def main():
input_file = p.liftover_input
output_file = p.liftover_output
error_file = output_file + '.error'
command_liftover = '../software/liftOver ' + input_file + ' ../software/hg38ToHg19.over.chain ' + output_file + ' ' + error_file
utils.run_command(command_liftover)
utils.now_time("liftOver script was successfully finished!!")
def main():
input_file = p.liftover_input
output_file = p.liftover_output
error_file = output_file + '.error'
command_liftover = '../software/liftOver ' + input_file + ' ../software/hg38ToHg19.over.chain ' + output_file + ' ' + error_file
utils.run_command(command_liftover)
utils.now_time("liftOver script was successfully finished!!")
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!!")
def main():
utils.now_time("Input_file: " + p.mirbase_gff2bed_input)
utils.now_time("Output_file: " + p.mirbase_gff2bed_output)
mirbase_gff_file = open(p.mirbase_gff2bed_input,'r')
mirbase_bed_file = open(p.mirbase_gff2bed_output,'w')
for line in mirbase_gff_file:
line = line.rstrip()
data = line.split("\t")
if re.match(r'^#',line):
continue
chrom = data[0]
status = data[2]
st = int(data[3]) - 1
ed = data[4]
strand = data[6]
if status == 'miRNA_primary_transcript':
continue
name_infor = data[8].split(';')
mir_id = re.sub(r'^ID=','',name_infor[0])
mir_id_number = ''
if re.search(r'_',mir_id):
mir_id, mir_id_number = mir_id.split('_')
else:
mir_id_number = 0 #there is ONLY one miRNA coding site in your genome
mir_name = re.sub(r'^Name=','',name_infor[2])
name = mir_name + '|' + mir_id + '|' + str(mir_id_number)
print (chrom, st, ed, name, 0, strand, file=mirbase_bed_file, sep="\t", end="\n")
utils.now_time("mirbase_gff2bed script was successfully finished!!")
mirbase_gff_file.close()
mirbase_bed_file.close()
def main():
utils.now_time("Input_file: " + p.mirbase_gff2bed_input)
utils.now_time("Output_file: " + p.mirbase_gff2bed_output)
mirbase_gff_file = open(p.mirbase_gff2bed_input, "r")
mirbase_bed_file = open(p.mirbase_gff2bed_output, "w")
for line in mirbase_gff_file:
line = line.rstrip()
data = line.split("\t")
if re.match(r"^#", line):
continue
chrom = data[0]
status = data[2]
st = int(data[3]) - 1
ed = data[4]
strand = data[6]
if status == "miRNA_primary_transcript":
continue
name_infor = data[8].split(";")
mir_id = re.sub(r"^ID=", "", name_infor[0])
mir_id_number = ""
if re.search(r"_", mir_id):
mir_id, mir_id_number = mir_id.split("_")
else:
mir_id_number = 0 # there is ONLY one miRNA coding site in your genome
mir_name = re.sub(r"^Name=", "", name_infor[2])
name = mir_name + "|" + mir_id + "|" + str(mir_id_number)
print(chrom, st, ed, name, 0, strand, file=mirbase_bed_file, sep="\t", end="\n")
utils.now_time("mirbase_gff2bed script was successfully finished!!")
mirbase_gff_file.close()
mirbase_bed_file.close()
def main():
utils.now_time("Input_file: " + p.mirbase_pre_input)
utils.now_time("Output_file: " + p.mirbase_pre_output)
input_file = open(p.mirbase_pre_input, 'r')
output_file = open(p.mirbase_pre_output, 'w')
flg = 0
seq = ""
for line in input_file:
line = line.rstrip()
if re.match(r"^>", line): #Header
data = line.split()
mir_id = data[0]
mir_id = mir_id.replace('>', '')
symbol = data[1]
infor = mir_id + '|' + symbol
if flg == 1:
print(seq, file=output_file, end="\n")
print(infor, file=output_file, end="\t")
flg = 1
seq = ""
else: #Sequence
seq += line
print(seq, file=output_file, end="\n")
utils.now_time("mirbase_pre script was successfully finished!!")
input_file.close()
output_file.close()
def main():
utils.now_time("Input_file: " + p.phylop_score_R_input)
utils.now_time("Output_file: " + p.phylop_score_R_output)
output_s = p.phylop_score_R_output + 'phyloP46way_miRBase_v21_hg38Tohg19.txt'
output_file = open(output_s,'w')
#for x in ['chrY']:
for x in ['chr1','chr2','chr3','chr4','chr5','chr6','chr7','chr8','chr9','chr10','chr11','chr12','chr13','chr14','chr15','chr16','chr17','chr18','chr19','chr20','chr21','chr22','chrX','chrY','chrM']:
input_s = p.phylop_score_R_input + x + '.phyloP46way_miRBase_v21_hg38Tohg19_for_MIRAGE.db'
input_shelve = shelve.open(input_s)
max_length = 28 #Max_length: 28nt(miRNA)
for keys in input_shelve.keys():
values = input_shelve[keys]
value_length = len(values)
add_length = max_length - value_length
null_value = [0.000 for i in range(add_length)]
values += null_value
value_string = "\t".join(map(str, values))
print(keys,value_string, file=output_file, sep="\t", end="\n")
input_shelve.close()
output_file.close()
utils.now_time("phylop_score_R script was successfully finished!!")
def main():
utils.now_time("Input_file: " + p.mirbase_pre_input)
utils.now_time("Output_file: " + p.mirbase_pre_output)
input_file = open(p.mirbase_pre_input,'r')
output_file = open(p.mirbase_pre_output,'w')
flg = 0
seq = ""
for line in input_file:
line = line.rstrip()
if re.match(r"^>",line): #Header
data = line.split()
mir_id = data[0]
mir_id = mir_id.replace('>','')
symbol = data[1]
infor = mir_id + '|' + symbol
if flg == 1:
print (seq,file=output_file,end="\n")
print (infor,file=output_file,end="\t")
flg = 1
seq = ""
else: #Sequence
seq += line
print (seq,file=output_file,end="\n")
utils.now_time("mirbase_pre script was successfully finished!!")
