % [labels, metaData]
return metaData
def main(path):
"""
Read in the Protein
"""
sheet_name = 'HMS-LINCS Kinases'
labels = {
'PP_Name': 'name',
'PP_LINCS_ID': 'lincs_id',
'PP_UniProt_ID': 'uniprot_id',
'PP_Alternate_Name': 'alternate_name',
'PP_Provider': 'provider',
'PP_Provider_Catalog_ID': 'provider_catalog_id',
'PP_Batch_ID': 'batch_id',
'PP_Amino_Acid_Sequence': 'amino_acid_sequence',
'PP_Gene_Symbol': 'gene_symbol',
'PP_Gene_ID': 'gene_id',
'PP_Protein_Source': 'protein_source',
'PP_Protein_Form': 'protein_form',
'PP_Protein_Purity': 'protein_purity',
'PP_Protein_Complex': 'protein_complex',
'PP_Isoform': 'isoform',
'PP_Protein_Type': 'protein_type',
'PP_Source_Organism': 'source_organism',
'PP_Reference': 'reference'
}
converters = {'lincs_id': lambda x: x[x.index('HMSL') + 4:]}
sheet = iu.readtable([path, sheet_name,
1]) # Note, skipping the header row by default
cols = {}
# first put the label row in (it contains the worksheet column, and its unique)
print 'labels: ', sheet.labels
for i, label in enumerate(sheet.labels):
if label in labels:
cols[i] = labels[label]
else:
print 'Note: column label not found:', label
#raise
rows = 0
i = 0
print 'cols: ', cols
proteins = {}
for row in sheet:
r = util.make_row(row)
dict = {}
for i, value in enumerate(r):
if i not in cols: continue
if cols[i] in converters:
value = converters[cols[i]](value)
dict[cols[i]] = value
try:
protein = Protein(**dict)
protein.save()
rows += 1
except Exception, e:
print "Invalid Protein, name: ", r[0]
raise
def main(path):
"""
Read in the Library and LibraryMapping sheets
"""
libraries = readLibraries(path, 'Library')
labels = {
'Facility': 'facility_id',
'Salt': 'sm_salt',
'Batch': 'facility_batch_id',
'Plate': 'plate',
'Well': 'well',
'Library Name': 'short_name',
'Concentration': 'concentration',
'Concentration Unit': 'concentration_unit'
}
small_molecule_lookup = ('facility_id', 'sm_salt', 'facility_batch_id')
sheet = iu.readtable([path, 'LibraryMapping'])
#dict to map spreadsheet fields to terms
cols = {}
# first put the label row in (it contains the worksheet column, and its unique)
for i, label in enumerate(sheet.labels):
if label in labels:
cols[labels[label]] = i
else:
print 'Note: column label not found:', label
rows = 0
for row in sheet:
r = util.make_row(row)
# small molecule
dict = {}
for field in small_molecule_lookup:
dict[field] = util.convertdata(r[cols[field]], int)
try:
dict['facility_id'] = 'HMSL' + str(
dict['facility_id']
) # TODO: convert all hmsl id's to integers!!
sm = SmallMolecule.objects.get(**dict)
except Exception, e:
print "Invalid small molecule identifiers: ", dict
raise
short_name = r[cols['short_name']]
if short_name not in libraries:
print "Library not found: ", short_name
raise
lm = {}
lm['concentration'] = util.convertdata(r[cols['concentration']], float)
lm['concentration_unit'] = util.convertdata(
r[cols['concentration_unit']], None)
lm['plate'] = util.convertdata(r[cols['plate']], int)
lm['well'] = r[cols['well']]
lm['small_molecule'] = sm
lm['library'] = libraries[short_name]
lm = LibraryMapping(**lm)
lm.save()
rows += 1
def readLibraries(path, sheetName):
sheet = iu.readtable([path, sheetName]) # Note, skipping the header row by default
# dict to map spreadsheet fields to the Library fields
properties = ('model_field','required','default','converter')
date_parser = lambda x : util.convertdata(x,date)
column_definitions = {'Name': ('name',True), # TODO use the model to determine if req'd
'ShortName': ('short_name',True),
'Library Type':'type',
'Date First Plated': ('date_first_plated',False,None,date_parser),
'Date Data Received':('date_data_received',False,None,date_parser),
'Date Loaded': ('date_loaded',False,None,date_parser),
'Date Publicly Available': ('date_publicly_available',False,None,date_parser),
'Most Recent Update': ('date_updated',False,None,util.date_converter),
'Is Restricted':('is_restricted',False,False) }
# 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
libraries = {}
for row in sheet:
logger.debug(str(('row raw: ',row)))
r = util.make_row(row)
logger.debug(str(('row: ',r)))
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:
library = Library(**initializer)
library.save()
logger.info(str(('library created', library)))
libraries[library.short_name] = library
rows += 1
except Exception, e:
logger.error(str(('library initializer problem: ', initializer)))
raise e
def main(path):
"""
Read in the Protein
"""
sheet_name = 'HMS-LINCS Kinases'
labels = { 'PP_Name':'name',
'PP_LINCS_ID':'lincs_id',
'PP_UniProt_ID':'uniprot_id',
'PP_Alternate_Name':'alternate_name',
'PP_Provider':'provider',
'PP_Provider_Catalog_ID':'provider_catalog_id',
'PP_Batch_ID':'batch_id',
'PP_Amino_Acid_Sequence':'amino_acid_sequence',
'PP_Gene_Symbol':'gene_symbol',
'PP_Gene_ID':'gene_id',
'PP_Protein_Source':'protein_source',
'PP_Protein_Form':'protein_form',
'PP_Protein_Purity':'protein_purity',
'PP_Protein_Complex':'protein_complex',
'PP_Isoform':'isoform',
'PP_Protein_Type':'protein_type',
'PP_Source_Organism':'source_organism',
'PP_Reference':'reference'}
converters = { 'lincs_id': lambda x: x[x.index('HMSL')+4:] }
sheet = iu.readtable([path, sheet_name, 1]) # Note, skipping the header row by default
cols = {}
# first put the label row in (it contains the worksheet column, and its unique)
print 'labels: ', sheet.labels
for i,label in enumerate(sheet.labels):
if label in labels:
cols[i] = labels[label]
else:
print 'Note: column label not found:', label
#raise
rows = 0
i = 0
print 'cols: ' , cols
proteins = {}
for row in sheet:
r = util.make_row(row)
dict = {}
for i,value in enumerate(r):
if i not in cols: continue
if cols[i] in converters:
value = converters[cols[i]](value)
dict[cols[i]]= value
try:
protein = Protein(**dict)
protein.save()
rows += 1
except Exception, e:
print "Invalid Protein, name: ", r[0]
raise
def main(path):
"""
Read in the Library and LibraryMapping sheets
"""
libraries = readLibraries(path,'Library')
labels = { 'Facility':'facility_id',
'Salt':'sm_salt',
'Batch':'facility_batch_id',
'Plate':'plate',
'Well':'well',
'Library Name':'short_name',
'Concentration': 'concentration',
'Concentration Unit':'concentration_unit'
}
small_molecule_lookup = ('facility_id', 'sm_salt', 'facility_batch_id')
sheet = iu.readtable([path, 'LibraryMapping'])
#dict to map spreadsheet fields to terms
cols = {}
# first put the label row in (it contains the worksheet column, and its unique)
for i,label in enumerate(sheet.labels):
if label in labels:
cols[labels[label]] = i
else:
print 'Note: column label not found:', label
rows = 0
for row in sheet:
r = util.make_row(row)
# small molecule
dict = {}
for field in small_molecule_lookup:
dict[field] = util.convertdata(r[cols[field]],int)
try:
dict['facility_id'] = 'HMSL' + str(dict['facility_id']) # TODO: convert all hmsl id's to integers!!
