#!usr/bin/env python
import re
from parameter.common_parameters import common_parameters
import utils.setting_utils as utils
utils.now_time("bed_3UTR script starting...")
p = utils.Bunch(common_parameters)
def main():
input_file = p.bed_3UTR_input
output_file = p.bed_3UTR_output
command_bed_3UTR = '../software/bed12to3UTRbed.sh ' + input_file + ' > ' + output_file
print (command_bed_3UTR)
utils.run_command(command_bed_3UTR)
utils.now_time("bed_3UTR script was successfully finished!!")
if __name__ == '__main__':
main()
import yaml
import itertools
import shelve
import utils.setting_utils as utils
from parameter.common_parameters import common_parameters
from parameter.mirna_seed_infor import mirna_seed_infor
from module.analysis.seed_match import find_mirna_target_candidates
from module.analysis.thermo_calc import calc_thermo
from module.analysis.motif_occurrence import motif_occurrence
from module.analysis.conservation_estimation import conservation_estimation
from module.analysis.target_site_composition import target_site_composition
#test
from module.analysis.seed_match_rev import find_mirna_subtarget_candidates
p = utils.Bunch(common_parameters)
seed_infor = utils.Bunch(mirna_seed_infor)
#print (seed_infor.seed_length)
flg_find_mirna_target_candidates = 0
def progress_bar(per, counter, barlen=50):
perb = int(per/(100.0/barlen))
s = '\r'
s += '['
s += '*' * perb
s += ' ' * (barlen - perb)
s += ']'
s += ' ' + (str(int(per)) + '%' + ' - ' + str(counter) + ' pairs').rjust(4)
sys.stdout.write(s)
def main():
parser = argparse.ArgumentParser(
prog="mirage_prepare",
description="MIRAGE preparation toolkit - Data preparation for MIRAGE")
parser.add_argument(
'preparation_type',
action='store',
choices=[
'bed_3UTR', 'mirbase_gff2bed', 'liftOver', 'phylop_score_prep',
'phastcons_prep', 'phylop_sizedown', 'phastcons_sizedown',
'phylop_score_list', 'phastcons_score_list', 'phastcons_score_R',
'phylop_score_R', 'refseq_pre', 'mirbase_pre', 'mirmark_result',
'cupid_result'
],
help=
'Preparation Type: refseq_pre|mirbase_pre|mirmark_result|cupid_result|'
)
parser.add_argument(
'-i',
'--input-file',
action='store',
dest='input_file',
help='Input file: Specify a input file name and its path')
parser.add_argument(
'-r',
'--reference-file',
action='store',
dest='reference_file',
help='reference file: Specify a reference file name and its path')
parser.add_argument(
'-a',
'--additional-file',
action='store',
dest='add_file',
nargs=3,
help=
'Additional_file: Specify 1-refseq_pre file dir, 2-mirbase_pre file dir, 3-error log dir)'
)
parser.add_argument(
'-o',
'--ouput-file',
action='store',
dest='output_file',
help='Output file: Specify a output file name and its path')
args = parser.parse_args()
#Start analysis - logging
greeting()
utils.now_time('MIRAGE Data Preparation starting...')
#Parameter preparation
prep_type = args.preparation_type
if (args.input_file or args.output_file):
if not (os.path.isfile(args.input_file)):
utils.now_time("ERROR: InputFile does not exist...")
sys.exit(1)
if not (args.output_file):
utils.now_time("ERROR: -o option are required...")
sys.exit(1)
custom_params = {}
if prep_type == 'bed_3UTR':
custom_params['bed_3UTR_input'] = args.input_file
custom_params['bed_3UTR_output'] = args.output_file
common_parameters.updata(custom_params)
p = utils.Bunch(common_parameters)
elif prep_type == 'mirbase_gff2bed':
custom_params['mirbase_gff2bed_input'] = args.input_file
custom_params['mirbase_gff2bed_output'] = args.output_file
common_parameters.update(custom_params)
p = utils.Bunch(common_parameters)
elif prep_type == 'liftOver':
custom_params['liftover_input'] = args.input_file
custom_params['liftover_output'] = args.output_file
common_parameters.update(custom_params)
p = utils.Bunch(common_parameters)
elif prep_type == 'phylop_score_prep':
custom_params['phylop_score_prep_input'] = args.input_file
custom_params['phylop_score_prep_output'] = args.output_file
common_parameters.update(custom_params)
p = utils.Bunch(common_parameters)
elif prep_type == 'phastcons_prep':
custom_params['phastcons_prep_input'] = args.input_file
custom_params['phastcons_prep_output'] = args.output_file
common_parameters.update(custom_params)
p = utils.Bunch(common_parameters)
elif prep_type == 'phylop_sizedown':
if args.reference_file:
custom_params[
'phylop_sizedown_bed_input'] = args.reference_file
custom_params['phylop_sizedown_score_input'] = args.input_file
custom_params[
'phylop_sizedown_score_output'] = args.output_file
common_parameters.update(custom_params)
p = utils.Bunch(common_parameters)
else:
utils.now_time("ERROR: -r option is required...")
