new_headers = headers
new_seqs = seqs
for append_fname in options.append_fasta:
if not os.path.isfile(append_fname):
raise IOError("# Error: file {} does not exist".format(append_fname))
with open(append_fname,'r') as inf:
# Read a FASTA file?
(app_headers, app_seqs) = biofile.readFASTA(inf)
info_outs.write("# Read {:d} sequences\n".format(len(app_seqs)))
assert len(app_seqs) == len(new_seqs)
if options.check_headers:
for (h1, h2) in zip(headers, app_headers):
assert h1==h2, "# Error: headers do not match:\n\t{}\n\t{}".format(h1,h2)
for (i,s) in enumerate(new_seqs):
new_seqs[i] += app_seqs[i]
# Write output
biofile.writeFASTA(new_seqs, fasta_outs, headers=new_headers)
n_written = len(new_seqs)
# Write out stopping time
data_outs.write("# Run finished {}\n".format(util.timestamp()))
# Shut down output
if not options.fasta_out_fname is None:
info_outs.write("# Wrote {} entries to {}\n".format(n_written, options.fasta_out_fname))
outf.close()
if local_fname is None:
local_fname = "tmp{:d}".format(random.randint(0, 1e20))
# Fetch file from OrthoDB
if not options.orthodb_id is None:
#local_fname = "uniprot-yeast.txt"
remote_fname = "http://cegg.unige.ch/orthodb7/fasta.fasta?ogs={:s}".format(
options.orthodb_id)
urllib.urlretrieve(remote_fname, local_fname)
print "# Downloaded {} to {}".format(remote_fname, local_fname)
info_outs.write("# Downloaded {} to {}\n".format(
remote_fname, local_fname))
# Read input
if not os.path.isfile(local_fname):
raise IOError("# Error: file {} does not exist".format(local_fname))
with open(local_fname, 'r') as inf:
# Read a FASTA file?
(headers, seqs) = biofile.readFASTA(inf)
if options.fasta_out_fname is None:
# Write data
biofile.writeFASTA(seqs, fasta_outs, headers=headers)
# Write out stopping time
info_outs.write("# Run finished {}\n".format(util.timestamp()))
# Shut down output
if not options.fasta_out_fname is None:
info_outs.write("# Fetched {} sequences to {}\n".format(
len(headers), options.fasta_out_fname))
outf.close()
new_headers = headers
new_seqs = seqs
for append_fname in options.append_fasta:
if not os.path.isfile(append_fname):
raise IOError(
"# Error: file {} does not exist".format(append_fname))
with open(append_fname, 'r') as inf:
# Read a FASTA file?
(app_headers, app_seqs) = biofile.readFASTA(inf)
info_outs.write("# Read {:d} sequences\n".format(len(app_seqs)))
assert len(app_seqs) == len(new_seqs)
if options.check_headers:
for (h1, h2) in zip(headers, app_headers):
assert h1 == h2, "# Error: headers do not match:\n\t{}\n\t{}".format(
h1, h2)
for (i, s) in enumerate(new_seqs):
new_seqs[i] += app_seqs[i]
# Write output
biofile.writeFASTA(new_seqs, fasta_outs, headers=new_headers)
n_written = len(new_seqs)
# Write out stopping time
data_outs.write("# Run finished {}\n".format(util.timestamp()))
# Shut down output
if not options.fasta_out_fname is None:
info_outs.write("# Wrote {} entries to {}\n".format(
n_written, options.fasta_out_fname))
outf.close()
opt_seq = ''
for (aai, aa) in enumerate(prot_seq):
#opt_seq += opt_codon_dict[aa] #random.choice(codons[aa])
codons_to_choose_from = codons[aa]
