def samplesheet_capture(lims, process_id, output_file):
"""Create manual pipetting samplesheet for capture protocol."""
process = Process(lims, id=process_id)
sample_count = len(process.analytes()[0])
# All input paramters
data = [
['Ampligase Buffer 10X', process.udf['Ampligase Buffer 10X']],
['MIP pool werkoplossing', process.udf['MIP pool werkoplossing']],
['*dNTP 0.25mM', process.udf['*dNTP 0.25mM']],
['Hemo Klentaq 10U/ul', process.udf['Hemo Klentaq 10U/ul']],
['Ampligase 100U/ul', process.udf['Ampligase 100U/ul']],
['Water', process.udf['Water']],
]
# Caculate for sample count
for i, item in enumerate(data):
data[i].append(sample_count * item[1] * 1.1)
# Calculate final volume
data.append([
'ul MM in elke well',
sum([item[1] for item in data]),
sum([item[2] for item in data]),
])
# Write samplesheet
output_file.write('Mastermix\t1\t{0}\n'.format(sample_count))
for item in data:
output_file.write('{0}\t{1:.2f}\t{2:.2f}\n'.format(
item[0], item[1], item[2]))
def sammplesheet_exonuclease(lims, process_id, output_file):
"""Create manual pipetting samplesheet for Exonuclease protocol"""
process = Process(lims, id=process_id)
sample_count = len(process.analytes()[0])
# All input paramters
data = [
['EXO I', process.udf['EXO I']],
['EXO III', process.udf['EXO III']],
['Ampligase buffer 10X', process.udf['Ampligase buffer 10X']],
['H2O', process.udf['H2O']],
]
# Caculate for sample count
for i, item in enumerate(data):
data[i].append(sample_count * item[1] * 1.25)
# Calculate total
data.append([
'TOTAL (incl. 25% overmaat)',
sum([item[1] for item in data]),
sum([item[2] for item in data]),
])
# Write samplesheet
output_file.write('\tMaster Mix (ul)\t{0}\n'.format(sample_count))
for item in data:
output_file.write('{0}\t{1:.2f}\t{2:.2f}\n'.format(
item[0], item[1], item[2]))
def main(lims, args):
currentStep = Process(lims, id=args.pid)
driver_file_out = None
driver = []
ar_driver = {}
valid_cols = set()
for output in currentStep.all_outputs():
if output.name == "Driver File":
driver_file_out = output
elif output.output_type == "ResultFile":
location_ar = output.location[1].split(":")
valid_cols.add(location_ar[0])
#idx = (ord(location_ar[0])-65)*12 + int(location_ar[1])-1
ar_driver[output.location[1].replace(":",
"")] = output.samples[0].name
col_idx = -1
for column in sorted(list(valid_cols)):
col_idx += 1
for i in xrange(1, 13):
location = "{}{}".format(column, i)
driver.append((col_idx * 12 + i, location,
ar_driver.get(location,
"ladder" if i == 12 else "")))
with open("frag_an_driver.csv", "w") as f:
for line in driver:
f.write("{0},{1},{2}\n".format(line[0], line[1], line[2]))
lims.upload_new_file(driver_file_out, "frag_an_driver.csv")
def copy_layout(lims, process_id):
"""Copy placement layout from previous steps."""
process = Process(lims, id=process_id)
used_placements = []
# Get parent container layout
parent_container = None
for parent_process in process.parent_processes():
if parent_process:
for container in parent_process.output_containers():
if container.type != Containertype(lims, id='2'): # skip tubes
parent_container = container
if parent_container:
parent_placements = {}
for placement in parent_container.placements:
sample = parent_container.placements[placement].samples[0].name
parent_placements[sample] = placement
# Create new container and copy layout
new_container = Container.create(lims, type=parent_container.type)
placement_list = []
for artifact in process.analytes()[0]:
sample_name = artifact.samples[0].name
if sample_name in parent_placements:
placement = parent_placements[sample_name]
if placement not in used_placements:
placement_list.append([artifact, (new_container, placement)])
used_placements.append(placement)
process.step.placements.set_placement_list(placement_list)
process.step.placements.post()
def main(lims, args, epp_logger):
pro = Process(lims, id=args.pid)
source_udf = 'Reference genome'
destination_udf = 'Reference Genome'
artifacts = pro.all_inputs(unique=True)
projects = all_projects_for_artifacts(artifacts)
correct_projects, incorrect_udf = check_udf_is_defined(
projects, source_udf)
correct_samples = filter_samples(artifacts, correct_projects)
session = Session(pro, source_udf, destination_udf)
session.copy_main(correct_samples)
if len(incorrect_udf) == 0:
warning = "no projects"
else:
warning = "WARNING: skipped {0} project(s)".format(len(incorrect_udf))
d = {'cs': len(correct_samples), 'warning': warning}
abstract = (
"Updated {cs} sample(s), {warning} with incorrect udf info.").format(
**d)
print >> sys.stderr, abstract # stderr will be logged and printed in GUI
def main(lims,args,epp_logger):
pro = Process(lims,id = args.pid)
source_udf = 'Reference genome'
destination_udf = 'Reference Genome'
artifacts = pro.all_inputs(unique=True)
projects = all_projects_for_artifacts(artifacts)
correct_projects, incorrect_udf = check_udf_is_defined(projects, source_udf)
correct_samples = filter_samples(artifacts, correct_projects)
session = Session(pro, source_udf, destination_udf)
session.copy_main(correct_samples)
if len(incorrect_udf) == 0:
warning = "no projects"
else:
warning = "WARNING: skipped {0} project(s)".format(len(incorrect_udf))
d = {'cs': len(correct_samples),
'warning' : warning
}
abstract = ("Updated {cs} sample(s), {warning} with incorrect udf info.").format(**d)
print >> sys.stderr, abstract # stderr will be logged and printed in GUI
def main(lims, pid, epp_logger):
process = Process(lims,id = pid)
target_files = dict((r.samples[0].name, r) for r in process.result_files())
file_handler = ReadResultFiles(process)
QiT = QuantitConc(process, file_handler)
QiT.fit_model()
QiT.prepare_result_files_dict()
if QiT.model and 'Linearity of standards' in QiT.udfs.keys():
R2 = QiT.model[0]
if R2 >= QiT.udfs['Linearity of standards']:
QiT.abstract.insert(0,"R2 = {0}. Standards OK.".format(R2))
if QiT.result_files:
for sample, target_file in target_files.items():
rel_fluor_int = QiT.get_and_set_fluor_int(target_file)
QiT.calc_and_set_conc(target_file, rel_fluor_int)
QiT.abstract.append("Concentrations uploaded for {0} "
"samples.".format(QiT.no_samps))
else:
QiT.abstract.append("Upload input file(s) for samples.")
else:
QiT.abstract.insert(0, "R2 = {0}. Problem with standards! Redo "
"measurement!".format(R2))
else:
QiT.missing_udfs.append('Linearity of standards')
if QiT.missing_samps:
QiT.abstract.append("The following samples are missing in Quant-iT "
"result File 1 or 2: {0}.".format(', '.join(QiT.missing_samps)))
if QiT.missing_udfs:
QiT.abstract.append("Are all of the following udfs set? : {0}".format(
', '.join(QiT.missing_udfs)))
print >> sys.stderr, ' '.join(QiT.abstract)
def samplesheet_pool_samples(lims, process_id, output_file):
"""Create manual pipetting samplesheet for pooling samples."""
