def test_filtered_profiles(args):
original_profiles_array = IO.unpack_profiles_file(args.profiles_full_file,
do_print=True)
with open(args.profiles_filtered_file, 'rb') as rf:
bitstring = rf.read()
filtered_profiles_array = IO.decompress_profiles_indices(bitstring)
print(original_profiles_array.shape)
print(original_profiles_array)
print(original_profiles_array[6:16, ].sum())
print(filtered_profiles_array.shape)
print(filtered_profiles_array)
print(filtered_profiles_array.sum())
def run_test_bins_fasta(args):
with open(args.rna_bin_file, 'rb') as rb:
bitstring = rb.read()
seq_objects_dict, seq_objects_order = IO.decompress_named_sequences(
bitstring)
full_string = IO.write_named_seq_to_fasta(seq_objects_dict,
seq_objects_order)
with open(args.rna_fastafile, 'r') as rf:
full_fasta_string = rf.read()
full_fasta_string_Us = full_fasta_string.replace('T', 'U').replace(
'ENSU', 'ENST')
assert (len(full_string) == len(full_fasta_string_Us))
assert (full_string == full_fasta_string_Us)
def time_calculate_MI_profiles(calculate_with_numba):
test_batch_folder = '/Users/student/Documents/hani/programs/pyteiser/data/test_1_batch_snrnpa1'
seeds_filename = os.path.join(test_batch_folder,
'seeds_4-7_4-9_4-6_14-20_30k_1.bin')
profiles_filename = os.path.join(
test_batch_folder, 'snrnpa_profiles_4-7_4-9_4-6_14-20_30k_1.bin')
exp_mask_filename = "/Users/student/Documents/hani/programs/pyteiser/data/mask_files/SNRNPA1_PSI_mask.bin"
nbins = 15
min_occurences = 5
decompressed_profiles_array, index_array, values_array = IO.unpack_profiles_and_mask(
profiles_filename, exp_mask_filename, do_print=True)
discr_exp_profile = MI.discretize_exp_profile(index_array, values_array,
nbins)
value, counts = np.unique(discr_exp_profile, return_counts=True, axis=0)
print(counts)
MI_values_array = calculate_MI_profiles.calculate_MI_for_seeds(
decompressed_profiles_array,
index_array,
discr_exp_profile,
min_occurences,
calculate_with_numba,
do_print=True)
def profiles_wrapper(args):
profiles_filename = args.profiles_full_file
decompressed_profiles_array = IO.unpack_profiles_file(profiles_filename,
args.indices_mode,
do_print=True)
run_test_compressing_decompressing_indices(args,
decompressed_profiles_array)
def main():
args = handler()
w_motifs_list = IO.read_motif_file(args.seeds_bin_file)
test_representation(w_motifs_list[2], args.temp_folder)
test_RNAstructure_plotting(w_motifs_list[0:10])
def main():
args = handler()
n_seqs_list = read_sequences(args.rna_bin_file)
index_array, values_array = IO.unpack_mask_file(args.exp_mask_file)
discr_exp_profile = MI.discretize_exp_profile(index_array, values_array, nbins = args.nbins)
seqs_of_interest = [n_seqs_list[x] for x in range(index_array.shape[0]) if index_array[x]]
test_elongated_seed(seqs_of_interest, discr_exp_profile, args.nbins, args.number_example_matches_to_print)
def test_bins_fasta(args):
with open(args.rna_bin_file, 'rb') as rb:
bitstring = rb.read()
seq_objects_dict, seq_objects_order = IO.decompress_named_sequences(
bitstring)
full_string = IO.write_named_seq_to_fasta(seq_objects_dict,
seq_objects_order)
with open(args.rna_fastafile, 'r') as rf:
full_fasta_string = rf.read()
with open("/Users/student/Documents/hani/temp/temp_fasta/1.txt",
'w') as wf:
wf.write(full_string)
full_fasta_string_Us = full_fasta_string.replace('T', 'U').replace(
'ENSU', 'ENST')
assert (len(full_string) == len(full_fasta_string_Us))
#
# print(full_string[0:200])
# print(full_fasta_string_Us[0:200])
assert (full_string == full_fasta_string_Us)
def run_test_profiles_compression_decompression(args, do_shorten_test = True):
args.seedfile = args.seeds_bin_file
n_motifs_list, n_seqs_list = calculate_seed_profiles.prepare_lists_for_calculations(args)
if do_shorten_test:
n_motifs_list = n_motifs_list[0:3]
calculated_profiles_array = calculate_seed_profiles.calculate_write_profiles(n_motifs_list, n_seqs_list,
args.profiles_bin_file, do_print=True,
do_return=True)
with open(args.profiles_bin_file, 'rb') as rf:
bitstring = rf.read()
decompressed_profiles_array = IO.decompress_profiles(bitstring)
assert(np.array_equal(calculated_profiles_array, decompressed_profiles_array))
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 test_compressing_decompressing_indices(args, decompressed_profiles_array):
with open(args.compressed_profiles_file, 'wb') as wf:
transcriptome_length = decompressed_profiles_array.shape[1]
for i in range(decompressed_profiles_array.shape[0]):
curr_profile = structures.w_profile(transcriptome_length)
curr_profile.values = decompressed_profiles_array[i]
curr_profile.compress_indices()
wf.write(curr_profile.bytestring_indices)
with open(args.compressed_profiles_file, 'rb') as rf:
bitstring = rf.read()
read_out_profiles_array = IO.decompress_profiles_indices(bitstring)
assert (read_out_profiles_array == decompressed_profiles_array
).all(), "decompression has changed the data!"
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 read_sequences(rna_bin_filename):
seqs_dict, seqs_order = IO.read_rna_bin_file(rna_bin_filename)
w_seqs_list = [seqs_dict[name] for name in seqs_order]
n_seqs_list = type_conversions.w_to_n_sequences_list(w_seqs_list)
return n_seqs_list
def time_compressing_sequences(fasta_file):
sequences_dict, seqs_order = IO.read_fasta(fasta_file)
for i in range(len(seqs_order)):
print(seqs_order[i])