Skip to content

My modifications #7

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
anikonn wants to merge 1 commit into
base: main
Choose a base branch
from
Open

My modifications #7

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
1 change: 1 addition & 0 deletions .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,7 @@
__pycache__
**/*.ckpt
logs/*
results/*
checkpoints/*
data/*/*/*.pt
data/*/*/*.pkl
Expand Down
4 changes: 2 additions & 2 deletions configs/msgym.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,8 +20,8 @@ enable_progress_bar: True
# Data
dataset: msgym
batch_size: 256
num_workers: 47
shuffle: True
num_workers: 16
shuffle: False
extra_nodes: True
swap: False

Expand Down
34 changes: 12 additions & 22 deletions evaluation_generation.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -79,22 +79,12 @@ def calculate_mces(mces, pairs):
mces_thld = 100
mces_cache = {}
myopic_mces = MyopicMCES(
threshold=20,
solver='HiGHS',
solver_options={
'msg': 0,
'log_to_console': False,
'output_flag': False,
'time_limit': 10, # Optional: add timeout
'log_file': os.devnull, # Redirect logs to nowhere
'highs_debug_level': 0,
'highs_verbosity': 'off'
}
threshold=20
)
for k in ks:
result_metric = {"accuracy": 0, "similarity": 0, "MCES": 0}
count = 0
sub_dfs = split_dataframe(df1, chunk_size=50)
sub_dfs = split_dataframe(df1, chunk_size=100)
for df in tqdm(sub_dfs):
smile = list(df["true"])[0]
pred_smiles = sorted(list(df["pred"]), key=lambda x: list(df["pred"]).count(x), reverse=True)
Expand Down Expand Up @@ -124,19 +114,19 @@ def calculate_mces(mces, pairs):
# if Chem.MolToSmiles(mol) != Chem.MolToSmiles(GetScaffoldForMol(Chem.MolFromSmiles(scaf_smi))):
# print('scaffold match', smile)
result_metric["accuracy"] += int(in_top_k)
# dists = []
dists = []
# pairs = [(smile, pred) for pred, pred_mol in zip(pred_smiles, pred_mols) if pred_mol is not None]
# results = calculate_mces(myopic_mces, pairs)

# dists = [results.get((smile, pred), mces_thld) for pred in pred_smiles]
# for pred, pred_mol in zip(pred_smiles, pred_mols):
# if pred_mol is None:
# dists.append(mces_thld)
# else:
# if (smile, pred) not in mces_cache:
# mce_val = myopic_mces(smile, pred)
# mces_cache[(smile, pred)] = mce_val
# dists.append(mces_cache[(smile, pred)])
for pred, pred_mol in zip(pred_smiles, pred_mols):
if pred_mol is None:
dists.append(mces_thld)
else:
if (smile, pred) not in mces_cache:
mce_val = myopic_mces(smile, pred)
mces_cache[(smile, pred)] = mce_val
dists.append(mces_cache[(smile, pred)])
mol_fp = GetMorganFingerprintAsBitVect(mol, radius=2, nBits=2048)
pred_fps = [
GetMorganFingerprintAsBitVect(pred, radius=2, nBits=2048) if pred is not None else None for pred in pred_mols
Expand All @@ -145,7 +135,7 @@ def calculate_mces(mces, pairs):
TanimotoSimilarity(mol_fp, pred) if pred is not None else 0 for pred in pred_fps
]
result_metric["similarity"] += max(sims)
# result_metric["MCES"] += min(min(dists), mces_thld)
result_metric["MCES"] += min(min(dists), mces_thld)
for key in result_metric:
result_metric[key] = result_metric[key] / len(sub_dfs)
print(dataset, k, result_metric)
Expand Down
Loading