Skip to content

fix: resolve file handling issues with long RNA sequences #3

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

fix: resolve file handling issues with long RNA sequences #3

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3d89fe9
Delete run.py
Listen-lei Oct 1, 2025
dc48398
fix: resolve file handling issues with long RNA sequences
Listen-lei Oct 1, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
70 changes: 59 additions & 11 deletions run.py
100755 → 100644
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,6 +47,36 @@

print('\nChecking for inputs features files in path ' + args.input_feats + '\n')

# for rna_id in list_rna_ids:

# print('\n', rna_id+':')

# if Path(args.input_feats + '/' + rna_id).is_file():
# print('RNA sequence \u2713')
# with open(args.input_feats + '/' + rna_id) as f:
# temp_1 = pd.read_csv(f, comment='#', delim_whitespace=True, header=None, skiprows=[0]).values
# seq_ref = ''.join([j.upper() for j in temp_1[0, 0]])
# else: raise ValueError('RNA sequence file does not exists in path ' + args.input_feats + '/' + rna_id + '\n')

# # if args.single_seq == 1:
# if Path(args.input_feats + '/' + rna_id + '_dp.ps').is_file(): print('base pair probability \u2713')
# else:
# print('base pair probability \u2717')
# print('base pair probability file does not exists in path ' + args.input_feats + '/' + rna_id + '_dp.ps')
# print('Generating RNAfold base-pair probability')
# process1 = subprocess.Popen(["RNAfold", "-p", "-i", args.input_feats + '/' + rna_id], stdout=subprocess.PIPE); time.sleep(2)
# process2 = subprocess.Popen(["mv", rna_id + "_dp.ps", args.input_feats + '/'], stdout=subprocess.PIPE)
# process2 = subprocess.Popen(["mv", rna_id + "_ss.ps", args.input_feats + '/'], stdout=subprocess.PIPE)
# if Path(args.input_feats + '/' + rna_id + '_dp.ps').is_file(): print('base pair probability \u2713')

# if args.single_seq != 1:
# if Path(args.input_feats + '/' + rna_id + '.pssm').is_file(): print('PSSM features \u2713')
# else: raise ValueError('PSSM file does not exists in path ' + args.input_feats + '/' + rna_id + '.pssm\n')

# if Path(args.input_feats + '/' + rna_id + '.dca').is_file(): print('DCA features \u2713')
# else: raise ValueError('DCA file does not exists in path ' + args.input_feats + '/' + rna_id + '.dca\n')
# time.sleep(0.1)
# print()
for rna_id in list_rna_ids:

print('\n', rna_id+':')
Expand All @@ -59,26 +89,44 @@
else: raise ValueError('RNA sequence file does not exists in path ' + args.input_feats + '/' + rna_id + '\n')

# if args.single_seq == 1:
if Path(args.input_feats + '/' + rna_id + '_dp.ps').is_file(): print('base pair probability \u2713')
if Path(args.input_feats + '/' + rna_id + '_dp.ps').is_file():
print('base pair probability \u2713')
else:
print('base pair probability \u2717')
print('base pair probability file does not exists in path ' + args.input_feats + '/' + rna_id + '_dp.ps')
print('Generating RNAfold base-pair probability')
process1 = subprocess.Popen(["RNAfold", "-p", "-i", args.input_feats + '/' + rna_id], stdout=subprocess.PIPE); time.sleep(0.5)
process2 = subprocess.Popen(["mv", rna_id + "_dp.ps", args.input_feats + '/'], stdout=subprocess.PIPE)
process2 = subprocess.Popen(["mv", rna_id + "_ss.ps", args.input_feats + '/'], stdout=subprocess.PIPE)
if Path(args.input_feats + '/' + rna_id + '_dp.ps').is_file(): print('base pair probability \u2713')
try:

subprocess.run(["RNAfold", "-p", "-i", args.input_feats + '/' + rna_id],
check=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)


subprocess.run(["mv", rna_id + "_dp.ps", args.input_feats + '/'], check=True)
subprocess.run(["mv", rna_id + "_ss.ps", args.input_feats + '/'], check=True)

if Path(args.input_feats + '/' + rna_id + '_dp.ps').is_file():
print('base pair probability \u2713')
else:
print('base pair probability \u2717 - file not found after generation')

except subprocess.CalledProcessError as e:
print(f'Error running RNAfold: {e}')
except Exception as e:
print(f'Unexpected error: {e}')

if args.single_seq != 1:
if Path(args.input_feats + '/' + rna_id + '.pssm').is_file(): print('PSSM features \u2713')
else: raise ValueError('PSSM file does not exists in path ' + args.input_feats + '/' + rna_id + '.pssm\n')

if Path(args.input_feats + '/' + rna_id + '.dca').is_file(): print('DCA features \u2713')
else: raise ValueError('DCA file does not exists in path ' + args.input_feats + '/' + rna_id + '.dca\n')
if Path(args.input_feats + '/' + rna_id + '.pssm').is_file():
print('PSSM features \u2713')
else:
raise ValueError('PSSM file does not exists in path ' + args.input_feats + '/' + rna_id + '.pssm\n')

if Path(args.input_feats + '/' + rna_id + '.dca').is_file():
print('DCA features \u2713')
else:
raise ValueError('DCA file does not exists in path ' + args.input_feats + '/' + rna_id + '.dca\n')
time.sleep(0.1)
print()


os.environ["CUDA_VISIBLE_DEVICES"]= str(args.gpu)
os.environ['KMP_WARNINGS'] = 'off'

Expand Down