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 exonic_circRNA(exon_list, args):
circRNA_seq = ""
for exon in exon_list:
exon_seq = Seq(pysam.faidx(args.G, exon), generic_dna)
if args.s == "-":
exon_seq = str(exon_seq[(
len(exon_seq.split('\n')[0])):-1].upper().reverse_complement())
circRNA_seq += exon_seq
elif args.s == "+":
exon_seq = str(exon_seq[(len(exon_seq.split('\n')[0])):-1].upper())
circRNA_seq += exon_seq
# Making a one line sequence
circRNA_seq = circRNA_seq.replace("\n", "")
return circRNA_seq
def find_frame(s):
# Finds longest ORF
s = s.replace("-", "")
seq1 = Seq(s, generic_dna).translate() # translate in every frame
seq2 = Seq(s[1:], generic_dna).translate()
seq3 = Seq(s[2:], generic_dna).translate()
L_seq1 = max([len(x)
for x in seq1.split("*")]) # find longest ORF in each frame
L_seq2 = max([len(x) for x in seq2.split("*")])
L_seq3 = max([len(x) for x in seq3.split("*")])
Ls = [L_seq1, L_seq2, L_seq3]
L_max = max(Ls) # get longest ORF among all frames
frames_max = [i for i, x in enumerate(Ls)
if x == L_max] # get frame of longest ORF
if len(frames_max) > 1:
print "Warning: more than one reading frame had max length ORF"
return frames_max[0]
def upstream_and_downstream_seq(coords, out_path):
chromosome = coords.split(":")[0]
start = str(int(coords.split(":")[1].split("-")[0]))
downstream = str(int(coords.split(":")[1].split("-")[0]) - 500)
end = str(int(coords.split(":")[1].split("-")[1]))
upstream = str(int(coords.split(":")[1].split("-")[1]) + 500)
#using the samtools faidx function to take the appropriate sequence from a reference genome
downstream_fa = Seq(
pysam.faidx(
"/Users/lachlan/Documents/Masters_Research_2019/Data/ICM/genome.fa",
chromosome + ":" + downstream + "-" + start), generic_dna)
upstream_fa = Seq(
pysam.faidx(
"/Users/lachlan/Documents/Masters_Research_2019/Data/ICM/genome.fa",
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")
# Writing sequences to fasta file
downstream_outfile = open(os.path.join(out_path, "downstream.fa"), "w")
downstream_outfile.write(">" + str(downstream_seq.id) + "\n" +
str(downstream_seq.seq))
upstream_outfile = open(os.path.join(out_path, "upstream.fa"), "w")
upstream_outfile.write(">" + str(reverse_compliment_upstream_seq.id) +
"\n" + str(reverse_compliment_upstream_seq.seq))
def randomprotein(percentage):
inp = percentage
length = 10000
gcpercent = float(inp) / 100
atpercent = 1 - gcpercent
gcthou = int(length * gcpercent)
atthou = int(length * atpercent)
seq = ""
goodlen = True
while goodlen:
rand = random.uniform(0, 1)
if (rand >= 0 and rand < gcpercent / 2):
seq += "G"
elif (rand >= gcpercent / 2 and rand < gcpercent):
seq += "C"
elif (rand >= gcpercent and rand < 1 - (atpercent / 2)):
seq += "A"
elif (rand >= 1 - (atpercent / 2) and rand <= 1):
seq += "T"
if (len(seq) == 10000):
goodlen = False
seq = Seq(seq)
seq = seq.translate()
split = seq.split("*")
for i in range(0, len(split)):
largest = ""
if (len(split[i]) > len(largest)):
largest = split[i]
return (len(largest))
dnaSeq = open("data\\dna_chromosome_1.seq", "r")
my_seq = dnaSeq.read()
print(my_seq)
RNA = Seq(my_seq).transcribe()
rev = RNA[::-1]
print(rev)
reverseRNASeq = open("reverse_RNAsequence_1.seq", "w")
reverseRNASeq.write(rev.__str__())
reverseRNASeq.close()
# Zad 6
mySeq = open("sampleData.txt", "r")
my_seq = mySeq.read()
#print(my_seq)
s, t = my_seq.split("\n")
print("s: " + s)
print("t: " + t)
for n in range(len(s) - len(t)):
if t == s[n:(len(t) + n)]:
print(n + 1)
# Zad 7
mySeq = open("seqSampleData.txt", "r")
my_seq = mySeq.read()
# RNA transcribe
RNA = Seq(my_seq).transcribe().__str__()
startCodon = "AUG"
rawseq=retr_db(database, elt[0])
clen=len(rawseq)
scaf.write('>'+elt[0]+'_'+rec[2]+'\n'+rawseq+'\n')
if sens=='+':
start=sstart-3*(qstart-1) if sstart-3*(qstart-1)>1 else sstart
end=send+3*(qlen-qend) if send+3*(qlen-qend)<clen else send
elif sens=='-':
start=sstart-3*(qlen-qend) if sstart-3*(qlen-qend)>1 else sstart
end=send+3*(qstart-1) if send+3*(qstart-1)<clen else send
print elt[0],elt[2],sens,sstart,send,qstart,qend,start,end,clen
hdseq=Seq(rawseq[start-1:end],IUPAC.unambiguous_dna)
if sens=='-':
hdseq=hdseq.reverse_complement()
hdseq=hdseq.split('N')[0]
print hdseq.translate()
#head='>'+prefix+'_'+elt[2].split('_')[1]+'-'+elt[0].split('|')[1]+'@'+'-'.join(map(str,elt[1]))+'\n'
head='>'+prefix+'_'+elt[2].split('_')[1]+'|ND'+elt[0].split('_')[1]+'@'+'-'.join(map(str,elt[1]))+'\n'
prot.write(head+hdseq.translate().tostring()+'\n')
nucl.write(head+hdseq.tostring()+'\n')
#+'-'.join(map(str,elt[1])
except:
d = None
orf_sequence = defaultdict(list)
for rec in orfs:
orf_sequence[str(rec.seq)].append(rec.id)
export = []
mapping = {}
count = 1
for seq in orf_sequence:
id = 'orf_sequence_{}'.format(str(count))
ids = orf_sequence[seq]
for i in ids:
mapping[i] = id
description = ';'.join(ids)
seq = Seq(''.join(seq.split('*')))
record = SeqRecord(id=id, description=description, seq=seq)
export.append(record)
count += 1
SeqIO.write(export, path + '/nr_translated_pg_orfs.fasta', 'fasta')
outpath = path + '/id_mapping.json'
mapping = json.dumps(mapping)
with open(outpath, 'w') as f:
f.write(mapping)
