def evaluate(self,seqs):
# Check seqs container
if isinstance(seqs,pd.DataFrame):
seq_col = qc.get_cols_from_df(seqs,'seqs')[0]
seqs_to_use = list(seqs[seq_col])
elif not (isinstance(seqs,list) or isinstance(seqs,pd.Series)):
raise SortSeqError('Sequences must be input as a list, pd.Series, or pd.DataFrame')
else:
seqs_to_use = list(seqs)
# Check length
if len(seqs_to_use[0]) != self.length:
raise SortSeqError(\
'Energy Matrix Length does not equal Sequence Length')
# Compute seqmats
t0 = time.time()
seqarray = fast.seqs2array_for_matmodel(list(seqs_to_use),self.seqtype)
t1 = time.time()
# Compute and return values
vals = self.evaluate_on_seqarray(seqarray)
t2 = time.time()
#print 't1-t0 = %.4f, t1-t2 = %.4f'%(t1-t0,t2-t1)
return vals
def dataset2mutarray(dataset_df, modeltype, chunksize=1000, rowsforwtcalc=100):
# Determine the type of model and set seq2array function appropriately
if modeltype=='MAT':
seqs2array = sortseq_tools.fast.seqs2array_for_matmodel
elif modeltype=='NBR':
seqs2array = sortseq_tools.fast.seqs2array_for_nbrmodel
else:
raise SortSeqError('Unknown model type: %s'%modeltype)
# Determine seqtype, etc.
seqcol = qc.get_cols_from_df(dataset_df,'seqs')[0]
seqtype = qc.colname_to_seqtype_dict[seqcol]
wtcol = qc.seqtype_to_wtcolname_dict[seqtype]
# Compute the wt sequence
rowsforwtcalc = min(rowsforwtcalc,dataset_df.shape[0])
dataset_head_df = dataset_df.head(rowsforwtcalc)
mut_df = profile_mut(dataset_head_df)
wtseq = ''.join(list(mut_df[wtcol]))
wtrow = seqs2array([wtseq], seq_type=seqtype).ravel().astype(bool)
numfeatures = len(wtrow)
# Process dataframe in chunks
startrow = 0
endrow = startrow+chunksize-1
numrows = dataset_df.shape[0]
# Fill in mutarray (a lil matrix) chunk by chunk
mutarray_lil = lil_matrix((numrows,numfeatures),dtype=int)
matrix_filled = False
while not matrix_filled:
if startrow >= numrows:
matrix_filled = True
continue
elif endrow >= numrows:
endrow = numrows-1
matrix_filled = True
# Compute seqarray
seqlist = list(dataset_df[seqcol][startrow:(endrow+1)])
seqarray = seqs2array(seqlist, seq_type=seqtype)
# Remove wt entries
tmp = seqarray.copy()
tmp[:,wtrow] = 0
# Store results from this chunk
mutarray_lil[startrow:(endrow+1),:] = tmp
# Increment rows
startrow = endrow+1
endrow = startrow + chunksize - 1
# Convert to csr matrix
mutarray_csr = mutarray_lil.tocsr()
# Return vararray as well as binary representation of wt seq
return mutarray_csr, wtrow
def main(
data_df,model_df,
start=0,end=None,err=False):
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=0)
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,modeltype=modeltype,err=False)
Std = np.std(sub_MI)/np.sqrt(2)
return MI,Std
def main(filelist_df,tags_df=None,indir='./',seq_type=None):
""" Merges datasets listed in the filelist_df dataframe
"""
# Validate filelist
qc.validate_filelist(filelist_df)
# Read datasets into dictionary indexed by bin number
dataset_df_dict = {}
for item in filelist_df.iterrows():
# Autodetect fasta, fastq, or text file based on file extension
fn = indir+item[1]['file']
b = item[1]['bin']
if re.search(fasta_filename_patterns,fn):
df = io.load_dataset(fn,file_type='fasta',seq_type=seq_type)
elif re.search(fastq_filename_patterns,fn):
df = io.load_dataset(fn,file_type='fastq',seq_type=seq_type)
else:
df = io.load_dataset(fn,file_type='text',seq_type=seq_type)
dataset_df_dict[b] = df
# Merge datasets into one
out_df = merge_datasets(dataset_df_dict)
# Add seqs if given tags_df
if not tags_df is None:
qc.validate_tagkey(tags_df)
tag_col = 'tag'
# Test to make sure all tags in dataset are a subset of tags
data_tags = set(out_df[tag_col])
all_tags = set(tags_df[tag_col])
if not (data_tags <= all_tags):
sys.stderr.write('Some tags probably could not be identified.')