sys.exit(1)
elif prep_type == 'phastcons_sizedown':
if args.reference_file:
custom_params[
'phastcons_sizedown_bed_input'] = args.reference_file
custom_params[
'phastcons_sizedown_score_input'] = args.input_file
custom_params[
'phastcons_sizedown_score_output'] = args.output_file
common_parameters.update(custom_params)
p = utils.Bunch(common_parameters)
else:
utils.now_time("ERROR: -r option is required...")
sys.exit(1)
elif prep_type == 'phylop_score_list':
if args.reference_file:
custom_params[
'phylop_score_list_reference'] = args.reference_file
custom_params['phylop_score_list_db_input'] = args.input_file
custom_params['phylop_score_list_db_output'] = args.output_file
common_parameters.update(custom_params)
p = utils.Bunch(common_parameters)
else:
utils.now_time("ERROR: -r option is required...")
sys.exit(1)
elif prep_type == 'phastcons_score_list':
if args.reference_file:
custom_params[
'phastcons_score_list_reference'] = args.reference_file
custom_params[
'phastcons_score_list_db_input'] = args.input_file
custom_params[
'phastcons_score_list_db_output'] = args.output_file
common_parameters.update(custom_params)
p = utils.Bunch(common_parameters)
else:
utils.now_time("ERROR: -r option is required...")
sys.exit(1)
elif prep_type == 'phastcons_score_R':
custom_params['phastcons_score_R_input'] = args.input_file
custom_params['phastcons_score_R_output'] = args.output_file
common_parameters.update(custom_params)
p = utils.Bunch(common_parameters)
elif prep_type == 'phylop_score_R':
custom_params['phylop_score_R_input'] = args.input_file
custom_params['phylop_score_R_output'] = args.output_file
common_parameters.update(custom_params)
p = utils.Bunch(common_parameters)
elif prep_type == 'refseq_pre':
custom_params['refseq_pre_input'] = args.input_file
custom_params['refseq_pre_output'] = args.output_file
common_parameters.update(custom_params)
p = utils.Bunch(common_parameters)
elif prep_type == 'mirbase_pre':
custom_params['mirbase_pre_input'] = args.input_file
custom_params['mirbase_pre_output'] = args.output_file
p = utils.Bunch(common_parameters)
elif prep_type == 'mirmark_result':
if args.add_file:
custom_params['refseq_pre_output'] = args.add_file[0]
custom_params['mirbase_pre_output'] = args.add_file[1]
custom_params['mirmark_pos'] = args.input_file
custom_params['mirmark_output'] = args.output_file
custom_params['mirmark_error'] = args.add_file[2]
p = utils.Bunch(common_parameters)
else:
utils.now_time("ERROR: -a option is required...")
sys.exit(1)
elif prep_type == 'cupid_result':
if args.add_file:
custom_params['refseq_pre_output'] = args.add_file[0]
custom_params['mirbase_pre_output'] = args.add_file[1]
custom_params['cupid_pos'] = args.input_file
custom_params['cupid_output'] = args.output_file
custom_params['cupid_error'] = args.add_file[2]
p = utils.Bunch(common_parameters)
else:
utils.now_time("ERROR: -a option is required...")
sys.exit(1)
else:
utils.now_time("ERROR: Wrong preparation type...")
sys.exit(1)
elif not (args.input_file and args.output_file):
if prep_type:
p = utils.Bunch(common_parameters)
else:
utils.now_time("ERROR: Wrong preparation type...")
sys.exit(1)
else:
utils.now_time("ERROR: -i and -o option are required...")
