def initialize_dir_struct():
print "Initializing YAP..."
print "Creating output directory structure"
#create temporary workspace directory
yap_tools.create_dir(wd.yap_temp_user_dir)
os.system("mkdir" + " " + wd.workflow_output_path)
os.system("mkdir" + " " + wd.temp_dir_path)
os.system("mkdir " + wd.consolidated_output)
# create output directory for regrouped samples
if wd.regroup_output =='yes':
os.system("mkdir" + " " + wd.regroup_output_path)
for i in wd.regroup_arr: # iterate over regroup arr
regroup_title = i[0]
file_dir_path = wd.regroup_output_path + "/" + regroup_title
os.system("mkdir" + " " + file_dir_path)
for barcode in wd.barcode_dict.iterkeys():
barcode_dir_path = file_dir_path + "/" + barcode
os.system("mkdir" + " " + barcode_dir_path)
preprocess_dir_path = barcode_dir_path + \
"/" + "preprocess_output"
aligner_output_dir_path = barcode_dir_path + \
"/" + "aligner_output"
barcode_basecount_dir = preprocess_dir_path + \
"/" + "basecount_analysis"
postprocess_dir_path = barcode_dir_path + \
"/" + "postprocess_output"
os.system("mkdir" + " " + postprocess_dir_path)
os.system("mkdir" + " " + preprocess_dir_path)
os.system("mkdir" + " " + aligner_output_dir_path)
# create log file to track the regroup samples
fw = open(wd.sample_track_log, 'wb')
for group in wd.inp_files_list:
each_file = group[2]
file_dir_path = wd.workflow_output_path + "/" + each_file
fw.write(each_file + "\t=>\t" + group[0] + "," + group[1] + "\n")
os.system("mkdir" + " " + file_dir_path)
for barcode in wd.barcode_dict.iterkeys():
barcode_dir_path = file_dir_path + "/" + barcode
os.system("mkdir" + " " + barcode_dir_path)
preprocess_dir_path = barcode_dir_path + "/" + "preprocess_output"
aligner_output_dir_path = barcode_dir_path + "/" + "aligner_output"
barcode_basecount_dir = preprocess_dir_path + \
"/" + "basecount_analysis"
postprocess_dir_path = barcode_dir_path + \
"/" + "postprocess_output"
os.system("mkdir" + " " + postprocess_dir_path)
os.system("mkdir" + " " + preprocess_dir_path)
os.system("mkdir" + " " + aligner_output_dir_path)
fw.close()
os.system("mkdir " + wd.log_path)
os.system("mkdir " + wd.err_log_path)
os.system("mkdir " + wd.stat_log_path)
for group in wd.inp_files_list:
each_file = group[2]
temp_err_path = ""
temp_stat_path = ""
temp_err_path = wd.err_log_path + "/" + each_file + "_log_temp"
temp_stat_path = wd.stat_log_path + "/" + each_file + "_log_temp"
os.system("mkdir" + " " + temp_err_path)
os.system("mkdir" + " " + temp_stat_path)
def initialize_dir_struct():
print "Initializing YAP..."
print "Creating output directory structure"
#create temporary workspace directory
yap_tools.create_dir(wd.yap_temp_user_dir)
os.system("mkdir" + " " + wd.workflow_output_path)
os.system("mkdir" + " " + wd.temp_dir_path)
os.system("mkdir " + wd.consolidated_output)
# create output directory for regrouped samples
if wd.regroup_output == 'yes':
os.system("mkdir" + " " + wd.regroup_output_path)
for i in wd.regroup_arr: # iterate over regroup arr
regroup_title = i[0]
file_dir_path = wd.regroup_output_path + "/" + regroup_title
os.system("mkdir" + " " + file_dir_path)
for barcode in wd.barcode_dict.iterkeys():
barcode_dir_path = file_dir_path + "/" + barcode
os.system("mkdir" + " " + barcode_dir_path)
preprocess_dir_path = barcode_dir_path + \
"/" + "preprocess_output"
aligner_output_dir_path = barcode_dir_path + \
"/" + "aligner_output"
barcode_basecount_dir = preprocess_dir_path + \
"/" + "basecount_analysis"
postprocess_dir_path = barcode_dir_path + \
"/" + "postprocess_output"
os.system("mkdir" + " " + postprocess_dir_path)
os.system("mkdir" + " " + preprocess_dir_path)
os.system("mkdir" + " " + aligner_output_dir_path)
# create log file to track the regroup samples
fw = open(wd.sample_track_log, 'wb')
for group in wd.inp_files_list:
each_file = group[2]
file_dir_path = wd.workflow_output_path + "/" + each_file
fw.write(each_file + "\t=>\t" + group[0] + "," + group[1] + "\n")
os.system("mkdir" + " " + file_dir_path)
for barcode in wd.barcode_dict.iterkeys():
barcode_dir_path = file_dir_path + "/" + barcode
os.system("mkdir" + " " + barcode_dir_path)
preprocess_dir_path = barcode_dir_path + "/" + "preprocess_output"
aligner_output_dir_path = barcode_dir_path + "/" + "aligner_output"
barcode_basecount_dir = preprocess_dir_path + \
"/" + "basecount_analysis"
postprocess_dir_path = barcode_dir_path + \
"/" + "postprocess_output"
os.system("mkdir" + " " + postprocess_dir_path)
os.system("mkdir" + " " + preprocess_dir_path)
os.system("mkdir" + " " + aligner_output_dir_path)
fw.close()
os.system("mkdir " + wd.log_path)
os.system("mkdir " + wd.err_log_path)
os.system("mkdir " + wd.stat_log_path)
for group in wd.inp_files_list:
each_file = group[2]
temp_err_path = ""
temp_stat_path = ""
temp_err_path = wd.err_log_path + "/" + each_file + "_log_temp"
temp_stat_path = wd.stat_log_path + "/" + each_file + "_log_temp"
os.system("mkdir" + " " + temp_err_path)
os.system("mkdir" + " " + temp_stat_path)
exit()
#communicate all the workflows to all processors
workflow_struct = comm.bcast(workflow_struct, root=0)
#loop over each workflow for data processing
for wk in range(1, len(workflow_struct)):
#store the current workflow details into a dictionary
workflow_config_dict = workflow_struct[wk]
#make workflow configuration variables global
workflow_obj=wd.workflow_dictionary()
workflow_obj.make_global(workflow_config_dict)
#summary file to store all the workflow provenance details
f_summary_file = wd.workflow_output_path + "/" + wd.workflow_name + "_workflow_summary.txt"
basecount_metrics_flag = ''
file_basecount_dict=wd.file_basecount_dict
#create temp directory, this is local for everynode
yap_tools.create_dir(wd.yap_temp_user_dir)
if (myrank == 0):
#create output directory structure
yap_init.initialize_dir_struct()
# printing analysis summary
yap_print_info.print_info()
str_out= "-"*20 +" PROVENANCE "+ "-"*20 +"\n\n"
yap_file_io.write_data(str_out,f_summary_file)
comm.barrier()
if wd.run_preprocess_analysis == "yes":
#if preprocess is set to 'yes', perform initial qc commands
for i in range(0, len(wd.preprocess_cmd_arr)):
preprocess_cmd_name = wd.preprocess_cmd_arr[i][2][0][0]
preprocess_cmd = wd.preprocess_cmd_arr[i][2][0][1]
if re.search('calculate_basecount_metrics', preprocess_cmd_name) is not None:
basecount_metrics_flag = 'True'