# Get name of seq column
seq_cols = qc.get_cols_from_df(tags_df, 'seqs')
if not len(seq_cols)==1:
raise SortSeqError('Multiple seq columns; exaclty 1 required.')
seq_col = seq_cols[0]
# Set tag to be index column of dataframe
tags_df = tags_df.set_index(tag_col)
# Add seqs corresponding to each tag
tags = out_df[tag_col]
seqs = tags_df[seq_col][tags].values
if not all([type(x)==str for x in seqs]):
raise SortSeqError('Some looked-up seqs are not strings.')
out_df[seq_col] = tags_df[seq_col][tags].values
qc.validate_dataset(out_df)
return out_df
def dataset2seqarray(dataset_df, modeltype):
# Determine the type of model and set seq2array function appropriately
if modeltype=='MAT':
seqs2array = sortseq_tools.fast.seqs2array_for_matmodel
elif modeltype=='NBR':
seqs2array = sortseq_tools.fast.seqs2array_for_nbrmodel
else:
raise SortSeqError('Unknown model type: %s'%modeltype)
seqcol = qc.get_cols_from_df(dataset_df,'seqs')[0]
seqtype = qc.colname_to_seqtype_dict[seqcol]
seqlist = list(dataset_df[seqcol])
seqarray = seqs2array(seqlist, seq_type=seqtype)
return seqarray
def __init__(self,model_df):
"""
Constructor takes model parameters in the form of a model dataframe
"""
model_df = qc.validate_model(model_df.copy(),fix=True)
seqtype, modeltype = qc.get_model_type(model_df)
if not modeltype=='NBR':
raise SortSeqError('Invalid modeltype: %s'%modeltype)
seq_dict,inv_dict = utils.choose_dict(seqtype,modeltype=modeltype)
self.seqtype = seqtype
self.seq_dict = seq_dict
self.inv_dict = inv_dict
self.df = model_df
self.length = model_df.shape[0]+1
# Extract matrix part of model dataframe
headers = qc.get_cols_from_df(model_df,'vals')
self.matrix = np.transpose(np.array(model_df[headers]))
def main(df,lm='IM',modeltype='MAT',LS_means_std=None,\
db=None,iteration=30000,burnin=1000,thin=10,\
runnum=0,initialize='LS',start=0,end=None,foreground=1,\
background=0,alpha=0,pseudocounts=1,test=False,drop_library=False,\
verbose=False):
# Determine dictionary
seq_cols = qc.get_cols_from_df(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,modeltype=modeltype)
'''Check to make sure the chosen dictionary type correctly describes
the sequences. An issue with this test is that if you have DNA sequence
but choose a protein dictionary, you will still pass this test bc A,C,
G,T are also valid amino acids'''
#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]
lin_seq_dict,lin_inv_dict = utils.choose_dict(dicttype,modeltype='MAT')
#wtseq = utils.profile_counts(df.copy(),dicttype,return_wtseq=True,start=start,end=end)
#wt_seq_dict_list = [{inv_dict[np.mod(i+1+seq_dict[w],len(seq_dict))]:i for i in range(len(seq_dict)-1)} for w in wtseq]
par_seq_dict = {v:k for v,k in seq_dict.items() if k != (len(seq_dict)-1)}
#drop any rows with ct = 0
df = df[df.loc[:,'ct'] != 0]
df.reset_index(drop=True,inplace=True)
#If there are sequences of different lengths, then print error but continue
if len(set(df[seq_col_name].apply(len))) > 1:
sys.stderr.write('Lengths of all sequences are not the same!')
