def seqpeek_view_data(self, request):
try:
hugo_symbol = request.hugo_symbol
cohort_id_array = request.cohort_id
gnab_feature_id = self.build_gnab_feature_id(hugo_symbol)
logging.debug("GNAB feature ID for SeqPeke: {0}".format(gnab_feature_id))
async_params = [ProviderClassQueryDescription(SeqPeekDataProvider, gnab_feature_id, cohort_id_array)]
maf_data_result = get_feature_vectors_tcga_only(async_params, skip_formatting_for_plot=True)
maf_data_vector = maf_data_result[gnab_feature_id]['data']
if len(maf_data_vector) > 0:
# Since the gene (hugo_symbol) parameter is part of the GNAB feature ID,
# it will be sanity-checked in the SeqPeekMAFDataAccess instance.
seqpeek_data = SeqPeekMAFDataFormatter().format_maf_vector_for_view(maf_data_vector, cohort_id_array)
seqpeek_maf_vector = seqpeek_data.maf_vector
seqpeek_cohort_info = seqpeek_data.cohort_info
removed_row_statistics_dict = seqpeek_data.removed_row_statistics
seqpeek_view_data = SeqPeekViewDataBuilder().build_view_data(hugo_symbol,
seqpeek_maf_vector,
seqpeek_cohort_info,
cohort_id_array,
removed_row_statistics_dict)
response = self.create_response(seqpeek_view_data)
return response
else:
# No data found
return SeqPeekViewRecord(plot_data=SeqPeekViewPlotDataRecord(tracks=[], protein=None, regions=[]),
hugo_symbol=hugo_symbol, cohort_id_list=[str(i) for i in cohort_id_array],
removed_row_statistics=[])
except Exception as e:
logging.exception(e)
raise InternalServerErrorException()
def get_merged_feature_vectors(self, x_id, y_id, c_id, cohort_id_array, logTransform, study_id_array):
"""
Fetches and merges data for two or three feature vectors (see parameter documentation below).
The vectors have to be an array of dictionaries, with each dictionary containing a 'value' field
(other fields are ignored):
[
{
'value': 0.5
},
{
'value': 1.0
}
]
The merged result:
[
{
'patient_id': <patient ID #0>
'x': <value for x for patient ID #0>
'y': <value for y for patient ID #0>
'c': <value for c for patient ID #0>
},
{
'patient_id': <patient ID #1>
'x': <value for x for patient ID #1>
'y': <value for y for patient ID #1>
'c': <value for c for patient ID #1>
}
...
]
:param x_id: Feature identifier for x-axis e.g. 'CLIN:age_at_initial_pathologic_diagnosis'
:param y_id: Feature identifier for y-axis. If None, values for 'y' in the response will be marked as missing.
:param c_id: Feature identifier for color-by. If None, values for 'c' in the response will be marked as missing.
:param cohort_id_array: Cohort identifier array.
:return: PlotDataResponse
"""
async_params = [FeatureIdQueryDescription(x_id, cohort_id_array, study_id_array)]
c_type, c_vec = ValueType.STRING, []
y_type, y_vec = ValueType.STRING, []
units = get_axis_units(x_id, y_id)
if c_id is not None:
async_params.append(FeatureIdQueryDescription(c_id, cohort_id_array, study_id_array))
if y_id is not None:
async_params.append(FeatureIdQueryDescription(y_id, cohort_id_array, study_id_array))
async_result = get_feature_vectors_tcga_only(async_params)
if c_id is not None:
c_type, c_vec = async_result[c_id]['type'], async_result[c_id]['data']
if y_id is not None:
y_type, y_vec = async_result[y_id]['type'], async_result[y_id]['data']
if logTransform is not None and logTransform['y'] and y_vec and is_log_transformable(y_type):
# If we opt to use a transform that attempts to account for values out of range for log transformation,
# this is the code to get the minimum y-value
'''
yvals = []
for yd in y_vec:
if 'value' in yd and yd['value'] is not None and yd['value'] != "NA" and yd['value'] != "None":
yvals.append(float(yd['value']))
y_min = min(yvals)
'''
for ydata in y_vec:
if 'value' in ydata and ydata['value'] is not None and ydata['value'] != "NA" and ydata['value'] != "None":
if float(ydata['value']) < 0:
ydata['value'] = "NA"
elif logTransform['yBase'] == 10:
ydata['value'] = str(math.log10((float(ydata['value']) + 1)))
elif logTransform['yBase'] == 'e':
ydata['value'] = str(math.log((float(ydata['value']) + 1)))
elif type(logTransform['yBase']) is int:
ydata['value'] = str(math.log((float(ydata['value']) + 1), logTransform['yBase']))
else:
logger.warn(
"[WARNING] No valid log base was supplied - log transformation will not be applied!"
