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 __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 Berg_von_Hippel(df,dicttype,foreground=1,background=0,pseudocounts=1):
'''Learn models using berg von hippel model. The foreground sequences are
usually bin_1 and background in bin_0, this can be changed via flags.'''
seq_dict,inv_dict = utils.choose_dict(dicttype)
#check that the foreground and background chosen columns actually exist.
columns_to_check = {'ct_' + str(foreground),'ct_' + str(background)}
if not columns_to_check.issubset(set(df.columns)):
raise SortSeqError('Foreground or Background column does not exist!')
#get counts of each base at each position
foreground_counts = utils.profile_counts(df,dicttype,bin_k=foreground)
background_counts = utils.profile_counts(df,dicttype,bin_k=background)
binheaders = utils.get_column_headers(foreground_counts)
#add pseudocounts to each position
foreground_counts[binheaders] = foreground_counts[binheaders] + pseudocounts
background_counts[binheaders] = background_counts[binheaders] + pseudocounts
#make sure there are no zeros in counts after addition of pseudocounts
ct_headers = utils.get_column_headers(foreground_counts)
if foreground_counts[ct_headers].isin([0]).values.any():
raise SortSeqError('''There are some bases without any representation in\
the foreground data, you should use pseudocounts to avoid failure \
of the learning method''')
if background_counts[ct_headers].isin([0]).values.any():
raise SortSeqError('''There are some bases without any representation in\
the background data, you should use pseudocounts to avoid failure \
of the learning method''')
#normalize to compute frequencies
foreground_freqs = foreground_counts.copy()
background_freqs = background_counts.copy()
foreground_freqs[binheaders] = foreground_freqs[binheaders].div(
foreground_freqs[binheaders].sum(axis=1),axis=0)
background_freqs[binheaders] = background_freqs[binheaders].div(
background_freqs[binheaders].sum(axis=1),axis=0)
output_df = -np.log(foreground_freqs/background_freqs)
#change column names accordingly (instead of ct_ we want val_)
rename_dict = {'ct_' + str(inv_dict[i]):'val_' + str(inv_dict[i]) for i in range(len(seq_dict))}
output_df = output_df.rename(columns=rename_dict)
return output_df
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
def main(wtseq=None, mutrate=0.10, numseq=10000,dicttype='dna',probarr=None,
tags=False,tag_length=10):
#generate sequence dictionary
seq_dict,inv_dict = utils.choose_dict(dicttype)
mutrate = float(mutrate)
if (mutrate < 0.0) or (mutrate > 1.0):
raise SortSeqError('Invalid mutrate==%f'%mutrate)
numseq = int(numseq)
if (numseq <= 0):
raise SortSeqError('numseq must be positive. Is %d'%numseq)
tag_length = int(tag_length)
if (tag_length <= 0):
raise SortSeqErorr('tag_length must be positive. Is %d'%tag_length)
if isinstance(probarr,np.ndarray):
L = probarr.shape[1]
#Generate bases according to provided probability matrix
letarr = np.zeros([numseq,L])
for z in range(L):
letarr[:,z] = np.random.choice(
range(len(seq_dict)),numseq,p=probarr[:,z])
else:
parr = []
wtseq = wtseq.upper()
L = len(wtseq)
letarr = np.zeros([numseq,L])
#Check to make sure the wtseq uses the correct bases.
lin_seq_dict,lin_inv_dict = utils.choose_dict(dicttype,modeltype='MAT')
def check_sequences(s):
return set(s).issubset(lin_seq_dict)
if not check_sequences(wtseq):
raise SortSeqError(
'wtseq can only contain bases in ' + str(lin_seq_dict.keys()))
#find wtseq array
wtarr = seq2arr(wtseq,seq_dict)
mrate = mutrate/(len(seq_dict)-1) #prob of non wildtype
#Generate sequences by mutating away from wildtype
'''probabilities away from wildtype (0 = stays the same, a 3 for
example means a C becomes an A, a 1 means C-> G)'''
parr = np.array(
[1-(len(seq_dict)-1)*mrate]
+ [mrate for i in range(len(seq_dict)-1)])
#Generate random movements from wtseq
letarr = np.random.choice(
range(len(seq_dict)),[numseq,len(wtseq)],p=parr)
#Find sequences
letarr = np.mod(letarr + wtarr,len(seq_dict))
seqs= []
#Convert Back to letters
for i in range(numseq):
seqs.append(arr2seq(letarr[i,:],inv_dict))
seq_col = qc.seqtype_to_seqcolname_dict[dicttype]
seqs_df = pd.DataFrame(seqs, columns=[seq_col])
# If simulating tags, each generated seq gets a unique tag
if tags:
tag_seq_dict,tag_inv_dict = utils.choose_dict('dna')
