def report_demultiplex_stats(config,mockdb,directory,flowcell,machine):
"""
Pulls the information form the demultiplex stats file
and prints it in a convenient csv format. The directory
in the arguments is the base output directory for casava,
i.e. it contains the Project_PROJECT_ID directories as well as the
Basecall_Stats_FCID directory.
"""
flowcell_key = flowcell.key
machine_key = machine.key
demultiplex_filename = os.path.join(directory, config.get('Common_directories','basecall_front')+ flowcell_key,config.get('Filenames','demultiplex'))
if not os.path.isfile(demultiplex_filename):
return
struct = extract_barcode_lane_stats(demultiplex_filename)
total_reads = calculate_lane_total(struct,'# Reads')
pf = calculate_weighted_percent(struct,'% PF')
q30 = calculate_weighted_percent(struct,'% of >= Q30 Bases (PF)')
print "sample_key,index,total_reads,pecentage_pf,pecenetage_qbove_q30,flowcell,hiseq_machine,lane_number";
for i in range(0,len(struct)):
number = struct[i]['Lane']
if re.search('lane',translate_sample_name(struct[i]['Sample ID'])):
continue
string = struct[i]['Sample ID']
string += "," + struct[i]['Index']
string += "," + struct[i]['# Reads']
string += "," + struct[i]['% PF']
string += "," + struct[i]['% of >= Q30 Bases (PF)']
string += "," + flowcell.key
string += "," + machine.key
string += "," + number
print string
return 1
def fill_demultiplex_stats(config,mockdb,directory,flowcell,machine):
"""
Pulls the information form the demultiplex stats file
and puts it in the correct objects. The directory
in the arguments is the base output directory for casava,
i.e. it contains the Project_PROJECT_ID directories as well as the
Basecall_Stats_FCID directory.
"""
flowcell_key = flowcell.key
machine_key = machine.key
demultiplex_filename = os.path.join(directory, config.get('Common_directories','basecall_front')+ flowcell_key,config.get('Filenames','demultiplex'))
if not os.path.isfile(demultiplex_filename):
return
struct = extract_barcode_lane_stats(demultiplex_filename)
total_reads = calculate_lane_total(struct,'# Reads')
pf = calculate_weighted_percent(struct,'% PF')
q30 = calculate_weighted_percent(struct,'% of >= Q30 Bases (PF)')
for i in range(0,len(struct)):
number = struct[i]['Lane']
lane_key = flowcell_key + '_lane_' + number
lane = mockdb['Lane'].__get__(config,key=lane_key,flowcell=flowcell,number=number)
lane.total_reads = total_reads[number]
lane.percentage_pf = pf[number]
lane.percentage_above_q30 = q30[number]
sample_key = translate_sample_name(struct[i]['Sample ID'])
if re.search('lane',sample_key):
lane.undetermined_reads = struct[i]['# Reads']
continue
sample = mockdb['Sample'].__get__(config,key=sample_key)
index = struct[i]['Index']
barcode_key = lane_key + "_" + index
barcode = mockdb['Barcode'].__get__(config,key=barcode_key,sample=sample,index=index,lane=lane)
barcode.reads = struct[i]['# Reads']
return 1