sm = SmallMolecule.objects.get(**dict)
except Exception, e:
print "Invalid small molecule identifiers: ", dict
raise
short_name = r[cols['short_name']]
if short_name not in libraries:
print "Library not found: ", short_name
raise
lm = {}
lm['concentration'] = util.convertdata(r[cols['concentration']],float)
lm['concentration_unit'] = util.convertdata(r[cols['concentration_unit']],None)
lm['plate'] = util.convertdata(r[cols['plate']], int)
lm['well'] = r[cols['well']]
lm['small_molecule'] = sm
lm['library'] = libraries[short_name]
lm = LibraryMapping(**lm)
lm.save()
rows += 1
def readLibraries(path, sheetName):
sheet = iu.readtable([path, sheetName
]) # Note, skipping the header row by default
# dict to map spreadsheet fields to the Library fields
labels = {
'Name': 'name',
'ShortName': 'short_name',
'Date First Plated': 'date_first_plated',
'Date Data Received': 'date_data_received',
'Date Loaded': 'date_loaded',
'Date Publicly Available': 'date_publicly_available'
}
date_parser = lambda x: util.convertdata(x, date)
converters = {
'date_first_plated': date_parser,
'date_loaded': date_parser,
'date_data_recieved': date_parser,
'date_publicly_available': date_parser
}
cols = {}
# first put the label row in (it contains the worksheet column, and its unique)
for i, label in enumerate(sheet.labels):
if label in labels:
cols[i] = labels[label]
else:
print 'Note: column label not found:', label
raise
rows = 0
i = 0
libraries = {}
for row in sheet:
r = util.make_row(row)
dict = {}
for i, value in enumerate(r):
if cols[i] in converters:
value = converters[cols[i]](value)
dict[cols[i]] = value
try:
print 'create library:', dict
library = Library(**dict)
library.save()
libraries[library.short_name] = library
rows += 1
except Exception, e:
print "Invalid Library, name: ", r[0]
raise
def readLibraries(path, sheetName):
sheet = iu.readtable([path, sheetName]) # Note, skipping the header row by default
# dict to map spreadsheet fields to the Library fields
labels = { 'Name': 'name',
'ShortName': 'short_name',
'Date First Plated': 'date_first_plated',
'Date Data Received':'date_data_received',
'Date Loaded': 'date_loaded',
'Date Publicly Available': 'date_publicly_available' }
date_parser = lambda x : util.convertdata(x,date)
converters = {'date_first_plated': date_parser,
'date_loaded': date_parser,
'date_data_recieved': date_parser,
'date_publicly_available': date_parser }
cols = {}
# first put the label row in (it contains the worksheet column, and its unique)
for i,label in enumerate(sheet.labels):
if label in labels:
cols[i] = labels[label]
else:
print 'Note: column label not found:', label
raise
rows = 0
i = 0
libraries = {}
for row in sheet:
r = util.make_row(row)
dict = {}
for i,value in enumerate(r):
if cols[i] in converters:
value = converters[cols[i]](value)
dict[cols[i]]= value
try:
print 'create library:', dict
library = Library(**dict)
library.save()
libraries[library.short_name] = library
rows += 1
except Exception, e:
print "Invalid Library, name: ", r[0]
raise
def readDataColumns(path):
# Read in the DataColumn Sheet
sheetname = 'Data Columns'
dataColumnSheet = iu.readtable([path, sheetname])
_fields = util.get_fields(DataColumn)
_typelookup = dict((f.name, iu.totype(f)) for f in _fields)
# TODO: Use the import_utils methods here
# TODO: compare and combine this with the fieldinformation entity
labels = {'Worksheet Column':'worksheet_column',
'Display Order':'display_order',
'Name':'name',
'Data Type':'data_type',
'Decimal Places':'precision',
'Description':'description',
'Replicate Number':'replicate',
'Time point':'time_point',
'Assay readout type':'readout_type',
'Comments':'comments'}
# create an array of dict's, each dict defines a DataColumn
dataColumnDefinitions = []
# first put the label row in (it contains the worksheet column, and its unique)
for v in dataColumnSheet.labels[1:]:
dataColumnDefinitions.append({labels['Worksheet Column']:v})
# now, for each row, create the appropriate dictionary entry in the dataColumnDefinitions
for row in dataColumnSheet:
rowAsUnicode = util.make_row(row)
keyRead = rowAsUnicode[0]
for i,cellText in enumerate(rowAsUnicode[1:]):
for key,fieldName in labels.items():
if re.match(key,keyRead,re.M|re.I): # if the row is one of the DataColumn fields, then add it to the dict
dataColumnDefinitions[i][fieldName] = util.convertdata(cellText,_typelookup.get(fieldName, None)) # Note: convert the data to the model field type
else:
logger.debug(str(( '"Data Column definition not used: ', cellText)) )
pass
logger.debug(str(("definitions: ", dataColumnDefinitions)) )
return dataColumnDefinitions
def readDataColumns(path):
# Read in the DataColumn Sheet
sheetname = 'Data Columns'
dataColumnSheet = iu.readtable([path, sheetname])
_fields = util.get_fields(DataColumn)
_typelookup = dict((f.name, iu.totype(f)) for f in _fields)
labels = {'Worksheet Column':'worksheet_column',
'Name':'name',
'Data Type':'data_type',
'Decimal Places':'precision',
'Description':'description',
'Replicate Number':'replicate',
'Time point':'time_point',
'Assay readout type':'readout_type',
'Comments':'comments'}
# create an array of dict's, each dict defines a DataColumn
dataColumnDefinitions = []
# first put the label row in (it contains the worksheet column, and its unique)
for v in dataColumnSheet.labels[1:]:
dataColumnDefinitions.append({labels['Worksheet Column']:v})
# now, for each row, create the appropriate dictionary entry in the dataColumnDefinitions
for row in dataColumnSheet:
rowAsUnicode = util.make_row(row)
keyRead = rowAsUnicode[0]
for i,cellText in enumerate(rowAsUnicode[1:]):
for key,fieldName in labels.items():
if re.match(key,keyRead,re.M|re.I): # if the row is one of the DataColumn fields, then add it to the dict
dataColumnDefinitions[i][fieldName] = util.convertdata(cellText,_typelookup.get(fieldName, None)) # Note: convert the data to the model field type
else:
pass
# print '"Data Column definition not used: ', cellText
print "definitions: ", dataColumnDefinitions
return dataColumnDefinitions
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 Antibody
"""
sheet_name = 'Sheet1'
sheet = iu.readtable([path, sheet_name, 1]) # Note, skipping the header row by default
properties = ('model_field','required','default','converter')
column_definitions = {
'AR_Name': ('name',True),
'AR_LINCS_ID': 'lincs_id',
'AR_Alternative_Name': 'alternative_names',
'AR_Center_ID': ('facility_id', True),
'AR_Target_Protein': 'target_protein_name',
'AR_Target_Protein_ID': 'target_protein_uniprot_id',
'AR_Target_Gene': 'target_gene_name',
'AR_Target_Gene_ID': 'target_gene_id',
'AR_Target_Organism': 'target_organism',
'AR_Immunogen': 'immunogen',
'AR_Immunogen_Sequence': 'immunogen_sequence',
'AR_AntibodyClonality': 'antibody_clonality',
'AR_Source_Organism': 'source_organism',
'AR_Antibody_Isotype': 'antibody_isotype',
'AR_Engineering': 'engineering',
'AR_Antibody_Purity': 'antibody_purity',
'AR_Antibody_Labeling': 'antibody_labeling',
'AR_Recommended_Experiment_Type': 'recommended_experiment_type',
'AR_Relevant_Reference': 'relevant_reference',
'AR_Specificity': 'specificity',
'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)}
# 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)
dict = {}
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)))
antibody = Antibody(**initializer)
antibody.save()
logger.info(str(('antibody created: ', antibody)))
rows += 1
except Exception, e:
logger.error(str(( "Invalid antibody initializer: ", initializer)))
raise
def read_metadata(path):
"""
Read in the DataSets, Datacolumns, and Data sheets. In the Data sheet, rows
are DataRecords, and columns are DataPoints
"""
# Read in the DataSet
sheetname = 'Meta'
# Note, skipping the header row by default
metaSheet = iu.readtable([path, sheetname])
# Define the Column Names -> model fields mapping
properties = ('model_field','required','default','converter')
field_definitions = {'Lead Screener First': 'lead_screener_firstname',
'Lead Screener Last': 'lead_screener_lastname',
'Lead Screener Email': 'lead_screener_email',
'Lab Head First': 'lab_head_firstname',
'Lab Head Last': 'lab_head_lastname',
'Lab Head Email': 'lab_head_email',
'Title': 'title',
'Facility ID': ('facility_id',True,None,
lambda x: util.convertdata(x,int)),
'Summary': 'summary',
'Protocol': 'protocol',
'References': 'protocol_references',
'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),
'Dataset Type':('dataset_type',False),
'Bioassay':('bioassay',False),
'Dataset Keywords':('dataset_keywords',False),
'Usage Message':('usage_message',False),
}
sheet_labels = []
for row in metaSheet:
rowAsUnicode = util.make_row(row)
sheet_labels.append(rowAsUnicode[0])
# convert the definitions to fleshed out dict's, with strategies for
# optional, default and converter
field_definitions = \
util.fill_in_column_definitions(properties,field_definitions)
# create a dict mapping the column/row ordinal to the proper definition dict
cols = util.find_columns(field_definitions, sheet_labels,
all_column_definitions_required=False)
initializer = {}
for i,row in enumerate(metaSheet):
rowAsUnicode = util.make_row(row)
properties = cols[i]
value = rowAsUnicode[1]
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'],row))
