def fetch_raw_replicate_counts(self, tids):
# fetch raw replicate lanes data
lanes = (
db_session.query(RawReplicateCounts)
.filter(
RawReplicateCounts.nucleotide_measurement_run_id == self.nucleotide_measurement_run_id,
RawReplicateCounts.transcript_id.in_(tids),
)
.order_by(
RawReplicateCounts.transcript_id,
RawReplicateCounts.minusplus_id,
RawReplicateCounts.bio_replicate_id,
RawReplicateCounts.tech_replicate_id,
)
.all()
)
# compile into counts
counts = {} # transcript_id => {minus_counts: ... , plus_counts: ... }
for lane in lanes:
lane_values = values_str_unpack_float(lane.values)
# initialise this transcript
if lane.transcript_id not in counts:
counts[lane.transcript_id] = {}
# set the plus or minus counts
if lane.minusplus_id not in counts[lane.transcript_id]:
counts[lane.transcript_id][lane.minusplus_id] = lane_values
else: # add to existing plus or minus counts
for pos in range(0, len(lane_values)):
counts[lane.transcript_id][lane.minusplus_id][pos] += lane_values[pos]
# insert the counts into the DB
for transcript_id in counts:
transcript_counts = counts[transcript_id]
# gotta handle the missing data gracefully
if "minus" not in transcript_counts:
minus_counts = [0] * len(transcript_counts["plus"])
else:
minus_counts = transcript_counts["minus"]
if "plus" not in transcript_counts:
plus_counts = [0] * len(transcript_counts["minus"])
else:
plus_counts = transcript_counts["plus"]
measurement_set = RawReactivities(
nucleotide_measurement_run_id=self.nucleotide_measurement_run_id,
transcript_id=transcript_id,
minus_values="\t".join(list(map(str, minus_counts))),
plus_values="\t".join(list(map(str, plus_counts))),
)
db_session.add(measurement_set)
db_session.commit()
def fetch_raw_replicate_counts(self, tids):
# fetch raw replicate lanes data
lanes = db_session \
.query(RawReplicateCounts) \
.filter(
RawReplicateCounts.nucleotide_measurement_run_id==self.nucleotide_measurement_run_id,
RawReplicateCounts.transcript_id.in_(tids)
) \
.order_by(
RawReplicateCounts.transcript_id,
RawReplicateCounts.minusplus_id,
RawReplicateCounts.bio_replicate_id,
RawReplicateCounts.tech_replicate_id
) \
.all()
# compile into counts
counts = {} # transcript_id => {minus_counts: ... , plus_counts: ... }
for lane in lanes:
lane_values = values_str_unpack_float(lane.values)
# initialise this transcript
if lane.transcript_id not in counts:
counts[lane.transcript_id] = {}
# set the plus or minus counts
if lane.minusplus_id not in counts[lane.transcript_id]:
counts[lane.transcript_id][lane.minusplus_id] = lane_values
else: # add to existing plus or minus counts
for pos in range(0, len(lane_values)):
counts[lane.transcript_id][lane.minusplus_id][pos] += lane_values[pos]
# insert the counts into the DB
for transcript_id in counts:
transcript_counts = counts[transcript_id]
# gotta handle the missing data gracefully
if "minus" not in transcript_counts:
minus_counts = [0] * len(transcript_counts["plus"])
else:
minus_counts = transcript_counts["minus"]
if "plus" not in transcript_counts:
plus_counts = [0] * len(transcript_counts["minus"])
else:
plus_counts = transcript_counts["plus"]
measurement_set = RawReactivities(
nucleotide_measurement_run_id=self.nucleotide_measurement_run_id,
transcript_id=transcript_id,
minus_values="\t".join(list(map(str, minus_counts))),
plus_values="\t".join(list(map(str, plus_counts)))
)
db_session.add(measurement_set)
db_session.commit()
def get_normalised(self):
# Grab sequence string
seq_str = Transcript(self.transcript_id).get_sequence_str()
# Use the ORM to grab all the normalised stuff
results = db_session \
.query(NucleotideMeasurementSet) \
.filter(
NucleotideMeasurementSet.nucleotide_measurement_run_id==self.nucleotide_measurement_run_id,
NucleotideMeasurementSet.transcript_id==self.transcript_id
) \
.all()
measurement_set = results[0]
