def run(input_file, folder, cutoff, out_folder):
manager = mp.Manager()
output = manager.Queue()
all_mic_scores = []
lines = util.read_file(input_file)
processes = []
for line in lines:
print("start processing ", line[0])
file = folder+os.sep+line[0]
p = mp.Process(target=run_01, args=(file, cutoff, output, out_folder))
processes.append(p)
for p in processes:
p.start()
for p in processes:
p.join()
print('after join')
results = [output.get() for p in processes]
print('no. of results ', len(results))
for list_of_mic_scores in results:
if len(list_of_mic_scores) > 0:
for mic_score in list_of_mic_scores:
all_mic_scores.append(mic_score)
print('no. of mic_scores ', len(all_mic_scores))
def run(input_file, folder, cutoff, out_folder):
manager = mp.Manager()
output = manager.Queue()
all_mic_scores = []
lines = util.read_file(input_file)
processes = []
for line in lines:
print("start processing ", line[0])
file = folder + os.sep + line[0]
p = mp.Process(target=run_01, args=(file, cutoff, output, out_folder))
processes.append(p)
for p in processes:
p.start()
for p in processes:
p.join()
print('after join')
results = [output.get() for p in processes]
print('no. of results ', len(results))
for list_of_mic_scores in results:
if len(list_of_mic_scores) > 0:
for mic_score in list_of_mic_scores:
all_mic_scores.append(mic_score)
print('no. of mic_scores ', len(all_mic_scores))
def run2(input_file, folder, cutoff, target):
manager = mp.Manager()
output = manager.Queue()
all_mic_scores = []
lines = util.read_file(input_file)
out_filename = folder + '_' + cutoff.replace(".", "") + '_' + target
processes = []
for line in lines:
print("start processing ", line[0], line[1])
file1 = folder + os.sep + line[0]
file2 = folder + os.sep + line[1]
if target == '0123':
p = mp.Process(target=run_0123,
args=(file1, file2, cutoff, output))
elif target == '01':
p = mp.Process(target=run_01, args=(file1, file2, cutoff, output))
elif target == 'B01a':
p = mp.Process(target=run_B01a,
args=(file1, file2, cutoff, output))
elif target == 'B01b':
p = mp.Process(target=run_B01b,
args=(file1, file2, cutoff, output))
processes.append(p)
for p in processes:
p.start()
for p in processes:
p.join()
print('after join')
def run2(input_file, folder, cutoff, target):
manager = mp.Manager()
output = manager.Queue()
all_mic_scores = []
lines = util.read_file(input_file)
out_filename = folder + '_' + cutoff.replace(".", "") + '_' + target
processes = []
for line in lines:
print("start processing ", line[0], line[1])
file1 = folder+os.sep+line[0]
file2 = folder+os.sep+line[1]
if target == '0123':
p = mp.Process(target=run_0123, args=(file1, file2, cutoff, output))
elif target == '01':
p = mp.Process(target=run_01, args=(file1, file2, cutoff, output))
elif target == 'B01a':
p = mp.Process(target=run_B01a, args=(file1, file2, cutoff, output))
elif target == 'B01b':
p = mp.Process(target=run_B01b, args=(file1, file2, cutoff, output))
processes.append(p)
for p in processes:
p.start()
for p in processes:
p.join()
print('after join')
def run_cooccurence_all_datasets():
#input_file = 'location of cooccurence_input.txt'
input_file = sys.argv[1]
lines = util.read_file(input_file)
for line in lines:
fasta_folder = line[0]
graphml_file = line[1]
dataset = line[2]
plot_cooccurences(graphml_file=graphml_file, fasta_folder=fasta_folder, dataset=dataset)
print('************************')
def create_unique_sequences(fasta_file, unique_strains_file):
sequences = AlignIO.read(fasta_file, 'fasta')
strains = list(util.read_file(unique_strains_file))[0]
new_fasta_sequences = []
for sequence in sequences:
strain_name = util.get_strain_name(sequence)
if strain_name in strains:
new_fasta_sequences.append(sequence)
strains.remove(strain_name)
return new_fasta_sequences
def create_unique_sequences(fasta_file, unique_strains_file):
sequences = AlignIO.read(fasta_file, 'fasta')
strains = list(util.read_file(unique_strains_file))[0]
new_fasta_sequences = []
for sequence in sequences:
strain_name = util.get_strain_name(sequence)
if strain_name in strains:
new_fasta_sequences.append(sequence)
strains.remove(strain_name)
return new_fasta_sequences
def run_cooccurence_all_datasets():
#input_file = 'location of cooccurence_input.txt'
input_file = sys.argv[1]
lines = util.read_file(input_file)
for line in lines:
