def Augustus(tool_pred, genome):
augustus_ORFs = collections.OrderedDict()
genome_size = len(genome)
genome_rev = revCompIterative(genome)
with open(tool_pred, 'r') as Augustus_input:
for line in Augustus_input:
line = line.split()
if len(line) == 12 and "CDS" in line[2]:
start = int(line[3])
stop = int(line[4])
strand = line[6]
if '-' in strand: # Reverse Compliment starts and stops adjusted
r_start = genome_size - stop
r_stop = genome_size - start
startCodon = genome_rev[r_start:r_start + 3]
stopCodon = genome_rev[r_stop - 2:r_stop + 1]
elif '+' in strand:
startCodon = genome[start - 1:start + 2]
stopCodon = genome[stop - 3:stop]
po = str(start) + ',' + str(stop)
orf = [strand, startCodon, stopCodon]
augustus_ORFs.update({po: orf})
augustus_ORFs = sortORFs(augustus_ORFs)
return augustus_ORFs
def FGENESB(tool_pred, genome):
FGENESB_ORFs = collections.OrderedDict()
genome_size = len(genome)
genome_rev = revCompIterative(genome)
with open(tool_pred, 'r') as FGENESB_input:
for line in FGENESB_input:
if '>GENE' in line:
line = line.split()
if '2208' in line:
print("ss")
if len(line) == 10 and ">GENE" in line[0]:
start = int(line[2])
stop = int(line[4])
strand = line[9]
if '-' in strand: # Reverse Compliment starts and stops adjusted
r_start = genome_size - stop
r_stop = genome_size - start
startCodon = genome_rev[r_start:r_start + 3]
stopCodon = genome_rev[r_stop - 2:r_stop + 1]
elif '+' in strand:
startCodon = genome[start - 1:start + 2]
stopCodon = genome[stop - 3:stop]
po = str(start) + ',' + str(stop)
orf = [strand, startCodon, stopCodon]
FGENESB_ORFs.update({po: orf})
FGENESB_ORFs = sortORFs(FGENESB_ORFs)
return FGENESB_ORFs
def GeneMark_HA(tool_pred, genome):
geneMark_HA_ORFs = collections.OrderedDict()
genome_size = len(genome)
genome_rev = revCompIterative(genome)
with open(tool_pred, 'r') as GeneMark_HA_input:
for line in GeneMark_HA_input:
line = line.split()
if len(line) >= 9 and "CDS" in line[5]:
start = int(line[6])
stop = int(line[7])
strand = line[9]
if '-' in strand: # Reverse Compliment starts and stops adjusted
r_start = genome_size - stop
r_stop = genome_size - start
startCodon = genome_rev[r_start:r_start + 3]
stopCodon = genome_rev[r_stop - 2:r_stop + 1]
elif '+' in strand:
startCodon = genome[start - 1:start + 2]
stopCodon = genome[stop - 3:stop]
po = str(start) + ',' + str(stop)
orf = [strand, startCodon, stopCodon]
geneMark_HA_ORFs.update({po: orf})
geneMark_HA_ORFs = sortORFs(geneMark_HA_ORFs)
return geneMark_HA_ORFs
def GLIMMER_3(tool_pred, genome):
GLIMMER_ORFs = collections.OrderedDict()
genome_size = len(genome)
genome_rev = revCompIterative(genome)
with open(
tool_pred, 'r'
) as glimmer_input: # GLIMMER_3 reverses the start and stop positions for ORFS on the negative strand
for line in glimmer_input:
if '>' not in line: # This will not work with multiple contigs
line = line.split()
if len(line) == 5 and "orf" in line[0]:
if '-' in line[
3]: # Reverse Compliment starts and stops adjusted - Switched to match Sense Strand
start = int(line[2])
stop = int(line[1])
strand = '-'
r_start = genome_size - stop
r_stop = genome_size - start
startCodon = genome_rev[r_start:r_start + 3]
stopCodon = genome_rev[r_stop - 2:r_stop + 1]
elif '+' in line[3]:
start = int(line[1])
stop = int(line[2])
strand = '+'
startCodon = genome[start - 1:start + 3]
stopCodon = genome[stop - 3:stop]
po = str(start) + ',' + str(stop)
orf = [strand, startCodon, stopCodon]
GLIMMER_ORFs.update({po: orf})
GLIMMER_ORFs = sortORFs(GLIMMER_ORFs)
return GLIMMER_ORFs
def GFF(tool_pred, genome):
GFF_ORFs = collections.OrderedDict()
genome_size = len(genome)
genome_rev = revCompIterative(genome)
with open(tool_pred, 'r') as gff_input:
for line in gff_input:
if '#' not in line:
line = line.split('\t')
if "CDS" in line[2] and len(line) == 9:
start = int(line[3])
stop = int(line[4])
strand = line[6]
if '-' in strand: # Reverse Compliment starts and stops adjusted
r_start = genome_size - stop
r_stop = genome_size - start
startCodon = genome_rev[r_start:r_start + 3]
stopCodon = genome_rev[r_stop - 2:r_stop + 1]
elif '+' in strand:
startCodon = genome[start - 1:start + 2]
stopCodon = genome[stop - 3:stop]
po = str(start) + ',' + str(stop)
orf = [strand, startCodon, stopCodon]
GFF_ORFs.update({po: orf})
elif "CDS" in line[2]:
sys.exit("SAS")
GFF_ORFs = sortORFs(GFF_ORFs)
return GFF_ORFs
def GeneMark(tool_pred, genome):
geneMark_ORFs = collections.OrderedDict()
genome_size = len(genome)
genome_rev = revCompIterative(genome)
prev_Start = 0
prev_Stop = 0
started = False
with open(tool_pred, 'r') as GeneMark_input:
for line in GeneMark_input:
line = line.split()
if len(line) == 7:
started = True
if 'direct' in line[2] or 'complement' in line[
2]: # Strange Output requires strange code - We select the Longest ORF from each set
start = int(line[0])
stop = int(line[1])
strand = line[2]
if 'complement' in strand: # Reverse Compliment starts and stops adjusted
if start != prev_Start:
r_start = genome_size - stop
r_stop = genome_size - start
strand = '-'
startCodon = genome_rev[r_start:r_start + 3]
stopCodon = genome_rev[r_stop - 2:r_stop + 1]
po = str(start) + ',' + str(stop)
orf = [strand, startCodon, stopCodon]
geneMark_ORFs.update({po: orf})
elif 'direct' in strand:
if stop != prev_Stop:
startCodon = genome[start - 1:start + 2]
stopCodon = genome[stop - 3:stop]
strand = '+'
po = str(start) + ',' + str(stop)
orf = [strand, startCodon, stopCodon]
geneMark_ORFs.update({po: orf})
prev_Start = start
prev_Stop = stop
elif len(line) == 0 and started == True:
prev_Stop = 0
prev_Start = 0
geneMark_ORFs = sortORFs(geneMark_ORFs)
return geneMark_ORFs