)
x_type, x_vec = async_result[x_id]['type'], async_result[x_id]['data']
if logTransform is not None and logTransform['x'] and x_vec and is_log_transformable(x_type):
# If we opt to use a transform that attempts to account for values out of range for log transformation,
# this is the code to get the minimum x-value
'''
xvals = []
for xd in x_vec:
if 'value' in xd and xd['value'] is not None and xd['value'] != "NA" and xd['value'] != "None":
xvals.append(float(xd['value']))
x_min = min(xvals)
'''
for xdata in x_vec:
if 'value' in xdata and xdata['value'] is not None and xdata['value'] != "NA" and xdata['value'] != "None":
if float(xdata['value']) < 0:
xdata['value'] = "NA"
elif logTransform['xBase'] == 10:
xdata['value'] = str(math.log10((float(xdata['value']) + 1)))
elif logTransform['xBase'] == 'e':
xdata['value'] = str(math.log((float(xdata['value']) + 1)))
elif type(logTransform['xBase']) is int:
xdata['value'] = str(math.log((float(xdata['value']) + 1), logTransform['xBase']))
else:
logger.warn(
"[WARNING] No valid log base was supplied - log transformation will not be applied!"
)
vms = VectorMergeSupport('NA', 'sample_id', 'case_id', ['x', 'y', 'c']) # changed so that it plots per sample not patient
vms.add_dict_array(x_vec, 'x', 'value')
vms.add_dict_array(y_vec, 'y', 'value')
vms.add_dict_array(c_vec, 'c', 'value')
merged = self.get_merged_dict_timed(vms)
# Resolve which (requested) cohorts each datapoint belongs to.
cohort_set_dict = CloudSQLCohortAccess.get_cohorts_for_datapoints(cohort_id_array)
# Get the name and ID for every requested cohort.
cohort_info_array = CloudSQLCohortAccess.get_cohort_info(cohort_id_array)
cohort_info_obj_array = []
for item in cohort_info_array:
cohort_info_obj_array.append(PlotDataCohortInfo(id=item['id'], name=item['name']))
items = []
for value_bundle in merged:
sample_id = value_bundle['sample_id']
