def test008(self):
"""zero-length nucleotides"""
s = ""
c = [cod for cod in translate.codons(s)]
self.assertTrue(len(c) == 0)
self.assertTrue(translate.translate(s) == "")
self.assertTrue(translate.translateRaw(s) == "")
def test004(self):
"""translation with problems"""
s = "ATGCatTCTNNNTAAAGA"
# print translate.translate(s)
self.assertTrue(translate.translate(s) is None)
# print translate.translateRaw(s,bad_aa='@')
self.assertTrue(translate.translateRaw(s, bad_aa="@") == "MHS@*R")
def test008(self):
"""zero-length nucleotides"""
s = ''
c = [cod for cod in translate.codons(s)]
self.assertTrue(len(c) == 0)
self.assertTrue(translate.translate(s) == '')
self.assertTrue(translate.translateRaw(s) == '')
def test004(self):
"""translation with problems"""
s = 'ATGCatTCTNNNTAAAGA'
#print translate.translate(s)
self.assertTrue(translate.translate(s) is None)
#print translate.translateRaw(s,bad_aa='@')
self.assertTrue(translate.translateRaw(s, bad_aa='@') == 'MHS@*R')
def test009(self):
"""odd-length coding sequence"""
s = "TCTCGTAAGTACGCAGC"
c = [cod for cod in translate.codons(s)]
self.assertTrue(len(c) == 5)
self.assertTrue(c[-1] == "GCA")
self.assertTrue(translate.translate(s) is None)
self.assertTrue(translate.translateRaw(s) == "SRKYA")
def test009(self):
"""odd-length coding sequence"""
s = 'TCTCGTAAGTACGCAGC'
c = [cod for cod in translate.codons(s)]
self.assertTrue(len(c) == 5)
self.assertTrue(c[-1] == 'GCA')
self.assertTrue(translate.translate(s) is None)
self.assertTrue(translate.translateRaw(s) == 'SRKYA')
def test007(self):
"""zero-length protein"""
s = "AT"
self.assertTrue(translate.translate(s) is None)
self.assertTrue(translate.translateRaw(s) == "")
for aa in aas])) # fractions
data_outs.write("\t" + "\t".join(["n.{}".format(aa)
for aa in aas])) # numbers
data_outs.write("\n")
if options.merge:
data_outs.write("# Merging {:d} sequences into one\n".format(
len(seqs)))
seqs = [''.join(seqs)]
headers = ["merged"]
gap = '-'
for (h, seq) in zip(headers, seqs):
if options.query:
if not options.query in h:
continue
if options.translate:
seq = translate.translateRaw(seq)
if options.degap:
seq = seq.replace(gap, '')
if not options.exclude:
if not options.end_aa is None and options.end_aa <= len(seq):
seq = seq[0:(options.end_aa)]
seq = seq[(options.begin_aa - 1):]
else: # Exclude the sequence
assert options.end_aa < len(seq)
assert options.begin_aa < options.end_aa
seq = seq[0:(options.begin_aa - 1)] + seq[(options.end_aa):]
degapped_seq = seq.replace(gap, "")
line = "#{}\n{}\t{:d}\t{:1.4f}\t{:1.4f}\t{:1.4f}".format(
h, biofile.firstField(h), pp.getLength(degapped_seq),
pp.getCharge(degapped_seq, options.pH),
pp.getIsoelectricPoint(degapped_seq),
type=float,
default=7.2,
help="pH for charge determination")
options = parser.parse_args()
outs = util.OutStreams()
if not options.out_fname is None:
outf = file(os.path.expanduser(options.out_fname), 'w')
outs.addStream(outf)
else:
outs.addStream(sys.stdout)
pp = protprop.ProteinProperties()
if not options.sequence is None:
if options.translate:
seq = translate.translateRaw(options.sequence)
else:
seq = options.sequence
seq_dict = {"input": seq}
else:
# Load from FASTA
seq_dict = biofile.readFASTADict(options.in_fname)
if options.translate:
for k in seq_dict.keys():
seq_dict[k] = translate.translate(seq_dict[k])
outs.write("# {}\n".format(options))
outs.write("pos\taa\tcharge\n")
n_seqs = len(seq_dict.keys())
for (seqid, seq) in seq_dict.items():
if n_seqs > 1:
"-t", "--translate", dest="translate", action="store_true", default=False, help="translate the input sequences?"