input_file.close()
output_file.close()
def main():
utils.now_time("Input_file: " + p.phylop_score_R_input)
utils.now_time("Output_file: " + p.phylop_score_R_output)
output_s = p.phylop_score_R_output + 'phyloP46way_miRBase_v21_hg38Tohg19.txt'
output_file = open(output_s, 'w')
#for x in ['chrY']:
for x in [
'chr1', 'chr2', 'chr3', 'chr4', 'chr5', 'chr6', 'chr7', 'chr8',
'chr9', 'chr10', 'chr11', 'chr12', 'chr13', 'chr14', 'chr15',
'chr16', 'chr17', 'chr18', 'chr19', 'chr20', 'chr21', 'chr22',
'chrX', 'chrY', 'chrM'
]:
input_s = p.phylop_score_R_input + x + '.phyloP46way_miRBase_v21_hg38Tohg19_for_MIRAGE.db'
input_shelve = shelve.open(input_s)
max_length = 28 #Max_length: 28nt(miRNA)
for keys in input_shelve.keys():
values = input_shelve[keys]
value_length = len(values)
add_length = max_length - value_length
null_value = [0.000 for i in range(add_length)]
values += null_value
value_string = "\t".join(map(str, values))
print(keys, value_string, file=output_file, sep="\t", end="\n")
input_shelve.close()
output_file.close()
utils.now_time("phylop_score_R script was successfully finished!!")
def main():
utils.now_time("Input_file: " + p.phastcons_prep_input)
utils.now_time("Output_file: " + p.phastcons_prep_output)
for x in ['chrY']: #['chr1','chr2','chr3','chr4','chr5','chr6','chr7','chr8','chr9','chr10','chr11','chr12','chr13','chr14','chr15','chr16','chr17','chr18','chr19','chr20','chr21','chr22','chrX','chrY','chrM']:
input_s = p.phastcons_prep_input + x + '.phastCons46way.wigFix'
output_s = p.phastcons_prep_input + x + '.phastCons46way.bed'
phastcons_prep_input_file = open(input_s,'r')
phastcons_prep_output_file = open(output_s,'w')
chrom = ''
start_site = 0
step = 1
for line in phastcons_prep_input_file:
line = line.rstrip()
if re.match(r'^fixedStep',line):
regex = r'fixedStep chrom=(?P<chrom>.+) start=(?P<start>.+) step=(?P<step>.+)'
seq = re.match(regex,line)
chrom = seq.group('chrom')
start_site = int(seq.group('start')) - 1
step = int(seq.group('step'))
continue
score = line
#end_site = start_site + step
for x in range(step):
print (start_site, score, file=phastcons_prep_output_file, sep="\t", end="\n")
start_site += 1
utils.now_time("phastcons_prep script was successfully finished!!")
phastcons_prep_input_file.close()
phastcons_prep_output_file.close()
def main():
utils.now_time("Input_file: " + p.phastcons_prep_input)
utils.now_time("Output_file: " + p.phastcons_prep_output)
for x in [
'chrY'
]: #['chr1','chr2','chr3','chr4','chr5','chr6','chr7','chr8','chr9','chr10','chr11','chr12','chr13','chr14','chr15','chr16','chr17','chr18','chr19','chr20','chr21','chr22','chrX','chrY','chrM']:
input_s = p.phastcons_prep_input + x + '.phastCons46way.wigFix'
output_s = p.phastcons_prep_input + x + '.phastCons46way.bed'
phastcons_prep_input_file = open(input_s, 'r')
phastcons_prep_output_file = open(output_s, 'w')
chrom = ''
start_site = 0
step = 1
for line in phastcons_prep_input_file:
line = line.rstrip()
if re.match(r'^fixedStep', line):
regex = r'fixedStep chrom=(?P<chrom>.+) start=(?P<start>.+) step=(?P<step>.+)'
seq = re.match(regex, line)
chrom = seq.group('chrom')
start_site = int(seq.group('start')) - 1
step = int(seq.group('step'))
continue
score = line
#end_site = start_site + step
for x in range(step):
print(start_site,
score,
file=phastcons_prep_output_file,
sep="\t",
end="\n")
start_site += 1
utils.now_time("phastcons_prep script was successfully finished!!")
phastcons_prep_input_file.close()
phastcons_prep_output_file.close()
def main():
utils.now_time("Input_file: " + p.refseq_pre_input)
utils.now_time("Output_file: " + p.refseq_pre_output)
input_file = open(p.refseq_pre_input,'r')
output_file = open(p.refseq_pre_output,'w')
flg = 0
seq = ""
for line in input_file:
line = line.rstrip()
if re.match(r"^>",line): #Header
data = line.split()
refseq_id = data[0]
refseq_id = refseq_id.replace('>hg19_refGene_','')
if flg == 1:
print (seq,file=output_file,end="\n")
print (refseq_id,file=output_file,end="\t")
flg = 1
seq = ""
else: #Sequence
seq += line
print (seq,file=output_file,end="\n")
utils.now_time("Refseq_pre script was successfully finished!!")
input_file.close()
output_file.close()
def main():
utils.now_time("Input_file: " + p.refseq_pre_input)
utils.now_time("Output_file: " + p.refseq_pre_output)
input_file = open(p.refseq_pre_input, 'r')
output_file = open(p.refseq_pre_output, 'w')
flg = 0
seq = ""
for line in input_file:
line = line.rstrip()
if re.match(r"^>", line): #Header
data = line.split()
refseq_id = data[0]
refseq_id = refseq_id.replace('>hg19_refGene_', '')
if flg == 1:
print(seq, file=output_file, end="\n")
print(refseq_id, file=output_file, end="\t")
flg = 1
seq = ""
else: #Sequence
seq += line
print(seq, file=output_file, end="\n")
utils.now_time("Refseq_pre script was successfully finished!!")
