def init_analysis(self):
#1: read annotation file
if 'file_annotation' in self.par.keys():
self.par['annot_df'] = myDataframe.basic().annot_df(
self.par['file_annotation'])
#genome annotation: associations of protein-peptides
self.par['dict_pro_pep'] = myCommon.basic(
self.par).protein_peptides()
#virus only
if 'VirScan' in self.par['file_annotation']:
#extract aa stretch
#get dependent petides that two peptides shared at least 7-aa.
self.par['dependent_pep'] = myCommon.basic(
self.par).taxon_dependent_peptides()
#2: check bowtie or build bowtie index
myAlign.alignment(self.par).build_bowtie_index()
#3: sample info
self.par = myParallel.samples(self.par).export_sample_info()
#samples of negative controls
group1 = self.par['group1']
if 'NC' in group1.keys():
self.par['NC_samples'] = group1['NC'].split(',')
self.par['phip_samples'] = list(
set(self.par['sample_names']) - set(self.par['NC_samples']))
print('\nNumber of negative Controls (Beads only): ',
self.par['NC_samples'].__len__())
print('Number of PhIP samples: ',
self.par['sample_names'].__len__())
#myDict.basic(self.par['sample_dirs']).print_dict()
#read reference sequence file (*.fa)
ref_dict, ref_ids = myGenome.genome(self.par['file_ref_fa']).read_fa()
self.par['ref_dict'] = ref_dict
#current dir
par['dir_bin'] = os.path.dirname(os.path.realpath(__file__)) + '/'
par['dir_home'] = os.path.abspath(
os.path.join(par['dir_bin'], os.pardir)) + '/'
print('Home directory of phip pipsline: ', par['dir_home'])
#libraries. default is human and virus
for lib in par['ref_libs']:
par['dir_result'] = myIO.dir_os(
os.path.abspath(par['out'] + '_' + lib)).create_dir()
if os.path.isdir(par['dir_result']):
#1: sample_info.csv
par['file_sample_info'] = par['dir_result'] + 'sample_info.csv'
print('The sample information file: ', par['file_sample_info'])
#read sample_info.csv
myParallel.samples(par).export_sample_info()
#2: copy template variables.txt into lib folder
template_file = '{}variables_{}.txt'.format(
par['dir_bin'], lib)
var_file = '{}variables.txt'.format(par['dir_result'])
print('Save {} and then update it.'.format(var_file))
shutil.copy(template_file, var_file)
#update parameters of variables.txt
refresh = {
'dir_home': par['dir_home'],
'dir_result': par['dir_result']
}
refresh['dir_raw_data'] = par['dir_raw_data'] if par[
'dir_raw'] == 'NA' else par['dir_raw']
myIO.file_os(var_file, '=').line_replace(refresh)
else:
def par_command(argv):
phip_libs = ['human', 'virus', 'PE', 'allergome', 'LISH']
#initiate parameters
par = {'fq_file':'NA','barcode_file':'NA','index_file':'NA','I1_file':'NA','I2_file':'NA', \
'dir_raw_data':'NA', 'dir_raw':'NA','dir_in':'NA', 'out':'NA', \
'dir_result':'NA', 'multiplexing_mode':0, 'ref_libs':phip_libs[:2], \
'seq_start':0, 'seq_end':0, 'seq_min':10, 'seq_max':0 }
usage_out = 'Usage:\n' + argv[0] + ' [options] -o <raw data directory> ' + \
'-f <fastq file> -i <index file> -b <barcode file>\n'
try:
opts, args = getopt.getopt(argv[1:],"hf:i:b:o:t:l:x:y:m:n:z:c:",["help",\
"fastq_file", "index_file", "barcode_file", "dir_raw_data", "trim_len",\
'fixed_end5', 'dir_in', 'out', 'I1_file','I2_file','dir_raw','ref_library'])
except getopt.GetoptError:
print(usage_out)
sys.exit(2)
#get parameters
for opt, arg in opts:
if opt in ('-h', '--help'):
print(usage_out)
#common usage
# python Process_FASTQ.py -f * -i * -b * -o * -y *"
print("-h --help\tUsage information of this script.")
print(
"-t --trim_len\tTrim sequences from the 5'-end or 3'-end of reads (Optional)"
)
print(
"-f --fastq_file\tFastq file determined by a sequencing analyzer."
)
print("-i --index_file\tIndex file matched with the fastq file.")
print(
"-b --barcode_file\tBarcode file matched with the index file.")
print(
"-o --raw_data\tDirectory storing demulitplexed *fastq files.")
print(
"-y --out\tDirectory storing sample_info.csv and variables.txt."
)
print(
"-c --ref_library\tReference libraries can be one of {}, default is {}."
