def test_profile_mut_bin_noerr(self):
""" Test the ability of sortseq_tools.profile_mut to compute mutation rates
"""
print '\nIn test_profile_mut_bin_noerr_...'
library_files = glob.glob(self.input_dir+'library_*.txt')
library_files += glob.glob(self.input_dir+'dataset_*.txt')
good_bin_num = 2
bad_bin_num = 5
for file_name in library_files:
print '\t%s ='%file_name,
description = file_name.split('_')[-1].split('.')[0]
executable = lambda:\
profile_mut.main(io.load_dataset(file_name),bin=good_bin_num,err=False)
print '(bin=%d)'%good_bin_num,
# If bad or library, then profile_mut.main should raise SortSeqError
if ('_bad' in file_name) or ('library' in file_name):
try:
self.assertRaises(SortSeqError,executable)
print 'badtype,',
except:
print 'good (ERROR).'
raise
# If good, then profile_mut.main should produce a valid df
elif '_good' in file_name:
try:
df = executable()
qc.validate_profile_mut(df)
out_file = self.output_dir+\
'profile_mut_bin_noerr_%s.txt'%description
io.write(df,out_file) # Test writing
io.load_profile_mut(out_file) # Test loading
print 'good,',
except:
print 'bad (ERROR).'
raise
# There are no other options
else:
raise SortSeqError('Unrecognized class of file_name.')
# Should always raise an error if bin num is too large
executable = lambda:\
profile_mut.main(io.load_dataset(file_name),bin=bad_bin_num)
print '(bin=%d)'%bad_bin_num,
try:
self.assertRaises(SortSeqError,executable)
print 'badtype.'
except:
print 'good (ERROR).'
raise
def main(dataset_df, bin=None, start=0, end=None, err=False):
"""
Computes the mutation rate (0.0 to 1.0) at each position. Mutation rate is defined as 1.0 minus the maximum character frequency at a position. Errors are estimated using bionomial uncertainty
Arguments:
dataset_df (pd.DataFrame): A dataframe containing a valid dataset.
bin (int): A bin number specifying which counts to use
start (int): An integer specifying the sequence start position
end (int): An integer specifying the sequence end position
Returns:
freq_df (pd.DataFrame): A dataframe containing results.
"""
# Validate dataset_df
qc.validate_dataset(dataset_df)
# Compute counts
counts_df = profile_ct.main(dataset_df, bin=bin, start=start, end=end)
# Create columns for profile_freqs table
ct_cols = [c for c in counts_df.columns if qc.is_col_type(c,'ct_')]
# Record positions in new dataframe
mut_df = counts_df[['pos']].copy()
# Compute mutation rate across counts
max_ct = counts_df[ct_cols].max(axis=1)
sum_ct = counts_df[ct_cols].sum(axis=1)
mut = 1.0 - (max_ct/sum_ct)
mut_df['mut'] = mut
# Computation of error rate is optional
if err:
mut_err = np.sqrt(mut*(1.0-mut)/sum_ct)
mut_df['mut_err'] = mut_err
# Figure out which alphabet the cts dataframe specifies
alphabet = ''.join([c.split('_')[1] for c in ct_cols])
seqtype = qc.alphabet_to_seqtype_dict[alphabet]
wt_col = qc.seqtype_to_wtcolname_dict[seqtype]
# Compute WT base at each position
mut_df[wt_col] = 'X'
for col in ct_cols:
indices = (counts_df[col]==max_ct).values
mut_df.loc[indices,wt_col] = col.split('_')[1]
# Validate as counts dataframe
mut_df = qc.validate_profile_mut(mut_df,fix=True)
return mut_df
def test_profile_mut_total_err(self):
""" Test the ability of sortseq_tools.profile_mut to compute mutation rates based on total count values
"""
print '\nIn test_profile_mut_total_err...'
library_files = glob.glob(self.input_dir+'library_*.txt')
library_files += glob.glob(self.input_dir+'dataset_*.txt')
for file_name in library_files:
print '\t%s ='%file_name,
description = file_name.split('_')[-1].split('.')[0]
executable = lambda: profile_mut.main(io.load_dataset(file_name),err=True)
# If good, then profile_mut.main should produce a valid df
if '_good' in file_name:
try:
df = executable()
qc.validate_profile_mut(df)
out_file = self.output_dir+\
'profile_mut_total_err_%s.txt'%description
io.write(df,out_file)
io.load_profile_mut(out_file)
print 'good.'
except:
print 'bad (ERROR).'
raise
# If bad, then profile_mut.main should raise SortSeqError
elif '_bad' in file_name:
try:
self.assertRaises(SortSeqError,executable)
print 'badtype.'
except:
print 'good (ERROR).'
raise
# There are no other options
else:
raise SortSeqError('Unrecognized class of file_name.')