input_file.close()
output_file.close()
def main():
utils.now_time("Input_file: " + p.mirmark_pos)
utils.now_time("Output_file: " + p.mirmark_output)
utils.now_time("miRNA_file: " + p.mirmark_mirna_fasta)
utils.now_time("TargetRNA_file: " + p.mirmark_targetrna_fasta)
utils.now_time("Refseq_data: " + p.refseq_pre_output)
utils.now_time("miRBase_data: " + p.mirbase_pre_output)
refseq_dict = {}
mirbase_dict = {}
#mirbase_dict
mirbase_file = open(p.mirbase_pre_output, 'r')
for line in mirbase_file:
line = line.rstrip()
data = line.split("\t")
infor = data[0].split('|')
mirbase_id = infor[0]
symbol = infor[1]
seq = data[1]
if not re.match('hsa', mirbase_id): #Only choose h**o sapiens miRNA
continue
mirbase_dict[mirbase_id] = [symbol,
seq] #miRNA_symbol => [0] | seq => [1]
#refseq_dict
refseq_file = open(p.refseq_pre_output, 'r')
for line in refseq_file:
line = line.rstrip()
data = line.split("\t")
refseq_id = data[0]
seq = data[1]
refseq_dict[refseq_id] = seq
#main
input_file = open(p.mirmark_pos, 'r')
output_file = open(p.mirmark_output, 'w')
mirna_file = open(p.mirmark_mirna_fasta, 'w')
targetrna_file = open(p.mirmark_targetrna_fasta, 'w')
error_file = open(p.mirmark_error, 'w')
mirna_dist = {}
targetrna_dist = {}
for line in input_file:
line = line.rstrip()
data = line.split(",")
if data[0] == 'miR_ID':
continue
mirbase_id = data[0]
refseq_id = data[1]
utr_st = 0 #int(data[3])-8 #int(data[2]) - 1
utr_ed = int(data[3])
if mirbase_id in convert_mirbase_id:
mirbase_id = convert_mirbase_id[mirbase_id]
if (refseq_id in refseq_dict and mirbase_id in mirbase_dict):
symbol = mirbase_dict[mirbase_id][0]
mir_seq = mirbase_dict[mirbase_id][1]
mir_seq_length = len(mir_seq)
utr_st = utr_ed - mir_seq_length - 5
ref_seq_raw = refseq_dict[refseq_id]
ref_seq = refseq_dict[refseq_id][utr_st:utr_ed]
ref_seq = ref_seq.replace("T", "U")
mir_tag = '>' + mirbase_id + '|' + symbol
refseq_tag = '>' + refseq_id
print(mirbase_id,
symbol,
mir_seq,
refseq_id,
utr_st,
utr_ed,
ref_seq,
file=output_file,
sep="\t",
end="\n")
mirna_dist[mir_tag] = mir_seq
targetrna_dist[refseq_tag] = ref_seq_raw
#miRNA_fasta
#print(mir_tag,file=mirna_file,end="\n")
#print(mir_seq,file=mirna_file,end="\n")
#targetRNA_fasta
#print(refseq_tag,file=targetrna_file,end="\n")
#print(ref_seq_raw,file=targetrna_file,end="\n")
else:
print("ERROR: " + refseq_id + '|' + mirbase_id,
file=error_file,
end="\n")
for key in list(mirna_dist.keys()):
print(key, file=mirna_file, end="\n")
print(mirna_dist[key], file=mirna_file, end="\n")
for key in list(targetrna_dist.keys()):
print(key, file=targetrna_file, end="\n")
print(targetrna_dist[key], file=targetrna_file, end="\n")
utils.now_time("mirmark_result script was successfully finished!!")
input_file.close()
output_file.close()
def main():
utils.now_time("Input_file: " + p.cupid_pos)
utils.now_time("Output_file: " + p.cupid_output)
utils.now_time("miRNA_file: " + p.cupid_mirna_fasta)
utils.now_time("targetRNA_file: " + p.cupid_targetrna_fasta)
utils.now_time("Refseq_data: " + p.refseq_pre_output)
utils.now_time("miRBase_data: " + p.mirbase_pre_output)
refseq_dict = {}
mirbase_dict = {}
#mirbase_dict
mirbase_file = open(p.mirbase_pre_output, 'r')
for line in mirbase_file:
line = line.rstrip()
data = line.split("\t")
infor = data[0].split('|')
mirbase_id = infor[0]
symbol = infor[1]
seq = data[1]
if not re.match('hsa', mirbase_id):
continue
mirbase_dict[mirbase_id] = [symbol,
seq] #miRNA_symbol => [0] | seq => [1]
#refseq_dict
refseq_file = open(p.refseq_pre_output, 'r')
for line in refseq_file:
line = line.rstrip()
data = line.split("\t")
refseq_id = data[0]
seq = data[1]
refseq_dict[refseq_id] = seq
#main
input_file = open(p.cupid_pos, 'r')
output_file = open(p.cupid_output, 'w')
mirna_file = open(p.cupid_mirna_fasta, 'w')
targetrna_file = open(p.cupid_targetrna_fasta, 'w')
error_file = open(p.cupid_error, 'w')
mirna_dist = {}
targetrna_dist = {}
for line in input_file:
line = line.rstrip()
data = line.split("\t")
if data[0] == 'AvgProb[0,1]':
continue
mirbase_id = data[4]
refseq_id = data[3]
if refseq_id == "NM_000927":
continue
utr_infor = data[5].split('-')
utr_st = int(utr_infor[0])
utr_ed = int(utr_infor[1])
if mirbase_id in convert_mirbase_id:
mirbase_id = convert_mirbase_id[mirbase_id]
if (refseq_id in refseq_dict and mirbase_id in mirbase_dict):
symbol = mirbase_dict[mirbase_id][0]
mir_seq = mirbase_dict[mirbase_id][1]
mir_seq_length = len(mir_seq)
utr_st = utr_ed - mir_seq_length - 5
ref_seq_raw = refseq_dict[refseq_id]
ref_seq = refseq_dict[refseq_id][utr_st:utr_ed]
ref_seq = ref_seq.replace("T", "U")
mir_tag = '>' + mirbase_id + '|' + symbol
refseq_tag = '>' + refseq_id
print(mirbase_id,
symbol,
mir_seq,
refseq_id,
utr_st,
utr_ed,
ref_seq,
file=output_file,
sep="\t",
end="\n")
mirna_dist[mir_tag] = mir_seq
targetrna_dist[refseq_tag] = ref_seq_raw
else:
print("ERROR: " + refseq_id + '|' + mirbase_id,
file=error_file,
end="\n")
for key in list(mirna_dist.keys()):
print(key, file=mirna_file, end="\n")
print(mirna_dist[key], file=mirna_file, end="\n")
for key in list(targetrna_dist.keys()):
print(key, file=targetrna_file, end="\n")
print(targetrna_dist[key], file=targetrna_file, end="\n")
utils.now_time("cupid_result script was successfully finished!!")