process = Process(lims, id=process_id)
# print header
output_file.write('Sample\tContainer\tWell\tPool\n')
# Get all input artifact and store per container
input_containers = {}
for input_artifact in process.all_inputs(resolve=True):
container = input_artifact.location[0].name
well = ''.join(input_artifact.location[1].split(':'))
if container not in input_containers:
input_containers[container] = {}
input_containers[container][well] = input_artifact
# print pool scheme per input artifact
# sort on container and well
for input_container in sorted(input_containers.keys()):
input_artifacts = input_containers[input_container]
for well in clarity_epp.export.utils.sort_96_well_plate(
input_artifacts.keys()):
output_file.write('{sample}\t{container}\t{well}\t{pool}\n'.format(
sample=input_artifacts[well].name,
container=input_artifacts[well].location[0].name,
well=well,
pool=process.outputs_per_input(input_artifacts[well].id,
Analyte=True)[0].name))
def sequencing_run(lims, email_settings, process_id):
process = Process(lims, id=process_id)
artifact = process.all_inputs()[0]
subject = "LIMS QC Controle - {0}".format(artifact.name)
message = "Sequencing Run: {0}\n".format(artifact.name)
message += "Technician: {0}\n".format(process.technician.name)
message += "LIMS Next Action: {0}\n\n".format(
process.step.actions.next_actions[0]['action'])
message += "UDF - Conversie rapport OK?: {0}\n".format(
process.udf['Conversie rapport OK?'])
if 'Fouten registratie (uitleg)' in process.udf:
message += "UDF - Fouten registratie (uitleg): {0}\n".format(
process.udf['Fouten registratie (uitleg)'])
if 'Fouten registratie (oorzaak)' in process.udf:
message += "UDF - Fouten registratie (oorzaak): {0}\n".format(
process.udf['Fouten registratie (uitleg)'])
if process.step.actions.escalation:
message += "\nManager Review LIMS:\n"
message += "{0}: {1}\n".format(
process.step.actions.escalation['author'].name,
process.step.actions.escalation['request'])
message += "{0}: {1}\n".format(
process.step.actions.escalation['reviewer'].name,
process.step.actions.escalation['answer'])
send_email(email_settings['server'], email_settings['from'],
email_settings['to_sequencing_run_complete'], subject, message)
def main(args, lims, epp_logger):
p = Process(lims, id=args.pid)
lines = []
cs = []
if args.container_id:
cs = p.output_containers()
for c in cs:
logging.info('Constructing barcode for container {0}.'.format(
c.id))
lines += makeContainerBarcode(c.id, copies=1)
if args.container_name:
cs = p.output_containers()
for c in cs:
logging.info('Constructing name label for container {0}.'.format(
c.id))
lines += makeContainerNameBarcode(c.name, copies=1)
if args.operator_and_date:
op = p.technician.name
date = str(datetime.date.today())
if cs: # list of containers
copies = len(cs)
else:
copies = args.copies
lines += makeOperatorAndDateBarcode(op, date, copies=copies)
if args.process_name:
pn = p.type.name
if cs: # list of containers
copies = len(cs)
else:
copies = args.copies
lines += makeProcessNameBarcode(pn, copies=copies)
if not (args.container_id or args.container_name or args.operator_and_date
or args.process_name):
logging.info('No recognized label type given, exiting.')
sys.exit(-1)
if not args.use_printer:
logging.info('Writing to stdout.')
epp_logger.saved_stdout.write('\n'.join(lines) + '\n')
elif lines: # Avoid printing empty files
lp_args = ["lp"]
if args.hostname:
#remove that when all the calls to this script have been updated
if args.hostname == 'homer.scilifelab.se:631':
args.hostname = 'homer2.scilifelab.se:631'
lp_args += ["-h", args.hostname]
if args.destination:
lp_args += ["-d", args.destination]
lp_args.append("-") # lp accepts stdin if '-' is given as filename
logging.info('Ready to call lp for printing.')
sp = subprocess.Popen(lp_args,
stdin=subprocess.PIPE,
stdout=subprocess.PIPE,
stderr=subprocess.PIPE)
sp.stdin.write(str('\n'.join(lines)))
logging.info('lp command is called for printing.')
stdout, stderr = sp.communicate() # Will wait for sp to finish
logging.info('lp stdout: {0}'.format(stdout))
logging.info('lp stderr: {0}'.format(stderr))
logging.info('lp command finished')
sp.stdin.close()
def main(lims, args, epp_logger):
p = Process(lims, id=args.pid)
udf_check = "Conc. Units"
value_check = "ng/ul"
concentration_udf = "Concentration"
size_udf = "Size (bp)"
if args.aggregate:
artifacts = p.all_inputs(unique=True)
else:
all_artifacts = p.all_outputs(unique=True)
artifacts = filter(lambda a: a.output_type == "ResultFile", all_artifacts)
correct_artifacts, no_concentration = check_udf_is_defined(artifacts, concentration_udf)
correct_artifacts, no_size = check_udf_is_defined(correct_artifacts, size_udf)
correct_artifacts, wrong_value = check_udf_has_value(correct_artifacts, udf_check, value_check)
apply_calculations(lims, correct_artifacts, concentration_udf, size_udf, udf_check, epp_logger)
d = {"ca": len(correct_artifacts), "ia": len(wrong_value) + len(no_size) + len(no_concentration)}
abstract = (
"Updated {ca} artifact(s), skipped {ia} artifact(s) with " "wrong and/or blank values for some udfs."
).format(**d)
print >>sys.stderr, abstract # stderr will be logged and printed in GUI
def main(lims, args, epp_logger):
p = Process(lims, id=args.pid)
udf_check = 'Conc. Units'
value_check = 'ng/ul'
concentration_udf = 'Concentration'
size_udf = 'Size (bp)'
if args.aggregate:
artifacts = p.all_inputs(unique=True)
else:
all_artifacts = p.all_outputs(unique=True)
artifacts = filter(lambda a: a.output_type == "ResultFile",
all_artifacts)
correct_artifacts, no_concentration = check_udf_is_defined(
artifacts, concentration_udf)
correct_artifacts, no_size = check_udf_is_defined(correct_artifacts,
size_udf)
correct_artifacts, wrong_value = check_udf_has_value(
correct_artifacts, udf_check, value_check)
apply_calculations(lims, correct_artifacts, concentration_udf, size_udf,
udf_check, epp_logger)
d = {
'ca': len(correct_artifacts),
'ia': len(wrong_value) + len(no_size) + len(no_concentration)
}
abstract = ("Updated {ca} artifact(s), skipped {ia} artifact(s) with "
"wrong and/or blank values for some udfs.").format(**d)
print >> sys.stderr, abstract # stderr will be logged and printed in GUI
def set_sequence_name(lims, process_id):
"""Change artifact name to sequnece name."""
process = Process(lims, id=process_id)
for artifact in process.analytes()[0]:
sample = artifact.samples[0]
artifact.name = get_sequence_name(sample)
artifact.put()
def samplesheet_dilute_library_pool(lims, process_id, output_file):
"""Create manual pipetting samplesheet for sequencing pools."""
output_file.write('Sample\tContainer\tWell\tul Sample\tul EB\n')
process = Process(lims, id=process_id)
output = [] # save pool data to list, to be able to sort on pool number.
