def test_run(self):
"""formatLine"""
# DAD: todo
#self.assertFalse(True)
dout = util.DelimitedOutput()
dout.addHeader("one", "first", 'd')
dout.addHeader("two", "second", 's')
entry = {'one': 2, 'two': 'this'}
line = dout.formatLine(entry)
# Remove gaps?
if options.degap:
for k in query_keys:
prot_dict[k] = prot_dict[k].replace("-", '')
if options.debugging:
query_keys = query_keys[0:min(len(query_keys, 100))]
# Set up motif to compare
fac = slide.SequenceCompositionComparatorFactory()
comparator = fac.make(options.motif, 'sequence')
# Write output
n_written = 0
dout = util.DelimitedOutput()
dout.addHeader('orf', 'S. cerevisiae systematic name', 's')
dout.addHeader('n.above', 'Number of windows with score >= threshold', 'd')
dout.addHeader(
'max.score',
'Maximum score (1 - chi-squared histogram distance on normalized aa-composition histograms)',
'f')
dout.addHeader(
'max.position',
'1-based sequence position of window (start of window) having the maximum score',
'd')
dout.describeHeader(data_outs)
dout.writeHeader(data_outs)
for orf in query_keys:
seq = gelscore.Sequence(prot_dict[orf])
def processFile(in_fname, out_fname, options, data_outs, info_outs):
resfile = pc_res3(in_fname)
# Parse the file
resfile.load()
'''
# List columns
print resfile.keys()
for k in resfile.keys():
print len(resfile[k]['data'])
'''
target_columns = ['UV'] #,'Cond','Pressure','Flow','Temp']
target_column = 'UV'
#print resfile[target_column].keys()
#sys.exit()
# Write out parameters
data_outs.write("# Run started {}\n".format(util.timestamp()))
data_outs.write("# Command: {}\n".format(' '.join(sys.argv)))
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))
data_outs.write("# Input filename: {}\n".format(in_fname))
data_outs.write("# Output filename: {}\n".format(out_fname))
# Write output
dout = util.DelimitedOutput()
dout.addHeader('ml', 'Elution volume (mL)', 'f')
dout.addHeader(
target_column,
'{name} ({unit})'.format(name=resfile[target_column]['data_name'],
unit=resfile[target_column]['unit']), 'f')
dout.describeHeader(data_outs)
dout.writeHeader(data_outs)
format = dout.getFormat(named=True)
data_length = len(resfile[target_column]['data'])
n_written = 0
last_entry_volume = resfile[target_column]['data'][0][0]
last_entry = False
cur_entry_volume = None
# Tuples of (mL,UV)
elution_window = []
for i in range(data_length):
entry = resfile[target_column]['data'][i]
cur_entry_volume = entry[0]
cur_entry_value = entry[1]
#print last_entry_volume, cur_entry_volume
if cur_entry_volume - last_entry_volume >= options.resolution_ml or i == data_length - 1:
# Compute averages
datdict = {
'ml': stats.mean([x[0] for x in elution_window]),
target_column: stats.mean([x[1] for x in elution_window])
}
# Write out
line = format.format(**datdict)
data_outs.write(line)
n_written += 1
# Reset
last_entry_volume = cur_entry_volume
elution_window = []
elution_window.append((cur_entry_volume, cur_entry_value))
# Write out stopping time
data_outs.write("# Run finished {}\n".format(util.timestamp()))
# Shut down output
if not out_fname is None:
info_outs.write("# Wrote {} lines to {}\n".format(
n_written, out_fname))