def main():
import_modules()
args = handler()
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)
seeds_passed = IO.read_motif_file(args.combined_seeds_filename)
profiles_passed = IO.unpack_profiles_file(args.combined_profiles_filename)
classification_array, N_families = filter_CMI(seeds_passed,
profiles_passed,
discr_exp_profile,
index_array,
args.nbins,
args.min_ratio,
do_print=args.do_print)
MI_values_array = calculate_MIs_all_seeds(profiles_passed,
discr_exp_profile, index_array,
args.nbins)
seeds_unique, profiles_unique = choose_best_reps_for_families(
seeds_passed,
profiles_passed,
classification_array,
N_families,
MI_values_array,
do_print=args.do_print)
IO.write_list_of_seeds(seeds_unique, args.unique_seeds_filename)
IO.write_array_of_profiles(profiles_unique, args.unique_profiles_filename)
IO.write_classification_array(classification_array,
args.families_classification_filename)
def main():
import_modules()
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)
seeds_initial = IO.read_motif_file(args.unique_seeds_filename)
profiles_initial = IO.unpack_profiles_file(args.unique_profiles_filename)
seqs_of_interest = [n_seqs_list[x] for x in range(index_array.shape[0]) if index_array[x]]
# get the task id
env_variables_dict = sge.get_env_variables()
seed_chunks, profiles_chunks = chunk_up_input_files(seeds_initial, profiles_initial, args.size_of_chunks)
seed_right_chunk, profiles_right_chunk = pick_one_chunk(seed_chunks, profiles_chunks, env_variables_dict)
seeds_filename_full, profiles_filename_full, \
char_filename_full, robustness_filename_full = make_output_filenames(env_variables_dict, args)
seeds_optimized, profiles_optimized, \
seed_charact_array, robustness_array = optimize_motifs(seed_right_chunk, profiles_right_chunk,
discr_exp_profile, args.nbins, index_array, seqs_of_interest,
args, do_print=True)
IO.write_list_of_seeds(seeds_optimized, seeds_filename_full)
IO.write_array_of_profiles(profiles_optimized, profiles_filename_full)
IO.write_np_array(seed_charact_array, char_filename_full)
IO.write_np_array(robustness_array, robustness_filename_full)
def main():
# I only import things if I run this script itself
# do relative import based on current working directory
# otherwise I have to install the package for relative import to work
import_modules()
args = handler()
# get mapping of task ids to input files
mapping_dict = sge.parse_task_mapping_file(args.task_mapping_file)
# get the task id
env_variables_dict = sge.get_env_variables()
# get the names of input and output files
profiles_filename_full, MI_values_filename_full, rna_bin_filename = get_current_in_out_filenames(
args, env_variables_dict, mapping_dict)
decompressed_profiles_array, index_array, values_array = IO.unpack_profiles_and_mask(
profiles_filename_full, args.exp_mask_file, do_print=True)
discr_exp_profile = MI.discretize_exp_profile(index_array, values_array,
args.nbins)
MI_values_array = calculate_MI_for_seeds(decompressed_profiles_array,
index_array,
discr_exp_profile,
args.nbins,
args.min_occurences,
do_print=True)
IO.write_MI_values(MI_values_array, args.nbins, MI_values_filename_full)
if args.print_qstat == 'y':
sge.print_qstat_proc(env_variables_dict, args.path_to_qstat)
def main():
# I only import things if I run this script itself
# do relative import based on current working directory
# otherwise I have to install the package for relative import to work
import_modules()
args = handler()
# get mapping of task ids to input files
mapping_dict = sge.parse_task_mapping_file(args.task_mapping_file)
# get the task id
env_variables_dict = sge.get_env_variables()
# get the names of input and output files
profiles_filename_full, MI_values_filename_full, \
passed_seed_filename_full, passed_profiles_filename, \
seed_filename_full, \
rna_bin_filename, exp_mask_filename = get_current_in_out_filenames(args, env_variables_dict, mapping_dict)
# read motifs, their profiles and MI values
profiles_array, index_array, values_array = IO.unpack_profiles_and_mask(
profiles_filename_full, exp_mask_filename, do_print=True)
w_motifs_list = IO.read_motif_file(seed_filename_full)
MI_values_array, nbins = IO.read_MI_values(MI_values_filename_full)
# find the threshold
discr_exp_profile = MI.discretize_exp_profile(index_array, values_array,
nbins)
last_positive_seed = determine_mi_threshold(MI_values_array,
discr_exp_profile,
nbins,
profiles_array,
index_array,
args,
do_print=True)
write_seeds_passed(last_positive_seed, MI_values_array, w_motifs_list,
passed_seed_filename_full)
write_profiles_passed(last_positive_seed, MI_values_array, profiles_array,
passed_profiles_filename)
if args.print_qstat == 'y':
sge.print_qstat_proc(env_variables_dict, args.path_to_qstat)
def main():
args = handler()
# read occurence profiles and expression profile
profiles_array, index_array, values_array = IO.unpack_profiles_and_mask(
args, do_print=False)
# read precalculated MI values
MI_values_array, nbins = IO.read_MI_values(args.MI_values_file)
# find the threshold
discr_exp_profile = MI.discretize_exp_profile(index_array, values_array,
nbins)
determine_mi_threshold(MI_values_array,
discr_exp_profile,
profiles_array,
index_array,
args,
do_print=True)