logger.debug(str(('model_field: ' , model_field, ', value: ', value)))
initializer[model_field] = value
return initializer
def main(path):
"""
Read in the smallmolecule batch info
"""
sheet_name = 'sheet 1'
start_row = 1
sheet = iu.readtable([path, sheet_name, start_row
]) # Note, skipping the header row by default
properties = ('model_field', 'required', 'default', 'converter')
column_definitions = {
# NOTE: even though these db field are not integers,
# it is convenient to convert the read in values to INT to make sure they are not interpreted as float values
'facility_id':
('facility_id', True, None, lambda x: util.convertdata(x, int)),
'salt_id': ('salt_id', True, None, lambda x: util.convertdata(x, int)),
'facility_batch_id':
('batch_id', True, None, lambda x: util.convertdata(x, int)),
'provider': ('provider_name', True),
'provider_catalog_id':
'provider_catalog_id',
'provider_sample_id':
'provider_batch_id',
'chemical_synthesis_reference':
'chemical_synthesis_reference',
'purity':
'purity',
'purity_method':
'purity_method',
'aqueous_solubility':
'aqueous_solubility',
# FIXME: should warn the user if no unit is provided when
# aqueous_solubility is provided
'aqueous_solubility_unit':
'aqueous_solubility_unit',
'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),
}
# 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 = {}
small_molecule_lookup = {'facility_id': None, 'salt_id': None}
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)))
if (model_field in small_molecule_lookup):
small_molecule_lookup[model_field] = value
if (None not in small_molecule_lookup.values()):
try:
sm = SmallMolecule.objects.get(**small_molecule_lookup)
initializer['reagent'] = sm
except Exception, e:
logger.error(
str(('sm identifiers not found',
small_molecule_lookup, 'row',
rows + start_row + 2)))
raise
else:
initializer[model_field] = value
try:
logger.debug(str(('initializer: ', initializer)))
smb = SmallMoleculeBatch(**initializer)
smb.save()
logger.debug(str(('smb created:', smb)))
rows += 1
except Exception, e:
logger.error(
str(("Invalid smallmolecule batch initializer: ", initializer,
'row', rows + start_row + 2, e)))
raise
def main(path):
"""
Read in the Protein
"""
sheet_name = 'HMS-LINCS Kinases'
# Note, skipping the header row by default
sheet = iu.readtable([path, sheet_name, 1])
properties = ('model_field','required','default','converter')
column_definitions = {
'PP_Name':('name',True),
'PP_LINCS_ID':('facility_id',True,None,lambda x: x[x.index('HMSL')+4:]),
'PP_UniProt_ID':'uniprot_id',
'PP_Alternate_Name':'alternative_names',
'PP_Alternate_Name[2]':'alternate_name_2',
'PP_Provider':'provider',
'PP_Provider_Catalog_ID':'provider_catalog_id',
'PP_Batch_ID':'batch_id',
'PP_Amino_Acid_Sequence':'amino_acid_sequence',
'PP_Gene_Symbol':'gene_symbol',
'PP_Gene_ID':'gene_id',
'PP_Protein_Source':'protein_source',
'PP_Protein_Form':'protein_form',
'PP_Mutation':'mutation',
'PP_Phosphorylation_State':'phosphlorylation',
'PP_Domain':'protein_domain',
'PP_Protein_Purity':'protein_purity',
'PP_Protein_Complex':'protein_complex',
'PP_Isoform':'isoform',
'PP_Protein_Type':'protein_type',
'PP_Source_Organism':'source_organism',
'PP_Reference':'reference',
'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)}
# 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
cols = util.find_columns(column_definitions, sheet.labels)
rows = 0
logger.debug(str(('cols: ' , cols)))
for row in sheet:
r = util.make_row(row)
dict = {}
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)))
protein = Protein(**initializer)
# FIXME: LINCS IDS for Protein
protein.lincs_id = protein.facility_id
protein.save()
logger.info(str(('protein created: ', protein)))
rows += 1
# create a default batch - 0
ProteinBatch.objects.create(reagent=protein,batch_id=0)
except Exception, e:
logger.error(str(("Invalid protein initializer: ", initializer, e)))
raise
def main(path):
"""
Read in the Library and LibraryMapping sheets
"""
libraries = readLibraries(path,'Library')
sheet = iu.readtable([path, 'LibraryMapping'])
properties = ('model_field','required','default','converter')
column_definitions = {'Facility':('facility_id',False,None, lambda x: util.convertdata(x,int)),
'Salt':('salt_id',False,None, lambda x: util.convertdata(x,int)),
'Batch':('facility_batch_id',False,None, lambda x: util.convertdata(x,int)),
'Is Control':('is_control',False,False,util.bool_converter),
'Plate':('plate',False,None, lambda x: util.convertdata(x,int)),
'Well':'well',
'Library Name':'short_name',
'Concentration': 'concentration',
'Concentration Unit':'concentration_unit'
}
# 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)
small_molecule_batch_lookup = ('smallmolecule', 'facility_batch_id')
library_mapping_lookup = ('smallmolecule_batch','library','is_control','plate','well','concentration','concentration_unit')
rows = 0
logger.debug(str(('cols: ' , cols)))
for row in sheet:
current_row = rows + 2
r = util.make_row(row)
initializer = {}
small_molecule_lookup = {'facility_id':None, 'salt_id':None}
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'],'row',current_row))
logger.debug(str(('model_field: ' , model_field, ', value: ', value)))
initializer[model_field] = value
if(model_field in small_molecule_lookup):
small_molecule_lookup[model_field]=value
if( None not in small_molecule_lookup.values()):
try:
sm = SmallMolecule.objects.get(**small_molecule_lookup)
initializer['smallmolecule'] = sm
except Exception, e:
raise Exception(str(('sm facility id not found', small_molecule_lookup,e,'row',current_row)))
elif(model_field == 'short_name'):
try:
library = libraries[value]
initializer['library'] = library
except Exception, e:
raise Exception(str(('library short_name not found', value,e,'row',current_row)))
def main(path):
"""
Read in the primary cell batch info
"""
sheet_name = "Sheet1"
start_row = 1
sheet = iu.readtable([path, sheet_name, start_row]) # 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 :]),
"PC_Center_Batch_ID": ("batch_id", True, None, lambda x: util.convertdata(x, int)),
"PC_Center_Specific_Code": "center_specific_code",
"PC_Provider_Name": "provider_name",
"PC_Provider_Catalog_ID": "provider_catalog_id",
"PC_Provider_Batch_ID": "provider_batch_id",
"PC_Source_Information": "source_information",
"PC_Date_Received": "date_received",
"PC_Quality_Verification": "quality_verification",
"PC_Culture_Conditions": "culture_conditions",
"PC_Passage_Number": ("passage_number", False, None, lambda x: util.convertdata(x, int)),
"PC_Transient_Modification": "transient_modification",
"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),
}
column_definitions = util.fill_in_column_definitions(properties, column_definitions)
cols = util.find_columns(column_definitions, sheet.labels)
rows = 0
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"]
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))
if model_field == "facility_id":
try:
cell = PrimaryCell.objects.get(facility_id=value)
initializer["reagent"] = cell
except:
logger.exception("Primary Cell not found: %r, row: %d", value, rows + start_row + 1)
raise
else:
initializer[model_field] = value
try:
logger.debug("initializer: %r", initializer)
cell = PrimaryCellBatch(**initializer)
cell.save()
logger.debug("primary cell batch created: %r", cell)
rows += 1
except Exception, e:
logger.exception("Invalid Primary CellBatch initializer: %r, row: %d", initializer, rows + start_row + 1)
raise
def main(path):
"""
Read in the smallmolecule batch info
"""
sheet_name = "sheet 1"
start_row = 1
sheet = iu.readtable([path, sheet_name, start_row]) # Note, skipping the header row by default
properties = ("model_field", "required", "default", "converter")
column_definitions = {
# NOTE: even though these db field are not integers,
# it is convenient to convert the read in values to INT to make sure they are not interpreted as float values
"facility_id": ("facility_id", True, None, lambda x: util.convertdata(x, int)),
"salt_id": ("salt_id", True, None, lambda x: util.convertdata(x, int)),
"facility_batch_id": ("facility_batch_id", True, None, lambda x: util.convertdata(x, int)),
"provider": ("provider", True),
"provider_catalog_id": "provider_catalog_id",
"provider_sample_id": "provider_sample_id",
"chemical_synthesis_reference": "chemical_synthesis_reference",
"purity": "purity",
"purity_method": "purity_method",
"aqueous_solubility": "aqueous_solubility",
"aqueous_solubility_unit": "aqueous_solubility_unit",
"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),
}
# 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 = {}
small_molecule_lookup = {"facility_id": None, "salt_id": None}
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)))
if model_field in small_molecule_lookup:
small_molecule_lookup[model_field] = value
if None not in small_molecule_lookup.values():
try:
sm = SmallMolecule.objects.get(**small_molecule_lookup)
initializer["smallmolecule"] = sm
except Exception, e:
logger.error(
str(("sm identifiers not found", small_molecule_lookup, "row", rows + start_row + 2))
)
raise
else:
initializer[model_field] = value
try:
logger.debug(str(("initializer: ", initializer)))
smb = SmallMoleculeBatch(**initializer)