# TODO detect whether float or int and use the correct unpacker.
# Needed for raw count values download option
unpacked = values_str_unpack_float(measurement_set.values)
# index measurements by pos
measurements = {}
for pos in range(0, len(unpacked)):
value = unpacked[pos]
measurements[pos + 1] = "NA" if value == None else value
# build the output string
buf = ""
n = 0
for n in range(0, len(seq_str)):
pos = n + 1
measurement = "NA" if pos not in measurements else measurements[pos]
buf += str(pos)+"\t"+ \
seq_str[n]+"\t"+ \
str(measurement)+"\n"
n += 1
return buf
def get_normalised(self):
# Grab sequence string
seq_str = Transcript(self.transcript_id).get_sequence_str()
# Use the ORM to grab all the normalised stuff
results = db_session \
.query(NucleotideMeasurementSet) \
.filter(
NucleotideMeasurementSet.nucleotide_measurement_run_id==self.nucleotide_measurement_run_id,
NucleotideMeasurementSet.transcript_id==self.transcript_id
) \
.all()
measurement_set = results[0]
# TODO detect whether float or int and use the correct unpacker.
# Needed for raw count values download option
unpacked = values_str_unpack_float(measurement_set.values)
# index measurements by pos
measurements = {}
for pos in range(0, len(unpacked)):
value = unpacked[pos]
measurements[pos + 1] = "NA" if value == None else value
# build the output string
buf = ""
n = 0
for n in range(0, len(seq_str)):
pos = n + 1
measurement = "NA" if pos not in measurements else measurements[pos]
buf += str(pos)+"\t"+ \
seq_str[n]+"\t"+ \
str(measurement)+"\n"
n += 1
return buf
def build_entries(self, experiment_ids):
from models import NucleotideMeasurementRun
# Load experiments
experiments = db_session \
.query(NucleotideMeasurementRun) \
.filter(NucleotideMeasurementRun.id.in_(experiment_ids)) \
.all()
# Load measurements
seq_str = str(
Transcript(self.transcript_id).get_sequence(self.strain_id).seq)
measurements_data = db_session \
.query(NucleotideMeasurementSet) \
.filter(
NucleotideMeasurementSet.nucleotide_measurement_run_id.in_(experiment_ids),
NucleotideMeasurementSet.transcript_id==self.transcript_id
) \
.all()
data = {}
# Populate experiment rows
for experiment in experiments:
experiment_data = {
"id": experiment.id,
"description": experiment.description,
"data": []
}
for n in range(len(seq_str)): # initialise the array
experiment_data["data"].append({
"position": n,
"nuc": seq_str[n],
"measurement": None
})
data[experiment.id] = experiment_data
# Add measurements to each experiment json element
# Loop since we might be dealing with > 1 measurement set
for measurement_set in measurements_data:
experiment_id = measurement_set.nucleotide_measurement_run_id
measurements = values_str_unpack_float(measurement_set.values)
for pos in range(0, len(measurements)):
measurement = measurements[pos]
data[experiment_id]["data"][pos]["measurement"] = measurement
# For each experiment, check whether there is no data and set empty flags accordingly.
self.empty = True # all empty flag
for experiment_id in data:
entry = data[experiment_id]
empty = True
for pos in entry["data"]:
if pos["measurement"] != 0 and pos["measurement"] != None:
empty = False
self.empty = False
if empty:
del entry["data"]
entry["empty"] = True
else:
entry["empty"] = False
self.data_json = json.dumps(data)
def build_entries(self, experiment_ids):
from models import NucleotideMeasurementRun
# Load experiments
experiments = db_session \
.query(NucleotideMeasurementRun) \
.filter(NucleotideMeasurementRun.id.in_(experiment_ids)) \
.all()
# Load measurements
seq_str = str(Transcript(self.transcript_id).get_sequence(self.strain_id).seq)
measurements_data = db_session \
.query(NucleotideMeasurementSet) \
.filter(
NucleotideMeasurementSet.nucleotide_measurement_run_id.in_(experiment_ids),
NucleotideMeasurementSet.transcript_id==self.transcript_id
) \
.all()
data = {}
# Populate experiment rows
for experiment in experiments:
experiment_data = {
"id": experiment.id,
"description": experiment.description,
"data": []
}
for n in range(len(seq_str)): # initialise the array
experiment_data["data"].append({
"position": n,
"nuc": seq_str[n],
"measurement": None
})
data[experiment.id] = experiment_data
# Add measurements to each experiment json element
# Loop since we might be dealing with > 1 measurement set
for measurement_set in measurements_data:
experiment_id = measurement_set.nucleotide_measurement_run_id
measurements = values_str_unpack_float(measurement_set.values)
for pos in range(0, len(measurements)):
measurement = measurements[pos]
data[experiment_id]["data"][pos]["measurement"] = measurement
# For each experiment, check whether there is no data and set empty flags accordingly.
self.empty = True # all empty flag
for experiment_id in data:
entry = data[experiment_id]
empty = True
for pos in entry["data"]:
if pos["measurement"] != 0 and pos["measurement"] != None:
empty = False
self.empty = False
if empty:
del entry["data"]
entry["empty"] = True
else:
entry["empty"] = False
self.data_json = json.dumps(data)
