def main(
data_df,model_df,
start=0,end=None,err=False,coarse_graining_level=0):
dicttype, modeltype = qc.get_model_type(model_df)
seq_cols = qc.get_cols_from_df(data_df,'seqs')
if not len(seq_cols)==1:
raise SortSeqError('Dataframe has multiple seq cols: %s'%str(seq_cols))
seq_dict,inv_dict = utils.choose_dict(dicttype,modeltype=modeltype)
#set name of sequences column based on type of sequence
type_name_dict = {'dna':'seq','rna':'seq_rna','protein':'seq_pro'}
seq_col_name = type_name_dict[dicttype]
#Cut the sequences based on start and end, and then check if it makes sense
if (start != 0 or end):
data_df.loc[:,seq_col_name] = data_df.loc[:,seq_col_name].str.slice(start,end)
if modeltype=='MAT':
if len(data_df.loc[0,seq_col_name]) != len(model_df.loc[:,'pos']):
raise SortSeqError('model length does not match dataset length')
elif modeltype=='NBR':
if len(data_df.loc[0,seq_col_name]) != len(model_df.loc[:,'pos'])+1:
raise SortSeqError('model length does not match dataset length')
col_headers = utils.get_column_headers(data_df)
if 'ct' not in data_df.columns:
data_df['ct'] = data_df[col_headers].sum(axis=1)
data_df = data_df[data_df.ct != 0]
if not end:
seqL = len(data_df[seq_col_name][0]) - start
else:
seqL = end-start
data_df = data_df[data_df[seq_col_name].apply(len) == (seqL)]
#make a numpy array out of the model data frame
model_df_headers = ['val_' + str(inv_dict[i]) for i in range(len(seq_dict))]
value = np.transpose(np.array(model_df[model_df_headers]))
#now we evaluate the expression of each sequence according to the model.
seq_mat,wtrow = numerics.dataset2mutarray(data_df.copy(),modeltype)
temp_df = data_df.copy()
temp_df['val'] = numerics.eval_modelmatrix_on_mutarray(np.array(model_df[model_df_headers]),seq_mat,wtrow)
temp_sorted = temp_df.sort_values(by='val')
temp_sorted.reset_index(inplace=True,drop=True)
#we must divide by the total number of counts in each bin for the MI calculator
#temp_sorted[col_headers] = temp_sorted[col_headers].div(temp_sorted['ct'],axis=0)
MI = EstimateMutualInfoforMImax.alt4(temp_sorted,coarse_graining_level=coarse_graining_level)
if not err:
Std = np.NaN
else:
data_df_for_sub = data_df.copy()
sub_MI = np.zeros(15)
for i in range(15):
sub_df = data_df_for_sub.sample(int(len(data_df_for_sub.index)/2))
sub_df.reset_index(inplace=True,drop=True)
sub_MI[i],sub_std = main(
sub_df,model_df,err=False)
Std = np.std(sub_MI)/np.sqrt(2)
return MI,Std
def emat(p=pymcdf,value=emat_0):
p['val'] = numerics.eval_modelmatrix_on_mutarray(np.transpose(value),seq_mat,wtrow)
MI = EstimateMutualInfoforMImax.alt4(p.copy()) # New and improved
return n_seqs*MI
def evaluate_on_mutarray(self, mutarray, wtrow):
return numerics.eval_modelmatrix_on_mutarray(\
modelmatrix=self.matrix.T, mutarray=mutarray, wtrow=wtrow)
def main(data_df,
model_df,
start=0,
end=None,
err=False,
coarse_graining_level=0,
rsquared=False,
return_freg=False):
#determine whether you are working with RNA, DNA, or protein.
#this also should determine modeltype (MAT, NBR, PAIR).
dicttype, modeltype = qc.get_model_type(model_df)
#get column header for the sequence column.
seq_cols = qc.get_cols_from_df(data_df, 'seqs')
if not len(seq_cols) == 1:
raise SortSeqError('Dataframe has multiple seq cols: %s' %
str(seq_cols))
#create dictionary that goes from, for example, nucleotide to number and
#visa versa.
seq_dict, inv_dict = utils.choose_dict(dicttype, modeltype=modeltype)
#set name of sequences column based on type of sequence
type_name_dict = {'dna': 'seq', 'rna': 'seq_rna', 'protein': 'seq_pro'}
seq_col_name = type_name_dict[dicttype]
if not end:
seqL = len(data_df[seq_col_name][0]) - start
else:
seqL = end - start
#throw out wrong length sequences.
#Cut the sequences based on start and end, and then check if it makes sense
if (start != 0 or end):
data_df.loc[:,seq_col_name] = \
data_df.loc[:,seq_col_name].str.slice(start,end)
right_length = data_df.loc[:, seq_col_name].apply(len) == (seqL)
if not right_length.all():
sys.stderr.write('''Not all sequences are the same length!
Throwing out incorrect sequences!''')
data_df = data_df.loc[right_length, :]
data_df = data_df.reset_index(drop=True)
if modeltype == 'MAT':
if seqL != len(model_df.loc[:, 'pos']):
raise SortSeqError(
'model length does not match dataset length')
elif modeltype == 'NBR':
if seqL != len(model_df.loc[:, 'pos']) + 1:
raise SortSeqError(
'model length does not match dataset length')
elif modeltype == 'PAIR':
if int(scipy.misc.comb(seqL, 2)) != len(model_df.loc[:, 'pos']):
raise SortSeqError(
'model length does not match dataset length')
#get column names of the counts columns (excluding total counts 'ct')
col_headers = utils.get_column_headers(data_df)
if 'ct' not in data_df.columns:
data_df['ct'] = data_df[col_headers].sum(axis=1)
#remove empty rows.
data_df = data_df[data_df.ct != 0]
#determine sequence length.
#make a numpy array out of the model data frame
model_df_headers = [
'val_' + str(inv_dict[i]) for i in range(len(seq_dict))
]
value = np.array(model_df[model_df_headers])
#now we evaluate the expression of each sequence according to the model.
#first convert to matrix representation of sequences
seq_mat, wtrow = numerics.dataset2mutarray(data_df.copy(), modeltype)
temp_df = data_df.copy()
#evaluate energy of each sequence
temp_df['val'] = numerics.eval_modelmatrix_on_mutarray(
value, seq_mat, wtrow)
#sort based on value
temp_sorted = temp_df.sort_values(by='val')
temp_sorted.reset_index(inplace=True, drop=True)
#freg is a regularized plot which show how sequences are distributed
#in energy space.
if return_freg:
fig, ax = plt.subplots()
MI, freg = EstimateMutualInfoforMImax.alt4(
temp_sorted,
coarse_graining_level=coarse_graining_level,
return_freg=return_freg)
plt.imshow(freg, interpolation='nearest', aspect='auto')
plt.savefig(return_freg)
else:
MI = EstimateMutualInfoforMImax.alt4(
temp_sorted,
coarse_graining_level=coarse_graining_level,
return_freg=return_freg)
#if we want to calculate error then use bootstrapping.
if not err:
Std = np.NaN
else:
data_df_for_sub = data_df.copy()
sub_MI = np.zeros(15)
for i in range(15):
sub_df = data_df_for_sub.sample(int(
len(data_df_for_sub.index) / 2))
sub_df.reset_index(inplace=True, drop=True)
sub_MI[i], sub_std = main(sub_df, model_df, err=False)
Std = np.std(sub_MI) / np.sqrt(2)
#we can return linfoot corrolation (rsquared) or return MI.
if rsquared:
return (1 - 2**(-2 * MI)), (1 - 2**(-2 * Std))
else:
return MI, Std