smb.save()
logger.debug(str(("smb created:", smb)))
rows += 1
except Exception, e:
logger.error(
str(("Invalid smallmolecule batch initializer: ", initializer, "row", rows + start_row + 2, e))
)
raise
def main(path):
sheet_name = 'sheet 1'
start_row = 1
sheet = iu.readtable([path, sheet_name, start_row])
properties = ('model_field','required','default','converter')
column_definitions = {
'facility_id': (
'facility_id',True,None, lambda x: util.convertdata(x,int)),
'salt_id': (
'salt_id',True,None, lambda x: util.convertdata(x,int)),
'facility_batch_id':(
'batch_id',True,None, lambda x: util.convertdata(x,int)),
'provider': ('provider_name',False),
'provider_catalog_id':'provider_catalog_id',
'provider_sample_id':'provider_batch_id',
'molecular_weight':(
'_molecular_weight',False,None,
lambda x: util.convertdata(x, float)),
'molecular_formula':'_molecular_formula',
'chemical_synthesis_reference':'_chemical_synthesis_reference',
'purity':'_purity',
'purity_method':'_purity_method',
'aqueous_solubility':'aqueous_solubility',
# FIXME: should warn the user if no unit is provided when
# aqueous_solubility is provided
'aqueous_solubility_unit':'aqueous_solubility_unit',
'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),
}
column_definitions = util.fill_in_column_definitions(
properties,column_definitions)
cols = util.find_columns(column_definitions, sheet.labels,
all_sheet_columns_required=False)
rows = 0
for row in sheet:
r = util.make_row(row)
initializer = {}
small_molecule_lookup = {'facility_id':None, 'salt_id':None}
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']
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))
if(model_field in small_molecule_lookup):
small_molecule_lookup[model_field]=value
if( None not in small_molecule_lookup.values()):
try:
sm = SmallMolecule.objects.get(**small_molecule_lookup)
initializer['reagent'] = sm
except Exception, e:
logger.exception(
'sm identifiers not found: %r, row: %d',
small_molecule_lookup,rows+start_row+2)
raise
else:
initializer[model_field] = value
try:
logger.debug(str(('initializer: ', initializer)))
smb = SmallMoleculeBatch(**initializer)
smb.save()
logger.debug(str(('smb created:', smb)))
rows += 1
except Exception, e:
logger.exception(
'Invalid smallmolecule batch initializer: %r, row: %d',
initializer, rows+start_row+2)
raise
def main(path):
"""
Read in the Library and LibraryMapping sheets
"""
libraries = readLibraries(path, 'Library')
sheet = iu.readtable([path, 'LibraryMapping'])
properties = ('model_field', 'required', 'default', 'converter')
date_parser = lambda x: util.convertdata(x, date)
column_definitions = {
'Facility':
('facility_id', False, None, lambda x: util.convertdata(x, int)),
'Salt': ('salt_id', False, None, lambda x: util.convertdata(x, int)),
'Batch': ('batch_id', False, None, lambda x: util.convertdata(x, int)),
'Is Control': ('is_control', False, False, util.bool_converter),
'Plate': ('plate', False, None, lambda x: util.convertdata(x, int)),
'Well':
'well',
'Library Name':
'short_name',
'Concentration':
'concentration',
'Concentration Unit':
'concentration_unit'
}
# 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)
small_molecule_batch_lookup = ('reagent', 'batch_id')
library_mapping_lookup = ('smallmolecule_batch', 'library', 'is_control',
'plate', 'well', 'concentration',
'concentration_unit')
rows = 0
logger.debug(str(('cols: ', cols)))
for row in sheet:
current_row = rows + 2
r = util.make_row(row)
initializer = {}
small_molecule_lookup = {'facility_id': None, 'salt_id': None}
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'], 'row', current_row))
logger.debug(
str(('model_field: ', model_field, ', value: ', value)))
initializer[model_field] = value
if (model_field in small_molecule_lookup):
small_molecule_lookup[model_field] = value
if (None not in small_molecule_lookup.values()):
try:
sm = SmallMolecule.objects.get(**small_molecule_lookup)
initializer['reagent'] = sm
except Exception, e:
raise Exception(
str(('sm facility id not found',
small_molecule_lookup, e, 'row',
current_row)))
elif (model_field == 'short_name'):
try:
library = libraries[value]
initializer['library'] = library
except Exception, e:
raise Exception(
str(('library short_name not found', value, e, 'row',
current_row)))
def readLibraries(path, sheetName):
sheet = iu.readtable([path, sheetName
]) # Note, skipping the header row by default
# dict to map spreadsheet fields to the Library fields
properties = ('model_field', 'required', 'default', 'converter')
date_parser = lambda x: util.convertdata(x, date)
column_definitions = {
'Name': ('name', True), # TODO use the model to determine if req'd
'ShortName': ('short_name', True),
'Library Type':
'type',
'Date First Plated': ('date_first_plated', False, None, date_parser),
'Date Data Received': ('date_data_received', False, None, date_parser),
'Date Loaded': ('date_loaded', False, None, date_parser),
'Date Publicly Available':
('date_publicly_available', False, None, date_parser),
'Most Recent Update':
('date_updated', False, None, util.date_converter),
'Is Restricted': ('is_restricted', False, False)
}
# 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
libraries = {}
for row in sheet:
logger.debug(str(('row raw: ', row)))
r = util.make_row(row)
logger.debug(str(('row: ', r)))
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:
library = Library(**initializer)
library.save()
logger.info(str(('library created', library)))
libraries[library.short_name] = library
rows += 1
except Exception, e:
logger.error(str(('library initializer problem: ', initializer)))
raise e
def main(path):
"""
Read in the Antibody Batches
"""
sheet_name = 'Sheet1'
sheet = iu.readtable([path, sheet_name, 1])
properties = ('model_field','required','default','converter')
column_definitions = {
'AR_Center_Specific_ID': ('antibody_facility_id',True,None, lambda x: x[x.index('HMSL')+4:]),
'AR_Center_Batch_ID': ('batch_id',True,None,lambda x:util.convertdata(x,int)),
'AR_Center_Name': 'center_name',
'AR_Provider_Name': 'provider_name',
'AR_Provider_Catalog_ ID': 'provider_catalog_id',
'AR_Provider_Batch_ID': 'provider_batch_id',
'AR_Antibody_Purity': 'antibody_purity',
'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),
}
# 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('cols: %s' % cols)
for row in sheet:
r = util.make_row(row)
dict = {}
initializer = {}
for i,value in enumerate(r):
if i not in cols: continue
properties = cols[i]
logger.debug('read col: %d: %s' % (i,properties))
required = properties['required']
default = properties['default']
converter = properties['converter']
model_field = properties['model_field']
logger.debug('raw value %r' % 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('model_field: %s, converted value %r'
% (model_field, value) )
initializer[model_field] = value
try:
logger.debug('initializer: %s' % initializer)
antibody_facility_id = initializer.pop('antibody_facility_id',None)
if antibody_facility_id:
try:
antibody = Antibody.objects.get(facility_id=antibody_facility_id)
initializer['reagent'] = antibody
except ObjectDoesNotExist, e:
logger.error('AR_Center_Specific_ID: "%s" does not exist, row: %d'
% (antibody_facility_id,i))
antibody_batch = AntibodyBatch(**initializer)
antibody_batch.save()
logger.info('antibody batch created: %s' % antibody_batch)
rows += 1
except Exception, e:
logger.error("Invalid antibody_batch initializer: %s" % initializer)
raise
def main(path):
sheet_name = 'Sheet1'
sheet = iu.readtable([path, sheet_name, 1])
properties = ('model_field','required','default','converter')
column_definitions = {
'AR_Name': ('name',True),
'AR_LINCS_ID': 'lincs_id',
'AR_Alternative_Name': 'alternative_names',
'AR_Alternative_ID': 'alternative_id',
'AR_Center_Canonical_ID': (
'facility_id',True,None, lambda x: x[x.index('HMSL')+4:]),
'AR_Clone_Name': 'clone_name',
'AR_RRID': 'rrid',
'AR_Antibody_Type': 'type',
'target_protein_center_ids': 'target_protein_center_ids',
'AR_Non-Protein_Target': 'non_protein_target_name',
'AR_Target_Organism': 'target_organism',
'other_target_information': 'other_target_information',
'other_human_target_protein_center_ids':
'other_human_target_protein_center_ids',
'AR_Immunogen': 'immunogen',
'AR_Immunogen_Sequence': 'immunogen_sequence',
'AR_Antibody_Species': 'species',
'AR_Antibody_Clonality': 'clonality',
'AR_Antibody_Isotype': 'isotype',
'AR_Antibody_Production_Source_Organism': 'source_organism',
'AR_Antibody_Production_Details': 'production_details',
'AR_Antibody_Labeling': 'labeling',
'AR_Antibody_Labeling_Details': 'labeling_details',
'AR_Relevant_Citations': 'relevant_citations',
'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)}
column_definitions = util.fill_in_column_definitions(properties,column_definitions)
cols = util.find_columns(column_definitions, sheet.labels,
all_sheet_columns_required=False)
rows = 0
logger.debug('cols: %s' % cols)
for row in sheet:
logger.debug('row %s - %s' %(rows,row))
r = util.make_row(row)
dict = {}
initializer = {}
for i,value in enumerate(r):
if i not in cols: continue
properties = cols[i]
logger.debug('read col: %d: %s' % (i,properties))
required = properties['required']
