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 convert_motif_text_file(inp_filename, out_filename):
current_sequence_str = ''
current_structure_str = ''
total_bitstring = b''
with open(inp_filename, 'r') as rf:
for i, line in enumerate(rf):
stripped_line = line.rstrip()
if i % 2 == 0:
current_structure_str = stripped_line
else:
current_sequence_str = stripped_line
stem_length = current_structure_str.index('.')
loop_length = len(current_structure_str) - stem_length
current_motif = structures.w_motif(stem_length, loop_length)
current_motif.from_string(current_sequence_str)
current_motif.compress()
total_bitstring += current_motif.bytestring
with open(out_filename, 'wb') as wf:
wf.write(total_bitstring)
def create_one_seed(do_print = True):
test_motif_1 = structures.w_motif(5, 4)
test_motif_1.from_string("BSHNVBCNU")
test_motif_1.change_structure_position(0, glob_var._loop)
if do_print:
print("Test motif:")
test_motif_1.print()
test_motif_1.print_linear()
n_test_motif = type_conversions.w_to_n_motif(test_motif_1)
return n_test_motif
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 prepare_known_seeds(args):
seqs_shape, seqs_to_test, bin_file_to_test, desired_numbers = define_constants(args)
w_motifs_list = [0] * len(seqs_to_test)
for ind, seq in enumerate(seqs_to_test):
curr_test_motif = structures.w_motif(seqs_shape[0], seqs_shape[1])
curr_test_motif.from_string(seq)
w_motifs_list[ind] = curr_test_motif
seqs_dict, seqs_order = IO.read_rna_bin_file(bin_file_to_test)
w_seqs_list = [seqs_dict[name] for name in seqs_order]
n_motifs_list = type_conversions.w_to_n_motifs_list(w_motifs_list)
n_seqs_list = type_conversions.w_to_n_sequences_list(w_seqs_list)
return n_motifs_list, n_seqs_list
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))