# If avoiding codons and we have a choice, eliminate the avoided codon.
if options.avoid_sequence and len(
codons_to_choose_from) > 1:
try:
codons_to_choose_from.remove(orig_codons[aai])
except ValueError: # codon to be avoided not among codon choices anyway
pass
opt_seq += random.choice(codons_to_choose_from)
assert translate.translate(opt_seq) == prot_seq
header_line = "{0} Fop = {1:.4f}, CAI = {2:.4f}, GC = {3:.2f}".format(
id, cai.getFop(opt_seq, opt_codons), cai_fxn(opt_seq),
cai.getGC(opt_seq))
info_outs.write("# Optimized {}\n".format(header_line))
opt_headers.append(header_line)
opt_seqs.append(opt_seq)
out_seqs = opt_seqs
out_headers = opt_headers
biofile.writeFASTA(out_seqs, data_outs, headers=out_headers)
elif options.reverse_translate: # Write out sequences but don't optimize
(out_headers, out_seqs) = zip(*seqs)
biofile.writeFASTA(out_seqs, data_outs, headers=out_headers)
if not options.out_fname is None:
info_outs.write("# Wrote {0} optimized sequences to {1}\n".format(
len(opt_seqs), options.out_fname))
outf.close()
# Iterate over tree and write out FASTA in tree-sorted order
n_written = 0
sorted_headers = []
sorted_seqs = []
for indiv in tree.get_terminals():
#print(indiv.name)
#spec = extractSpeciesName(h)
spec = indiv.name.strip()
spec.replace('\\', '')
#print("^{}$\n".format(spec))
if spec in header_dict:
hdr = header_dict[spec]
if options.generate_short_ids:
hdr = "{} {}".format(short_species_names[spec], hdr)
seq = seq_dict[spec]
sorted_headers.append(hdr)
sorted_seqs.append(seq)
else:
#print(dir(indiv))
info_outs.write("# Can't find {}\n".format(spec))
if not options.fasta_out_fname is None:
fasta_outs = util.OutStreams(
open(os.path.expanduser(options.fasta_out_fname), 'w'))
biofile.writeFASTA(sorted_seqs, fasta_outs, headers=sorted_headers)
info_outs.write("# Wrote {} entries to {}\n".format(
len(sorted_seqs), options.fasta_out_fname))
# Write out stopping time
data_outs.write("# Run finished {}\n".format(util.timestamp()))
info_outs.write("# No starting position or sequence given; nothing to do. Exiting\n")
new_headers = []
new_seqs = []
for (h,seq) in zip(headers,seqs):
if not options.exclude:
ex_seq = seq[start_index:end_index]
else: # Exclude the sequence
#assert options.end_aa < len(seq)
#assert options.begin_aa < options.end_aa
ex_seq = seq[0:start_index] + seq[end_index:]
#degapped_seq = seq.replace(gap,"")
new_seqs.append(ex_seq)
new_headers.append(h)
seqs = new_seqs
headers = new_headers
# Write output
biofile.writeFASTA(seqs, fasta_outs, headers=headers)
n_written = len(seqs)
# Write out stopping time
data_outs.write("# Run finished {}\n".format(util.timestamp()))
# Shut down output
if not options.fasta_out_fname is None:
info_outs.write("# Wrote {} entries to {}\n".format(n_written, options.fasta_out_fname))
outf.close()
codons[aa] = [c for c in translate.getCodonsForAA(aa, rna=False) if relad_dict[c] >= options.min_rel_adapt]
opt_seq = ''
for (aai, aa) in enumerate(prot_seq):
#opt_seq += opt_codon_dict[aa] #random.choice(codons[aa])
codons_to_choose_from = codons[aa]
# If avoiding codons and we have a choice, eliminate the avoided codon.
if options.avoid_sequence and len(codons_to_choose_from)>1:
try:
codons_to_choose_from.remove(orig_codons[aai])
except ValueError: # codon to be avoided not among codon choices anyway
pass
opt_seq += random.choice(codons_to_choose_from)
assert translate.translate(opt_seq) == prot_seq
header_line = "{0} Fop = {1:.4f}, CAI = {2:.4f}, GC = {3:.2f}".format(id, cai.getFop(opt_seq, opt_codons), cai_fxn(opt_seq), cai.getGC(opt_seq))
info_outs.write("# Optimized {}\n".format(header_line))
opt_headers.append(header_line)
opt_seqs.append(opt_seq)
out_seqs = opt_seqs
out_headers = opt_headers
biofile.writeFASTA(out_seqs, data_outs, headers=out_headers)
elif options.reverse_translate: # Write out sequences but don't optimize
(out_headers,out_seqs) = zip(*seqs)
biofile.writeFASTA(out_seqs, data_outs, headers=out_headers)
if not options.out_fname is None:
info_outs.write("# Wrote {0} optimized sequences to {1}\n".format(len(opt_seqs), options.out_fname))
outf.close()