def run_test_matchmaker_elongated_seed():
test_motif_1 = structures.w_motif(5, 6)
test_motif_1.from_string("NNVBGNSBGNN")
test_motif_1.change_structure_position(0, glob_var._loop)
#test_motif_1.print()
test_motif_2 = structures.w_motif(6, 6)
test_motif_2.from_string("ANGAGCAANNNA")
test_motif_2.change_structure_position(1, glob_var._loop)
test_motif_2.change_structure_position(3, glob_var._loop)
#test_motif_2.print()
test_string_1 = 'AAGGGAGGGAACCCU'
test_sequence_1 = structures.w_sequence(len(test_string_1))
test_sequence_1.from_sequence(test_string_1)
test_string_2 = 'ACGAGCAAAAAAGCCU'
test_sequence_2 = structures.w_sequence(len(test_string_2))
test_sequence_2.from_sequence(test_string_2)
w_motifs = [test_motif_1, test_motif_2]
w_sequences = [test_sequence_1, test_sequence_2]
n_motifs = type_conversions.w_to_n_motifs_list(w_motifs)
n_sequences = type_conversions.w_to_n_sequences_list(w_sequences)
boolean_matchmaker_desired = np.array([[1, 0], [0, 1]], dtype=bool)
boolean_matchmaker_res = np.zeros(shape=(2, 2), dtype=bool)
for i, mt in enumerate(n_motifs):
for k, sq in enumerate(n_sequences):
is_match = matchmaker.is_there_motif_instance(mt, sq, is_degenerate=True)
boolean_matchmaker_res[i,k] = is_match
assert(np.array_equal(boolean_matchmaker_res, boolean_matchmaker_desired))
def run_test_elongated_seed(seqs_of_interest,
discr_exp_profile,
nbins,
N,
do_print=True):
elong_seed = create_one_seed(do_print)
current_profile, time_spent = matchmaker.calculate_profile_one_motif(
elong_seed, seqs_of_interest, is_degenerate=True)
matching_sequences = [
seqs_of_interest[x] for x in range(current_profile.values.shape[0])
if current_profile.values[x]
]
curr_mi = MI.mut_info(current_profile.values,
discr_exp_profile,
x_bins=2,
y_bins=nbins)
if do_print:
print(curr_mi)
first_N_matching_sequences = matching_sequences[0:N]
counter = 0
for seq in first_N_matching_sequences:
curr_matching_indices = matchmaker.find_all_motif_instances(
elong_seed, seq, is_degenerate=True)
for match_index in curr_matching_indices:
counter += 1
match_sequence = structures.w_sequence(elong_seed.linear_length)
match_sequence.nts = seq.nts[match_index:match_index +
elong_seed.linear_length]
match_string = match_sequence.print(return_string=True)
print("Match %d: %s" % (counter, match_string))
def time_reading_fasta(fasta_file):
tr_dict_loc = {}
seqs_order = []
with open(fasta_file, 'r') as f:
split_string = f.read().split('>')
for entry in split_string:
if entry == '':
continue
seq_start = entry.find('\n')
annotation = entry[:seq_start]
sequence_string = entry[seq_start + 1:].replace('\n', '')
current_sequence = structures.w_sequence(len(sequence_string))
current_sequence.from_sequence(sequence_string)
time_create_object = timeit.timeit(
lambda: structures.w_sequence(len(sequence_string)),
number=100)
time_fill_object = timeit.timeit(
lambda: current_sequence.from_sequence(sequence_string),
number=100)
time_compress_object = timeit.timeit(
lambda: current_sequence.compress(), number=100)
time_compress_named_object = timeit.timeit(
lambda: IO.compress_named_sequences(
{annotation: current_sequence}, [annotation]),
number=100)
print("Create object: %.5f" % time_create_object)
print("Fill object: %.5f" % time_fill_object)
print("Compress object: %.5f" % time_compress_object)
print("Compress named object: %.5f" % time_compress_named_object)
print()
