def upstream_and_downstream_seq(args):
chromosome = split_coords(args.coords)[0]
start = str(split_coords(args.coords)[1])
downstream = str(int(start)-1000)
end = str(split_coords(args.coords.replace('"', ""))[2])
upstream = str(int(end)+1000)
#using the samtools faidx function to take the appropriate sequence from a reference genome
downstream_fa = Seq(pysam.faidx(args.genome, chromosome+":"+downstream+"-"+start), generic_dna)
upstream_fa = Seq(pysam.faidx(args.genome, chromosome+":"+end+"-"+upstream), generic_dna)
# Selecting only the sequence and converting to uppercase
downstream_seq = downstream_fa[(len(downstream_fa.split('\n')[0])):-1].upper()
# Selecting only the sequence, converting to uppercase, reversing and then getting the complementary sequence
reverse_compliment_upstream_seq = upstream_fa[(len(upstream_fa.split('\n')[0])):-1].upper().reverse_complement()
# Making sequence records with ID header and sequence
downstream_seq = SeqRecord(downstream_seq, id="downstream_sequence")
reverse_compliment_upstream_seq = SeqRecord(reverse_compliment_upstream_seq, id="upstream_sequence")
if os.path.isdir(args.directory+"tmp/") == False:
os.mkdir(args.directory+"tmp/")
# Writing sequences to fasta file
downstream_outfile = open(os.path.join(args.directory+"tmp/", "downstream.fa"), "w")
downstream_outfile.write(">"+str(downstream_seq.id) + "\n" + str(downstream_seq.seq))
upstream_outfile = open(os.path.join(args.directory+"tmp/", "upstream.fa"), "w")
upstream_outfile.write(">"+str(reverse_compliment_upstream_seq.id) + "\n" + str(reverse_compliment_upstream_seq.seq))
def location_of_binding(args, outlist, exon_list):
finaloutlist = []
for line in outlist:
col = line.split("\t")
if int(col[9]) < split_coords(args.coords)[1]:
line = line + "\t" + "Downstream"
elif int(col[9]) > split_coords(args.coords)[2]:
line = line + "\t" + "Upstream"
elif int(col[9]) > split_coords(args.coords)[1] and int(
col[10]) < split_coords(args.coords)[2]:
line = line + "\t" + "circRNA"
elif int(col[9]) == split_coords(args.coords)[1] or int(
col[10]) == split_coords(args.coords)[2]:
line = line + "\t" + "BSJ"
elif int(col[10]) > split_coords(args.coords)[1] or int(
col[9]) < split_coords(args.coords)[2]:
line = line + "\t" + "BSJ"
finaloutlist.append(line)
for exon in exon_list:
if int(col[9]) >= split_coords(exon)[1] and int(
col[10]) <= split_coords(exon)[2]:
line = line + "\t" + "Exon Binding"
finaloutlist.append(line)
return finaloutlist
def exon_coords(args):
line_number1 = []
line_number2 = []
exon_file = open(args.exon).read().splitlines()
for line in exon_file:
col = line.split("\t")
if col[0] == split_coords(
args.coords)[0] and col[2] == "exon" and col[3] == str(
split_coords(args.coords)[1]):
line_number1.append(exon_file.index(line))
if col[0] == split_coords(
args.coords)[0] and col[2] == "exon" and col[4] == str(
split_coords(args.coords)[2]):
line_number2.append(exon_file.index(line))
# Making list of exons composing circRNA
exon_list = []
for line in exon_file[line_number1[0]:line_number2[0] + 1]:
col = line.split("\t")
if col[2] == "exon":
exon_list.append(col[0] + ":" + col[3] + "-" + col[4])
exon_list = remove_duplicates(exon_list)
return exon_list
def intron_binding(args, finaloutlist):
yes_count = 0
for element in finaloutlist:
col = element.split("\t")
if int(col[9]) < split_coords(args.coords)[1] \
or int(col[9]) > split_coords(args.coords)[2]:
yes_count += 1
return yes_count
def check_circBase(args, circBase):
match = []
for line in circBase:
col = line.split("\t")
if "#" not in line:
if split_coords(args.coords)[0] == col[0] and split_coords(
args.coords)[1] == int(col[1]) and split_coords(
args.coords)[2] == int(col[2]):
match.append(line)
return match
def index_gtf(args):
line_number1 = []
line_number2 = []
gtf_file = open(args.A).read().splitlines()
for line in gtf_file:
col = line.split("\t")
if col[0] == split_coords(
args.ID)[0] and col[2] == "exon" and col[3] == str(
split_coords(args.ID)[1]):
line_number1.append(gtf_file.index(line))
elif col[0] == split_coords(
args.ID)[0] and col[2] == "exon" and col[4] == str(
split_coords(args.ID)[2]):
line_number2.append(gtf_file.index(line))
return line_number1, line_number2, gtf_file
def up_intron(args):
annotation = open(args.annotation, "r").read().splitlines()
for line in annotation:
col = line.split("\t")
if int(col[1]) == split_coords(args.coords)[2]:
upstream_intron = (int(col[2]))
return upstream_intron
def ENCORI(args, downstream_intron, upstream_intron):
outlist = []
infile = open(args.infile, "r").read().splitlines()
for line in infile:
if "#" not in line:
col = line.split("\t")
if col[8] == split_coords(args.coords)[0] \
and int(col[9]) >= downstream_intron + 1 \
and int(col[10]) <= upstream_intron:
outlist.append(line)
return outlist