input_file.close()
output_file.close()
def main():
utils.now_time("Input_file: " + p.mirmark_pos)
utils.now_time("Output_file: " + p.mirmark_output)
utils.now_time("miRNA_file: " + p.mirmark_mirna_fasta)
utils.now_time("TargetRNA_file: " + p.mirmark_targetrna_fasta)
utils.now_time("Refseq_data: " + p.refseq_pre_output)
utils.now_time("miRBase_data: " + p.mirbase_pre_output)
refseq_dict = {}
mirbase_dict = {}
#mirbase_dict
mirbase_file = open(p.mirbase_pre_output,'r')
for line in mirbase_file:
line = line.rstrip()
data = line.split("\t")
infor = data[0].split('|')
mirbase_id = infor[0]
symbol = infor[1]
seq = data[1]
if not re.match('hsa',mirbase_id): #Only choose h**o sapiens miRNA
continue
mirbase_dict[mirbase_id] = [symbol,seq] #miRNA_symbol => [0] | seq => [1]
#refseq_dict
refseq_file = open(p.refseq_pre_output,'r')
for line in refseq_file:
line = line.rstrip()
data = line.split("\t")
refseq_id = data[0]
seq = data[1]
refseq_dict[refseq_id] = seq
#main
input_file = open(p.mirmark_pos,'r')
output_file = open(p.mirmark_output,'w')
mirna_file = open(p.mirmark_mirna_fasta,'w')
targetrna_file = open(p.mirmark_targetrna_fasta,'w')
error_file = open(p.mirmark_error,'w')
mirna_dist = {}
targetrna_dist = {}
for line in input_file:
line = line.rstrip()
data = line.split(",")
if data[0] == 'miR_ID':
continue
mirbase_id = data[0]
refseq_id = data[1]
utr_st = 0 #int(data[3])-8 #int(data[2]) - 1
utr_ed = int(data[3])
if mirbase_id in convert_mirbase_id:
mirbase_id = convert_mirbase_id[mirbase_id]
if (refseq_id in refseq_dict and mirbase_id in mirbase_dict):
symbol = mirbase_dict[mirbase_id][0]
mir_seq = mirbase_dict[mirbase_id][1]
mir_seq_length = len(mir_seq)
utr_st = utr_ed - mir_seq_length - 5
ref_seq_raw = refseq_dict[refseq_id]
ref_seq = refseq_dict[refseq_id][utr_st:utr_ed]
ref_seq = ref_seq.replace("T","U")
mir_tag = '>' + mirbase_id + '|' + symbol
refseq_tag = '>' + refseq_id
print(mirbase_id,symbol,mir_seq,refseq_id,utr_st,utr_ed,ref_seq,file=output_file,sep="\t",end="\n")
mirna_dist[mir_tag] = mir_seq
targetrna_dist[refseq_tag] = ref_seq_raw
#miRNA_fasta
#print(mir_tag,file=mirna_file,end="\n")
#print(mir_seq,file=mirna_file,end="\n")
#targetRNA_fasta
#print(refseq_tag,file=targetrna_file,end="\n")
#print(ref_seq_raw,file=targetrna_file,end="\n")
else:
print ("ERROR: " + refseq_id + '|' + mirbase_id,file=error_file,end="\n")
for key in list(mirna_dist.keys()):
print(key,file=mirna_file,end="\n")
print(mirna_dist[key],file=mirna_file,end="\n")
for key in list(targetrna_dist.keys()):
print(key,file=targetrna_file,end="\n")
print(targetrna_dist[key],file=targetrna_file,end="\n")
utils.now_time("mirmark_result script was successfully finished!!")
input_file.close()
output_file.close()
def main():
utils.now_time("Input_file: " + p.phylop_score_list_db_input)
utils.now_time("Reference_file: " + p.phylop_score_list_reference)
utils.now_time("Output_file: " + p.phylop_score_list_db_output)
output_merge = p.phylop_score_list_db_output + 'phyloP46way_Refseq_for_MIRAGE_CDS.db' #'phyloP46way_miRBase_v21_hg38Tohg19_for_MIRAGE.db'
output_merge_shelve = shelve.open(output_merge)
#for x in ['chrY']:
for x in ['chr1','chr2','chr3','chr4','chr5','chr6','chr7','chr8','chr9','chr10','chr11','chr12','chr13','chr14','chr15','chr16','chr17','chr18','chr19','chr20','chr21','chr22','chrX','chrY','chrM']:
ref_s = p.phylop_score_list_reference #mirBase, Refseq etc...
ref_file = open(ref_s,'r')
input_s = p.phylop_score_list_db_input + x + '.phyloP46way_Refseq_CDS.db' #'.phyloP46way_Refseq.db'
output_s = p.phylop_score_list_db_output + x + '.phyloP46way_Refseq_for_MIRAGE_CDS.db' #'.phyloP46way_Refseq_for_MIRAGE.db'
input_shelve = shelve.open(input_s)
output_shelve = shelve.open(output_s)
score_list_dict = {}
for line in ref_file:
line = line.rstrip()
data = line.split("\t")
chrom = data[0]
if not chrom == x:
continue
strand = data[5]
if len(data) >= 12: #12bed format
exon_block = data[10].split(',')
exon_block.pop() #Remove the last item ''
exon_st = data[11].split(',')
exon_st.pop() #Remove the last item ''
name = data[3]
score_list_dict[name] = []
for y in range(len(exon_block)):
st = int(data[1]) + int(exon_st[y])
ed = int(data[1]) + int(exon_st[y]) + int(exon_block[y])
length = ed - st
for z in range(length):
score = input_shelve[str(st)]
score_list_dict[name].append(score)
st += 1
if strand == '-':
rev_score = score_list_dict[name][::-1]
score_list_dict[name] = rev_score
elif len(data) >= 3: #6bed format
st = int(data[1])
ed = int(data[2])
length = ed - st
name = data[3]
score_list_dict[name] = []
for z in range(length):
score = input_shelve[str(st)]
score_list_dict[name].append(score)
st += 1
if strand == '-':
rev_score = score_list_dict[name][::-1]
score_list_dict[name] = rev_score
else:
print('ERROR: Your BED format file have less than three column.')
print ('BED format file need to have at least three column [chr, st, ed]...')
sys.exit(1)
output_shelve.update(score_list_dict)
output_merge_shelve.update(score_list_dict)
input_shelve.close()
output_shelve.close()
utils.now_time("phylop_score_list script was successfully finished!!")