nM_pool = process.udf['Dx Pool verdunning (nM)']
output_ul = process.udf['Eindvolume (ul)']
for input in process.all_inputs():
search_number = re.search(r'Pool #(\d+)_', input.name)
if search_number:
input_number = int(search_number.group(1))
else:
input_number = 0
qc_artifact = input.input_artifact_list()[0]
size = float(qc_artifact.udf['Dx Fragmentlengte (bp)'])
concentration = float(
qc_artifact.udf['Dx Concentratie fluorescentie (ng/ul)'])
nM_dna = (concentration * 1000 * (1 / 660.0) * (1 / size)) * 1000
ul_sample = (nM_pool / nM_dna) * output_ul
ul_EB = output_ul - ul_sample
line = '{pool_name}\t{container}\t{well}\t{ul_sample:.2f}\t{ul_EB:.2f}\n'.format(
pool_name=input.name,
container=input.location[0].name,
well=input.location[1],
ul_sample=ul_sample,
ul_EB=ul_EB)
output.append((input_number, line))
for number, line in sorted(output):
output_file.write(line)
def main(lims, pid, epp_logger):
process = Process(lims, id=pid)
QiT = QuantitQC(process)
QiT.assign_QC_flag()
if QiT.flour_int_missing:
QiT.abstract.append("Fluorescence intensity is missing for {0} "
"samples.".format(QiT.flour_int_missing))
if QiT.missing_udfs:
QiT.abstract.append("Could not set QC flags. Some of the following "
"required udfs seems to be missing: {0}.".format(
QiT.missing_udfs))
else:
QiT.abstract.append("{0} out of {1} samples failed "
"QC.".format(QiT.no_failed,
len(process.result_files())))
if QiT.saturated:
QiT.abstract.append("{0} samples had saturated fluorescence "
"intensity.".format(QiT.saturated))
if QiT.hig_CV_fract:
QiT.abstract.append("{0} samples had high %CV.".format(
QiT.hig_CV_fract))
if QiT.low_conc:
QiT.abstract.append("{0} samples had low concentration.".format(
QiT.low_conc))
if QiT.conc_missing:
QiT.abstract.append("Concentration is missing for {0} "
"sample(s).".format(QiT.conc_missing))
QiT.abstract = list(set(QiT.abstract))
print >> sys.stderr, ' '.join(QiT.abstract)
def sammplesheet_pcr_exonuclease(lims, process_id, output_file):
"""Create manual pipetting samplesheet for PCR after Exonuclease protocol"""
process = Process(lims, id=process_id)
sample_count = len(process.analytes()[0])
# All input paramters
data = [
['2X iProof', process.udf['2X iProof']],
[
'Illumina forward primer(100uM) MIP_OLD_BB_FOR',
process.udf['Illumina forward primer(100uM) MIP_OLD_BB_FOR']
],
['H2O', process.udf['H2O']],
]
# Caculate for sample count
for i, item in enumerate(data):
data[i].append(sample_count * item[1] * 1.1)
# Calculate total
data.append([
'TOTAL (incl. 10% overmaat)',
sum([item[1] for item in data]) * 1.1,
sum([item[2] for item in data]),
])
# Write samplesheet
output_file.write('\tMaster Mix (ul)\t{0}\n'.format(sample_count))
for item in data:
output_file.write('{0}\t{1:.2f}\t{2:.2f}\n'.format(
item[0], item[1], item[2]))
def main(lims,args,epp_logger):
p = Process(lims,id = args.pid)
udf_factor1 = 'Concentration (ng/ul)'
result_udf = 'Concentration nM'
udf_factor2 = 'Size (bp)'
if args.aggregate:
artifacts = p.all_inputs(unique=True)
else:
all_artifacts = p.all_outputs(unique=True)
artifacts = filter(lambda a: a.output_type == "Analyte", all_artifacts)
# print rrtifacts
correct_artifacts, wrong_factor1 = check_udf_is_defined(artifacts, udf_factor1)
correct_artifacts, wrong_factor2 = check_udf_is_defined(correct_artifacts, udf_factor2)
f = open(args.res, "a")
if correct_artifacts:
apply_calculations(lims, correct_artifacts, udf_factor1,
udf_factor2, result_udf, epp_logger, f)
f.close()
d = {'ca': len(correct_artifacts),
'ia': len(wrong_factor1)+ len(wrong_factor2) }
abstract = ("Updated {ca} artifact(s), skipped {ia} artifact(s) with "
"wrong and/or blank values for some udfs.").format(**d)
print >> sys.stderr, abstract # stderr will be logged and printed in GUI
def results(lims, process_id):
"""Upload bioanalyzer results to artifacts."""
process = Process(lims, id=process_id)
sample_measurements = {}
# Parse File
for output in process.all_outputs(unique=True):
if output.name == 'Bioanalyzer Output':
bioanalyzer_result_file = output.files[0]
for line in lims.get_file_contents(
bioanalyzer_result_file.id).split('\n'):
if line.startswith('Sample Name'):
sample = line.rstrip().split(',')[1]
elif line.startswith('Region 1'):
line = re.sub(
r'"([0-9]+),([0-9\.]+)"', r'\1\2', line
) # Fix remove thousands seperator (,) and quotes ("")
size = line.rstrip().split(',')[5]
sample_measurements[sample] = int(size)
# Set UDF
for artifact in process.all_outputs():
if artifact.name in sample_measurements:
artifact.udf['Dx Fragmentlengte (bp)'] = sample_measurements[
artifact.name]
artifact.put()
def main(lims, args, epp_logger):
p = Process(lims, id=args.pid)
udf_check = "Conc. Units"
value_check = "ng/ul"
udf_factor1 = "Concentration"
udf_factor2 = "Volume (ul)"
result_udf = "Amount (ng)"
if args.aggregate:
artifacts = p.all_inputs(unique=True)
else:
all_artifacts = p.all_outputs(unique=True)
artifacts = filter(lambda a: a.output_type == "ResultFile", all_artifacts)
correct_artifacts, wrong_factor1 = check_udf_is_defined(artifacts, udf_factor1)
correct_artifacts, wrong_factor2 = check_udf_is_defined(correct_artifacts, udf_factor2)
correct_artifacts, wrong_value = check_udf_has_value(correct_artifacts, udf_check, value_check)
if correct_artifacts:
apply_calculations(lims, correct_artifacts, udf_factor1, "*", udf_factor2, result_udf, epp_logger, p)
d = {"ca": len(correct_artifacts), "ia": len(wrong_factor1) + len(wrong_factor2) + len(wrong_value)}
abstract = (
"Updated {ca} artifact(s), skipped {ia} artifact(s) with " "wrong and/or blank values for some udfs."
).format(**d)
print >>sys.stderr, abstract # stderr will be logged and printed in GUI
def main(lims, pid, epp_logger):
process = Process(lims,id = pid)
QiT = QuantitQC(process)
QiT.assign_QC_flag()
if QiT.flour_int_missing:
QiT.abstract.append("Fluorescence intensity is missing for {0} "
"samples.".format(QiT.flour_int_missing))
if QiT.missing_udfs:
QiT.abstract.append("Could not set QC flags. Some of the following "
"required udfs seems to be missing: {0}.".format(QiT.missing_udfs))
else:
QiT.abstract.append("{0} out of {1} samples failed "
"QC.".format(QiT.no_failed, len(process.result_files())))
if QiT.saturated:
QiT.abstract.append("{0} samples had saturated fluorescence "
"intensity.".format(QiT.saturated))
if QiT.hig_CV_fract:
QiT.abstract.append("{0} samples had high %CV.".format(QiT.hig_CV_fract))
if QiT.low_conc:
QiT.abstract.append("{0} samples had low concentration.".format(
QiT.low_conc))
if QiT.conc_missing:
QiT.abstract.append("Concentration is missing for {0} "
"sample(s).".format(QiT.conc_missing))
QiT.abstract = list(set(QiT.abstract))
print >> sys.stderr, ' '.join(QiT.abstract)
def main(lims, pid, epp_logger):
process = Process(lims, id=pid)
target_files = dict((r.samples[0].name, r) for r in process.result_files())
file_handler = ReadResultFiles(process)
QiT = QuantitConc(process, file_handler)
QiT.fit_model()
QiT.prepare_result_files_dict()
if QiT.model and 'Linearity of standards' in QiT.udfs.keys():
R2 = QiT.model[0]
if R2 >= QiT.udfs['Linearity of standards']:
QiT.abstract.insert(0, "R2 = {0}. Standards OK.".format(R2))
if QiT.result_files:
for sample, target_file in target_files.items():
rel_fluor_int = QiT.get_and_set_fluor_int(target_file)
QiT.calc_and_set_conc(target_file, rel_fluor_int)
QiT.abstract.append("Concentrations uploaded for {0} "
"samples.".format(QiT.no_samps))
else:
QiT.abstract.append("Upload input file(s) for samples.")
else:
QiT.abstract.insert(
0, "R2 = {0}. Problem with standards! Redo "
"measurement!".format(R2))
else:
QiT.missing_udfs.append('Linearity of standards')
if QiT.missing_samps:
QiT.abstract.append("The following samples are missing in Quant-iT "
"result File 1 or 2: {0}.".format(', '.join(
QiT.missing_samps)))
if QiT.missing_udfs:
QiT.abstract.append("Are all of the following udfs set? : {0}".format(
', '.join(QiT.missing_udfs)))
print >> sys.stderr, ' '.join(QiT.abstract)
def results(lims, process_id):
"""Upload tapestation results to artifacts."""
