def borodovsky_blosum_50_2():
seqs = sequence.readFastaFile("./files/simple_seqs/borodovsky.fasta")
profile1 = aln_profile.AlignmentProfile([seqs[0]])
profile2 = aln_profile.AlignmentProfile([seqs[1]])
phmm = align.load_params(params.borodovsky_4_7, [profile1, profile2],
sub_matrix.blosum62LatestProbs,
log_transform=False)
return phmm
def durbin_blosum_50_2():
seqs = sequence.readFastaFile("./files/simple_seqs/durbin_2.fasta")
profile1 = aln_profile.AlignmentProfile([seqs[0]])
profile2 = aln_profile.AlignmentProfile([seqs[1]])
phmm = align.load_params(params.basic_params, [profile1, profile2],
sub_matrix.blosum50,
log_transform=True)
return phmm
def probabilities_blosum_62_2():
seqs = sequence.readFastaFile("./files/simple_seqs/simple_2.fasta")
profile1 = aln_profile.AlignmentProfile([seqs[0]])
profile2 = aln_profile.AlignmentProfile([seqs[1]])
phmm = align.load_params(params.basic_params, [profile1, profile2],
sub_matrix.blosum62LatestProbs,
log_transform=True)
return phmm
def two_col_62_2():
seqs = sequence.readFastaFile("./files/custom_seqs/2_col.fasta")
profile1 = aln_profile.AlignmentProfile([seqs[0]])
profile2 = aln_profile.AlignmentProfile([seqs[1]])
phmm = align.load_params(params.basic_params, [profile1, profile2],
sub_matrix.blosum62,
log_transform=True)
return phmm
def ox_104t17_1():
seqs = sequence.readFastaFile(
"./files/qscore_corrections/ox_104t17_1.fasta")
profile1 = aln_profile.AlignmentProfile([seqs[0]])
profile2 = aln_profile.AlignmentProfile([seqs[1]])
phmm = align.load_params(params.qscore_params, [profile1, profile2],
sub_matrix.blosum62EstimatedWithX,
log_transform=True)
return phmm
def runBaumWelch(parameters, profiles, aln_type, count=0, stop=2):
if count == stop:
return parameters
pair_hmm = align.load_params(parameters, profiles, subsmat=sub_matrix.blosum62EstimatedWithX_dict,
log_transform=True, predecessors=predecessors)
print ('Delta value is ')
print (pair_hmm.delta)
print ('Epsilon value is')
print (pair_hmm.epsilon)
print ("Emission X value is ")
print (pair_hmm.emissionX)
print ("Emission Y value is ")
print (pair_hmm.emissionY)
if aln_type == 'viterbi':
pair_hmm.performViterbiAlignment()
copy_hmm = copy.deepcopy(pair_hmm)
aligned_profile = copy_hmm.get_alignment(type_to_get='viterbi')
print (aligned_profile)
# Update parameters
parameters['epsilon'] = float(pair_hmm.epsilon + 0.00001)
parameters['delta'] = float(pair_hmm.delta + 0.00001)
parameters['emissionX'] = float(pair_hmm.emissionX + 0.00001)
parameters['emissionY'] = float(pair_hmm.emissionY + 0.00001)
return runBaumWelch(parameters, profiles, aln_type, count +1)
elif aln_type == 'mea':
pair_hmm.performMEAAlignment()
copy_hmm = copy.deepcopy(pair_hmm)
aligned_profile = copy_hmm.get_alignment(type_to_get='mea')
print (aligned_profile)
# Update parameters
parameters['epsilon'] = float(pair_hmm.epsilon + 0.00001)
parameters['delta'] = float(pair_hmm.delta + 0.00001)
parameters['emissionX'] = float(pair_hmm.emissionX + 0.00001)
parameters['emissionY'] = float(pair_hmm.emissionY + 0.00001)
return runBaumWelch(parameters, profiles, aln_type, count +1)
# seqs = sequence.readFastaFile(sequences, alphabet=Protein_Alphabet_wB_X_Z)
#
# aln_order = [("N0", [seqs[0].name, seqs[1].name])]
#
# seqs = get_profiles(seqs, aln_order)
#
# # Reload parameters
#
# pair_hmm = align.load_params(parameters, seqs, subsmat=sub_matrix.blosum62EstimatedWithX_dict,
# log_transform=True)
# seq_file = '../tests/files/custom_seqs/2_col.fasta'
# output_file = '../tests/files/custom_seqs/col_3.aln'
# aln_type = 'mea'
# seqs = sequence.readFastaFile(seq_file, alphabet=Protein_Alphabet_wB_X_Z)
#
#
# for seq_order in list(itertools.combinations(seqs, 2)):
#
# profiles = [aln_profile.AlignmentProfile([x]) for x in seq_order]
# print (seq_order)
#
# change_params = runBaumWelch(change_params, profiles, aln_type)
#
#
# print (params)
# print (change_params)
# alignment = align.align_seqs(seq_file,
# output_file, aln_type,
# params=params, subsmat=sub_matrix.blosum62EstimatedWithX_dict,log_transform=True)
#
# change_alignment = align.align_seqs(seq_file,
# output_file, aln_type,
# params=change_params, subsmat=sub_matrix.blosum62EstimatedWithX_dict,log_transform=True)