#select target sequence region
df.loc[:,seq_col_name] = df.loc[:,seq_col_name].str.slice(start,end)
df = utils.collapse_further(df)
col_headers = utils.get_column_headers(df)
#make sure all counts are ints
df[col_headers] = df[col_headers].astype(int)
#create vector of column names
val_cols = ['val_' + inv_dict[i] for i in range(len(seq_dict))]
df.reset_index(inplace=True,drop=True)
#Drop any sequences with incorrect length
if not end:
'''is no value for end of sequence was supplied, assume first seq is
correct length'''
seqL = len(df[seq_col_name][0]) - start
else:
seqL = end-start
df = df[df[seq_col_name].apply(len) == (seqL)]
df.reset_index(inplace=True,drop=True)
#Do something different for each type of learning method (lm)
if lm == 'ER':
emat = Berg_von_Hippel(
df,dicttype,foreground=foreground,background=background,
pseudocounts=pseudocounts)
if lm == 'LS':
'''First check that is we don't have a penalty for ridge regression,
that we at least have all possible base values so that the analysis
will not fail'''
if LS_means_std: #If user supplied preset means and std for each bin
means_std_df = io.load_meanstd(LS_means_std)
#change bin number to 'ct_number' and then use as index
labels = list(means_std_df['bin'].apply(add_label))
std = means_std_df['std']
std.index = labels
#Change Weighting of each sequence by dividing counts by bin std
df[labels] = df[labels].div(std)
means = means_std_df['mean']
means.index = labels
else:
means = None
#drop all rows without counts
df['ct'] = df[col_headers].sum(axis=1)
df = df[df.ct != 0]
df.reset_index(inplace=True,drop=True)
''' For sort-seq experiments, bin_0 is library only and isn't the lowest
expression even though it is will be calculated as such if we proceed.
Therefore is drop_library is passed, drop this column from analysis.'''
if drop_library:
try:
df.drop('ct_0',inplace=True)
col_headers = utils.get_column_headers(df)
if len(col_headers) < 2:
raise SortSeqError(
'''After dropping library there are no longer enough
columns to run the analysis''')
except:
raise SortSeqError('''drop_library option was passed, but no ct_0
column exists''')
#parameterize sequences into 3xL vectors
raveledmat,batch,sw = utils.genweightandmat(
df,par_seq_dict,dicttype,means=means,modeltype=modeltype)
#Use ridge regression to find matrix.
emat = Compute_Least_Squares(raveledmat,batch,sw,alpha=alpha)
if lm == 'IM':
seq_mat,wtrow = numerics.dataset2mutarray(df.copy(),modeltype)
#this is also an MCMC routine, do the same as above.
if initialize == 'rand':
if modeltype == 'MAT':
emat_0 = utils.RandEmat(len(df[seq_col_name][0]),len(seq_dict))
elif modeltype == 'NBR':
emat_0 = utils.RandEmat(len(df['seq'][0])-1,len(seq_dict))
elif initialize == 'LS':
emat_cols = ['val_' + inv_dict[i] for i in range(len(seq_dict))]
emat_0_df = main(df.copy(),lm='LS',modeltype=modeltype,alpha=alpha,start=0,end=None,verbose=verbose)
emat_0 = np.transpose(np.array(emat_0_df[emat_cols]))
#pymc doesn't take sparse mat
emat = MaximizeMI_memsaver(
seq_mat,df.copy(),emat_0,wtrow,db=db,iteration=iteration,burnin=burnin,
thin=thin,runnum=runnum,verbose=verbose)
#now format the energy matrices to get them ready to output
if (lm == 'IM' or lm == 'memsaver'):
if modeltype == 'NBR':
emat_typical = gauge.fix_neighbor(np.transpose(emat))
elif modeltype == 'MAT':
emat_typical = gauge.fix_matrix(np.transpose(emat))
elif lm == 'ER':
'''the emat for this format is currently transposed compared to other formats
it is also already a data frame with columns [pos,val_...]'''
emat_cols = ['val_' + inv_dict[i] for i in range(len(seq_dict))]
emat_typical = emat[emat_cols]
emat_typical = (gauge.fix_matrix((np.array(emat_typical))))
else: #must be Least squares
emat_typical = utils.emat_typical_parameterization(emat,len(seq_dict))
if modeltype == 'NBR':
emat_typical = gauge.fix_neighbor(np.transpose(emat_typical))
elif modeltype == 'MAT':
emat_typical = gauge.fix_matrix(np.transpose(emat_typical))
em = pd.DataFrame(emat_typical)
em.columns = val_cols
#add position column
if modeltype == 'NBR':
pos = pd.Series(range(start,start - 1 + len(df[seq_col_name][0])),name='pos')
else:
pos = pd.Series(range(start,start + len(df[seq_col_name][0])),name='pos')
output_df = pd.concat([pos,em],axis=1)
# Validate model and return
output_df = qc.validate_model(output_df,fix=True)
return output_df