tag_alphabet_list = tag_seq_dict.keys()
# Make sure tag_length is long enough for the number of tags needed
if len(tag_alphabet_list)**tag_length < 2*numseq:
raise SortSeqError(\
'tag_length=%d is too short for num_tags_needed=%d'%\
(tag_length,numseq))
# Generate a unique tag for each unique sequence
tag_set = set([])
while len(tag_set) < numseq:
num_tags_left = numseq - len(tag_set)
new_tags = [''.join(choice(tag_alphabet_list,size=tag_length)) \
for i in range(num_tags_left)]
tag_set = tag_set.union(new_tags)
df = seqs_df.copy()
df.loc[:,'ct'] = 1
df.loc[:,'tag'] = list(tag_set)
# If not simulating tags, list only unique seqs w/ corresponding counts
else:
seqs_counts = seqs_df[seq_col].value_counts()
df = seqs_counts.reset_index()
df.columns = [seq_col,'ct']
# Convert into valid dataset dataframe and return
return qc.validate_dataset(df,fix=True)
x = fast.seq2sitelist(seq,site_length, rc=True, safe=False)
c_time = time.time()-t
print 'cython, seq2sitelist w/ rc: %f sec to chop seq into %d rc sites'%\
(c_time,len(x))
print '%.1f-fold speedup.'%(p_time/c_time)
print '-----------------------------'
# Test seqs2array_for_matmodel
sites = fast.seq2sitelist(seq,20)
site_length = len(sites[0])
num_sites = len(sites)
t = time.time()
seq_dict,inv_dict = utils.choose_dict(seqtype,modeltype='MAT')
sitearray_p = np.zeros([num_sites,(site_length*len(seq_dict))],dtype=int)
for i, site in enumerate(sites):
sitearray_p[i,:] = utils.seq2mat(site,seq_dict).ravel()
p_time = time.time()-t
print 'python, seqs2array_for_matmodel: %f sec to convert %d %s seqs of length %d'%\
(p_time,num_sites,seqtype,site_length)
t = time.time()
sitearray = fast.seqs2array_for_matmodel(sites,seqtype,safe=False)
c_time = time.time()-t
print 'cython, seqs2array_for_matmodel: %f sec to convert %d %s seqs of length %d'%\
(c_time,num_sites,seqtype,site_length)
print '%.1f-fold speedup.'%(p_time/c_time)
def main(model_df, contig_list, numsites=10, verbose=False):
# Determine type of string from model
qc.validate_model(model_df)
seqtype, modeltype = qc.get_model_type(model_df)
seq_dict,inv_dict = utils.choose_dict(seqtype,modeltype=modeltype)
# Check that all characters are from the correct alphabet
alphabet = qc.seqtype_to_alphabet_dict[seqtype]
search_string = r"[^%s]"%alphabet
for contig_str, contig_name, pos_offset in contig_list:
if re.search(search_string,contig_str):
raise SortSeqError(\
'Invalid character for seqtype %s found in %s.'%\
(seqtype,contig_name))
# Create model object to evaluate on seqs
if modeltype == 'MAT':
model_obj = Models.LinearModel(model_df)
elif modeltype == 'NBR':
model_obj = Models.NeighborModel(model_df)
# Create list of dataframes, one for each contig
seq_col = qc.seqtype_to_seqcolname_dict[seqtype]
L = model_obj.length
sitelist_df = pd.DataFrame(\
columns=['val',seq_col,'left','right','ori','contig'])
for contig_str, contig_name, pos_offset in contig_list:
if len(contig_str) < L:
continue
this_df = pd.DataFrame(\
columns=['val',seq_col,'left','right','ori','contig'])
num_sites = len(contig_str) - L + 1
poss = np.arange(num_sites).astype(int)
this_df['left'] = poss + pos_offset
this_df['right'] = poss + pos_offset + L - 1
#this_df[seq_col] = [contig_str[i:(i+L)] for i in poss]
this_df[seq_col] = fast.seq2sitelist(contig_str,L) #Cython
this_df['ori'] = '+'
this_df['contig'] = contig_name
this_df['val'] = model_obj.evaluate(this_df[seq_col])
sitelist_df = pd.concat([sitelist_df,this_df], ignore_index=True)
# If scanning DNA, scan reverse-complement as well
if seqtype=='dna':
#this_df[seq_col] = [qc.rc(s) for s in this_df[seq_col]]
this_df[seq_col] = fast.seq2sitelist(contig_str,L,rc=True) #Cython
this_df['ori'] = '-'
this_df['val'] = model_obj.evaluate(this_df[seq_col])
sitelist_df = pd.concat([sitelist_df,this_df], ignore_index=True)
# Sort by value and reindex
sitelist_df.sort_values(by='val', ascending=False, inplace=True)
sitelist_df.reset_index(drop=True,inplace=True)
# Crop list at numsites
if sitelist_df.shape[0]>numsites:
sitelist_df.drop(sitelist_df.index[numsites:], inplace=True)
if verbose:
print '.',
sys.stdout.flush()
if verbose:
print ''
sys.stdout.flush()
# If no sites were found, raise error
if sitelist_df.shape[0]==0:
raise SortSeqError(\
'No full-length sites found within provided contigs.')
sitelist_df = qc.validate_sitelist(sitelist_df,fix=True)
return sitelist_df