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')
def secondField(h): f = None try: f = biofile.secondField(h) except: f = biofile.firstField(h) return f
def secondField(h): f = None try: f = biofile.secondField(h) except: f = biofile.firstField(h) return f
# Set up some output
info_outs = util.OutStreams(sys.stdout)
outs = util.OutStreams()
params_outs = util.OutStreams([outs])
if not options.out_fname is None:
outf = open(os.path.expanduser(options.out_fname),'w')
outs.addStream(outf)
else:
outs.addStream(sys.stdout)
orf_dict = None
gene_orf_map = None
if not options.fasta_fname is None:
fname = os.path.expanduser(options.fasta_fname)
(headers, sequences) = biofile.readFASTA(fname)
orf_dict = dict(zip([biofile.firstField(h) for h in headers], sequences))
gene_orf_map = dict([(biofile.secondField(h), biofile.firstField(h)) for h in headers])
# Set the weight matrix
try:
matrix = motif.weight_matrices[options.pssm_name]
except KeyError as ke:
outs.write("# Unable to find weight matrix {}; try one of {}\n".format(options.pssm_name, ','.join(motif.weight_matrices.keys())))
window_size = len(matrix['A']) #len(matrix.values()[0])
# for associating windows with residues, center them
mid_window = int(math.floor(window_size/2.0))
# Write out parameters
params_outs.write("# Run started {}\n".format(util.timestamp()))
params_outs.write("# Command: {}\n".format(' '.join(sys.argv)))
f = biofile.secondField(h)
except:
f = biofile.firstField(h)
return f
# 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]
if not options.dont_align_sequences:
aligned_seqs = muscle.alignSequences(seqs)
seqs = aligned_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([(secondField(h), biofile.firstField(h)) for h in headers])
orf_gene_dict = dict([(v,k) for (k,v) in gene_orf_dict.items()])
# Write output
n_written = 0
data_outs.write("header\n")
for orf in query_keys:
n_written += 1
# Write out stopping time
data_outs.write("# Run finished {}\n".format(util.timestamp()))
# Shut down output
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)
freqs = Composition()
freqs.initFromSequence(degapped_seq)
freqs.normalize()
line += '\t' + '\t'.join([
"{:1.4f}".format(freqs[aa]) for aa in aas
]) + '\t' + '\t'.join(["{:d}".format(counts[aa]) for aa in aas])
data_outs.write(line + '\n')
#print("# Wrote line\n")
if not options.out_fname is None:
else:
fname = os.path.expanduser(options.composition_fname)
if not os.path.isfile(fname):
raise IOError("# Error: file {} does not exist".format(fname))
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]
# Write out parameters
params_outs.write("# Run started {}\n".format(util.timestamp()))
params_outs.write("# Command: {}\n".format(' '.join(sys.argv)))
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
def parseHeader(x):
name = biofile.firstField(x)
property_entries = [tuple(y.split('=')) for y in x.split() if '=' in y]
props = dict(property_entries)
return name, props
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)
freqs = Composition()
freqs.initFromSequence(degapped_seq)
freqs.normalize()
line += '\t' + '\t'.join(["{:1.4f}".format(freqs[aa]) for aa in aas]) + '\t' + '\t'.join(["{:d}".format(counts[aa]) for aa in aas])
data_outs.write(line + '\n')
#print("# Wrote line\n")
if not options.out_fname is None:
outf.close()