output_merge_shelve.close()
def main():
utils.now_time("Input_file: " + p.cupid_pos)
utils.now_time("Output_file: " + p.cupid_output)
utils.now_time("miRNA_file: " + p.cupid_mirna_fasta)
utils.now_time("targetRNA_file: " + p.cupid_targetrna_fasta)
utils.now_time("Refseq_data: " + p.refseq_pre_output)
utils.now_time("miRBase_data: " + p.mirbase_pre_output)
refseq_dict = {}
mirbase_dict = {}
#mirbase_dict
mirbase_file = open(p.mirbase_pre_output,'r')
for line in mirbase_file:
line = line.rstrip()
data = line.split("\t")
infor = data[0].split('|')
mirbase_id = infor[0]
symbol = infor[1]
seq = data[1]
if not re.match('hsa',mirbase_id):
continue
mirbase_dict[mirbase_id] = [symbol,seq] #miRNA_symbol => [0] | seq => [1]
#refseq_dict
refseq_file = open(p.refseq_pre_output,'r')
for line in refseq_file:
line = line.rstrip()
data = line.split("\t")
refseq_id = data[0]
seq = data[1]
refseq_dict[refseq_id] = seq
#main
input_file = open(p.cupid_pos,'r')
output_file = open(p.cupid_output,'w')
mirna_file = open(p.cupid_mirna_fasta,'w')
targetrna_file = open(p.cupid_targetrna_fasta,'w')
error_file = open(p.cupid_error,'w')
mirna_dist = {}
targetrna_dist = {}
for line in input_file:
line = line.rstrip()
data = line.split("\t")
if data[0] == 'AvgProb[0,1]':
continue
mirbase_id = data[4]
refseq_id = data[3]
if refseq_id == "NM_000927":
continue
utr_infor = data[5].split('-')
utr_st = int(utr_infor[0])
utr_ed = int(utr_infor[1])
if mirbase_id in convert_mirbase_id:
mirbase_id = convert_mirbase_id[mirbase_id]
if (refseq_id in refseq_dict and mirbase_id in mirbase_dict):
symbol = mirbase_dict[mirbase_id][0]
mir_seq = mirbase_dict[mirbase_id][1]
mir_seq_length = len(mir_seq)
utr_st = utr_ed - mir_seq_length - 5
ref_seq_raw = refseq_dict[refseq_id]
ref_seq = refseq_dict[refseq_id][utr_st:utr_ed]
ref_seq = ref_seq.replace("T","U")
mir_tag = '>' + mirbase_id + '|' + symbol
refseq_tag = '>' + refseq_id
print(mirbase_id,symbol,mir_seq,refseq_id,utr_st,utr_ed,ref_seq,file=output_file,sep="\t",end="\n")
mirna_dist[mir_tag] = mir_seq
targetrna_dist[refseq_tag] = ref_seq_raw
else:
print ("ERROR: " + refseq_id + '|' + mirbase_id,file=error_file,end="\n")
for key in list(mirna_dist.keys()):
print(key,file=mirna_file,end="\n")
print(mirna_dist[key],file=mirna_file,end="\n")
for key in list(targetrna_dist.keys()):
print(key,file=targetrna_file,end="\n")
print(targetrna_dist[key],file=targetrna_file,end="\n")
utils.now_time("cupid_result script was successfully finished!!")
input_file.close()
output_file.close()
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)
def main():
utils.now_time("Input_file: " + p.phylop_sizedown_score_input)
utils.now_time("Reference_file: " + p.phylop_sizedown_bed_input)
utils.now_time("Output_file: " + p.phylop_sizedown_score_output)
'''
ref_s = p.phastcons_sizedown_bed_input #mirBase, Refseq etc...
ref_file = open(ref_s,'r')
ref_dict = {} #{NM_000XXXX: [st1,ed1],[st2,ed2]}
for line in ref_file:
line = line.rstrip()
data = line.split("\t")
if len(data) >= 12: #12bed format
st = 0
ed = 0
exon_block = data[10].split(',')
exon_block.pop()
exon_st = data[11].split(',')
exon_st.pop()
chrom = data[0]
name = data[3]
for y in range(len(exon_block)):
st = int(data[1]) + int(exon_st[y])
ed = int(data[1]) + int(exon_st[y]) + int(exon_block[y])
if not name in ref_dict:
ref_dict[name] = [[chrom,st,ed]]
else:
ref_dict[name].append([chrom,st,ed])
else: #6bed format
st = data[1]
ed = data[2]
name = data[3]
if not name in ref_dict:
ref_dict[name] = [[chrom,st,ed]]
else:
ref_dict[name].append([chrom,st,ed])
'''
for x in ['chr1','chr2','chr3','chr4','chr5','chr6','chr7','chr8','chr9','chr10','chr11','chr12','chr13','chr14','chr15','chr16','chr17','chr18','chr19','chr20','chr21','chr22','chrX','chrY','chrM']:
#for x in ['chrY']:
ref_s = p.phylop_sizedown_bed_input #mirBase, Refseq etc...
ref_file = open(ref_s,'r')
input_s = p.phylop_sizedown_score_input + x + '.phyloP46way.bed'
output_s = p.phylop_sizedown_score_output + x + '.phyloP46way_Refseq_CDS.db'
phylop_sizedown_input_file = open(input_s,'r')
score_dict = {}
for line in ref_file:
line = line.rstrip()
data = line.split("\t")
chrom = data[0]
if not x == chrom:
continue
if len(data) >= 12: #12bed format
exon_block = data[10].split(',')
exon_block.pop() #Remove the last item ''
exon_st = data[11].split(',')
exon_st.pop() #Remove the last item ''
#name = data[3]
for y in range(len(exon_block)):
st = int(data[1]) + int(exon_st[y])
ed = int(data[1]) + int(exon_st[y]) + int(exon_block[y])
length = ed - st
for z in range(length):
score_dict[str(st)] = 0
st += 1
elif len(data) >= 3: #6bed format
st = int(data[1])
ed = int(data[2])
length = ed - st
for z in range(length):
score_dict[str(st)] = 0
st += 1
else:
print('ERROR: Your BED format file have less than three column.')
print ('BED format file need to have at least three column [chr, st, ed]...')
sys.exit(1)
utils.now_time('Reference_file was loaded.')
for line in phylop_sizedown_input_file:
line = line.rstrip()
data = line.split("\t")
st_site = 0
score = 0
if re.match(r'^chr',data[0]):
st_site = data[1] #
score = data[2] #
else:
st_site = data[0] #
score = data[1] #
if st_site in score_dict:
score_dict[str(st_site)] = score
shelve_db = shelve.open(output_s)
shelve_db.update(score_dict)
utils.now_time("phylop_sizedown script was successfully finished!!")
phylop_sizedown_input_file.close()
shelve_db.close()
#!usr/bin/env python
import re
from parameter.common_parameters import common_parameters
from parameter.convert_mirbase_id import convert_mirbase_id
import utils.setting_utils as utils
utils.now_time("cupid_result script starting...")
p = utils.Bunch(common_parameters)
def main():
utils.now_time("Input_file: " + p.cupid_pos)
utils.now_time("Output_file: " + p.cupid_output)
utils.now_time("miRNA_file: " + p.cupid_mirna_fasta)
utils.now_time("targetRNA_file: " + p.cupid_targetrna_fasta)
utils.now_time("Refseq_data: " + p.refseq_pre_output)
utils.now_time("miRBase_data: " + p.mirbase_pre_output)
refseq_dict = {}
mirbase_dict = {}
#mirbase_dict
mirbase_file = open(p.mirbase_pre_output,'r')
for line in mirbase_file:
line = line.rstrip()
data = line.split("\t")
infor = data[0].split('|')
mirbase_id = infor[0]
symbol = infor[1]
seq = data[1]
if not re.match('hsa',mirbase_id):
continue
#!usr/bin/env python
import re
from parameter.common_parameters import common_parameters
import utils.setting_utils as utils
utils.now_time("mirbase_pre script starting...")
