def test_run(self): """secondOrFirstField""" x = 'FIRST SECOND' self.assertTrue(biofile.firstField(x)=='FIRST') self.assertTrue(biofile.secondField(x)=='SECOND') y = 'FIRST' self.assertTrue(biofile.secondOrFirstField(y)=='FIRST')
with file(fname, 'r') as inf:
composition.read(inf)
# Read input
if not os.path.isfile(options.in_fname):
raise IOError("# Error: file {} does not exist".format(
options.in_fname))
(headers, seqs) = biofile.readFASTA(file(options.in_fname, 'r'))
if options.translate_sequences:
seqs = [translate.translate(s) for s in seqs]
zhs = [(h, s) for (h, s) in zip(headers, seqs) if not s is None]
all_keys = [biofile.firstField(h) for (h, s) in zhs]
(headers, seqs) = zip(*zhs)
prot_dict = dict([(biofile.firstField(h), s) for (h, s) in zhs])
gene_orf_dict = dict([
(biofile.secondOrFirstField(h), biofile.firstField(h)) for h in headers
])
orf_gene_dict = dict([(v, k) for (k, v) in gene_orf_dict.items()])
# Select which genes to process
query_keys = []
if not options.query_orf is []:
# Specific ORF(s)
query_keys += options.query_orf
if not options.query_gene is []:
# Specific gene(s)
query_keys += [gene_orf_dict[k] for k in options.query_gene]
if len(query_keys) == 0:
# Go through all proteins in database
query_keys = all_keys
params_outs.write("# Parameters:\n")
optdict = vars(options)
for (k,v) in optdict.items():
params_outs.write("#\t{k}: {v}\n".format(k=k, v=v))
# Read input
if not os.path.isfile(options.in_fname):
raise IOError("# Error: file {} does not exist".format(options.in_fname))
(headers, seqs) = biofile.readFASTA(file(options.in_fname, 'r')) #, key_fxn=biofile.secondField)
if options.translate_sequences:
seqs = [translate.translate(s) for s in seqs]
zhs = [(h,s) for (h,s) in zip(headers,seqs) if not s is None]
all_keys = [biofile.firstField(h) for (h,s) in zhs]
(headers, seqs) = zip(*zhs)
prot_dict = dict([(biofile.firstField(h), s) for (h,s) in zhs])
gene_orf_dict = dict([(biofile.secondOrFirstField(h), biofile.firstField(h)) for h in headers])
orf_gene_dict = dict([(v,k) for (k,v) in gene_orf_dict.items()])
# Select which genes to process
query_keys = []
if not options.query_orf is []:
# Specific ORF(s)
query_keys += options.query_orf
if not options.query_gene is []:
# Specific gene(s)
query_keys += [gene_orf_dict[k] for k in options.query_gene]
if len(query_keys) == 0:
# Go through all proteins in database
query_keys = all_keys
start_position, end_position = scriptutil.findSequencePositions(options.start_position, options.end_position,
data_outs.write("# Parameters:\n")
optdict = vars(options)
for (k,v) in optdict.items():
data_outs.write("#\t{k}: {v}\n".format(k=k, v=v))
# Read input
if not os.path.isfile(options.in_fname):
raise IOError("# Error: file {} does not exist".format(options.in_fname))
(headers, seqs) = biofile.readFASTA(file(options.in_fname, 'r')) #, key_fxn=biofile.secondField)
if options.translate_sequences:
seqs = [translate.translate(s) for s in seqs]
zhs = [(h,s) for (h,s) in zip(headers,seqs) if not s is None]
all_keys = [biofile.firstField(h) for (h,s) in zhs]
(headers, seqs) = zip(*zhs)
prot_dict = dict([(biofile.firstField(h), s) for (h,s) in zhs])
gene_orf_dict = dict([(biofile.secondOrFirstField(h), biofile.firstField(h)) for h in headers])
orf_gene_dict = dict([(v,k) for (k,v) in gene_orf_dict.items()])
# Select which genes to process
query_keys = []
if not options.query_orf is []:
# Specific ORF(s)
query_keys += options.query_orf
if not options.query_gene is []:
# Specific gene(s)
query_keys += [gene_orf_dict[k] for k in options.query_gene]
if len(query_keys) == 0:
# Go through all proteins in database
query_keys = all_keys
start_position = 0
end_position = len(seqs[0])