def main():
parser = argparse.ArgumentParser(
description=
"Make a gpd with unique transcript names and a key to their original gpd entry\n"
)
parser.add_argument("gpd_infile", help="FILENAME genepred file")
parser.add_argument("gpd_outfile", help="FILENAME genepred file")
args = parser.parse_args()
gfr = GenericFileReader(args.gpd_infile)
seen = {}
while True:
line = gfr.readline()
if not line: break
if re.match('^#', line): continue
line = line.rstrip()
f = line.split("\t")
if f[1] not in seen:
seen[f[1]] = []
seen[f[1]].append(line)
gfr.close()
of_gpd = open(args.gpd_outfile, 'w')
of_key = open(args.gpd_outfile + ".key_file", 'w')
for tx in seen:
for i in range(0, len(seen[tx])):
name = tx
if len(seen[tx]) > 1:
name = tx + '[' + str(i + 1) + '/' + str(len(seen[tx])) + ']'
f = seen[tx][i].split("\t")
f[1] = name
newline = "\t".join(f)
of_key.write(name + "\t" + seen[tx][i] + "\n")
of_gpd.write(newline + "\n")
of_key.close()
of_gpd.close()
def main():
parser = argparse.ArgumentParser(description="Make a gpd with unique transcript names and a key to their original gpd entry\n")
parser.add_argument("gpd_infile",help="FILENAME genepred file")
parser.add_argument("gpd_outfile",help="FILENAME genepred file")
args = parser.parse_args()
gfr = GenericFileReader(args.gpd_infile)
seen = {}
while True:
line = gfr.readline()
if not line: break
if re.match('^#',line): continue
line = line.rstrip()
f = line.split("\t")
if f[1] not in seen:
seen[f[1]] = []
seen[f[1]].append(line)
gfr.close()
of_gpd = open(args.gpd_outfile,'w')
of_key = open(args.gpd_outfile+".key_file",'w')
for tx in seen:
for i in range(0,len(seen[tx])):
name = tx
if len(seen[tx]) > 1:
name = tx + '['+str(i+1)+'/'+str(len(seen[tx]))+']'
f = seen[tx][i].split("\t")
f[1] = name
newline = "\t".join(f)
of_key.write(name + "\t" + seen[tx][i] + "\n")
of_gpd.write(newline + "\n")
of_key.close()
of_gpd.close()
def main():
parser = argparse.ArgumentParser(description='Use reference junctions when they are close',formatter_class=argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument('--min_intron_size',type=int,default=68,help="INT min intron size")
parser.add_argument('--min_local_support',type=int,default=0,help="INT min number of junctions within search_size of a junction in order to count it")
parser.add_argument('--search_size',type=int,default=10,help="INT search space for reference")
parser.add_argument('--output_fake_psl',help="FASTAFILE reference genome to make a fake PSL output")
parser.add_argument('psl',help="PSLFILENAME or '-' for STDIN")
parser.add_argument('reference_genepred',help="FASTAFILENAME for reference genepred")
args = parser.parse_args()
cpus = multiprocessing.cpu_count()
genome = {}
if args.output_fake_psl:
genome = read_fasta_into_hash(args.output_fake_psl)
#read in the reference genepred first
gpf = GenePredBasics.GenePredFile(args.reference_genepred)
#lets sort entries by chromosome
ref = {}
for e in [x.entry for x in gpf.entries]:
if len(e['exonStarts']) <= 1: continue
if e['chrom'] not in ref:
ref[e['chrom']] = {}
for i in range(1,len(e['exonStarts'])):
if e['exonEnds'][i-1] not in ref[e['chrom']]:
ref[e['chrom']][e['exonEnds'][i-1]] = {}
if e['exonStarts'][i]+1 not in ref[e['chrom']][e['exonEnds'][i-1]]:
ref[e['chrom']][e['exonEnds'][i-1]][e['exonStarts'][i]+1] = e['strand']
#Stored all junctions as 1-base
read_info = {}
pf = GenericFileReader(args.psl)
fcount_total = 0
while True:
line = pf.readline()
if not line: break
if re.match('^#',line): continue
line = line.rstrip()
pe = PSLBasics.line_to_entry(line)
if len(pe['tStarts']) != len(pe['blockSizes']) or len(pe['qStarts']) != len(pe['blockSizes']):
sys.stderr.write("WARNING invalid psl\n")
continue
genepred_line = PSLBasics.convert_entry_to_genepred_line(pe)
ge = GenePredBasics.smooth_gaps(GenePredBasics.line_to_entry(genepred_line),args.min_intron_size)
refjuns = {}
if pe['tName'] in ref: refjuns = ref[pe['tName']]
new_ge = nudge(pe,ge,refjuns,args)
if args.output_fake_psl:
new_psl_line = GenePredBasics.entry_to_fake_psl_line(new_ge,genome)
print new_psl_line
else:
print GenePredBasics.entry_to_line(new_ge)