p = utils.Bunch(common_parameters)
def main():
utils.now_time("Input_file: " + p.mirbase_pre_input)
utils.now_time("Output_file: " + p.mirbase_pre_output)
input_file = open(p.mirbase_pre_input,'r')
output_file = open(p.mirbase_pre_output,'w')
flg = 0
seq = ""
for line in input_file:
line = line.rstrip()
if re.match(r"^>",line): #Header
data = line.split()
mir_id = data[0]
mir_id = mir_id.replace('>','')
symbol = data[1]
infor = mir_id + '|' + symbol
if flg == 1:
print (seq,file=output_file,end="\n")
print (infor,file=output_file,end="\t")
flg = 1
seq = ""
else: #Sequence
seq += line
#!usr/bin/env python
import re
from parameter.common_parameters import common_parameters
import utils.setting_utils as utils
utils.now_time("mirbase_gff2bed script starting...")
p = utils.Bunch(common_parameters)
def main():
utils.now_time("Input_file: " + p.mirbase_gff2bed_input)
utils.now_time("Output_file: " + p.mirbase_gff2bed_output)
mirbase_gff_file = open(p.mirbase_gff2bed_input, "r")
mirbase_bed_file = open(p.mirbase_gff2bed_output, "w")
for line in mirbase_gff_file:
line = line.rstrip()
data = line.split("\t")
if re.match(r"^#", line):
continue
chrom = data[0]
status = data[2]
st = int(data[3]) - 1
ed = data[4]
strand = data[6]
if status == "miRNA_primary_transcript":
continue
name_infor = data[8].split(";")
mir_id = re.sub(r"^ID=", "", name_infor[0])
#!usr/bin/env python
import re
from parameter.common_parameters import common_parameters
import utils.setting_utils as utils
utils.now_time("liftOver script starting...")
p = utils.Bunch(common_parameters)
def main():
input_file = p.liftover_input
output_file = p.liftover_output
error_file = output_file + '.error'
command_liftover = '../software/liftOver ' + input_file + ' ../software/hg38ToHg19.over.chain ' + output_file + ' ' + error_file
utils.run_command(command_liftover)
utils.now_time("liftOver script was successfully finished!!")
if __name__ == '__main__':
main()
#!usr/bin/env python
import re
from parameter.common_parameters import common_parameters
from parameter.convert_mirbase_id import convert_mirbase_id
import utils.setting_utils as utils
utils.now_time("mirmark_result script starting...")
p = utils.Bunch(common_parameters)
def main():
utils.now_time("Input_file: " + p.mirmark_pos)
utils.now_time("Output_file: " + p.mirmark_output)
utils.now_time("miRNA_file: " + p.mirmark_mirna_fasta)
utils.now_time("TargetRNA_file: " + p.mirmark_targetrna_fasta)
utils.now_time("Refseq_data: " + p.refseq_pre_output)
utils.now_time("miRBase_data: " + p.mirbase_pre_output)
refseq_dict = {}
mirbase_dict = {}
#mirbase_dict
mirbase_file = open(p.mirbase_pre_output, 'r')
for line in mirbase_file:
line = line.rstrip()
data = line.split("\t")
infor = data[0].split('|')
mirbase_id = infor[0]
symbol = infor[1]
seq = data[1]
if not re.match('hsa', mirbase_id): #Only choose h**o sapiens miRNA
#!usr/bin/env python
import sys
import re
import shelve
from parameter.common_parameters import common_parameters
import utils.setting_utils as utils
utils.now_time("phastcons_sizedown script starting...")
p = utils.Bunch(common_parameters)
def main():
utils.now_time("Input_file: " + p.phastcons_sizedown_score_input)
utils.now_time("Reference_file: " + p.phastcons_sizedown_bed_input)
utils.now_time("Output_file: " + p.phastcons_sizedown_score_output)
'''
ref_s = p.phastcons_sizedown_bed_input #mirBase, Refseq etc...
ref_file = open(ref_s,'r')
ref_dict = {} #{NM_000XXXX: [st1,ed1],[st2,ed2]}
for line in ref_file:
line = line.rstrip()
data = line.split("\t")
if len(data) >= 12: #12bed format
st = 0
ed = 0
exon_block = data[10].split(',')
exon_block.pop()
exon_st = data[11].split(',')
exon_st.pop()
#!usr/bin/env python
import re
from parameter.common_parameters import common_parameters
import utils.setting_utils as utils
utils.now_time("Refseq_pre script starting...")
p = utils.Bunch(common_parameters)
def main():
utils.now_time("Input_file: " + p.refseq_pre_input)
utils.now_time("Output_file: " + p.refseq_pre_output)
input_file = open(p.refseq_pre_input,'r')
output_file = open(p.refseq_pre_output,'w')
flg = 0
seq = ""
for line in input_file:
line = line.rstrip()
if re.match(r"^>",line): #Header
data = line.split()
refseq_id = data[0]
refseq_id = refseq_id.replace('>hg19_refGene_','')
if flg == 1:
print (seq,file=output_file,end="\n")
print (refseq_id,file=output_file,end="\t")
flg = 1
seq = ""
else: #Sequence
seq += line
print (seq,file=output_file,end="\n")
utils.now_time("Refseq_pre script was successfully finished!!")
#run_log("Calculating target site composition...", 4)
result_dict = target_site_composition(targetrna_seq, tmp_dict)
return run_result(result_dict)
def detect_rev_seed_match(mirna_id, targetrna_id):
'''
X1_seed_match_rev
'''
mirna_seq, targetrna_seq = get_sequence(mirna_id, targetrna_id)
targetrna_seq_revcomp = utils.reverse_complement(targetrna_seq)
tmp_dict = find_mirna_subtarget_candidates(mirna_id,mirna_seq,targetrna_id,targetrna_seq_revcomp) # => list()
return run_result(tmp_dict)
###MAIN###
utils.now_time("MIRAGE estimate is starting...")
mirna_dict = utils.load_fasta(p.MIRNA_FASTA_PATH)
targetrna_dict = utils.load_fasta(p.TARGETRNA_FASTA_PATH)
'''#shelve
#shelve_file
###Save_file
shelve_path = utils.get_absolute_path('./seed_match.db')
if os.path.isfile(shelve_path): #if shelve_file exists, it'll be removed.
os.remove(shelve_path)
seed_match_db = shelve.open('./seed_match.db')
'''#shelve
###Conservation_files
mirna_phastcons_path = utils.get_absolute_path('../data/PhastCons46Ways/phastCons46way_miRBase_v21_hg38Tohg19_for_MIRAGE.db')
mirna_phylop_path = utils.get_absolute_path('../data/PhyloP/phyloP46way_miRBase_v21_hg38Tohg19_for_MIRAGE.db')
#!usr/bin/env python
import sys
import re
import shelve
from parameter.common_parameters import common_parameters
import utils.setting_utils as utils
utils.now_time("phylop_sizedown script starting...")