default = properties['default']
converter = properties['converter']
model_field = properties['model_field']
logger.debug('raw value %r' % value)
if(value == None or value == 'None'):
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))
if(value and converter != None):
value = converter(value)
logger.debug('model_field: %s, converted value %r'
% (model_field, value) )
initializer[model_field] = value
try:
logger.debug('row: %s, initializer: %s' % (rows,initializer))
target_protein_center_ids = initializer.pop(
'target_protein_center_ids',None)
other_human_target_protein_center_ids = initializer.pop(
'other_human_target_protein_center_ids',None)
antibody = Antibody.objects.create(**initializer)
if target_protein_center_ids:
ids = [x for x in target_protein_center_ids.split(';')]
try:
target_proteins = []
for id in ids:
id = id[id.index('HMSL')+4:]
target_proteins.append(
Protein.objects.get(facility_id=id))
antibody.target_proteins = target_proteins
except ObjectDoesNotExist, e:
logger.error(
'target_protein_center_ids "%s" does not exist, row: %d'
% (id,i))
raise
if other_human_target_protein_center_ids:
ids = [x for x in
other_human_target_protein_center_ids.split(';')]
try:
other_target_proteins = []
for id in ids:
id = id[id.index('HMSL')+4:]
other_target_proteins.append(
Protein.objects.get(facility_id=id))
antibody.other_human_target_proteins = other_target_proteins
except ObjectDoesNotExist, e:
logger.error(
'other_human_target_protein_center_ids "%s"'
' does not exist, row: %d'
% (id,i))
raise
antibody.save()
logger.info('antibody created: %s' % antibody)
rows += 1
# create a default batch - 0
AntibodyBatch.objects.create(reagent=antibody,batch_id=0)
def main(import_file,file_directory,deploy_dir):
"""
Read in the qc events for batches
- version 1 - for small molecule batches
"""
sheet_name = 'Sheet1'
start_row = 0
sheet = iu.readtable([import_file, sheet_name, start_row]) # Note, skipping the header row by default
properties = ('model_field','required','default','converter')
column_definitions = {
'facility_id': ('facility_id_for',True,None, lambda x: util.convertdata(x,int)),
'salt_id': ('salt_id_for',False,None, lambda x: util.convertdata(x,int)),
'batch_id':('batch_id_for',True,None, lambda x: util.convertdata(x,int)),
'QC event date': ('date',True,None,util.date_converter),
'outcome': ('outcome',True),
'comment': 'comment',
'is_restricted':('is_restricted',False,False,util.bool_converter),
'file1': 'file1',
'file2': 'file2',
'file3': 'file3',
'file4': 'file4',
'file5': 'file5',
}
# 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)
# store each row in a dict
_dict = {}
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']
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)))
_dict[model_field] = value
logger.debug(str(('dict: ', _dict)))
files_to_attach = []
for i in range(10):
filenameProp = 'file%s'%i;
if _dict.get(filenameProp, None):
fileprop = _dict[filenameProp]
filepath = os.path.join(file_directory,fileprop)
if not os.path.exists(filepath):
raise Exception(str(('file does not exist:',filepath,'row',
rows+start_row)))
filename = os.path.basename(filepath)
relative_path = fileprop[:fileprop.index(filename)]
# Move the file
dest_dir = deploy_dir
if not dest_dir:
dest_dir = settings.STATIC_AUTHENTICATED_FILE_DIR
if not os.path.isdir(dest_dir):
raise Exception(str(('no such deploy directory, please create it', dest_dir)))
if relative_path:
dest_dir = os.path.join(dest_dir, relative_path)
if not os.path.exists(dest_dir):
os.makedirs(dest_dir)
deployed_path = os.path.join(dest_dir, filename)
logger.debug(str(('deploy',filepath, deployed_path)))
if os.path.exists(deployed_path):
os.remove(deployed_path)
copy(filepath,deployed_path)
if not os.path.isfile (deployed_path):
raise Exception(str(('could not deploy to', deployed_path)))
else:
logger.debug(str(('successfully deployed to', deployed_path)))
files_to_attach.append((filename,relative_path))
initializer = None
try:
# create the qc record
initializer = {key:_dict[key] for key in
['facility_id_for','salt_id_for','batch_id_for','outcome','comment','date']}
qc_event = QCEvent(**initializer)
qc_event.save()
logger.debug(str(('saved', qc_event)))
# create attached file records
for (filename,relative_path) in files_to_attach:
initializer = {
'qc_event':qc_event,
'filename':filename,
'relative_path':relative_path,
'is_restricted':_dict['is_restricted']
}
qc_attached_file = QCAttachedFile(**initializer)
qc_attached_file.save()
logger.debug(str(('created qc attached file', qc_attached_file)))
rows += 1
except Exception, e:
logger.error(str(("Invalid initializer: ", initializer, 'row',
rows+start_row+2, e)))
raise
def main(path):
"""
Read in the Antibody
"""
sheet_name = 'Sheet1'
sheet = iu.readtable([path, sheet_name, 0])
properties = ('model_field','required','default','converter')
column_definitions = {
'AR_Name': ('name',True),
'AR_LINCS_ID': 'lincs_id',
'AR_Alternative_Name': 'alternative_names',
'AR_Center_Specific_ID': ('facility_id',True,None, lambda x: x[x.index('HMSL')+4:]),
'AR_Clone_Name': 'clone_name',
'AR_RRID': 'rrid',
'AR_Antibody_Type': 'type',
'target_protein_lincs_id': (
'target_protein_lincs_id',False,None,
lambda x: x[x.index('HMSL')+4:] if x else None ),
'AR_Non-Protein_Target': 'non_protein_target_name',
'AR_Target_Organism': 'target_organism',
'AR_Immunogen': 'immunogen',
'AR_Immunogen_Sequence': 'immunogen_sequence',
'AR_Antibody_Species': 'species',
'AR_Antibody_Clonality': 'clonality',
'AR_Antibody_Isotype': 'isotype',
'AR_Antibody_Production_Source_Organism': 'source_organism',
'AR_Antibody_Production_Details': 'production_details',
'AR_Antibody_Labeling': 'labeling',
'AR_Antibody_Labeling_Details': 'labeling_details',
'AR_Relevant_Citations': 'relevant_citations',
'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('cols: %s' % cols)
for row in sheet:
logger.debug('row %s - %s' %(rows,row))
r = util.make_row(row)
dict = {}
initializer = {}
for i,value in enumerate(r):
if i not in cols: continue
properties = cols[i]
logger.debug('read col: %d: %s' % (i,properties))
required = properties['required']
default = properties['default']
converter = properties['converter']
model_field = properties['model_field']
logger.debug('raw value %r' % value)
if(value == None or value == 'None'):
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))
if(value and converter != None):
value = converter(value)
logger.debug('model_field: %s, converted value %r'
% (model_field, value) )
initializer[model_field] = value
try:
logger.debug('row: %s, initializer: %s' % (rows,initializer))
target_protein_lincs_id = initializer.pop('target_protein_lincs_id',None)
if target_protein_lincs_id:
try:
target_protein = Protein.objects.get(lincs_id=target_protein_lincs_id)
initializer['target_protein'] = target_protein
except ObjectDoesNotExist, e:
logger.error('target_protein_lincs_id "%s" does not exist, row: %d'
% (target_protein_lincs_id,i))
antibody = Antibody(**initializer)
antibody.save()
logger.info('antibody created: %s' % antibody)
rows += 1
# create a default batch - 0
AntibodyBatch.objects.create(reagent=antibody,batch_id=0)
except Exception, e:
logger.error("Invalid antibody initializer: %s" % initializer)
raise
def main(path):
"""
Read in the smallmolecule batch info
"""
sheet_name = 'sheet 1'
start_row = 1
sheet = iu.readtable([path, sheet_name, start_row]) # Note, skipping the header row by default
properties = ('model_field','required','default','converter')
column_definitions = {
# NOTE: even though these db field are not integers,
# it is convenient to convert the read in values to INT to make sure they are not interpreted as float values
'facility_id': ('facility_id',True,None, lambda x: util.convertdata(x,int)),
'salt_id': ('salt_id',True,None, lambda x: util.convertdata(x,int)),
'facility_batch_id':('batch_id',True,None, lambda x: util.convertdata(x,int)),
'provider': ('provider_name',True),
'provider_catalog_id':'provider_catalog_id',
'provider_sample_id':'provider_batch_id',
'chemical_synthesis_reference':'chemical_synthesis_reference',
'purity':'purity',
'purity_method':'purity_method',
'aqueous_solubility':'aqueous_solubility',
# FIXME: should warn the user if no unit is provided when
# aqueous_solubility is provided
'aqueous_solubility_unit':'aqueous_solubility_unit',
'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),
}
# 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 = {}
small_molecule_lookup = {'facility_id':None, 'salt_id':None}
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)))
if(model_field in small_molecule_lookup):
small_molecule_lookup[model_field]=value
if( None not in small_molecule_lookup.values()):
try:
sm = SmallMolecule.objects.get(**small_molecule_lookup)
initializer['reagent'] = sm
except Exception, e:
logger.error(str(('sm identifiers not found', small_molecule_lookup,'row',rows+start_row+2)))
raise
else:
initializer[model_field] = value
try:
logger.debug(str(('initializer: ', initializer)))
smb = SmallMoleculeBatch(**initializer)
smb.save()
logger.debug(str(('smb created:', smb)))
rows += 1
except Exception, e:
logger.error(str(( "Invalid smallmolecule batch initializer: ", initializer, 'row', rows+start_row+2, e)))