)
parser.add_argument("--pH", dest="pH", type=float, default=7.2, help="pH for charge determination")
options = parser.parse_args()
outs = util.OutStreams()
if not options.out_fname is None:
outf = file(os.path.expanduser(options.out_fname), "w")
outs.addStream(outf)
else:
outs.addStream(sys.stdout)
pp = protprop.ProteinProperties()
if not options.sequence is None:
if options.translate:
seq = translate.translateRaw(options.sequence)
else:
seq = options.sequence
seq_dict = {"input": seq}
else:
# Load from FASTA
seq_dict = biofile.readFASTADict(options.in_fname)
if options.translate:
for k in seq_dict.keys():
seq_dict[k] = translate.translate(seq_dict[k])
outs.write("# {}\n".format(options))
outs.write("pos\taa\tcharge\n")
n_seqs = len(seq_dict.keys())
for (seqid, seq) in seq_dict.items():
if n_seqs > 1:
dnaseq = translate.randomReverseTranslate(seq)
#dnaseq = translate.reverseTranslate(seq)
assert(translate.translate(dnaseq)==seq)
fullseq = options.prefix + dnaseq + options.suffix
mutant_seqs[name] = (dnaseq, fullseq)
#name = biofile.firstField(hdr)
line = "{name:s}\t{dna:s}\tL={length:d}bp, {desc:s}\n".format(name=name, dna=fullseq, length=len(fullseq), desc=hdr)
data_outs.write(line)
n_written += 1
data_outs.write("\n\n# Confirmation details:\n")
for (hdr,seq) in zip(headers,seqs):
(name, props) = parseHeader(hdr)
(mutant_seq, fullseq) = mutant_seqs[name]
prot = translate.translate(mutant_seq)
fullprots = [translate.translateRaw(fullseq[i:]) for i in range(3)]
allnames = ['core','frame 1','frame 2','frame 3']
data_outs.write("# {name:s} core and 3-frame full translation\n".format(name=name))
for (i,p) in enumerate([prot] + fullprots):
line = "# {name:s} {prot:s}\n".format(prot=p, name=allnames[i])
data_outs.write(line)
data_outs.write("#\n")
# Write out stopping time
data_outs.write("# Run finished {}\n".format(util.timestamp()))
# Shut down output
if not options.out_fname is None:
info_outs.write("# Wrote {} lines to {}\n".format(n_written, options.out_fname))
outf.close()
data_outs.write("orf\tlength\tcharge\tpI\thydrophobicity")
if not aas is None:
data_outs.write("\t"+"\t".join(["f.{}".format(aa) for aa in aas])) # fractions
data_outs.write("\t"+"\t".join(["n.{}".format(aa) for aa in aas])) # numbers
data_outs.write("\n")
if options.merge:
data_outs.write("# Merging {:d} sequences into one\n".format(len(seqs)))
seqs = [''.join(seqs)]
headers = ["merged"]
gap = '-'
for (h,seq) in zip(headers,seqs):
if options.query:
if not options.query in h:
continue
if options.translate:
seq = translate.translateRaw(seq)
if options.degap:
seq = seq.replace(gap,'')
if not options.exclude:
if not options.end_aa is None and options.end_aa <= len(seq):
seq = seq[0:(options.end_aa)]
seq = seq[(options.begin_aa-1):]
else: # Exclude the sequence
assert options.end_aa < len(seq)
assert options.begin_aa < options.end_aa
seq = seq[0:(options.begin_aa-1)] + seq[(options.end_aa):]
degapped_seq = seq.replace(gap,"")
line = "#{}\n{}\t{:d}\t{:1.4f}\t{:1.4f}\t{:1.4f}".format(h, biofile.firstField(h), pp.getLength(degapped_seq), pp.getCharge(degapped_seq, options.pH), pp.getIsoelectricPoint(degapped_seq), pp.getHydrophobicity(degapped_seq))
if not aas is None:
counts = Composition()
counts.initFromSequence(degapped_seq)
def test007(self):
"""zero-length protein"""
s = 'AT'
self.assertTrue(translate.translate(s) is None)
self.assertTrue(translate.translateRaw(s) == '')