sys.exit(1)
#Preparation type
if prep_type == 'bed_3UTR':
runpy.run_module('module.preparation.bed_3UTR',
run_name="__main__",
alter_sys=True)
elif prep_type == 'mirbase_gff2bed':
runpy.run_module('module.preparation.mirbase_gff2bed',
run_name="__main__",
alter_sys=True)
elif prep_type == 'liftOver':
runpy.run_module('module.preparation.liftOver',
run_name="__main__",
alter_sys=True)
elif prep_type == 'phylop_score_prep':
runpy.run_module('module.preparation.phylop_score_prep',
run_name="__main__",
alter_sys=True)
elif prep_type == 'phastcons_prep':
runpy.run_module('module.preparation.phastcons_score_prep',
run_name="__main__",
alter_sys=True)
elif prep_type == 'phastcons_sizedown':
runpy.run_module('module.preparation.phastcons_sizedown',
run_name='__main__',
alter_sys=True)
elif prep_type == 'phylop_sizedown':
runpy.run_module('module.preparation.phylop_sizedown',
run_name="__main__",
alter_sys=True)
elif prep_type == 'phylop_score_list':
runpy.run_module('module.preparation.phylop_score_list',
run_name='__main__',
alter_sys=True)
elif prep_type == 'phastcons_score_list':
runpy.run_module('module.preparation.phastcons_score_list',
run_name='__main__',
alter_sys=True)
elif prep_type == 'phastcons_score_R':
runpy.run_module('module.preparation.phastcons_score_R',
run_name='__main__',
alter_sys=True)
elif prep_type == 'phylop_score_R':
runpy.run_module('module.preparation.phylop_score_R',
run_name='__main__',
alter_sys=True)
elif prep_type == 'refseq_pre':
runpy.run_module('module.preparation.refseq_pre',
run_name="__main__",
alter_sys=True)
elif prep_type == 'mirbase_pre':
runpy.run_module('module.preparation.mirbase_pre',
run_name="__main__",
alter_sys=True)
elif prep_type == 'mirmark_result':
runpy.run_module('module.preparation.mirmark_result',
run_name="__main__",
alter_sys=True)
elif prep_type == 'cupid_result':
runpy.run_module('module.preparation.cupid_result',
run_name="__main__",
alter_sys=True)
else:
utils.now_time("ERROR: Wrong preparation type...")
sys.exit(1)
def main():
parser = argparse.ArgumentParser(
prog='mirage',
description='MIRAGE - Comprehensive miRNA target prediction pipeline')
parser.add_argument('analysis_type',
action='store',
help='Analysis_type: Choose estimation or prediction',
choices=['estimation', 'prediction'])
parser.add_argument(
'mirna_fasta',
action='store',
help='miRNA fasta file: Specify miRNA fasta file to use the analysis')
parser.add_argument(
'targetrna_fasta',
action='store',
help=
'TargetRNA fasta file: Specify TargetRNA fasta file to use the analysis'
)
parser.add_argument(
'-m',
'--mirna-conservation-score-file',
action='store',
dest='mirna_conservation',
help=
'Conservation score file about miRNA: Specify your conservation score db file. MIRAGE preparetion toolkits enables you to make the score files about TargetRNA or miRNA bed files.'
)
parser.add_argument(
'-t',
'--targetrna-conservation-score-file',
action='store',
dest='targetrna_conservation',
help=
'Conservation score file about TargetRNA: Specify your conservation score db file. MIRAGE preparetion toolkits enables you to make the score files about TargetRNA or miRNA bed files.'
)
args = parser.parse_args()
#Start analysis - logging
greeting()
utils.now_time("MIRAGE miRNA target prediction starting...")
analysis_type = args.analysis_type
mirna_fasta_path = args.mirna_fasta
targetrna_fasta_path = args.targetrna_fasta
mirna_conservation_score = args.mirna_conservation
targetrna_conservation_score = args.targetrna_conservation
#Check fasta files
if not os.path.isfile(mirna_fasta_path):
print("Error: miRNA fasta file does not exist...")
sys.exit(1)
if not os.path.isfile(targetrna_fasta_path):
print("Error: TargetRNA fasta file does not exist...")
#Check conservation score db files
#if
#parameters
param = dict(
MIRNA_FASTA_PATH=mirna_fasta_path,
TARGETRNA_FASTA_PATH=targetrna_fasta_path,
)
common_parameters.update(param)
p = utils.Bunch(common_parameters)
print('miRNA_Fasta_file: ' + p.MIRNA_FASTA_PATH, end="\n")
print('TargetRNA_Fasta_file: ' + p.TARGETRNA_FASTA_PATH, end="\n")
'''
mirna_dict = utils.load_fasta(mirna_fasta_path)
#print (mirna_dict['hsa-miR-34b-5p|MIMAT0000685'],end="\n")
#print (mirna_dict['hsa-miR-20a-5p|MIMAT0000075'],end="\n")
targetrna_dict = utils.load_fasta(targetrna_fasta_path)
#print (targetrna_dict['NM_000594'],end="\n")
#print (targetrna_dict['NM_030938'],end="\n")
query_mirna.update(mirna_dict)
print (query_mirna)
mirna = utils.Bunch(query_mirna)
query_targetrna.update(targetrna_dict)
targetrna = utils.Bunch(query_targetrna)
if hasattr (mirna,'hsa-miR-34b-5p|MIMAT0000685'):
print ("OK!!")
print (mirna.items())
sys.exit(0)
else:
print ("Error...")
sys.exit(1)
#test = targetrna.'NM_000594'
#print (test,end="\n")
#sys.exit(0)
'''
#runpy - choose analysis type
if analysis_type == 'estimation':
runpy.run_module('module.estimate',
run_name="__main__",
alter_sys=True)
elif analysis_type == 'prediction':
runpy.run_module('module.predict', run_name="__main__", alter_sys=True)
else:
print('Error: Analysis type is wrong...')
sys.exit(1)