process = Process(lims, id=process_id)
sample_size_measurements = {}
sample_concentration_measurements = {}
# Parse File
for output in process.all_outputs(unique=True):
if output.name == 'TapeStation Output':
tapestation_result_file = output.files[0]
for line in lims.get_file_contents(
tapestation_result_file.id).split('\n'):
if line.startswith('FileName'):
header = line.split(',')
if 'Size [bp]' in header: # Tapestation compact peak table
size_index = header.index('Size [bp]')
concentration_index = None
else: # Tapestation compact region table
size_index = header.index('Average Size [bp]')
try:
concentration_index = header.index(
u'Conc. [pg/\xb5l]') # micro sign
concentration_correction = 1000 # Used to transform pg/ul to ng/ul
except ValueError:
concentration_index = header.index(
u'Conc. [ng/\xb5l]') # micro sign
concentration_correction = 1
sample_index = header.index('Sample Description')
elif line:
data = line.split(',')
sample = data[sample_index]
if sample != 'Ladder':
if data[size_index]:
size = int(data[size_index])
sample_size_measurements[sample] = size
if concentration_index and data[concentration_index]:
# Correct concentration
concentration = float(data[concentration_index]
) / concentration_correction
sample_concentration_measurements[
sample] = concentration
# Set UDF
for artifact in process.all_outputs():
if artifact.name not in [
'TapeStation Output', 'TapeStation Samplesheet',
'TapeStation Sampleplots PDF'
]:
sample_name = artifact.name.split('_')[0]
if sample_name in sample_size_measurements:
artifact.udf[
'Dx Fragmentlengte (bp)'] = sample_size_measurements[
sample_name]
if sample_name in sample_concentration_measurements:
artifact.udf[
'Dx Concentratie fluorescentie (ng/ul)'] = sample_concentration_measurements[
sample_name]
artifact.put()
def main(lims, args):
p = Process(lims, id=args.pid)
log = []
datamap = {}
wsname = None
username = "******".format(p.technician.first_name,
p.technician.last_name)
user_email = p.technician.email
for art in p.all_inputs():
if len(art.samples) != 1:
log.append(
"Warning : artifact {0} has more than one sample".format(
art.id))
for sample in art.samples:
#take care of lamda DNA
if sample.project:
if sample.project.id not in datamap:
datamap[sample.project.id] = [sample.name]
else:
datamap[sample.project.id].append(sample.name)
for art in p.all_outputs():
try:
wsname = art.location[0].name
break
except:
pass
now = datetime.now().strftime("%Y-%m-%d %H:%M:%S.%f")
for pid in datamap:
pj = Project(lims, id=pid)
if len(datamap[pid]) > 1:
rnt = "{0} samples planned for {1}".format(len(datamap[pid]),
wsname)
else:
rnt = "{0} sample planned for {1}".format(len(datamap[pid]),
wsname)
running_note = {
"note": rnt,
"user": username,
"email": user_email,
"category": "Workset"
}
write_note_to_couch(pid, now, running_note, lims.get_uri())
log.append(
"Updated project {0} : {1}, {2} samples in this workset".format(
pid, pj.name, len(datamap[pid])))
with open("EPP_Notes.log", "w") as flog:
flog.write("\n".join(log))
for out in p.all_outputs():
#attach the log file
if out.name == "RNotes Log":
attach_file(os.path.join(os.getcwd(), "EPP_Notes.log"), out)
sys.stderr.write("Updated {0} projects successfully".format(
len(list(datamap.keys()))))
def main(args,lims,epp_logger):
p = Process(lims,id=args.pid)
lines = []
cs = []
if args.container_id:
cs = p.output_containers()
for c in cs:
logging.info('Constructing barcode for container {0}.'.format(c.id))
lines += makeContainerBarcode(c.id, copies=1)
if args.container_name:
cs = p.output_containers()
for c in cs:
logging.info('Constructing name label for container {0}.'.format(c.id))
lines += makeContainerNameBarcode(c.name,copies=1)
if args.operator_and_date:
op = p.technician.name
date = str(datetime.date.today())
if cs: # list of containers
copies = len(cs)
else:
copies = args.copies
lines += makeOperatorAndDateBarcode(op,date,copies=copies)
if args.process_name:
pn = p.type.name
if cs: # list of containers
copies = len(cs)
else:
copies = args.copies
lines += makeProcessNameBarcode(pn,copies=copies)
if not (args.container_id or args.container_name or
args.operator_and_date or args.process_name):
logging.info('No recognized label type given, exiting.')
sys.exit(-1)
if not args.use_printer:
logging.info('Writing to stdout.')
epp_logger.saved_stdout.write('\n'.join(lines)+'\n')
elif lines: # Avoid printing empty files
lp_args = ["lp"]
if args.hostname:
#remove that when all the calls to this script have been updated
if args.hostname == 'homer.scilifelab.se:631':
args.hostname='homer2.scilifelab.se:631'
lp_args += ["-h",args.hostname]
if args.destination:
lp_args += ["-d",args.destination]
lp_args.append("-") # lp accepts stdin if '-' is given as filename
logging.info('Ready to call lp for printing.')
sp = subprocess.Popen(lp_args,
stdin=subprocess.PIPE,
stdout=subprocess.PIPE,
stderr=subprocess.PIPE)
sp.stdin.write(str('\n'.join(lines)))
logging.info('lp command is called for printing.')
stdout,stderr = sp.communicate() # Will wait for sp to finish
logging.info('lp stdout: {0}'.format(stdout))
logging.info('lp stderr: {0}'.format(stderr))
logging.info('lp command finished')
sp.stdin.close()
def main(lims, args):
process = Process(lims, id=args.pid)
artifacts = process.all_outputs()
updated_arts = 0
for art in artifacts:
updated_arts += get_buffer(art, args.process_types)
print >> sys.stderr, 'Updated ' + str(
updated_arts) + ' samples with volume from Buffer step.'
def main(lims, args):
process = Process(lims, id=args.p)
duplicates = get_duplicate_samples(process.all_inputs())
if duplicates:
sys.exit('Samples: ' + ', '.join(duplicates) +
' appeared more than once in this step.')
else:
print >> sys.stderr, 'No duplicated samples!'
def storage_location(lims, process_id, output_file):
"""Generate storage location label file."""
process = Process(lims, id=process_id)
for artifact in process.analytes()[0]:
storage_location = artifact.samples[0].udf['Dx Opslaglocatie']
output_file.write(
'{sample}\t{storage_location}\t{birth_date}\n'.format(
sample=artifact.samples[0].name,
storage_location=storage_location,
birth_date=artifact.samples[0].udf['Dx Geboortejaar']))
def get(self, workset):
self.set_header("Content-type", "application/json")
p = Process(self.lims, id=workset)
p.get(force=True)
# Sorted running notes, by date
workset_notes = json.loads(p.udf['Workset Notes']) if 'Workset Notes' in p.udf else {}
sorted_workset_notes = OrderedDict()
for k, v in sorted(workset_notes.items(), key=lambda t: t[0], reverse=True):
sorted_workset_notes[k] = v
self.write(sorted_workset_notes)
def __init__(self, lims, pid, inp_is_source):
self.lims = lims
self.source_is_input_artifact = inp_is_source
self.process = Process(lims, id=pid)
self.input_output_maps = self.process.input_output_maps
self.artifacts = {}
self.failed_arts = False
self.passed_arts = 0
self.all_arts = 0
self.result_file = None
def get(self, workset):
self.set_header("Content-type", "application/json")
p = Process(self.lims, id=workset)
p.get(force=True)
# Sorted running notes, by date
workset_notes = json.loads(p.udf['Workset Notes']) if 'Workset Notes' in p.udf else {}
sorted_workset_notes = OrderedDict()
for k, v in sorted(workset_notes.iteritems(), key=lambda t: t[0], reverse=True):
sorted_workset_notes[k] = v
self.write(sorted_workset_notes)
def main(args):
log = []
lims = Lims(BASEURI, USERNAME, PASSWORD)
process = Process(lims, id=args.pid)
for io in process.input_output_maps:
if io[1]['output-generation-type'] != 'PerInput':
continue
try:
starting_amount = obtain_amount(io[0]['uri'])
except Exception as e:
log.append(str(e))
starting_amount = 0
log.append("Starting amount of {} : {} ng".format(
io[0]['uri'].samples[0].name, starting_amount))
current_amount = starting_amount
#preps
preps = lims.get_processes(
inputartifactlimsid=io[0]['uri'].id,
type=["Setup Workset/Plate", "Amount confirmation QC"])
for pro in preps:
if pro.id == args.pid:
continue # skip the current step
for prepio in pro.input_output_maps:
if prepio[1]['output-generation-type'] == 'PerInput' and prepio[
0]['uri'].id == io[0]['uri'].id:
if "Amount taken (ng)" in prepio[1][
'uri'].udf: #should always be true
prep_amount = prepio[1]['uri'].udf["Amount taken (ng)"]
log.append(
"Removing {} ng for prep {} for sample {}".format(
prep_amount, pro.id,
io[0]['uri'].samples[0].name))
current_amount = current_amount - prep_amount
else:
log.append(
"No Amount Taken found for prep {} of sample {}".