fasta_folder = line[0]
graphml_file = line[1]
dataset = line[2]
plot_cooccurences(graphml_file=graphml_file,
fasta_folder=fasta_folder,
dataset=dataset)
print('************************')
def run_in_out_acc_comparision_all_datasets():
acc_in = []
acc_out = []
input_file = 'C:\\Users\\uday\\pycharm_projects\\network_analysis\\data\\acc_input.txt'
lines = util.read_file(input_file)
for line in lines:
folder = line[0]
graphml_file = line[1]
dataset = line[2]
acc_in_dict, acc_out_dict = run_in_out_acc_comparision(dataset=dataset, graphml_file=graphml_file, folder=folder)
acc_in.append(acc_in_dict)
acc_out.append(acc_out_dict)
util.write_avg_accs_to_csv(acc_in, filename='average_in_acc.csv')
util.write_avg_accs_to_csv(acc_out, filename='average_out_acc.csv')
def run_in_out_acc_comparision_all_datasets():
acc_in = []
acc_out = []
input_file = 'C:\\Users\\uday\\pycharm_projects\\network_analysis\\data\\acc_input.txt'
lines = util.read_file(input_file)
for line in lines:
folder = line[0]
graphml_file = line[1]
dataset = line[2]
acc_in_dict, acc_out_dict = run_in_out_acc_comparision(
dataset=dataset, graphml_file=graphml_file, folder=folder)
acc_in.append(acc_in_dict)
acc_out.append(acc_out_dict)
util.write_avg_accs_to_csv(acc_in, filename='average_in_acc.csv')
util.write_avg_accs_to_csv(acc_out, filename='average_out_acc.csv')
def run_in_out_entropy_comparision_all_datasets():
avg_entropies = []
avg_in_entropies = []
avg_out_entropies = []
input_file = 'C:\\Users\\uday\\pycharm_projects\\network_analysis\\data\\entropy_input.txt'
lines = util.read_file(input_file)
for line in lines:
folder = line[0]
graphml_file = line[1]
dataset = line[2]
avg_entropy_dict, avg_in_nx_entropy_dict, avg_out_nx_entropy_dict = run_in_out_entropy_comparision(dataset=dataset, graphml_file=graphml_file, folder=folder)
avg_entropies.append(avg_entropy_dict)
avg_in_entropies.append(avg_in_nx_entropy_dict)
avg_out_entropies.append(avg_out_nx_entropy_dict)
util.write_avg_entropies_to_csv(avg_entropies, filename='average_entropies.csv')
util.write_avg_entropies_to_csv(avg_in_entropies, filename='average_in_entropies.csv')
util.write_avg_entropies_to_csv(avg_out_entropies, filename='average_out_entropies.csv')
def run(input_file, folder, cutoff, target):
manager = mp.Manager()
output = manager.Queue()
all_mic_scores = []
lines = util.read_file(input_file)
out_filename = folder + '_' + cutoff.replace(".", "") + '_' + target
processes = []
for line in lines:
print("start processing ", line[0], line[1])
file1 = folder + os.sep + line[0]
file2 = folder + os.sep + line[1]
if target == '0123':
p = mp.Process(target=run_0123,
args=(file1, file2, cutoff, output))
elif target == '01':
p = mp.Process(target=run_01, args=(file1, file2, cutoff, output))
elif target == 'B01a':
p = mp.Process(target=run_B01a,
args=(file1, file2, cutoff, output))
elif target == 'B01b':
p = mp.Process(target=run_B01b,
args=(file1, file2, cutoff, output))
processes.append(p)
for p in processes:
p.start()
for p in processes:
p.join()
print('after join')
results = [output.get() for p in processes]
print('no. of results ', len(results))
for list_of_mic_scores in results:
if len(list_of_mic_scores) > 0:
for mic_score in list_of_mic_scores:
all_mic_scores.append(mic_score)
print('no. of mic_scores ', len(all_mic_scores))
mic_df = util.create_df_from_dict(all_mic_scores)
util.create_graph(mic_df, out_filename)
def run_pairwise_counts_manual_edges():
folder = sys.argv[2]
significant_residues_file = 'pairs.txt'
lines = util.read_file(significant_residues_file)
logo_folder = 'C:\\uday\\gmu\\correlations\\results\\10proteins\\logos'
for line in lines:
print(line)
protein1 = line[0]
residue1 = int(line[1])-1
protein2 = line[2]
residue2 = int(line[3])-1
file1 = folder + os.sep + protein1 + '.afasta'
file2 = folder + os.sep + protein2 + '.afasta'
residue_comparision_count = perform_residue_analysis(file1, file2, residue1, residue2)
residue1_str = protein1+str(residue1+1)
residue2_str = protein2+str(residue2+1)
filename = residue1_str + '_' + residue2_str + '.bat'
pu.create_image_magick_script(residue_comparision_count, residue1_str, residue2_str, logo_folder, filename)
def run(input_file, folder, cutoff, target):
manager = mp.Manager()
output = manager.Queue()
all_mic_scores = []