# curr_timing = timeit.timeit('current_sequence.from_sequence(sequence_string)',
# 'from __main__ import current_sequence, sequence_string')
# print(curr_timing)
#
# tr_dict_loc[annotation] = current_sequence
# seqs_order.append(annotation)
return tr_dict_loc, seqs_order
def run_test_matchmaker_non_degenerate():
# test matchmaking algorithms
# 3 strings listed here contain instances of 3 matches that are also listed here
test_motif_1 = structures.w_motif(4,6)
test_motif_2 = structures.w_motif(4,6)
test_motif_3 = structures.w_motif(4,6)
test_motif_1.from_string("GNCANCNNUU")
test_motif_2.from_string("AAUNNGNGNU")
test_motif_3.from_string("NNACGNNCUU")
test_motifs_list_w = [test_motif_1, test_motif_2, test_motif_3]
test_motifs_list = type_conversions.w_to_n_motifs_list(test_motifs_list_w)
test_string_1 = 'UUUUUUUGACAACAAUUTGTCUUUUU' # instance motif_1 at 7
test_string_2 = "GGCAUCAGUUUUUUAAUGUGUGAUCAUUGGGUUCCCCCUUUUU" # instance motif_2 at 14
test_string_3 = "AAUUAAAACCCCCCCAAACGCCCUUGUUUCCCACCACGGGCUUGUGGAAAAUUUUUU" # instances motif_3 at 15 and 33
test_sequence_1 = structures.w_sequence(len(test_string_1))
test_sequence_2 = structures.w_sequence(len(test_string_2))
test_sequence_3 = structures.w_sequence(len(test_string_3))
test_sequence_1.from_sequence(test_string_1)
test_sequence_2.from_sequence(test_string_2)
test_sequence_3.from_sequence(test_string_3)
test_sequences_list_w = [test_sequence_1, test_sequence_2, test_sequence_3]
test_sequences_list = type_conversions.w_to_n_sequences_list(test_sequences_list_w)
boolean_matchmaker_desired = np.array([[1, 0, 0], [0, 1, 0], [0, 0, 1]], dtype=bool)
boolean_matchmaker_res = np.zeros(shape=(3, 3), dtype=bool)
indices_matchmaker_desired = [[7],[],[],[],[14],[],[],[],[15,33]]
indices_matchmaker_res = []
for i, mt in enumerate(test_motifs_list):
for k, sq in enumerate(test_sequences_list):
is_match = matchmaker.is_there_motif_instance(mt, sq)
matching_indices = matchmaker.find_all_motif_instances(mt, sq)
boolean_matchmaker_res[i,k] = is_match
indices_matchmaker_res.append(matching_indices)
assert(np.array_equal(boolean_matchmaker_res, boolean_matchmaker_desired))
assert(indices_matchmaker_res == indices_matchmaker_desired)
def create_single_pair(stem=4,
loop=7,
motif_str="NGCAUNGNANN",
seq_str="UGCAUUGUAUGUGUG"):
test_motif = structures.w_motif(stem, loop)
test_motif.from_string(motif_str)
n_test_motif = type_conversions.w_to_n_motif(test_motif)
test_sequence = structures.w_sequence(len(seq_str))
test_sequence.from_sequence(seq_str)
n_test_sequence = type_conversions.w_to_n_sequence(test_sequence)
return n_test_motif, n_test_sequence
def run_test_current_pair(stem = 4, loop = 7,
motif_str = "NGCAUNGNANN",
seq_str = "UGCAUUGUAUGUGUG"):
test_motif = structures.w_motif(stem, loop)
test_motif.from_string(motif_str)
n_test_motif = type_conversions.w_to_n_motif(test_motif)
test_sequence = structures.w_sequence(len(seq_str))
test_sequence.from_sequence(seq_str)
n_test_sequence = type_conversions.w_to_n_sequence(test_sequence)
is_match = matchmaker.is_there_motif_instance(n_test_motif, n_test_sequence)
if is_match:
print("Sequence %s matches the motif %s" % (seq_str, motif_str))
motif_instances = matchmaker.find_all_motif_instances(n_test_motif, n_test_sequence)
print("Motif instances are: ", ", ".join([str(x) for x in motif_instances]))
else:
print("Sequence %s DOES NOT matches the motif %s" % (seq_str, motif_str))