p = utils.Bunch(common_parameters)
def main():
utils.now_time("Input_file: " + p.phylop_sizedown_score_input)
utils.now_time("Reference_file: " + p.phylop_sizedown_bed_input)
utils.now_time("Output_file: " + p.phylop_sizedown_score_output)
'''
ref_s = p.phastcons_sizedown_bed_input #mirBase, Refseq etc...
ref_file = open(ref_s,'r')
ref_dict = {} #{NM_000XXXX: [st1,ed1],[st2,ed2]}
for line in ref_file:
line = line.rstrip()
data = line.split("\t")
if len(data) >= 12: #12bed format
st = 0
ed = 0
exon_block = data[10].split(',')
exon_block.pop()
exon_st = data[11].split(',')
exon_st.pop()
def run_log(comment, step):
global flg_find_mirna_target_candidates
if flg_find_mirna_target_candidates == step:
utils.now_time(comment)
flg_find_mirna_target_candidates += 1
#!usr/bin/env python
import os
import re
from parameter.common_parameters import common_parameters
import utils.setting_utils as utils
utils.now_time("phastcons_prep script starting...")
p = utils.Bunch(common_parameters)
def main():
utils.now_time("Input_file: " + p.phastcons_prep_input)
utils.now_time("Output_file: " + p.phastcons_prep_output)
for x in [
'chrY'
]: #['chr1','chr2','chr3','chr4','chr5','chr6','chr7','chr8','chr9','chr10','chr11','chr12','chr13','chr14','chr15','chr16','chr17','chr18','chr19','chr20','chr21','chr22','chrX','chrY','chrM']:
input_s = p.phastcons_prep_input + x + '.phastCons46way.wigFix'
output_s = p.phastcons_prep_input + x + '.phastCons46way.bed'
phastcons_prep_input_file = open(input_s, 'r')
phastcons_prep_output_file = open(output_s, 'w')
chrom = ''
start_site = 0
step = 1
for line in phastcons_prep_input_file:
line = line.rstrip()
if re.match(r'^fixedStep', line):
regex = r'fixedStep chrom=(?P<chrom>.+) start=(?P<start>.+) step=(?P<step>.+)'
#!usr/bin/env python
import re
from parameter.common_parameters import common_parameters
import utils.setting_utils as utils
utils.now_time("mirbase_pre script starting...")
p = utils.Bunch(common_parameters)
def main():
utils.now_time("Input_file: " + p.mirbase_pre_input)
utils.now_time("Output_file: " + p.mirbase_pre_output)
input_file = open(p.mirbase_pre_input, 'r')
output_file = open(p.mirbase_pre_output, 'w')
flg = 0
seq = ""
for line in input_file:
line = line.rstrip()
if re.match(r"^>", line): #Header
data = line.split()
mir_id = data[0]
mir_id = mir_id.replace('>', '')
symbol = data[1]
infor = mir_id + '|' + symbol
if flg == 1:
print(seq, file=output_file, end="\n")
print(infor, file=output_file, end="\t")
flg = 1
seq = ""
else: #Sequence
#!/usr/bin/env python
import shelve
from parameter.common_parameters import common_parameters
import utils.setting_utils as utils
utils.now_time("phastcons_score_R script starting...")
p = utils.Bunch(common_parameters)
def main():
utils.now_time("Input_file: " + p.phylop_score_R_input)
utils.now_time("Output_file: " + p.phylop_score_R_output)
output_s = p.phylop_score_R_output + 'phyloP46way_miRBase_v21_hg38Tohg19.txt'
output_file = open(output_s, 'w')
#for x in ['chrY']:
for x in [
'chr1', 'chr2', 'chr3', 'chr4', 'chr5', 'chr6', 'chr7', 'chr8',
'chr9', 'chr10', 'chr11', 'chr12', 'chr13', 'chr14', 'chr15',
'chr16', 'chr17', 'chr18', 'chr19', 'chr20', 'chr21', 'chr22',
'chrX', 'chrY', 'chrM'
]:
input_s = p.phylop_score_R_input + x + '.phyloP46way_miRBase_v21_hg38Tohg19_for_MIRAGE.db'
input_shelve = shelve.open(input_s)
max_length = 28 #Max_length: 28nt(miRNA)
for keys in input_shelve.keys():
values = input_shelve[keys]
value_length = len(values)
add_length = max_length - value_length
#!usr/bin/env python
import re
from parameter.common_parameters import common_parameters
import utils.setting_utils as utils
utils.now_time("mirbase_gff2bed script starting...")
p = utils.Bunch(common_parameters)
def main():
utils.now_time("Input_file: " + p.mirbase_gff2bed_input)
utils.now_time("Output_file: " + p.mirbase_gff2bed_output)
mirbase_gff_file = open(p.mirbase_gff2bed_input,'r')
mirbase_bed_file = open(p.mirbase_gff2bed_output,'w')
for line in mirbase_gff_file:
line = line.rstrip()
data = line.split("\t")
if re.match(r'^#',line):
continue
chrom = data[0]
status = data[2]
st = int(data[3]) - 1
ed = data[4]
strand = data[6]
if status == 'miRNA_primary_transcript':
continue
name_infor = data[8].split(';')
mir_id = re.sub(r'^ID=','',name_infor[0])
mir_id_number = ''
#!usr/bin/env python
import sys
import re
import shelve
from parameter.common_parameters import common_parameters
import utils.setting_utils as utils
utils.now_time("phylop_score_list script starting...")
p = utils.Bunch(common_parameters)
def main():
utils.now_time("Input_file: " + p.phylop_score_list_db_input)
utils.now_time("Reference_file: " + p.phylop_score_list_reference)
utils.now_time("Output_file: " + p.phylop_score_list_db_output)
output_merge = p.phylop_score_list_db_output + 'phyloP46way_Refseq_for_MIRAGE_CDS.db' #'phyloP46way_miRBase_v21_hg38Tohg19_for_MIRAGE.db'
output_merge_shelve = shelve.open(output_merge)
#for x in ['chrY']:
for x in ['chr1','chr2','chr3','chr4','chr5','chr6','chr7','chr8','chr9','chr10','chr11','chr12','chr13','chr14','chr15','chr16','chr17','chr18','chr19','chr20','chr21','chr22','chrX','chrY','chrM']:
ref_s = p.phylop_score_list_reference #mirBase, Refseq etc...