def __init__(self, filename):
self.filename = filename
self.gfr = GenericFileReader(filename)
self.entries = []
while True:
line = self.gfr.readline()
if not line: break
if re.match('^#', line): continue
gpe = GenePredEntry()
gpe.line_to_entry(line)
self.entries.append(gpe)
return
def set_mapping_counts(self,psl_filename):
self.mapping_counts_set = True
gfr0 = GenericFileReader(psl_filename)
qcnts = {}
while True:
line = gfr0.readline()
if not line: break
try:
psle = PSLBasics.line_to_entry(line.rstrip())
except:
sys.stderr.write("Problem parsing line:\n"+line.rstrip()+"\n")
continue
if psle['qName'] not in qcnts: qcnts[psle['qName']] = 0
qcnts[psle['qName']] += 1
gfr0.close()
self.mapping_counts = qcnts
def set_mapping_counts(self, psl_filename):
self.mapping_counts_set = True
gfr0 = GenericFileReader(psl_filename)
qcnts = {}
while True:
line = gfr0.readline()
if not line: break
try:
psle = PSLBasics.line_to_entry(line.rstrip())
except:
sys.stderr.write("Problem parsing line:\n" + line.rstrip() +
"\n")
continue
if psle['qName'] not in qcnts: qcnts[psle['qName']] = 0
qcnts[psle['qName']] += 1
gfr0.close()
self.mapping_counts = qcnts
class GenericFastaFileReader:
def __init__(self, filename):
self.filename = filename
self.gfr = GenericFileReader(self.filename)
self.previous_name = None
def close(self):
self.gfr.close()
def read_entry(self):
buffer = ''
original = ''
t = {}
t['name'] = ''
t['seq'] = ''
t['original'] = ''
while True:
newline = self.gfr.readline()
if not self.previous_name and not newline:
# no name in the buffer and new data being input, exit
return None
if not newline:
# end of the line, then finish it
t['name'] = self.previous_name
t['seq'] = buffer
t['original'] = original
self.previous_name = None
t['original'] = '>' + t['name'] + "\n" + t['original']
return t
m = re.match('^>(.*)$', newline.rstrip())
if not self.previous_name and m:
self.previous_name = m.group(1)
#special case of our first entry
continue
if m:
t['name'] = self.previous_name
t['seq'] = buffer
t['original'] = original
self.previous_name = m.group(1)
t['original'] = '>' + t['name'] + "\n" + t['original']
return t
buffer += newline.rstrip()
original += newline
class GenericFastaFileReader:
def __init__(self,filename):
self.filename = filename
self.gfr = GenericFileReader(self.filename)
self.previous_name = None
def close(self):
self.gfr.close()
def read_entry(self):
buffer = ''
original = ''
t = {}
t['name'] = ''
t['seq'] = ''
t['original'] = ''
while True:
newline = self.gfr.readline()
if not self.previous_name and not newline:
# no name in the buffer and new data being input, exit
return None
if not newline:
# end of the line, then finish it
t['name'] = self.previous_name
t['seq'] = buffer
t['original'] = original
self.previous_name = None
t['original'] = '>'+t['name'] + "\n" + t['original']
return t
m = re.match('^>(.*)$',newline.rstrip())
if not self.previous_name and m:
self.previous_name = m.group(1)
#special case of our first entry
continue
if m:
t['name'] = self.previous_name
t['seq'] = buffer
t['original'] = original
self.previous_name = m.group(1)
t['original'] = '>'+t['name'] + "\n" + t['original']
return t
buffer += newline.rstrip()
original += newline
def __init__(self,filename):
self.filename = filename
self.gfr = GenericFileReader(filename)
self.entries = []
while True:
line = self.gfr.readline()
if not line: break
if re.match('^#',line): continue
gpe = GenePredEntry()
gpe.line_to_entry(line)
self.entries.append(gpe)
return
class GenericFastqFileReader:
def __init__(self,filename):
self.filename = filename
self.gfr = GenericFileReader(self.filename)
self.previous_name = None
def close(self):
self.gfr.close()
def read_entry(self):
line1 = self.gfr.readline()
if not line1:
return False
line2 = self.gfr.readline()
if not line2:
sys.stderr.write("Warning: Improperly terminated fastq file line count not a multiple of 4\n")
line3 = self.gfr.readline()
if not line3:
sys.stderr.write("Warning: Improperly terminated fastq file line count not a multiple of 4\n")
line4 = self.gfr.readline()
if not line4:
sys.stderr.write("Warning: Improperly terminated fastq file line count not a multiple of 4\n")
m = re.match('^@([^\t]+)',line1.rstrip())
if not m:
sys.stderr.write("Warning: Could not read name\n")
t = {}
t['name'] = m.group(1)
t['seq'] = line2.rstrip()
t['quality'] = line4.rstrip()
return t
class GenericFastqFileReader:
def __init__(self,filename):
self.filename = filename
self.gfr = GenericFileReader(self.filename)
self.previous_name = None
def close(self):
self.gfr.close()
def read_entry(self):
line1 = self.gfr.readline()
if not line1:
return False
line2 = self.gfr.readline()
if not line2:
sys.stderr.write("Warning: Improperly terminated fastq file line count not a multiple of 4\n")
line3 = self.gfr.readline()
if not line3:
sys.stderr.write("Warning: Improperly terminated fastq file line count not a multiple of 4\n")
line4 = self.gfr.readline()
if not line4:
sys.stderr.write("Warning: Improperly terminated fastq file line count not a multiple of 4\n")
m = re.match('^@([^\t]+)',line1.rstrip())
if not m:
sys.stderr.write("Warning: Could not read name\n")
t = {}
t['name'] = m.group(1)
t['seq'] = line2.rstrip()
t['quality'] = line4.rstrip()
return t
def __init__(self,filename): self.filename = filename self.gfr = GenericFileReader(self.filename) self.previous_name = None
def __init__(self,filename): self.filename = filename self.gfr = GenericFileReader(self.filename) self.previous_name = None
def main():
parser = argparse.ArgumentParser(
description=
'Split FASTQ file(s) into smaller ones with as many entries as you specify'
)
parser.add_argument('size',
type=int,
help='Number of sequences to put into each file')
parser.add_argument('output_directory',
help='Name of the directory to put sequences')
parser.add_argument('fastq_files',
nargs='+',
help='FILENAME(S) for fastq files')
args = parser.parse_args()
if len(args.fastq_files) > 2:
sys.stderr.write("ERROR only two fastq files at most are supported\n")
return
if os.path.exists(args.output_directory):
sys.stderr.write("ERROR output directory exists already\n")
return
os.makedirs(args.output_directory)
if len(args.fastq_files) == 1:
out_iter = 1
fcount = 0
of = open(
args.output_directory.rstrip('/') + '/' + str(out_iter) + '.fq',
'w')
gfr = sys.stdin
if (args.fastq_files[0] != '-'):
gfr = GenericFileReader(args.fastq_files[0])
while True:
lineA = gfr.readline()
if not lineA: break
lineB = gfr.readline()
lineC = gfr.readline()
lineD = gfr.readline()
of.write(lineA)
of.write(lineB)
of.write(lineC)
of.write(lineD)
fcount += 1
if args.size <= fcount:
fcount = 0
out_iter += 1
of.close()
of = open(
args.output_directory.rstrip('/') + '/' + str(out_iter) +
'.fq', 'w')
gfr.close()
else: # we have two fastq files
out_iter = 1
fcount = 0
of1 = open(
args.output_directory.rstrip('/') + '/' + str(out_iter) + '_1.fq',
'w')
gfr1 = GenericFileReader(args.fastq_files[0])
of2 = open(
args.output_directory.rstrip('/') + '/' + str(out_iter) + '_2.fq',
'w')
gfr2 = GenericFileReader(args.fastq_files[1])
while True:
line1a = gfr1.readline()
line2a = gfr2.readline()
if not line1a or not line2a:
if line1a or line2a:
sys.stderr.write(
"WARNING paired file lengths appear different\n")
break
line1b = gfr1.readline()
line2b = gfr2.readline()
line1c = gfr1.readline()
line2c = gfr2.readline()
line1d = gfr1.readline()
line2d = gfr2.readline()
of1.write(line1a)
of2.write(line2a)
of1.write(line1b)
of2.write(line2b)
of1.write(line1c)
of2.write(line2c)
of1.write(line1d)
of2.write(line2d)
fcount += 1
if args.size <= fcount:
fcount = 0
out_iter += 1
of1.close()
of2.close()
of1 = open(
args.output_directory.rstrip('/') + '/' + str(out_iter) +
'_1.fq', 'w')
of2 = open(
args.output_directory.rstrip('/') + '/' + str(out_iter) +
'_2.fq', 'w')
gfr1.close()
gfr2.close()
def main():
parser = argparse.ArgumentParser(description='Split FASTQ file(s) into smaller ones with as many entries as you specify')
parser.add_argument('size',type=int,help='Number of sequences to put into each file')
parser.add_argument('output_directory',help='Name of the directory to put sequences')
parser.add_argument('fastq_files',nargs='+',help='FILENAME(S) for fastq files')
args = parser.parse_args()
