def match_fasta(self):
files = myIO.dir_os(self.par['dir_out']).incrusive_files()
#select a fasta file
fa_files = filter(lambda x: x.endswith(('.fa', '.fasta')), files)
self.par['match_fa'] = mySystem.system().select_key(fa_files)
#select a gtf or gff file
gtf_files = filter(lambda x: x.endswith(('.gtf', '.gff3')), files)
self.par['match_gtf'] = mySystem.system().select_key(gtf_files)
#match
if par['web_site'] == 'ENSEML':
myGenome.genome(par['match_fa']).match_ensembl_fa(par['match_gtf'])
elif par['web_site'] == 'NCBI':
myGenome.genome(par['match_fa']).match_ncbi_fa(par['match_gtf'])
def phipseq_alignment(self, sample_name):
print('\n######Anslysis of {} will be trigerred!#####'.format(
sample_name))
#initiate sample par
sample_var = dict(self.par)
sample_var['start_time'] = time.time()
#sample name
sample_var['sample_name'] = sample_name
#sample directory
sample_dir = self.par['sample_dirs'][sample_name]
sample_var['sample_dir'] = myIO.dir_os(sample_dir).create_dir()
print('\tSample directory: ', sample_var['sample_dir'])
#raw data
sample_var['sample_raw_files'] = ','.join(
sample_var['sample_to_raw'][sample_name])
print('\tRaw files: ', sample_var['sample_raw_files'])
#export
sample_var['file_head'] = sample_var['sample_dir'] + sample_name
#default same file
sample_var['sample_sam_file'] = sample_var['file_head'] + '.sam'
#file of read counts
sample_var['sample_RC_file'] = sample_var['file_head'] + '_RC.txt'
sample_var['sample_pro_sumRC_file'] = sample_var[
'file_head'] + '_pro_sumRC.txt'
sample_var['sample_pro_maxRC_file'] = sample_var[
'file_head'] + '_pro_maxRC.txt'
#file for saturation analysis
sample_var['sample_saturation_file'] = sample_var[
'file_head'] + '_saturation.txt'
#sample log
sample_var['sample_log'] = sample_var['file_head'] + '.log'
#sequence alignment
if sample_var['phip_alignment'] == 'yes':
print("\n###sequence alignment", sample_var['tool_aligner'])
#output is sam file
if sample_var['tool_aligner'] == 'bowtie1':
myAlign.alignment(sample_var).bowtie1_alignment()
#counts reads
if sample_var['phip_counting'] == 'yes':
#RC matrix by peptides
myAlign.alignment(sample_var).count_reads()
#RC matrix by proteins
if 'file_annotation' in self.par.keys():
self.combine_peptides(sample_var)
#update sample log
sample_times = mySystem.system().get_time(sample_var['start_time'])
sample_times['sample_name'] = sample_name
myIO.file_os(sample_var['sample_log'], '=').line_replace(sample_times)
def genome_annot(self):
if par['web_site'] == 'ENSEML':
#1: select data type
data_types = ['dna_fa', 'genome_CDS', 'gtf', 'gff', 'protein']
self.par['data_type'] = mySystem.system().select_key(data_types)
#2: download
if par['data_type'] == 'dna_fa':
myDownload.ensembl(par['specie'],
par['dir_out']).download_dna()
else:
myDownload.ensembl(par['specie'],
par['dir_out']).download_annot(
par['data_type'])
elif par['web_site'] == 'NCBI':
#1: select data type
data_types = ['dna_fa', 'RNA', 'gff', 'protein']
self.par['data_type'] = mySystem.system().select_key(data_types)
#2: donwload
if par['data_type'] == 'dna_fa':
myDownload.NCBI(par['specie'], par['dir_out']).download_dna()
else:
myDownload.NCBI(par['specie'], par['dir_out']).download_annot(
par['data_type'])
def download_idmapping(self):
#get web file list
url_idmapping = self.url+'knowledgebase/idmapping/by_organism/'
web_dir, web_files = web(url_idmapping).ls_html()
#print web_files
#select file
file_names = filter(lambda x: '.dat.' in x, web_files.values())
file_names.sort()
file_name = mySystem.system().select_key(file_names, 'Select web file')
#download idmapping dat file
url_file = url_idmapping + file_name
local_file = self.out_dir + file_name
web(url_file).download_file(local_file)
#decompress file
ungz_file = myIO.file_os(local_file).decompress_gz()
print('Save ', url_file, ' as ', ungz_file)
return ungz_file
#check python version
if int(sys.version[0]) <= 2:
print(sys.version)
print(
'\nError: The version of python required for the pipeline running is at least v3.4.~\n'
)
sys.exits(2)
########################################
#read variables.txt
#var_file = '/home/yuan/rawdata_phip/phipseq17_virus_variables.txt'
var_file = os.path.abspath(sys.argv[1])
#print(var_file)
par = myIO.file_os(var_file, '=').to_dict()
par['file_var'] = var_file
#initiate parameters, directories and files
par = launch_phip(par).init_par()
######################################
#main loop
bioPHIPfunc.phip(par).main_loop()
######################################
#end
times_dict = mySystem.system().get_time(start_time)
myIO.file_os(par['file_total_log'], '=').line_replace(times_dict)
print('\n\nDuration: ', times_dict['duration'])
print('\n\nGreat! It is done!!!\n\n\n')
#initiate dictionary saving parameters
par = {
'in_out': 'Continue'
}
annot = download_annot(par)
########################################
#
#2: download dir
par['dir_home'] = myIO.dir_os('/home/yuan/data_preparation/').stdin_dir(
'Enter the directory path storing downloads files')
print par['dir_home']
while (par['in_out'] == 'Continue'):
#2:select ftp or web site
web_sites = ['NCBI', 'ENSEML', 'UniProt']
par['web_site'] = mySystem.system().select_key(
web_sites, 'Select public database')
par['dir_out'] = par['dir_home'] + par['web_site'] + '/'
#1: select file types
if par['web_site'] in ['NCBI', 'ENSEML']:
operations = ['Genome annotation', 'match fasta and gtf']
par['operations'] = mySystem.system().select_key(
operations, 'What is your operations')
elif par['web_site'] == 'UniProt':
par['operations'] = 'UniProt idmapping'
#download genome annotations
if par['operations'] == 'Genome annotation':
#2: select specie
species = ['human', 'mouse', 'rat', 'maize']
par['specie'] = mySystem.system().select_key(
species, 'Select specie of genome')