Skip to content

save the features.pkl file of the monomer #184

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 3 commits into
base: main
Choose a base branch
from
Open

save the features.pkl file of the monomer #184

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
4fc8977
save prediction output pickle file of monomer
Feb 23, 2023
e897d65
Merge branch 'hpcaitech:main' into main
double-vin Dec 2, 2023
5f08e3f
save features.pkl of the monomer
double-vin Dec 2, 2023
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
37 changes: 23 additions & 14 deletions inference.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -341,24 +341,13 @@ def inference_monomer_model(args):
print("running in monomer mode...")
config = model_config(args.model_name)

template_featurizer = templates.TemplateHitFeaturizer(
mmcif_dir=args.template_mmcif_dir,
max_template_date=args.max_template_date,
max_hits=config.data.predict.max_templates,
kalign_binary_path=args.kalign_binary_path,
release_dates_path=args.release_dates_path,
obsolete_pdbs_path=args.obsolete_pdbs_path
)

use_small_bfd = args.preset == 'reduced_dbs' # (args.bfd_database_path is None)
if use_small_bfd:
assert args.bfd_database_path is not None
else:
assert args.bfd_database_path is not None
assert args.uniref30_database_path is not None

data_processor = data_pipeline.DataPipeline(template_featurizer=template_featurizer,)

output_dir_base = args.output_dir

random_seed = args.data_random_seed
Expand Down Expand Up @@ -423,11 +412,31 @@ def inference_monomer_model(args):
use_small_bfd=use_small_bfd,
no_cpus=args.cpus,
)
t = time.perf_counter()
alignment_runner.run(fasta_path, local_alignment_dir)
print(f"Alignment data time: {time.perf_counter() - t}")

feature_dict = data_processor.process_fasta(fasta_path=fasta_path,
alignment_dir=local_alignment_dir)

features_output_path = os.path.join(local_alignment_dir, 'features.pkl')
if os.path.exists(features_output_path):
feature_dict = pickle.load(open(features_output_path, 'rb'))

else:
template_featurizer = templates.TemplateHitFeaturizer(
mmcif_dir=args.template_mmcif_dir,
max_template_date=args.max_template_date,
max_hits=config.data.predict.max_templates,
kalign_binary_path=args.kalign_binary_path,
release_dates_path=args.release_dates_path,
obsolete_pdbs_path=args.obsolete_pdbs_path
)

data_processor = data_pipeline.DataPipeline(template_featurizer=template_featurizer,)

feature_dict = data_processor.process_fasta(fasta_path=fasta_path,
alignment_dir=local_alignment_dir)
with open(features_output_path, 'wb') as f:
pickle.dump(feature_dict, f, protocol=4)

# Remove temporary FASTA file
os.remove(fasta_path)

Expand Down