raise
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
# Now that the array of DataColumn dicts is created,
# use them to create the DataColumn instances.
dataColumns = {}
for i,dc in enumerate(dataColumnDefinitions):
dc['dataset'] = dataset
if(not 'display_order' in dc or dc['display_order']==None):
dc['display_order']=i
dataColumn = DataColumn(**dc)
dataColumn.save()
logger.debug(str(('====datacolumn created:', dataColumn)))
dataColumns[dataColumn.name] = dataColumn
logger.debug('read the Data sheet')
sheetname = 'Data'
dataSheet = iu.readtable([path, sheetname])
# First, map the sheet column indices to the DataColumns that were created.
dataColumnList = {}
# Follows are optional columns
# Meta columns contain forensic information, all are optional
metaColumnDict = {'Control Type':-1, 'batch_id':-1}
# What is being studied - at least one is required
mappingColumnDict = {
'Small Molecule Batch':-1, 'Plate':-1, 'Well':-1,
'Cell':-1, 'Protein':-1, 'Antibody': -1, 'OtherReagent': -1}
# NOTE: this scheme is matching based on the labels between the
# "Data Column" sheet and the "Data" sheet.
for i,label in enumerate(dataSheet.labels):
if(label == 'None' or label.strip()=='' or label == 'Exclude' ):
continue
def main(path):
"""
Read in the Protein
"""
sheet_name = "HMS-LINCS Kinases"
sheet = iu.readtable([path, sheet_name, 1]) # Note, skipping the header row by default
properties = ("model_field", "required", "default", "converter")
column_definitions = {
"PP_Name": ("name", True),
"PP_LINCS_ID": ("lincs_id", True, None, lambda x: x[x.index("HMSL") + 4 :]),
"PP_UniProt_ID": "uniprot_id",
"PP_Alternate_Name": "alternate_name",
"PP_Alternate_Name[2]": "alternate_name_2",
"PP_Provider": "provider",
"PP_Provider_Catalog_ID": "provider_catalog_id",
"PP_Batch_ID": "batch_id",
"PP_Amino_Acid_Sequence": "amino_acid_sequence",
"PP_Gene_Symbol": "gene_symbol",
"PP_Gene_ID": "gene_id",
"PP_Protein_Source": "protein_source",
"PP_Protein_Form": "protein_form",
"PP_Protein_Purity": "protein_purity",
"PP_Protein_Complex": "protein_complex",
"PP_Isoform": "isoform",
"PP_Protein_Type": "protein_type",
"PP_Source_Organism": "source_organism",
"PP_Reference": "reference",
"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),
"Is Restricted": ("is_restricted", False, False),
}
# 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)
dict = {}
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)))
protein = Protein(**initializer)
protein.save()
logger.info(str(("protein created: ", protein)))
rows += 1
except Exception, e:
logger.error(str(("Invalid protein initializer: ", initializer)))
raise
def main(path):
# read in the two columns of the meta sheet to a dict that defines a DataSet
metadata = read_metadata(path)
dataset = DataSet(**metadata)
dataset.save()
# read in the data columns sheet to an array of dict's, each dict defines a DataColumn
dataColumnDefinitions = readDataColumns(path)
# now that the array of DataColumn dicts is created, use them to create the DataColumn instances
dataColumns = {}
for dc in dataColumnDefinitions:
dc['dataset'] = dataset
dataColumn = DataColumn(**dc)
dataColumn.save()
dataColumns[dataColumn.name] = dataColumn
# read the Data sheet
sheetname = 'Data'
dataSheet = iu.readtable([path, sheetname])
# First, map the sheet column indices to the DataColumns that were created
dataColumnList = {}
metaColumnDict = {'Well':-1, 'Plate':-1, 'Control Type':-1} # meta columns contain forensic information
mappingColumnDict = {'Small Molecule':-1, 'Cell':-1, 'Protein':-1} # what is being studied - at least one is required
# NOTE: this scheme is matching based on the labels between the "Data Column" sheet and the "Data" sheet
for i,label in enumerate(dataSheet.labels):
if(label == 'None' or label == 'well_id' or label.strip()=='' or label == 'Exclude' ): continue
if label in metaColumnDict:
metaColumnDict[label] = i
continue
if label in mappingColumnDict:
mappingColumnDict[label] = i
continue
if label in dataColumns:
dataColumnList[i] = dataColumns[label] # note here "i" is the index to the dict
else:
#raise Exception("no datacolumn for the label: " + label)
columnName = chr(ord('A') + i)
findError = True
for column in dataColumns.values():
if(column.worksheet_column == columnName):
dataColumnList[i] = column
findError = False
break
if findError:
print "Error: no datacolumn for ", label
sys.exit(-1)
found=False
for key,value in mappingColumnDict.items():
if(value != -1):
found=True
if(not found):
raise Exception('at least one of: ' + str(mappingColumnDict.keys()) + ' must be defined and used in the Data sheet.')
# Read in the Data sheet, create DataPoint values for mapped column in each row
pointsSaved = 0
rowsRead = 0
for row in dataSheet:
r = util.make_row(row)
dataRecord = DataRecord(dataset=dataset )
map_column = mappingColumnDict['Small Molecule']
mapped = False
if(map_column > -1):
try:
value = util.convertdata(r[map_column].strip())
if(value != None and value != '' ):
facility = value.split("-")[0] # TODO: purge "HMSL" from the db
salt = value.split("-")[1]
dataRecord.small_molecule = SmallMolecule.objects.get(facility_id=facility, sm_salt=salt)
mapped = True
except Exception, e:
print "Invalid Small Molecule facility id: ", value
raise
map_column = mappingColumnDict['Cell']
if(map_column > -1):
try:
value = util.convertdata(r[map_column].strip())
if(value != None and value != '' ):
facility_id = value
dataRecord.cell = Cell.objects.get(facility_id=facility_id) # TODO: purge "HMSL" from the db
mapped = True
except Exception, e:
print "Invalid Cell facility id: ", facility_id
raise
def main(path):
"""
Read in the Protein
"""
sheet_name = 'HMS-LINCS Kinases'
# Note, skipping the header row by default
sheet = iu.readtable([path, sheet_name, 1])
properties = ('model_field','required','default','converter')
column_definitions = {
'PP_Name':('name',True),
'PP_LINCS_ID':('lincs_id',True,None,lambda x: x[x.index('HMSL')+4:]),
'PP_UniProt_ID':'uniprot_id',
'PP_Alternate_Name':'alternate_name',
'PP_Alternate_Name[2]':'alternate_name_2',
'PP_Provider':'provider',
'PP_Provider_Catalog_ID':'provider_catalog_id',
'PP_Batch_ID':'batch_id',
'PP_Amino_Acid_Sequence':'amino_acid_sequence',
'PP_Gene_Symbol':'gene_symbol',
'PP_Gene_ID':'gene_id',
'PP_Protein_Source':'protein_source',
'PP_Protein_Form':'protein_form',
'PP_Mutation':'mutation',
'PP_Phosphorylation_State':'phosphlorylation',
'PP_Domain':'protein_domain',
'PP_Protein_Purity':'protein_purity',
'PP_Protein_Complex':'protein_complex',
'PP_Isoform':'isoform',
'PP_Protein_Type':'protein_type',
'PP_Source_Organism':'source_organism',
'PP_Reference':'reference',
'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)}
# 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
cols = util.find_columns(column_definitions, sheet.labels)
rows = 0
logger.debug(str(('cols: ' , cols)))
for row in sheet:
r = util.make_row(row)
dict = {}
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)))
protein = Protein(**initializer)
protein.save()
logger.info(str(('protein created: ', protein)))
rows += 1
except Exception, e:
logger.error(str(("Invalid protein initializer: ", initializer, e)))
raise
def main(path):
"""
Read in the OtherReagent
"""
sheet_name = 'Sheet1'
sheet = iu.readtable([path, sheet_name,
1]) # Note, skipping the header row by default
properties = ('model_field', 'required', 'default', 'converter')
column_definitions = {
'OR_ID':
'lincs_id',
'Facility ID': ('facility_id', True),
'OR_Alternate_ID':
'alternate_id',
'OR_Primary_Name': ('name', True),
'OR_Alternate_Name':
'alternative_names',
'OR_Role':
'role',
'OR_Reference':
'reference',
'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)
}
# 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)
dict = {}
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)))
reagent = OtherReagent(**initializer)
reagent.save()
logger.info(str(('OtherReagent created: ', reagent)))
rows += 1
# create a default batch - 0
OtherReagentBatch.objects.create(reagent=reagent, batch_id=0)
except Exception, e:
logger.error(
str(("Invalid OtherReagent initializer: ", initializer)))
raise
def readDataColumns(path):
# Read in the DataColumn Sheet
sheetname = 'Data Columns'
dataColumnSheet = iu.readtable([path, sheetname])