lines = util.read_file(input_file)
out_filename = folder + '_' + cutoff.replace(".", "") + '_' + target
processes = []
for line in lines:
print("start processing ", line[0], line[1])
file1 = folder+os.sep+line[0]
file2 = folder+os.sep+line[1]
if target == '0123':
p = mp.Process(target=run_0123, args=(file1, file2, cutoff, output))
elif target == '01':
p = mp.Process(target=run_01, args=(file1, file2, cutoff, output))
elif target == 'B01a':
p = mp.Process(target=run_B01a, args=(file1, file2, cutoff, output))
elif target == 'B01b':
p = mp.Process(target=run_B01b, args=(file1, file2, cutoff, output))
processes.append(p)
for p in processes:
p.start()
for p in processes:
p.join()
print('after join')
results = [output.get() for p in processes]
print('no. of results ', len(results))
for list_of_mic_scores in results:
if len(list_of_mic_scores) > 0:
for mic_score in list_of_mic_scores:
all_mic_scores.append(mic_score)
print('no. of mic_scores ', len(all_mic_scores))
mic_df = util.create_df_from_dict(all_mic_scores)
util.create_graph(mic_df, out_filename)
def run_pairwise_counts_manual_edges():
folder = sys.argv[2]
significant_residues_file = 'pairs.txt'
lines = util.read_file(significant_residues_file)
logo_folder = 'C:\\uday\\gmu\\correlations\\results\\10proteins\\logos'
for line in lines:
print(line)
protein1 = line[0]
residue1 = int(line[1]) - 1
protein2 = line[2]
residue2 = int(line[3]) - 1
file1 = folder + os.sep + protein1 + '.afasta'
file2 = folder + os.sep + protein2 + '.afasta'
residue_comparision_count = perform_residue_analysis(
file1, file2, residue1, residue2)
residue1_str = protein1 + str(residue1 + 1)
residue2_str = protein2 + str(residue2 + 1)
filename = residue1_str + '_' + residue2_str + '.bat'
pu.create_image_magick_script(residue_comparision_count, residue1_str,
residue2_str, logo_folder, filename)
def run_in_out_entropy_comparision_all_datasets():
avg_entropies = []
avg_in_entropies = []
avg_out_entropies = []
input_file = 'C:\\Users\\uday\\pycharm_projects\\network_analysis\\data\\entropy_input.txt'
lines = util.read_file(input_file)
for line in lines:
folder = line[0]
graphml_file = line[1]
dataset = line[2]
avg_entropy_dict, avg_in_nx_entropy_dict, avg_out_nx_entropy_dict = run_in_out_entropy_comparision(
dataset=dataset, graphml_file=graphml_file, folder=folder)
avg_entropies.append(avg_entropy_dict)
avg_in_entropies.append(avg_in_nx_entropy_dict)
avg_out_entropies.append(avg_out_nx_entropy_dict)
util.write_avg_entropies_to_csv(avg_entropies,
filename='average_entropies.csv')
util.write_avg_entropies_to_csv(avg_in_entropies,
filename='average_in_entropies.csv')
util.write_avg_entropies_to_csv(avg_out_entropies,
filename='average_out_entropies.csv')
for line in lines:
print("start processing ", line[0])
file = folder+os.sep+line[0]
p = mp.Process(target=run_01, args=(file, cutoff, output, out_folder))
processes.append(p)
for p in processes:
p.start()
for p in processes:
p.join()
print('after join')
results = [output.get() for p in processes]
print('no. of results ', len(results))
for list_of_mic_scores in results:
if len(list_of_mic_scores) > 0:
for mic_score in list_of_mic_scores:
all_mic_scores.append(mic_score)
print('no. of mic_scores ', len(all_mic_scores))
if __name__ == '__main__':
args_file = sys.argv[1]
arglines = util.read_file(args_file)
for argline in arglines:
print("start processing ", argline[0], argline[1], argline[2], argline[3])
run(argline[0], argline[1], argline[2], argline[3])
print("done processing ", argline[0], argline[1], argline[2], argline[3])
for p in processes:
p.start()
for p in processes:
p.join()
print('after join')
results = [output.get() for p in processes]
print('no. of results ', len(results))
for list_of_mic_scores in results:
if len(list_of_mic_scores) > 0:
for mic_score in list_of_mic_scores:
all_mic_scores.append(mic_score)
print('no. of mic_scores ', len(all_mic_scores))
mic_df = util.create_df_from_dict(all_mic_scores)
util.create_graph(mic_df, out_filename)
if __name__ == '__main__':
args_file = sys.argv[1]
arglines = util.read_file(args_file)
for argline in arglines:
print("start processing ", argline[0], argline[1], argline[2],
argline[3])
run(argline[0], argline[1], argline[2], argline[3])
print("done processing ", argline[0], argline[1], argline[2],
argline[3])