.format(phip_libs, phip_libs[:2]))
sys.exit(2)
elif opt in ("-f", "--fastq_file"):
par['fq_file'] = os.path.abspath(arg)
par['multiplexing_mode'] += 1
elif opt in ("-i", "--index_file"):
par['index_file'] = os.path.abspath(arg)
par['multiplexing_mode'] += 1
elif opt in ("-b", "--barcode_file"):
par['barcode_file'] = os.path.abspath(arg)
par['multiplexing_mode'] += 1
elif opt in ("-o", "--raw_data"):
par['dir_raw_data'] = myIO.dir_os(
os.path.abspath(arg)).create_dir()
elif opt in (
"-z",
"--all_raw_data"): # only for one more sets of fastq splits
par['dir_raw'] = myIO.dir_os(os.path.abspath(arg)).create_dir()
elif opt in ('-x', "--dir_in"):
par['dir_in'] = os.path.abspath(arg)
par['fq_files'] = myParallel.samples({}).seek_fq(par['dir_in'])
elif opt in ('-y', "--out"):
par['out'] = arg
elif opt in ("-l", "--fixed_len"):
len_min, len_max = arg.split(':')
par['seq_min'] = abs(int(len_min))
par['seq_max'] = abs(int(len_max))
elif opt in ("-t", "--trim_len"):
trim_end5, trim_end3 = arg.split(':')
par['seq_start'] = abs(int(trim_end5))
par['seq_end'] = -abs(int(trim_end3))
elif opt in ("-m", "--I1_file"):
par['I1_file'] = os.path.abspath(arg)
elif opt in ("-n", "--I2_file"):
par['I2_file'] = os.path.abspath(arg)
elif opt in ("-c", "--ref_library"):
libs = arg.split(',')
par['ref_libs'] = [x for x in libs if x in phip_libs]
#
if par['seq_max'] > 0:
par['seq_end'] = par['seq_max']
#
myDict.basic(par).print_dict()
return par
def par_command(argv):
phip_libs = ['human', 'virus', 'allergome', 'provirome', 'toxome', 'mouse', 'PE', 'zika', 'arbo', 'LISH']
#initiate parameter
na_str='fq_file,barcode_file,index_file,I1_file,I2_file,dir_raw_data,dir_in,out,dir_result'
par=dict([(key, 'NA') for key in na_str.split(',')])
par.update({'ref_libs':phip_libs[:2], 'seq_start':0, 'seq_end':None, 'seq_min':10})
usage_out = 'Usage:\n' + argv[0] + ' [options] -o <raw data directory> ' + \
'-f <fastq file> -i <index file> -b <barcode file>\n'
try:
opts, args = getopt.getopt(argv[1:],"hf:i:b:o:t:r:l:x:y:m:n:c:",["help",\
"fastq_file", "index_file", "barcode_file", "dir_raw_data", "trim_5end", 'len_trim',\
'fixed_end5', 'dir_in', 'out', 'I1_file','I2_file','ref_library'])
except getopt.GetoptError:
print(usage_out)
sys.exit(2)
#get parameters
for opt, arg in opts:
if opt in ('-h', '--help'):
print(usage_out)
#common usage
# python Process_FASTQ.py -f * -i * -b * -o * -y *"
print("-h --help\tUsage information of this script.")
print("-t --trim_len\tTrim sequences from the 5'-end or 3'-end of reads (Optional)")
print("-f --fastq_file\tFastq file determined by a sequencing analyzer.")
print("-i --index_file\tIndex file matched with the fastq file.")
print("-b --barcode_file\tBarcode file matched with the index file.")
print("-o --raw_data\tDirectory storing demulitplexed *fastq files.")
print("-y --out\tDirectory storing sample_info.csv and variables.txt.")
print("-c --ref_library\tReference libraries can be any of {}, default is {}.".format(phip_libs, phip_libs[:2]))
sys.exit(2)
elif opt in ("-f", "--fastq_file"):
par['fq_file'] = os.path.abspath(arg)
elif opt in ("-i", "--index_file"):
par['index_file'] = os.path.abspath(arg)
elif opt in ("-b", "--barcode_file"):
par['barcode_file'] = os.path.abspath(arg)
elif opt in ("-o", "--raw_data"):
par['dir_raw_data'] = myIO.dir_os(os.path.abspath(arg)).create_dir()
elif opt in ('-x', "--dir_in"):
par['dir_in'] = os.path.abspath(arg)
par['fq_files'] = myParallel.samples({}).seek_fq(par['dir_in'])
elif opt in ('-y', "--out"):
par['out'] = arg
elif opt in ("-l", "--min_len"):
# discard shorter reads due to poor sequencing
par['seq_min'] = abs(int(arg))
elif opt in ("-t", "--trim_5end"):
#trim_end5: length of nt from the 5-end
par['seq_start'] = abs(int(arg))
elif opt in ("-r", "--fixed_len"):
#len_trim: length of nt after trimming 5-end and 3-end
par['seq_len'] = abs(int(arg))
par['seq_end'] = par['seq_start'] + par['seq_len']
elif opt in ("-m", "--I1_file"):
par['I1_file'] = os.path.abspath(arg)
elif opt in ("-n", "--I2_file"):
par['I2_file'] = os.path.abspath(arg)
elif opt in ("-c", "--ref_library"):
libs = arg.split(',')
par['ref_libs'] = [x for x in libs if x in phip_libs]
#
myDict.basic(par).print_dict()
return par