# Add an array of cohort
# only if the number of containing cohort exceeds the configured threshold.
cohort_set = []
# TODO FIX - this check shouldn't be needed
if sample_id in cohort_set_dict:
cohort_set = cohort_set_dict[sample_id]
if len(cohort_set) >= DATAPOINT_COHORT_THRESHOLD:
value_bundle['cohort'] = cohort_set
items.append(PlotDataPoint(**value_bundle))
counts = self.get_counts(merged)
count_message = PlotDatapointCount(**counts)
type_message = PlotDataTypes(x=x_type, y=y_type, c=c_type)
# TODO assign label for y if y_id is None, as in that case the y-field will be missing from the response
label_message = PlotDataFeatureLabels(x=x_id, y=y_id, c=c_id)
# TODO Refactor pairwise call to separate function
# Include pairwise results
input_vectors = [PairwiseInputVector(x_id, x_type, x_vec)]
if c_id is not None:
input_vectors.append(PairwiseInputVector(c_id, c_type, c_vec))
if y_id is not None:
input_vectors.append(PairwiseInputVector(y_id, y_type, y_vec))
pairwise_result = None
if len(input_vectors) > 1:
pairwise_result = self.get_pairwise_result(input_vectors)
if pairwise_result is None:
logger.warn("[WARNING] Pairwise results not included in returned object")
return PlotDataResponse(types=type_message, labels=label_message, items=items,
cohort_set=cohort_info_obj_array,
counts=count_message, pairwise_result=pairwise_result, xUnits=units['x'], yUnits=units['y'])
def seqpeek_view_data(self, request):
try:
hugo_symbol = request.hugo_symbol
cohort_id_array = request.cohort_id
gnab_feature_id = self.build_gnab_feature_id(hugo_symbol)
logging.debug("GNAB feature ID for SeqPeke: {0}".format(gnab_feature_id))
# Lifted from api/data_access.py line 509+
# Get the study IDs these cohorts' samples come from
cohort_vals = ()
cohort_params = ""
for cohort in cohort_id_array:
cohort_params += "%s,"
cohort_vals += (cohort,)
cohort_params = cohort_params[:-1]
db = sql_connection()
cursor = db.cursor()
tcga_studies = fetch_isbcgc_project_set()
cursor.execute("SELECT DISTINCT study_id FROM cohorts_samples WHERE cohort_id IN (" + cohort_params + ");",
cohort_vals)
# Only samples whose source studies are TCGA studies, or extended from them, should be used
confirmed_study_ids = []
unconfirmed_study_ids = []
for row in cursor.fetchall():
if row[0] in tcga_studies:
if row[0] not in confirmed_study_ids:
confirmed_study_ids.append(row[0])
elif row[0] not in unconfirmed_study_ids:
unconfirmed_study_ids.append(row[0])
if len(unconfirmed_study_ids) > 0:
studies = Study.objects.filter(id__in=unconfirmed_study_ids)
for study in studies:
if study.get_my_root_and_depth()['root'] in tcga_studies:
confirmed_study_ids.append(study.id)
async_params = [ProviderClassQueryDescription(SeqPeekDataProvider, gnab_feature_id, cohort_id_array, confirmed_study_ids)]
maf_data_result = get_feature_vectors_tcga_only(async_params, skip_formatting_for_plot=True)
maf_data_vector = maf_data_result[gnab_feature_id]['data']
if len(maf_data_vector) > 0:
# Since the gene (hugo_symbol) parameter is part of the GNAB feature ID,
# it will be sanity-checked in the SeqPeekMAFDataAccess instance.
seqpeek_data = SeqPeekMAFDataFormatter().format_maf_vector_for_view(maf_data_vector, cohort_id_array)
seqpeek_maf_vector = seqpeek_data.maf_vector
seqpeek_cohort_info = seqpeek_data.cohort_info
removed_row_statistics_dict = seqpeek_data.removed_row_statistics
seqpeek_view_data = SeqPeekViewDataBuilder().build_view_data(hugo_symbol,
seqpeek_maf_vector,
seqpeek_cohort_info,
cohort_id_array,
removed_row_statistics_dict)
response = self.create_response(seqpeek_view_data)
return response
else:
# No data found
return SeqPeekViewRecord(plot_data=SeqPeekViewPlotDataRecord(tracks=[], protein=None, regions=[]),
hugo_symbol=hugo_symbol, cohort_id_list=[str(i) for i in cohort_id_array],
removed_row_statistics=[])
except Exception as e:
logging.exception(e)
raise InternalServerErrorException()
def get_merged_feature_vectors(self, x_id, y_id, c_id, cohort_id_array):
"""
Fetches and merges data for two or three feature vectors (see parameter documentation below).
