def test_profile_mut_bin_noerr(self):
""" Test the ability of mpathic.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 test_profile_mut_bin_noerr(self):
""" Test the ability of mpathic.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 test_profile_mut_total_err(self):
""" Test the ability of mpathic.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.')
def test_profile_mut_total_err(self):
""" Test the ability of mpathic.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.')
def test_profile_mut_seqslicing(self):
""" Test the ability of mpathic.profile_mut to slice sequences properly, and to raise the correct errors
"""
print '\nIn test_profile_mut_seqslicing...'
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_good1 =\
lambda: profile_mut.main(io.load_dataset(file_name),\
start=2,end=10)
executable_good2 =\
lambda: profile_mut.main(io.load_dataset(file_name),\
end=10)
executable_good3 =\
lambda: profile_mut.main(io.load_dataset(file_name),\
end=2)
executable_nopro =\
lambda: profile_mut.main(io.load_dataset(file_name),\
start=50,end=60)
executable_bad1 =\
lambda: profile_mut.main(io.load_dataset(file_name),\
start=-1)
executable_bad2 =\
lambda: profile_mut.main(io.load_dataset(file_name),\
end=100)
executable_bad3 =\
lambda: profile_mut.main(io.load_dataset(file_name),\
start=20,end=10)
# If good, then sequences will be valid
if '_good' in file_name:
try:
df = executable_good1()
io.write(df,self.output_dir+\
'profile_mut_splice2-10_%s.txt'%description)
executable_good2()
executable_good3()
self.assertRaises(SortSeqError,executable_bad1)
self.assertRaises(SortSeqError,executable_bad2)
self.assertRaises(SortSeqError,executable_bad3)
if '_pro' in file_name:
self.assertRaises(SortSeqError,executable_nopro)
else:
df = executable_nopro()
print 'ok.'
except:
print 'ok (ERROR).'
raise
# If bad, then profile_mut.main should raise SortSeqError
elif '_bad' in file_name:
try:
self.assertRaises(SortSeqError,executable_good1)
self.assertRaises(SortSeqError,executable_good2)
self.assertRaises(SortSeqError,executable_good3)
self.assertRaises(SortSeqError,executable_nopro)
self.assertRaises(SortSeqError,executable_bad1)
self.assertRaises(SortSeqError,executable_bad2)
self.assertRaises(SortSeqError,executable_bad3)
print 'ok.'
except:
print 'not ok (ERROR).'
raise
# There are no other options
else:
raise SortSeqError('Unrecognized class of file_name.')
def test_profile_mut_seqslicing(self):
""" Test the ability of mpathic.profile_mut to slice sequences properly, and to raise the correct errors
"""
print '\nIn test_profile_mut_seqslicing...'
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_good1 =\
lambda: profile_mut.main(io.load_dataset(file_name),\
start=2,end=10)
executable_good2 =\
lambda: profile_mut.main(io.load_dataset(file_name),\
end=10)
executable_good3 =\
lambda: profile_mut.main(io.load_dataset(file_name),\
end=2)
executable_nopro =\
lambda: profile_mut.main(io.load_dataset(file_name),\
start=50,end=60)
executable_bad1 =\
lambda: profile_mut.main(io.load_dataset(file_name),\
start=-1)
executable_bad2 =\
lambda: profile_mut.main(io.load_dataset(file_name),\
end=100)
executable_bad3 =\
lambda: profile_mut.main(io.load_dataset(file_name),\
start=20,end=10)
# If good, then sequences will be valid
if '_good' in file_name:
try:
df = executable_good1()
io.write(df,self.output_dir+\
'profile_mut_splice2-10_%s.txt'%description)
executable_good2()
executable_good3()
self.assertRaises(SortSeqError, executable_bad1)
self.assertRaises(SortSeqError, executable_bad2)
self.assertRaises(SortSeqError, executable_bad3)
if '_pro' in file_name:
self.assertRaises(SortSeqError, executable_nopro)
else:
df = executable_nopro()
print 'ok.'
except:
print 'ok (ERROR).'