# Lookup all of the field types of the Datacolumn table.
# These will be used to validate input type by converting on read
_fields = util.get_fields(DataColumn)
_typelookup = dict((f.name, iu.totype(f)) for f in _fields)
# TODO: Use the import_utils methods here
# TODO: compare and combine this with the fieldinformation entity
labels = {'Worksheet Column':'worksheet_column',
'Display Order':'display_order',
'Name':'name',
'Display Name':'display_name',
'Data Type':'data_type',
'Decimal Places':'precision',
'Description':'description',
'Replicate Number':'replicate',
'Unit':'unit',
'Assay readout type':'readout_type',
'Comments':'comments',
'Protein HMS LINCS ID': 'protein',
'Cell HMS LINCS ID': 'cell'}
# create an array of dict's, each dict defines a DataColumn
dataColumnDefinitions = []
#Note we also allow a list of pro
# first the label row (it contains the worksheet column, it is unique)
for v in dataColumnSheet.labels[1:]:
dataColumnDefinitions.append({labels['Worksheet Column']:v})
logger.debug(str(('========== datacolumns:',dataColumnDefinitions)))
# for each row, create the dictionary entry in the dataColumnDefinitions
for row in dataColumnSheet:
rowAsUnicode = util.make_row(row)
keyRead = rowAsUnicode[0]
for i,cellText in enumerate(rowAsUnicode[1:]):
try:
for key,fieldName in labels.items():
# if one of the DataColumn fields, add it to the dict
if re.match(key,keyRead,re.M|re.I):
if re.match('Protein HMS LINCS ID', keyRead, re.M|re.I):
facility_id = util.convertdata(cellText, int);
if facility_id:
dataColumnDefinitions[i][fieldName] = \
Protein.objects.get(lincs_id=facility_id)
elif re.match('Cell HMS LINCS ID', keyRead, re.M|re.I):
facility_id = util.convertdata(cellText, int);
if facility_id:
dataColumnDefinitions[i][fieldName] = \
Cell.objects.get(facility_id=facility_id)
else:
# Use the type from the fieldinformation table
# to read in the data for each DC field
dataColumnDefinitions[i][fieldName] = \
util.convertdata(cellText,
_typelookup.get(fieldName, None))
else:
logger.debug(str((
'"Data Column definition not used: ', cellText)) )
pass
except Exception, e:
logger.error(str(('Exception reading data for cell', i, cellText, e)))
raise e
logger.debug(str(("definitions: ", dataColumnDefinitions)) )
def main(path):
"""
Read in the cell batch info
"""
sheet_name = 'Sheet1'
start_row = 1
sheet = iu.readtable([path, sheet_name, start_row]) # 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_Batch_ID':('batch_id',True,None,lambda x:util.convertdata(x,int)),
'CL_Provider_Name':'provider_name',
'CL_Provider_Batch_ID':'provider_batch_id',
'CL_Provider_Catalog_ID':'provider_catalog_id',
'CL_Quality_Verification':'quality_verification',
'CL_Transient_Modification': 'transient_modification',
'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),
}
# 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']
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)))
if model_field == 'facility_id':
try:
cell = Cell.objects.get(facility_id=value)
initializer['reagent'] = cell
except:
logger.error(str(("Cell not found", value, 'row',rows+start_row+2)))
raise
else:
initializer[model_field] = value
try:
logger.debug(str(('initializer: ', initializer)))
cell = CellBatch(**initializer)
cell.save()
logger.debug(str(('cell created:', cell)))
rows += 1
except Exception, e:
logger.error(str(( "Invalid CellBatch initializer: ", initializer,
'row', rows+start_row+2, e)))
raise
def main(path):
"""
Read in the cell batch info
"""
sheet_name = 'Sheet1'
start_row = 1
sheet = iu.readtable([path, sheet_name, start_row
]) # 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_Batch_ID':
('batch_id', True, None, lambda x: util.convertdata(x, int)),
'CL_Provider_Name':
'provider_name',
'CL_Provider_Batch_ID':
'provider_batch_id',
'CL_Provider_Catalog_ID':
'provider_catalog_id',
'CL_Quality_Verification':
'quality_verification',
'CL_Transient_Modification':
'transient_modification',
'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),
}
# 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']
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)))
if model_field == 'facility_id':
try:
cell = Cell.objects.get(facility_id=value)
initializer['reagent'] = cell
except:
logger.error(
str(("Cell not found", value, 'row',
rows + start_row + 2)))
raise
else:
initializer[model_field] = value
try:
logger.debug(str(('initializer: ', initializer)))
cell = CellBatch(**initializer)
cell.save()
logger.debug(str(('cell created:', cell)))
rows += 1
except Exception, e:
logger.error(
str(("Invalid CellBatch initializer: ", initializer, 'row',
rows + start_row + 2, e)))
raise
def main(import_file, file_directory, deploy_dir):
"""
Read in the qc events for batches
- version 1 - for small molecule batches
"""
sheet_name = "Sheet1"
start_row = 0
sheet = iu.readtable([import_file, sheet_name, start_row]) # Note, skipping the header row by default
properties = ("model_field", "required", "default", "converter")
column_definitions = {
"facility_id": ("facility_id_for", True, None, lambda x: util.convertdata(x, int)),
"salt_id": ("salt_id_for", False, None, lambda x: util.convertdata(x, int)),
"batch_id": ("batch_id_for", True, None, lambda x: util.convertdata(x, int)),
"QC event date": ("date", True, None, util.date_converter),
"outcome": ("outcome", True),
"comment": "comment",
"is_restricted": ("is_restricted", False, False, util.bool_converter),
"file1": "file1",
"file2": "file2",
"file3": "file3",
"file4": "file4",
"file5": "file5",
}
# 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)
# store each row in a dict
_dict = {}
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"]
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)))
_dict[model_field] = value
logger.debug(str(("dict: ", _dict)))
files_to_attach = []
for i in range(10):
filenameProp = "file%s" % i
if _dict.get(filenameProp, None):
fileprop = _dict[filenameProp]
filepath = os.path.join(file_directory, fileprop)
if not os.path.exists(filepath):
raise Exception(str(("file does not exist:", filepath, "row", rows + start_row)))
filename = os.path.basename(filepath)
relative_path = fileprop[: fileprop.index(filename)]
# Move the file
dest_dir = deploy_dir
if not dest_dir:
dest_dir = settings.STATIC_AUTHENTICATED_FILE_DIR
if not os.path.isdir(dest_dir):
raise Exception(str(("no such deploy directory, please create it", dest_dir)))
if relative_path:
dest_dir = os.path.join(dest_dir, relative_path)
if not os.path.exists(dest_dir):
os.makedirs(dest_dir)
deployed_path = os.path.join(dest_dir, filename)
logger.debug(str(("deploy", filepath, deployed_path)))
if os.path.exists(deployed_path):
os.remove(deployed_path)
copy(filepath, deployed_path)
if not os.path.isfile(deployed_path):
raise Exception(str(("could not deploy to", deployed_path)))
else:
logger.debug(str(("successfully deployed to", deployed_path)))
files_to_attach.append((filename, relative_path))
initializer = None
try:
# create the qc record
initializer = {
key: _dict[key]
for key in ["facility_id_for", "salt_id_for", "batch_id_for", "outcome", "comment", "date"]
}
qc_event = QCEvent(**initializer)
qc_event.save()
logger.debug(str(("saved", qc_event)))
# create attached file records
for (filename, relative_path) in files_to_attach:
initializer = {
"qc_event": qc_event,
"filename": filename,
"relative_path": relative_path,
"is_restricted": _dict["is_restricted"],
}
qc_attached_file = QCAttachedFile(**initializer)
qc_attached_file.save()
logger.debug(str(("created qc attached file", qc_attached_file)))
rows += 1
except Exception, e:
logger.error(str(("Invalid initializer: ", initializer, "row", rows + start_row + 2, e)))
raise
def main(path):
"""
Read in the OtherReagent
"""
sheet_name = 'Sheet1'
sheet = iu.readtable([path, sheet_name, 1]) # Note, skipping the header row by default
properties = ('model_field','required','default','converter')
column_definitions = {
'OR_ID': 'lincs_id',
'Facility ID': ('facility_id',True),
'OR_Alternate_ID': 'alternate_id',
'OR_Primary_Name': ('name',True),
'OR_Alternate_Name': 'alternative_names',
'OR_Role': 'role',
'OR_Reference': 'reference',
'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)}
# 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)
dict = {}
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)))
reagent = OtherReagent(**initializer)
reagent.save()
logger.info(str(('OtherReagent created: ', reagent)))
rows += 1
except Exception, e:
logger.error(str(( "Invalid OtherReagent initializer: ", initializer)))
raise
def main(path):
"""
Read in the Antibody Batches
"""
sheet_name = 'Sheet1'
sheet = iu.readtable([path, sheet_name, 0])
properties = ('model_field', 'required', 'default', 'converter')
column_definitions = {
'AR_Center_Specific_ID': ('antibody_facility_id', True, None,
lambda x: x[x.index('HMSL') + 4:]),
'AR_Batch_ID':
('batch_id', True, None, lambda x: util.convertdata(x, int)),