format(pro.id, io[0]['uri'].samples[0].name))
if current_amount < 0:
log.append(
"Estimated amount for sample {} is {}, correcting to zero".
format(io[0]['uri'].samples[0].name, current_amount))
current_amount = 0
update_output_values(io[0]['uri'], io[1]['uri'], current_amount)
with open("amount_check_log.txt", "w") as f:
f.write("\n".join(log))
for out in process.all_outputs():
if out.name == "QC Assignment Log File":
for f in out.files:
lims.request_session.delete(f.uri)
lims.upload_new_file(out, "amount_check_log.txt")
def unpooling(lims, process_id):
"""Unpool samples after sequencing."""
process = Process(lims, id=process_id)
pool_artifact = process.all_inputs()[0]
pool_artifact_parent_process = pool_artifact.parent_process
pool_artifact_demux = lims.get(pool_artifact.uri + '/demux')
run_id = pool_artifact.name # Assume run id is set as pool name using placement/artifact/set_runid_name
sample_artifacts = [] # sample artifacts before pooling
sample_projects = {}
for artifact in pool_artifact_parent_process.result_files():
if (artifact.name == 'SampleSheet csv'
or artifact.name == 'Sample Sheet') and artifact.files:
file_id = artifact.files[0].id
sample_sheet = lims.get_file_contents(id=file_id)
project_index = None
sample_index = None
for line in sample_sheet.split('\n'):
data = line.rstrip().split(',')
if 'Sample_Project' in data and 'Sample_ID' in data:
project_index = data.index('Sample_Project')
sample_index = data.index('Sample_ID')
elif project_index and len(data) >= project_index:
sample_projects[data[sample_index]] = data[project_index]
for node in pool_artifact_demux.getiterator('artifact'):
if node.find('samples'):
if len(node.find('samples').findall('sample')) == 1:
sample_artifact = Artifact(lims, uri=node.attrib['uri'])
sample = sample_artifact.samples[0] # 1 sample per artifact.
# Get sample sequencing run and project from samplesheet
sample_artifact.udf['Dx Sequencing Run ID'] = run_id
if 'Sample Type' in sample.udf and 'library' in sample.udf[
'Sample Type']: # Use sample.name for external (clarity_portal) samples
sample_artifact.udf[
'Dx Sequencing Run Project'] = sample_projects[
sample.name]
else: # Use sample_artifact.name for Dx samples (upload via Helix)
sample_artifact.udf[
'Dx Sequencing Run Project'] = sample_projects[
sample_artifact.name]
sample_artifact.put()
if sample_artifact.samples[
0].project and sample_artifact.samples[0].project.udf[
'Application'] == 'DX': # Only move DX production samples to post sequencing workflow
sample_artifacts.append(sample_artifact)
lims.route_artifacts(sample_artifacts,
workflow_uri=Workflow(
lims, id=config.post_sequencing_workflow).uri)
def main(lims, pid, epp_logger):
process = Process(lims,id = pid)
sample_names = map(lambda a: a.name, process.analytes()[0])
target_files = process.result_files()
file_handler = ReadResultFiles(process)
files = file_handler.shared_files['Qubit Result File']
qubit_result_file = file_handler.format_file(files,
name = 'Qubit Result File',
first_header = 'Sample',
find_keys = sample_names)
missing_samples = 0
low_conc = 0
bad_formated = 0
abstract = []
udfs = dict(process.udf.items())
if udfs.has_key("Minimum required concentration (ng/ul)"):
min_conc = udfs["Minimum required concentration (ng/ul)"]
else:
min_conc = None
abstract.append("Set 'Minimum required concentration (ng/ul)' to get qc-flaggs based on this treshold!")
for target_file in target_files:
sample = target_file.samples[0].name
if qubit_result_file.has_key(sample):
sample_mesurements = qubit_result_file[sample]
if "Sample Concentration" in sample_mesurements.keys():
conc, unit = sample_mesurements["Sample Concentration"]
if conc == 'Out Of Range':
target_file.qc_flag = "FAILED"
elif conc.replace('.','').isdigit():
conc = float(conc)
if unit == 'ng/mL':
conc = np.true_divide(conc, 1000)
if min_conc:
if conc < min_conc:
target_file.qc_flag = "FAILED"
low_conc +=1
else:
target_file.qc_flag = "PASSED"
target_file.udf['Concentration'] = conc
target_file.udf['Conc. Units'] = 'ng/ul'
else:
bad_formated += 1
set_field(target_file)
else:
missing_samples += 1
if low_conc:
abstract.append('{0}/{1} samples have low concentration.'.format(low_conc, len(target_files)))
if missing_samples:
abstract.append('{0}/{1} samples are missing in Qubit Result File.'.format(missing_samples, len(target_files)))
if bad_formated:
abstract.append('There are {0} badly formated samples in Qubit Result File. Please fix these to get proper results.'.format(bad_formated))
print >> sys.stderr, ' '.join(abstract)
def samplesheet_normalization(lims, process_id, output_file):
"""Create manual pipetting samplesheet for normalizing (MIP) samples."""
output_file.write(
'Sample\tConcentration (ng/ul)\tVolume sample (ul)\tVolume water (ul)\tOutput (ng)\tIndampen\n'
)
process = Process(lims, id=process_id)
# Find all QC process types
qc_process_types = clarity_epp.export.utils.get_process_types(
lims, ['Dx Qubit QC', 'Dx Tecan Spark 10M QC'])
for input_artifact in process.all_inputs(resolve=True):
artifact = process.outputs_per_input(
input_artifact.id,
Analyte=True)[0] # assume one artifact per input
sample = input_artifact.samples[
0] # asume one sample per input artifact
# Find last qc process for artifact
qc_process = sorted(
lims.get_processes(type=qc_process_types,
inputartifactlimsid=input_artifact.id),
key=lambda process: int(process.id.split('-')[-1]))[-1]
# Find concentration measurement
for qc_artifact in qc_process.outputs_per_input(input_artifact.id):
if qc_artifact.name.split(' ')[0] == artifact.name:
concentration = float(
qc_artifact.udf['Dx Concentratie fluorescentie (ng/ul)'])
final_volume = float(artifact.udf['Dx Eindvolume (ul)'])
input_ng = float(artifact.udf['Dx Input (ng)'])
if 'Dx pipetteervolume (ul)' in artifact.udf:
input_ng = concentration * float(
artifact.udf['Dx pipetteervolume (ul)'])
sample_volume = input_ng / concentration
water_volume = final_volume - sample_volume
evaporate = 'N'
if sample_volume < 0.5:
sample_volume = 0.5
water_volume = final_volume - sample_volume
elif sample_volume > final_volume:
evaporate = 'J'
water_volume = 0
output_file.write(
'{sample}\t{concentration:.1f}\t{sample_volume:.1f}\t{water_volume:.1f}\t{output:.1f}\t{evaporate}\n'
.format(sample=sample.name,
concentration=concentration,
sample_volume=sample_volume,
water_volume=water_volume,
output=input_ng,
evaporate=evaporate))
def old_main(lims, pid, epp_logger):
process = Process(lims,id = pid)
sample_names = map(lambda a: a.name, process.analytes()[0])
target_files = process.result_files()
file_handler = ReadResultFiles(process)
files = file_handler.shared_files['Qubit Result File']
qubit_result_file = file_handler.format_file(files,
name = 'Qubit Result File',
first_header = ['Test','Sample'],
find_keys = sample_names)
missing_samples = 0
low_conc = 0
bad_formated = 0
abstract = []
udfs = dict(process.udf.items())
if udfs.has_key("Minimum required concentration (ng/ul)"):
min_conc = udfs["Minimum required concentration (ng/ul)"]
else:
min_conc = None
abstract.append("Set 'Minimum required concentration (ng/ul)' to get qc-flaggs based on this treshold!")