raise
# If bad, then profile_mut.main should raise SortSeqError
elif '_bad' in file_name:
try:
self.assertRaises(SortSeqError, executable_good1)
self.assertRaises(SortSeqError, executable_good2)
self.assertRaises(SortSeqError, executable_good3)
self.assertRaises(SortSeqError, executable_nopro)
self.assertRaises(SortSeqError, executable_bad1)
self.assertRaises(SortSeqError, executable_bad2)
self.assertRaises(SortSeqError, executable_bad3)
print 'ok.'
except:
print 'not ok (ERROR).'
raise
# There are no other options
else:
raise SortSeqError('Unrecognized class of file_name.')
def _check_mut_rate(partialdf, buffer):
mut = profile_mut.main(partialdf)
#Check mutation rate of non-primer and non-wildtype bases
relevantmuts = mut.loc[buffer + 20:179-buffer*2,'mut']
return ((relevantmuts > .14).any() or (relevantmuts < .07).any())
def main(dataset_df,
bin=None,
start=0,
end=None,
bins_df=None,
pseudocounts=1,
return_profile=False):
"""
Computes character frequencies (0.0 to 1.0) at each position
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 counts for each
nucleotide/amino acid character at each position.
"""
seq_cols = qc.get_cols_from_df(dataset_df, 'seqs')
if not len(seq_cols) == 1:
raise SortSeqError('Dataframe has multiple seq cols: %s' %
str(seq_cols))
dicttype = qc.colname_to_seqtype_dict[seq_cols[0]]
seq_dict, inv_dict = utils.choose_dict(dicttype)
# Validate dataset_df
qc.validate_dataset(dataset_df)
#for each bin we need to find character frequency profile, then sum over all
#bins to get activity.
#first make sure we have activities of each bin:
if not bins_df:
bins = utils.get_column_headers(dataset_df)
#in this case no activity was specified so just assume the activity
#equals bin number
activity = [float(b.split('_')[-1]) for b in bins]
else:
bins = list(bins_df['bins'])
activity = list(bins_df['activity'])
#initialize dataframe for total counts in all bins
output_ct_df = pd.DataFrame()
#initialize dataframe for running activity calculation
output_activity_df = pd.DataFrame()
for i, b in enumerate(bins):
bin_num = int(b.split('_')[-1])
# Compute counts
counts_df = profile_ct.main(dataset_df,
bin=bin_num,
start=start,
end=end)
# Create columns for profile_freqs table
ct_cols = utils.get_column_headers(counts_df)
#add_pseudocounts
counts_df[ct_cols] = counts_df[ct_cols] + pseudocounts
#add to all previous bin counts
#print output_activity_df
if i == 0:
output_ct_df = counts_df[ct_cols]
output_activity_df = counts_df[ct_cols] * activity[i]
else:
output_ct_df = output_ct_df + counts_df[ct_cols]
output_activity_df = output_activity_df + counts_df[
ct_cols] * activity[i]
#now normalize by each character at each position, this is the activity
#profile
output_activity_df = output_activity_df[ct_cols].div(output_ct_df[ct_cols])
mut_rate = profile_mut.main(dataset_df, bin=bin)
freq = profile_freq.main(dataset_df, bin=bin)
freq_cols = [x for x in freq.columns if 'freq_' in x]
#now normalize by the wt activity
wtseq = ''.join(mut_rate['wt'])
wtarr = utils.seq2mat(wtseq, seq_dict)
wt_activity = np.transpose(wtarr) * (np.array(output_activity_df[ct_cols]))
#sum this to get total
wt_activity2 = wt_activity.sum(axis=1)
delta_activity = output_activity_df.subtract(pd.Series(wt_activity2),
axis=0)
if return_profile:
#first find mutation rate according to formula in SI text
profile_delta_activity = mut_rate['mut']*np.sum(
(1-np.transpose(wtarr))*np.array(\
freq[freq_cols])*np.array(delta_activity),axis=1)
#format into dataframe
output_df = pd.DataFrame()
output_df['pos'] = range(start,
start + len(profile_delta_activity.index))
output_df['mut_activity'] = profile_delta_activity
return output_df
else:
#just add pos column and rename counts columns to activity columns
output_df = pd.DataFrame(delta_activity)
output_df.insert(0, 'pos',
range(start, start + len(delta_activity.index)))
#reorder columns
activity_col_dict = {x:'activity_' + x.split('_')[-1] \
for x in delta_activity.columns if 'ct_' in x}
output_df = output_df.rename(columns=activity_col_dict)
return output_df