'AR_Provider_Name':
'provider_name',
'AR_Provider_Catalog_ ID':
'provider_catalog_id',
'AR_Provider_Batch_ID':
'provider_batch_id',
'AR_Antibody_Purity':
'antibody_purity',
'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),
}
# 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('cols: %s' % cols)
for row in sheet:
r = util.make_row(row)
dict = {}
initializer = {}
for i, value in enumerate(r):
if i not in cols: continue
properties = cols[i]
logger.debug('read col: %d: %s' % (i, properties))
required = properties['required']
default = properties['default']
converter = properties['converter']
model_field = properties['model_field']
logger.debug('raw value %r' % 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('model_field: %s, converted value %r' %
(model_field, value))
initializer[model_field] = value
try:
logger.debug('initializer: %s' % initializer)
antibody_facility_id = initializer.pop('antibody_facility_id',
None)
if antibody_facility_id:
try:
antibody = Antibody.objects.get(
facility_id=antibody_facility_id)
initializer['reagent'] = antibody
except ObjectDoesNotExist, e:
logger.error(
'AR_Center_Specific_ID: "%s" does not exist, row: %d' %
(antibody_facility_id, i))
antibody_batch = AntibodyBatch(**initializer)
antibody_batch.save()
logger.info('antibody batch created: %s' % antibody_batch)
rows += 1
except Exception, e:
logger.error("Invalid antibody_batch initializer: %s" %
initializer)
raise
def main(path):
"""
Read in the Antibody
"""
sheet_name = 'Sheet1'
sheet = iu.readtable([path, sheet_name, 0])
properties = ('model_field', 'required', 'default', 'converter')
column_definitions = {
'AR_Name': ('name', True),
'AR_LINCS_ID':
'lincs_id',
'AR_Alternative_Name':
'alternative_names',
'AR_Center_Specific_ID':
('facility_id', True, None, lambda x: x[x.index('HMSL') + 4:]),
'AR_Clone_Name':
'clone_name',
'AR_RRID':
'rrid',
'AR_Antibody_Type':
'type',
'target_protein_lincs_id': ('target_protein_lincs_id', False, None,
lambda x: x[x.index('HMSL') + 4:]
if x else None),
'AR_Non-Protein_Target':
'non_protein_target_name',
'AR_Target_Organism':
'target_organism',
'AR_Immunogen':
'immunogen',
'AR_Immunogen_Sequence':
'immunogen_sequence',
'AR_Antibody_Species':
'species',
'AR_Antibody_Clonality':
'clonality',
'AR_Antibody_Isotype':
'isotype',
'AR_Antibody_Production_Source_Organism':
'source_organism',
'AR_Antibody_Production_Details':
'production_details',
'AR_Antibody_Labeling':
'labeling',
'AR_Antibody_Labeling_Details':
'labeling_details',
'AR_Relevant_Citations':
'relevant_citations',
'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('cols: %s' % cols)
for row in sheet:
logger.debug('row %s - %s' % (rows, row))
r = util.make_row(row)
dict = {}
initializer = {}
for i, value in enumerate(r):
if i not in cols: continue
properties = cols[i]
logger.debug('read col: %d: %s' % (i, properties))
required = properties['required']
default = properties['default']
converter = properties['converter']
model_field = properties['model_field']
logger.debug('raw value %r' % value)
if (value == None or value == 'None'):
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))
if (value and converter != None):
value = converter(value)
logger.debug('model_field: %s, converted value %r' %
(model_field, value))
initializer[model_field] = value
try:
logger.debug('row: %s, initializer: %s' % (rows, initializer))
target_protein_lincs_id = initializer.pop(
'target_protein_lincs_id', None)
if target_protein_lincs_id:
try:
target_protein = Protein.objects.get(
lincs_id=target_protein_lincs_id)
initializer['target_protein'] = target_protein
except ObjectDoesNotExist, e:
logger.error(
'target_protein_lincs_id "%s" does not exist, row: %d'
% (target_protein_lincs_id, i))
antibody = Antibody(**initializer)
antibody.save()
logger.info('antibody created: %s' % antibody)
rows += 1
# create a default batch - 0
AntibodyBatch.objects.create(reagent=antibody, batch_id=0)
except Exception, e:
logger.error("Invalid antibody initializer: %s" % initializer)
raise
def main(path):
sheet_name = 'sheet 1'
start_row = 1
sheet = iu.readtable([path, sheet_name, start_row])
properties = ('model_field','required','default','converter')
column_definitions = {
'facility_id': (
'facility_id',True,None, lambda x: util.convertdata(x,int)),
'facility_batch_id':(
'batch_id',True,None, lambda x: util.convertdata(x,int)),
'provider': ('provider_name',False),
'provider_catalog_id':'provider_catalog_id',
'provider_sample_id':'provider_batch_id',
'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),
}
column_definitions = util.fill_in_column_definitions(
properties,column_definitions)
cols = util.find_columns(column_definitions, sheet.labels,
all_sheet_columns_required=False)
rows = 0
logger.debug('cols: %s' % cols)
for row in sheet:
r = util.make_row(row)
dict = {}
initializer = {}
for i,value in enumerate(r):
if i not in cols: continue
properties = cols[i]
logger.debug('read col: %d: %s' % (i,properties))
required = properties['required']
default = properties['default']
converter = properties['converter']
model_field = properties['model_field']
logger.debug('raw value %r' % 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('model_field: %s, converted value %r'
% (model_field, value) )
initializer[model_field] = value
try:
logger.debug('initializer: %s' % initializer)
facility_id = initializer.pop('facility_id',None)
try:
other_reagent = OtherReagent.objects.get(facility_id=facility_id)
initializer['reagent'] = other_reagent
except ObjectDoesNotExist, e:
logger.error('facility_id: "%s" does not exist, row: %d'
% (facility_id,i))
batch = OtherReagentBatch(**initializer)
batch.save()
logger.debug('batch created: %s', batch)
rows += 1
except Exception, e:
logger.error("Invalid other_reagent_batch initializer: %s" % initializer)
raise
def main(import_file, file_directory, deploy_dir):
"""
Read in the qc events for batches
- version 1 - for small molecule batches
"""
sheet_name = 'Sheet1'
start_row = 0
sheet = iu.readtable([import_file, sheet_name, start_row
]) # Note, skipping the header row by default
properties = ('model_field', 'required', 'default', 'converter')
column_definitions = {
'facility_id':
('facility_id_for', True, None, lambda x: util.convertdata(x, int)),
'salt_id':
('salt_id_for', False, None, lambda x: util.convertdata(x, int)),
'batch_id':
('batch_id_for', True, None, lambda x: util.convertdata(x, int)),
'QC event date': ('date', True, None, util.date_converter),
'outcome': ('outcome', True),
'comment':
'comment',
'is_restricted': ('is_restricted', False, False, util.bool_converter),
'file1':
'file1',
'file2':
'file2',
'file3':
'file3',
'file4':
'file4',
'file5':
'file5',
}
# 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)
# store each row in a dict
_dict = {}
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']
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)))
_dict[model_field] = value
logger.debug(str(('dict: ', _dict)))
files_to_attach = []
for i in range(10):
filenameProp = 'file%s' % i
if _dict.get(filenameProp, None):
fileprop = _dict[filenameProp]
filepath = os.path.join(file_directory, fileprop)
if not os.path.exists(filepath):
raise Exception(
str(('file does not exist:', filepath, 'row',
rows + start_row)))
filename = os.path.basename(filepath)
relative_path = fileprop[:fileprop.index(filename)]
# Move the file
dest_dir = deploy_dir
if not dest_dir:
dest_dir = settings.STATIC_AUTHENTICATED_FILE_DIR
if not os.path.isdir(dest_dir):
raise Exception(
str(('no such deploy directory, please create it',
dest_dir)))
if relative_path:
dest_dir = os.path.join(dest_dir, relative_path)
if not os.path.exists(dest_dir):
os.makedirs(dest_dir)
deployed_path = os.path.join(dest_dir, filename)
logger.debug(str(('deploy', filepath, deployed_path)))
if os.path.exists(deployed_path):
os.remove(deployed_path)
copy(filepath, deployed_path)
if not os.path.isfile(deployed_path):
raise Exception(str(
('could not deploy to', deployed_path)))
else:
logger.debug(
str(('successfully deployed to', deployed_path)))
files_to_attach.append((filename, relative_path))
initializer = None
try:
# create the qc record
initializer = {
key: _dict[key]
for key in [
'facility_id_for', 'salt_id_for', 'batch_id_for',
'outcome', 'comment', 'date'
]
}
qc_event = QCEvent(**initializer)
qc_event.save()
logger.debug(str(('saved', qc_event)))
# create attached file records
for (filename, relative_path) in files_to_attach:
initializer = {
'qc_event': qc_event,
'filename': filename,
'relative_path': relative_path,
'is_restricted': _dict['is_restricted']
}
qc_attached_file = QCAttachedFile(**initializer)
qc_attached_file.save()
logger.debug(
str(('created qc attached file', qc_attached_file)))
rows += 1
except Exception, e:
logger.error(
str(("Invalid initializer: ", initializer, 'row',
rows + start_row + 2, e)))
raise
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