for target_file in target_files:
sample = target_file.samples[0].name
if qubit_result_file.has_key(sample):
sample_mesurements = qubit_result_file[sample]
if "Sample Concentration" in sample_mesurements.keys():
conc, unit = sample_mesurements["Sample Concentration"]
if conc == 'Out Of Range':
target_file.qc_flag = "FAILED"
elif conc.replace('.','').isdigit():
conc = float(conc)
if unit == 'ng/mL':
conc = np.true_divide(conc, 1000)
if min_conc:
if conc < min_conc:
target_file.qc_flag = "FAILED"
low_conc +=1
else:
target_file.qc_flag = "PASSED"
target_file.udf['Concentration'] = conc
target_file.udf['Conc. Units'] = 'ng/ul'
else:
bad_formated += 1
set_field(target_file)
else:
missing_samples += 1
if low_conc:
abstract.append('{0}/{1} samples have low concentration.'.format(low_conc, len(target_files)))
if missing_samples:
abstract.append('{0}/{1} samples are missing in Qubit Result File.'.format(missing_samples, len(target_files)))
if bad_formated:
abstract.append('There are {0} badly formated samples in Qubit Result File. Please fix these to get proper results.'.format(bad_formated))
print >> sys.stderr, ' '.join(abstract)
def samplesheet(lims, process_id, output_file):
"""Create Tapestation samplesheet."""
process = Process(lims, id=process_id)
well_plate = {}
for placement, artifact in process.output_containers(
)[0].placements.iteritems():
placement = ''.join(placement.split(':'))
well_plate[placement] = artifact.name.split('_')[0]
for well in clarity_epp.export.utils.sort_96_well_plate(well_plate.keys()):
output_file.write('{sample}\n'.format(sample=well_plate[well]))
def main(lims, args, epp_logger):
source_udfs = args.source_udf
dest_udfs = args.dest_udf
correct_artifacts = 0
incorrect_artifacts = 0
no_updated = 0
p = Process(lims, id=args.pid)
artifacts, inf = p.analytes()
if args.status_changelog:
epp_logger.prepend_old_log(args.status_changelog)
if not dest_udfs:
dest_udfs = source_udfs
elif len(dest_udfs) != len(source_udfs):
logging.error(
"source_udfs and dest_udfs lists of arguments are uneven.")
sys.exit(-1)
for i in range(len(source_udfs)):
source_udf = source_udfs[i]
dest_udf = dest_udfs[i]
with open(args.status_changelog, 'a') as changelog_f:
for artifact in artifacts:
if source_udf in artifact.udf:
correct_artifacts = correct_artifacts + 1
copy_sesion = CopyField(artifact, artifact.samples[0],
source_udf, dest_udf)
test = copy_sesion.copy_udf(changelog_f)
if test:
no_updated = no_updated + 1
else:
incorrect_artifacts = incorrect_artifacts + 1
logging.warning(("Found artifact for sample {0} with {1} "
"undefined/blank, exiting").format(
artifact.samples[0].name, source_udf))
if incorrect_artifacts == 0:
warning = "no artifacts"
else:
warning = "WARNING: skipped {0} udfs(s)".format(incorrect_artifacts)
d = {
'ua': no_updated,
'ca': correct_artifacts,
'ia': incorrect_artifacts,
'warning': warning
}
abstract = ("Updated {ua} udf(s), out of {ca} in total, "
"{warning} with incorrect udf info.").format(**d)
print(abstract,
file=sys.stderr) # stderr will be logged and printed in GUI
def main(lims, args, epp_logger):
d_elts = []
no_updated = 0
incorrect_udfs = 0
project_names = ''
source_udfs = args.source_udf
dest_udfs = args.dest_udf
s_elt = Process(lims, id=args.pid)
analytes, inf = s_elt.analytes()
for analyte in analytes:
for samp in analyte.samples:
d_elts.append(samp.project)
d_elts = list(set(d_elts))
if args.status_changelog:
epp_logger.prepend_old_log(args.status_changelog)
if not dest_udfs:
dest_udfs = source_udfs
elif len(dest_udfs) != len(source_udfs):
logging.error(
"source_udfs and dest_udfs lists of arguments are uneven.")
sys.exit(-1)
for d_elt in d_elts:
project_names = ' '.join([project_names, d_elt.name])
for i in range(len(source_udfs)):
source_udf = source_udfs[i]
dest_udf = dest_udfs[i]
with open(args.status_changelog, 'a') as changelog_f:
if source_udf in s_elt.udf:
copy_sesion = CopyField(s_elt, d_elt, source_udf, dest_udf)
test = copy_sesion.copy_udf(changelog_f)
if test:
no_updated = no_updated + 1
else:
logging.warning(
("Udf: {1} in Process {0} is undefined/blank, exiting"
).format(s_elt.id, source_udf))
incorrect_udfs = incorrect_udfs + 1
if incorrect_udfs > 0:
warn = "Failed to update %s udf(s) due to missing/wrong source udf info." % incorrect_udfs
else:
warn = ''
d = {'up': no_updated, 'ap': len(d_elts), 'w': warn, 'pr': project_names}
abstract = ("Updated {up} udf(s). Handeled project(s): {pr} {w}").format(
**d)
print(abstract, file=sys.stderr)
def get(self, lims_step):
self.set_header("Content-type", "application/json")
p = Process(self.lims, id=lims_step)
p.get(force=True)
links = json.loads(p.udf['Links']) if 'Links' in p.udf else {}
#Sort by descending date, then hopefully have deviations on top
sorted_links = OrderedDict()
for k, v in sorted(links.iteritems(), key=lambda t: t[0], reverse=True):
sorted_links[k] = v
sorted_links = OrderedDict(sorted(sorted_links.iteritems(), key=lambda (k,v): v['type']))
self.write(sorted_links)
def get(self, lims_step):
self.set_header("Content-type", "application/json")
p = Process(self.lims, id=lims_step)
p.get(force=True)
links = json.loads(p.udf['Links']) if 'Links' in p.udf else {}
#Sort by descending date, then hopefully have deviations on top
sorted_links = OrderedDict()
for k, v in sorted(links.items(), key=lambda t: t[0], reverse=True):
sorted_links[k] = v
sorted_links = OrderedDict(sorted(sorted_links.items(), key=lambda k : k[1]['type']))
self.write(sorted_links)
def main(lims, args):
p=Process(lims, id=args.pid)
log=[]
datamap={}
wsname=None
username="******".format(p.technician.first_name, p.technician.last_name)
user_email=p.technician.email
for art in p.all_inputs():
if len(art.samples)!=1:
log.append("Warning : artifact {0} has more than one sample".format(art.id))
for sample in art.samples:
#take care of lamda DNA
if sample.project:
if sample.project.id not in datamap:
datamap[sample.project.id]=[sample.name]
else:
datamap[sample.project.id].append(sample.name)
for art in p.all_outputs():
try:
wsname=art.location[0].name
break
except:
pass
now=datetime.now().strftime("%Y-%m-%d %H:%M:%S.%f")
for pid in datamap:
pj=Project(lims, id=pid)
running_notes=json.loads(pj.udf['Running Notes'])
if len(datamap[pid]) > 1:
rnt="{0} samples planned for {1}".format(len(datamap[pid]), wsname)
else:
rnt="{0} sample planned for {1}".format(len(datamap[pid]), wsname)
running_notes[now]={"note": rnt, "user" : username, "email":user_email, "category":"Workset"}
pj.udf['Running Notes']=json.dumps(running_notes)
pj.put()
log.append("Updated project {0} : {1}, {2} samples in this workset".format(pid,pj.name, len(datamap[pid])))
with open("EPP_Notes.log", "w") as flog:
flog.write("\n".join(log))
for out in p.all_outputs():
#attach the log file
if out.name=="RNotes Log":
attach_file(os.path.join(os.getcwd(), "EPP_Notes.log"), out)
sys.stderr.write("Updated {0} projects successfully".format(len(datamap.keys())))
def main(lims, args, epp_logger):
d_elts = []
no_updated = 0
incorrect_udfs = 0
project_names = ''
source_udfs = args.source_udf
dest_udfs = args.dest_udf
s_elt = Process(lims,id = args.pid)
analytes, inf = s_elt.analytes()
for analyte in analytes:
for samp in analyte.samples:
d_elts.append(samp.project)
d_elts = list(set(d_elts))
if args.status_changelog:
epp_logger.prepend_old_log(args.status_changelog)
if not dest_udfs:
dest_udfs = source_udfs
elif len(dest_udfs) != len(source_udfs):
logging.error("source_udfs and dest_udfs lists of arguments are uneven.")