The vectors have to be an array of dictionaries, with each dictionary containing a 'value' field
(other fields are ignored):
[
{
'value': 0.5
},
{
'value': 1.0
}
]
The merged result:
[
{
'patient_id': <patient ID #0>
'x': <value for x for patient ID #0>
'y': <value for y for patient ID #0>
'c': <value for c for patient ID #0>
},
{
'patient_id': <patient ID #1>
'x': <value for x for patient ID #1>
'y': <value for y for patient ID #1>
'c': <value for c for patient ID #1>
}
...
]
:param x_id: Feature identifier for x-axis e.g. 'CLIN:age_at_initial_pathologic_diagnosis'
:param y_id: Feature identifier for y-axis. If None, values for 'y' in the response will be marked as missing.
:param c_id: Feature identifier for color-by. If None, values for 'c' in the response will be marked as missing.
:param cohort_id_array: Cohort identifier array.
:return: PlotDataResponse
"""
async_params = [FeatureIdQueryDescription(x_id, cohort_id_array)]
c_type, c_vec = ValueType.STRING, []
y_type, y_vec = ValueType.STRING, []
if c_id is not None:
async_params.append(FeatureIdQueryDescription(c_id, cohort_id_array))
if y_id is not None:
async_params.append(FeatureIdQueryDescription(y_id, cohort_id_array))
async_result = get_feature_vectors_tcga_only(async_params)
if c_id is not None:
c_type, c_vec = async_result[c_id]['type'], async_result[c_id]['data']
if y_id is not None:
y_type, y_vec = async_result[y_id]['type'], async_result[y_id]['data']
x_type, x_vec = async_result[x_id]['type'], async_result[x_id]['data']
vms = VectorMergeSupport('NA', 'sample_id', ['x', 'y', 'c']) # changed so that it plots per sample not patient
vms.add_dict_array(x_vec, 'x', 'value')
vms.add_dict_array(y_vec, 'y', 'value')
vms.add_dict_array(c_vec, 'c', 'value')
merged = self.get_merged_dict_timed(vms)
# Resolve which (requested) cohorts each datapoint belongs to.
cohort_set_dict = CloudSQLCohortAccess.get_cohorts_for_datapoints(cohort_id_array)
# Get the name and ID for every requested cohort.
cohort_info_array = CloudSQLCohortAccess.get_cohort_info(cohort_id_array)
cohort_info_obj_array = []
for item in cohort_info_array:
cohort_info_obj_array.append(PlotDataCohortInfo(id=item['id'], name=item['name']))
items = []
for value_bundle in merged:
sample_id = value_bundle['sample_id']
# Add an array of cohort
# only if the number of containing cohort exceeds the configured threshold.
cohort_set = []
# TODO FIX - this check shouldn't be needed
if sample_id in cohort_set_dict:
cohort_set = cohort_set_dict[sample_id]
if len(cohort_set) >= DATAPOINT_COHORT_THRESHOLD:
value_bundle['cohort'] = cohort_set
items.append(PlotDataPoint(**value_bundle))
counts = self.get_counts(merged)
count_message = PlotDatapointCount(**counts)
type_message = PlotDataTypes(x=x_type, y=y_type, c=c_type)
# TODO assign label for y if y_id is None, as in that case the y-field will be missing from the response
label_message = PlotDataFeatureLabels(x=x_id, y=y_id, c=c_id)
# TODO Refactor pairwise call to separate function
# Include pairwise results
input_vectors = [PairwiseInputVector(x_id, x_type, x_vec),
PairwiseInputVector(c_id, c_type, c_vec)]
if y_id is not None:
input_vectors.append(PairwiseInputVector(y_id, y_type, y_vec))
pairwise_result = None
try:
pairwise_result = self.get_pairwise_result(input_vectors)
except Exception as e:
logging.warn("Pairwise results not included in returned object")
logging.exception(e)
return PlotDataResponse(types=type_message, labels=label_message, items=items,
cohort_set=cohort_info_obj_array,
counts=count_message, pairwise_result=pairwise_result)