if len(args.fastq_files) > 2:
sys.stderr.write("ERROR only two fastq files at most are supported\n")
return
if os.path.exists(args.output_directory):
sys.stderr.write("ERROR output directory exists already\n")
return
os.makedirs(args.output_directory)
if len(args.fastq_files) == 1:
out_iter = 1
fcount = 0
of = open(args.output_directory.rstrip('/')+'/'+str(out_iter)+'.fq','w')
gfr = sys.stdin
if(args.fastq_files[0] != '-'):
gfr = GenericFileReader(args.fastq_files[0])
while True:
lineA = gfr.readline()
if not lineA: break
lineB = gfr.readline()
lineC = gfr.readline()
lineD = gfr.readline()
of.write(lineA)
of.write(lineB)
of.write(lineC)
of.write(lineD)
fcount += 1
if args.size <= fcount:
fcount = 0
out_iter += 1
of.close()
of = open(args.output_directory.rstrip('/')+'/'+str(out_iter)+'.fq','w')
gfr.close()
else: # we have two fastq files
out_iter = 1
fcount = 0
of1 = open(args.output_directory.rstrip('/')+'/'+str(out_iter)+'_1.fq','w')
gfr1 = GenericFileReader(args.fastq_files[0])
of2 = open(args.output_directory.rstrip('/')+'/'+str(out_iter)+'_2.fq','w')
gfr2 = GenericFileReader(args.fastq_files[1])
while True:
line1a = gfr1.readline()
line2a = gfr2.readline()
if not line1a or not line2a:
if line1a or line2a:
sys.stderr.write("WARNING paired file lengths appear different\n")
break
line1b = gfr1.readline()
line2b = gfr2.readline()
line1c = gfr1.readline()
line2c = gfr2.readline()
line1d = gfr1.readline()
line2d = gfr2.readline()
of1.write(line1a)
of2.write(line2a)
of1.write(line1b)
of2.write(line2b)
of1.write(line1c)
of2.write(line2c)
of1.write(line1d)
of2.write(line2d)
fcount += 1
if args.size <= fcount:
fcount = 0
out_iter += 1
of1.close()
of2.close()
of1 = open(args.output_directory.rstrip('/')+'/'+str(out_iter)+'_1.fq','w')
of2 = open(args.output_directory.rstrip('/')+'/'+str(out_iter)+'_2.fq','w')
gfr1.close()
gfr2.close()
def main():
parser = argparse.ArgumentParser(
description='Use reference junctions when they are close',
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument('--min_intron_size',
type=int,
default=68,
help="INT min intron size")
parser.add_argument(
'--min_local_support',
type=int,
default=0,
help=
"INT min number of junctions within search_size of a junction in order to count it"
)
parser.add_argument('--search_size',
type=int,
default=10,
help="INT search space for reference")
parser.add_argument(
'--output_fake_psl',
help="FASTAFILE reference genome to make a fake PSL output")
parser.add_argument('psl', help="PSLFILENAME or '-' for STDIN")
parser.add_argument('reference_genepred',
help="FASTAFILENAME for reference genepred")
args = parser.parse_args()
cpus = multiprocessing.cpu_count()
genome = {}
if args.output_fake_psl:
genome = read_fasta_into_hash(args.output_fake_psl)
#read in the reference genepred first
gpf = GenePredBasics.GenePredFile(args.reference_genepred)
#lets sort entries by chromosome
ref = {}
for e in [x.entry for x in gpf.entries]:
if len(e['exonStarts']) <= 1: continue
if e['chrom'] not in ref:
ref[e['chrom']] = {}
for i in range(1, len(e['exonStarts'])):
if e['exonEnds'][i - 1] not in ref[e['chrom']]:
ref[e['chrom']][e['exonEnds'][i - 1]] = {}
if e['exonStarts'][i] + 1 not in ref[e['chrom']][e['exonEnds'][i -
1]]:
ref[e['chrom']][e['exonEnds'][i - 1]][e['exonStarts'][i] +
1] = e['strand']
#Stored all junctions as 1-base
read_info = {}
pf = GenericFileReader(args.psl)
fcount_total = 0
while True:
line = pf.readline()
if not line: break
if re.match('^#', line): continue
line = line.rstrip()
pe = PSLBasics.line_to_entry(line)
if len(pe['tStarts']) != len(pe['blockSizes']) or len(
pe['qStarts']) != len(pe['blockSizes']):
sys.stderr.write("WARNING invalid psl\n")
continue
genepred_line = PSLBasics.convert_entry_to_genepred_line(pe)
ge = GenePredBasics.smooth_gaps(
GenePredBasics.line_to_entry(genepred_line), args.min_intron_size)
refjuns = {}
if pe['tName'] in ref: refjuns = ref[pe['tName']]
new_ge = nudge(pe, ge, refjuns, args)
if args.output_fake_psl:
new_psl_line = GenePredBasics.entry_to_fake_psl_line(
new_ge, genome)
print new_psl_line
else:
print GenePredBasics.entry_to_line(new_ge)