sys.exit(-1)
for d_elt in d_elts:
project_names = ' '.join([project_names, d_elt.name])
for i in range(len(source_udfs)):
source_udf = source_udfs[i]
dest_udf = dest_udfs[i]
with open(args.status_changelog, 'a') as changelog_f:
if source_udf in s_elt.udf:
copy_sesion = CopyField(s_elt, d_elt, source_udf, dest_udf)
test = copy_sesion.copy_udf(changelog_f)
if test:
no_updated = no_updated + 1
else:
logging.warning(("Udf: {1} in Process {0} is undefined/blank, exiting").format(s_elt.id, source_udf))
incorrect_udfs = incorrect_udfs + 1
if incorrect_udfs > 0:
warn = "Failed to update %s udf(s) due to missing/wrong source udf info." %incorrect_udfs
else:
warn = ''
d = {'up': no_updated,
'ap': len(d_elts),
'w' : warn,
'pr': project_names}
abstract = ("Updated {up} udf(s). Handeled project(s): {pr} {w}").format(**d)
print >> sys.stderr, abstract
def main(lims, args):
process = Process(lims, id=args.pid)
# Read in run recipe file
for outart in process.all_outputs():
if outart.type == 'ResultFile' and outart.name == 'Run Recipe':
try:
fid = outart.files[0].id
file_name = outart.files[0].original_location
content = lims.get_file_contents(id=fid).read()
except:
raise(RuntimeError("Cannot access the run recipe file."))
break
with open("/srv/mfs/NovaSeq_data/gls_recipe_novaseq/{}".format(file_name), 'w') as sf:
sf.write(content)
def main(lims, args, epp_logger):
source_udfs = args.source_udf
dest_udfs = args.dest_udf
correct_artifacts = 0
incorrect_artifacts = 0
no_updated = 0
p = Process(lims,id = args.pid)
artifacts, inf = p.analytes()
if args.status_changelog:
epp_logger.prepend_old_log(args.status_changelog)
if not dest_udfs:
dest_udfs = source_udfs
elif len(dest_udfs) != len(source_udfs):
logging.error("source_udfs and dest_udfs lists of arguments are uneven.")
sys.exit(-1)
for i in range(len(source_udfs)):
source_udf = source_udfs[i]
dest_udf = dest_udfs[i]
with open(args.status_changelog, 'a') as changelog_f:
for artifact in artifacts:
if source_udf in artifact.udf:
correct_artifacts = correct_artifacts +1
copy_sesion = CopyField(artifact, artifact.samples[0], source_udf, dest_udf)
test = copy_sesion.copy_udf(changelog_f)
if test:
no_updated = no_updated + 1
else:
incorrect_artifacts = incorrect_artifacts + 1
logging.warning(("Found artifact for sample {0} with {1} "
"undefined/blank, exiting").format(artifact.samples[0].name, source_udf))
if incorrect_artifacts == 0:
warning = "no artifacts"
else:
warning = "WARNING: skipped {0} udfs(s)".format(incorrect_artifacts)
d = {'ua': no_updated,
'ca': correct_artifacts,
'ia': incorrect_artifacts,
'warning' : warning}
abstract = ("Updated {ua} udf(s), out of {ca} in total, "
"{warning} with incorrect udf info.").format(**d)
print >> sys.stderr, abstract # stderr will be logged and printed in GUI
def main(args):
log = []
lims = Lims(BASEURI,USERNAME,PASSWORD)
process = Process(lims, id=args.pid)
for io in process.input_output_maps:
if io[1]['output-generation-type'] != 'PerInput':
continue
try:
starting_amount = obtain_amount(io[0]['uri'])
except Exception as e:
log.append(str(e))
starting_amount = 0
log.append("Starting amount of {} : {} ng".format(io[0]['uri'].samples[0].name, starting_amount))
current_amount = starting_amount
#preps
preps = lims.get_processes(inputartifactlimsid=io[0]['uri'].id, type=["Setup Workset/Plate", "Amount confirmation QC"])
for pro in preps:
if pro.id == args.pid:
continue # skip the current step
for prepio in pro.input_output_maps:
if prepio[1]['output-generation-type'] == 'PerInput' and prepio[0]['uri'].id == io[0]['uri'].id:
if "Amount taken (ng)" in prepio[1]['uri'].udf: #should always be true
prep_amount = prepio[1]['uri'].udf["Amount taken (ng)"]
log.append("Removing {} ng for prep {} for sample {}".format(prep_amount, pro.id, io[0]['uri'].samples[0].name))
current_amount = current_amount - prep_amount
else:
log.append("No Amount Taken found for prep {} of sample {}".format(pro.id, io[0]['uri'].samples[0].name))
if current_amount < 0:
log.append("Estimated amount for sample {} is {}, correcting to zero".format(io[0]['uri'].samples[0].name, current_amount))
current_amount = 0
update_output_values(io[0]['uri'], io[1]['uri'], current_amount)
with open("amount_check_log.txt", "w") as f:
f.write("\n".join(log))
for out in process.all_outputs():
if out.name == "QC Assignment Log File" :
for f in out.files:
lims.request_session.delete(f.uri)
lims.upload_new_file(out, "amount_check_log.txt")
def get(self):
data={}
lims_url=self.request.query
lims_id="24-{}".format(lims_url.split("/")[-1])
mylims = lims.Lims(BASEURI, USERNAME, PASSWORD)
try:
p=Process(mylims, id=lims_id)
if p.type.name!='Setup Workset/Plate':
raise Exception("Wrong process type")
except:
self.set_status(400, reason="Wrong process type : use a Setup Workset/Plate")
self.finish()
data['comments']={}
data['samples']={}
for i in p.all_inputs():
sample_name=i.samples[0].name
if not i.samples[0].project:
continue
else:
project=i.samples[0].project
if 'Project Comment' in project.udf and project.id not in data['comments']:
data['comments'][project.id]=project.udf['Project Comment']
data['samples'][sample_name]={}
data['samples'][sample_name]['amount']=i.udf['Amount (ng)']
data['samples'][sample_name]['previous_preps']={}
if 'Library construction method' in project.udf:
data['samples'][sample_name]['lib_method']=project.udf['Library construction method']
if 'Sequencing platform' in project.udf:
data['samples'][sample_name]['seq_pl']=project.udf['Sequencing platform']
other_preps=mylims.get_processes(inputartifactlimsid=i.id, type="Setup Workset/Plate")
for op in other_preps:
if op.id != p.id:
for o in op.all_outputs():
if o.type=="Analyte" and o.samples[0].name==sample_name:
data['samples'][sample_name]['previous_preps'][o.location[0].name]={}
data['samples'][sample_name]['previous_preps'][o.location[0].name]['position']=o.location[1]
data['samples'][sample_name]['previous_preps'][o.location[0].name]['amount']=o.udf['Amount taken (ng)']
self.set_header("Content-type", "application/json")
self.write(json.dumps(data))
def post(self, lims_step):
user = self.get_secure_cookie('user')
email = self.get_secure_cookie('email')
a_type = self.get_argument('type', '')
title = self.get_argument('title', '')
url = self.get_argument('url', '')
desc = self.get_argument('desc','')
if not a_type or not title:
self.set_status(400)