ref_file = open(ref_s,'r')
input_s = p.phylop_score_list_db_input + x + '.phyloP46way_Refseq_CDS.db' #'.phyloP46way_Refseq.db'
output_s = p.phylop_score_list_db_output + x + '.phyloP46way_Refseq_for_MIRAGE_CDS.db' #'.phyloP46way_Refseq_for_MIRAGE.db'
input_shelve = shelve.open(input_s)
output_shelve = shelve.open(output_s)
score_list_dict = {}
#!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()
#!usr/bin/env python
import re
from parameter.common_parameters import common_parameters
from parameter.convert_mirbase_id import convert_mirbase_id
import utils.setting_utils as utils
utils.now_time("mirmark_result script starting...")
p = utils.Bunch(common_parameters)
def main():
utils.now_time("Input_file: " + p.mirmark_pos)
utils.now_time("Output_file: " + p.mirmark_output)
utils.now_time("miRNA_file: " + p.mirmark_mirna_fasta)
utils.now_time("TargetRNA_file: " + p.mirmark_targetrna_fasta)
utils.now_time("Refseq_data: " + p.refseq_pre_output)
utils.now_time("miRBase_data: " + p.mirbase_pre_output)
refseq_dict = {}
mirbase_dict = {}
#mirbase_dict
mirbase_file = open(p.mirbase_pre_output,'r')
for line in mirbase_file:
line = line.rstrip()
data = line.split("\t")
infor = data[0].split('|')
mirbase_id = infor[0]
symbol = infor[1]
seq = data[1]
if not re.match('hsa',mirbase_id): #Only choose h**o sapiens miRNA
continue
#!usr/bin/env python
import re
from parameter.common_parameters import common_parameters
import utils.setting_utils as utils
utils.now_time("Refseq_pre script starting...")
p = utils.Bunch(common_parameters)
def main():
utils.now_time("Input_file: " + p.refseq_pre_input)
utils.now_time("Output_file: " + p.refseq_pre_output)
input_file = open(p.refseq_pre_input, 'r')
output_file = open(p.refseq_pre_output, 'w')
flg = 0
seq = ""
for line in input_file:
line = line.rstrip()
if re.match(r"^>", line): #Header
data = line.split()
refseq_id = data[0]
refseq_id = refseq_id.replace('>hg19_refGene_', '')
if flg == 1:
print(seq, file=output_file, end="\n")
print(refseq_id, file=output_file, end="\t")
flg = 1
seq = ""
else: #Sequence
seq += line
print(seq, file=output_file, end="\n")
#!usr/bin/env python
import re
from parameter.common_parameters import common_parameters
from parameter.convert_mirbase_id import convert_mirbase_id
import utils.setting_utils as utils
utils.now_time("cupid_result script starting...")
p = utils.Bunch(common_parameters)
def main():
utils.now_time("Input_file: " + p.cupid_pos)
utils.now_time("Output_file: " + p.cupid_output)
utils.now_time("miRNA_file: " + p.cupid_mirna_fasta)
utils.now_time("targetRNA_file: " + p.cupid_targetrna_fasta)
utils.now_time("Refseq_data: " + p.refseq_pre_output)
utils.now_time("miRBase_data: " + p.mirbase_pre_output)
refseq_dict = {}
mirbase_dict = {}
#mirbase_dict
mirbase_file = open(p.mirbase_pre_output, 'r')
for line in mirbase_file:
line = line.rstrip()
data = line.split("\t")
infor = data[0].split('|')
mirbase_id = infor[0]
symbol = infor[1]
seq = data[1]
if not re.match('hsa', mirbase_id):
#!/usr/bin/env python
import shelve
from parameter.common_parameters import common_parameters
import utils.setting_utils as utils
utils.now_time("phastcons_score_R script starting...")
p = utils.Bunch(common_parameters)
def main():
utils.now_time("Input_file: " + p.phylop_score_R_input)
utils.now_time("Output_file: " + p.phylop_score_R_output)
output_s = p.phylop_score_R_output + 'phyloP46way_miRBase_v21_hg38Tohg19.txt'
output_file = open(output_s,'w')
#for x in ['chrY']:
for x in ['chr1','chr2','chr3','chr4','chr5','chr6','chr7','chr8','chr9','chr10','chr11','chr12','chr13','chr14','chr15','chr16','chr17','chr18','chr19','chr20','chr21','chr22','chrX','chrY','chrM']:
input_s = p.phylop_score_R_input + x + '.phyloP46way_miRBase_v21_hg38Tohg19_for_MIRAGE.db'
input_shelve = shelve.open(input_s)
max_length = 28 #Max_length: 28nt(miRNA)
for keys in input_shelve.keys():
values = input_shelve[keys]
value_length = len(values)
add_length = max_length - value_length
null_value = [0.000 for i in range(add_length)]
values += null_value
value_string = "\t".join(map(str, values))
print(keys,value_string, file=output_file, sep="\t", end="\n")
input_shelve.close()
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)
#!usr/bin/env python
import os
import re
from parameter.common_parameters import common_parameters
import utils.setting_utils as utils
utils.now_time("phastcons_prep script starting...")
p = utils.Bunch(common_parameters)
def main():
utils.now_time("Input_file: " + p.phastcons_prep_input)
utils.now_time("Output_file: " + p.phastcons_prep_output)
for x in ['chrY']: #['chr1','chr2','chr3','chr4','chr5','chr6','chr7','chr8','chr9','chr10','chr11','chr12','chr13','chr14','chr15','chr16','chr17','chr18','chr19','chr20','chr21','chr22','chrX','chrY','chrM']:
input_s = p.phastcons_prep_input + x + '.phastCons46way.wigFix'
output_s = p.phastcons_prep_input + x + '.phastCons46way.bed'
phastcons_prep_input_file = open(input_s,'r')
phastcons_prep_output_file = open(output_s,'w')
chrom = ''
start_site = 0
step = 1
for line in phastcons_prep_input_file:
line = line.rstrip()
if re.match(r'^fixedStep',line):
regex = r'fixedStep chrom=(?P<chrom>.+) start=(?P<start>.+) step=(?P<step>.+)'
seq = re.match(regex,line)
chrom = seq.group('chrom')
start_site = int(seq.group('start')) - 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)
#!usr/bin/env python
import re
from parameter.common_parameters import common_parameters
import utils.setting_utils as utils
utils.now_time("liftOver script starting...")
p = utils.Bunch(common_parameters)
def main():
input_file = p.liftover_input
output_file = p.liftover_output
error_file = output_file + '.error'
command_liftover = '../software/liftOver ' + input_file + ' ../software/hg38ToHg19.over.chain ' + output_file + ' ' + error_file
utils.run_command(command_liftover)
utils.now_time("liftOver script was successfully finished!!")
if __name__ == '__main__':
main()