self.finish('<html><body>Link title and type is required</body></html>')
else:
p = Process(self.lims, id=lims_step)
p.get(force=True)
links = json.loads(p.udf['Links']) if 'Links' in p.udf else {}
links[str(datetime.datetime.now())] = {'user': user,
'email': email,
'type': a_type,
'title': title,
'url': url,
'desc': desc}
p.udf['Links'] = json.dumps(links)
p.put()
self.set_status(200)
#ajax cries if it does not get anything back
self.set_header("Content-type", "application/json")
self.finish(json.dumps(links))
def delete(self, workset):
note_id=self.get_argument('note_id')
p = Process(self.lims, id=workset)
p.get(force=True)
workset_notes = json.loads(p.udf['Workset Notes']) if 'Workset Notes' in p.udf else {}
try:
self.set_header("Content-type", "application/json")
del workset_notes[note_id]
p.udf['Workset Notes'] = json.dumps(workset_notes)
p.put()
self.set_status(201)
self.write(json.dumps(workset_notes))
except:
self.set_status(400)
self.finish('<html><body>No note found</body></html>')
def post(self, workset):
note = self.get_argument('note', '')
user = self.get_secure_cookie('user')
email = self.get_secure_cookie('email')
if not note:
self.set_status(400)
self.finish('<html><body>No workset id or note parameters found</body></html>')
else:
newNote = {'user': user, 'email': email, 'note': note}
p = Process(self.lims, id=workset)
p.get(force=True)
workset_notes = json.loads(p.udf['Workset Notes']) if 'Workset Notes' in p.udf else {}
workset_notes[str(datetime.datetime.now())] = newNote
p.udf['Workset Notes'] = json.dumps(workset_notes)
p.put()
self.set_status(201)
self.write(json.dumps(newNote))
def main(lims, args):
log=[]
thisyear=datetime.now().year
content = None
if args.mytest:
test()
else:
process = Process(lims, id=args.pid)
if process.type.name == 'Cluster Generation (HiSeq X) 1.0':
header = gen_X_header(process)
reads = gen_X_reads_info(process)
(data, obj) = gen_X_lane_data(process)
check_index_distance(obj, log)
content = "{}{}{}".format(header, reads, data)
if os.path.exists("/srv/mfs/samplesheets/HiSeqX/{}".format(thisyear)):
try:
with open("/srv/mfs/samplesheets/HiSeqX/{}/{}.csv".format(thisyear, obj[0]['fc']), 'w') as sf:
sf.write(content)
os.chmod("/srv/mfs/samplesheets/HiSeqX/{}/{}.csv".format(thisyear, obj[0]['fc']), 0664)
except Exception as e:
log.append(e)
elif process.type.name == 'Cluster Generation (Illumina SBS) 4.0':
(content, obj) = gen_Hiseq_lane_data(process)
check_index_distance(obj, log)
if os.path.exists("/srv/mfs/samplesheets/{}".format(thisyear)):
try:
with open("/srv/mfs/samplesheets/{}/{}.csv".format(thisyear, obj[0]['fc']), 'w') as sf:
sf.write(content)
os.chmod("/srv/mfs/samplesheets/{}/{}.csv".format(thisyear, obj[0]['fc']), 0664)
except Exception as e:
log.append(e)
elif process.type.name == 'Denature, Dilute and Load Sample (MiSeq) 4.0':
header = gen_Miseq_header(process)
reads = gen_Miseq_reads(process)
settings = gen_Miseq_settings(process)
(data, obj) = gen_Miseq_data(process)
check_index_distance(obj, log)
content = "{}{}{}{}".format(header, reads, settings, data)
if not args.test:
for out in process.all_outputs():
if out.name == "Scilifelab SampleSheet" :
ss_art = out
elif out.name == "Scilifelab Log" :
log_id= out.id
elif out.type == "Analyte":
fc_name = out.location[0].name
with open("{}.csv".format(fc_name), "w", 0o664) as f:
f.write(content)
os.chmod("{}.csv".format(fc_name),0664)
for f in ss_art.files:
lims.request_session.delete(f.uri)
lims.upload_new_file(ss_art, "{}.csv".format(fc_name))
if log:
with open("{}_{}_Error.log".format(log_id, fc_name), "w") as f:
f.write('\n'.join(log))
sys.stderr.write("Errors were met, check the log.")
sys.exit(1)
else:
print content
print log
def main(lims, args):
conc_is_local = True
process = Process(lims, id=args.pid)
log_art = None
log = []
fid = None
# first, read the fragment analyzer results
for o in process.all_outputs():
if o.name == 'CSV Result File':
try:
fid = o.files[0].id
except:
sys.exit("Please upload a CSV result file.")
if o.name == 'Calculation Log':
log_art = o
file_contents = lims.get_file_contents(id=fid)
frag_data = {}
keys = []
for line in file_contents.splitlines():
if not keys:
keys = line.split(',')
else:
values = line.split(',')
frag_data[values[0]] = {}
for i in xrange(1, len(values)):
frag_data[values[0]][keys[i]] = values[i]
# Then, read the concentration from the step defined in the process udf
try:
conc_process_name = process.udf['Concentration Source']
conc_is_local = False
except KeyError:
conc_is_local = True
for io in process.input_output_maps:
if 'Fragment Analyzer' in io[1]['uri'].name and io[1]['output-generation-type']== 'PerInput':
base_concentration = None
base_conc_unit = None
well = io[1]['uri'].location[1].replace(":", "")
if conc_is_local:
base_concentration = float(frag_data[well]['ng/uL'])
base_conc_unit = 'ng/uL'
else:
try:
concentration_step = lims.get_processes(type=conc_process_name, inputartifactlimsid=io[0]['limsid'])[0]
except IndexError:
log.append("Cannot find a {} step starting with {}".format(conc_process_name, io[0]['limsid']))
else:
for io2 in concentration_step.input_output_maps:
if io2[0]['limsid'] == io[0]['limsid'] and "Concentration" in io2[1]['uri'].udf:
base_concentration = io2[1]['uri'].udf['Concentration']
base_conc_unit = io2[1]['uri'].udf['Conc. Units']
try:
io[1]['uri'].udf['Min Size (bp)'] = int(frag_data[well]['Range'].split('to')[0].split('bp')[0].strip())
io[1]['uri'].udf['Max Size (bp)'] = int(frag_data[well]['Range'].split('to')[1].split('bp')[0].strip())
if 'Ratio (%)' not in io[1]['uri'].udf:
io[1]['uri'].udf['Ratio (%)'] = float(frag_data[well]['% Total'])
io[1]['uri'].udf['Size (bp)'] = int(frag_data[well]['Avg. Size'])
io[1]['uri'].put()
if base_concentration and base_conc_unit:
if conc_is_local:
io[1]['uri'].udf['Concentration'] = base_concentration
else:
io[1]['uri'].udf['Concentration'] = base_concentration * (float(io[1]['uri'].udf['Ratio (%)']) / 100.0)
io[1]['uri'].udf['Conc. Units'] = base_conc_unit
io[1]['uri'].put()
log.append("Updated values for output {}".format(io[1]['uri'].name))
else:
log.append("Failed to update the concentration of output {}".format(io[1]['uri'].name))
except Exception as e:
log.append("Error updating {} with fragment analyzer data : {}".format(io[1]['uri'].name, e))
if log:
with open("{}_frag_analyzer.log".format(log_art.id), "w") as logContext:
logContext.write("\n".join(log))