Skip to content

Implement element filtering in the Ace datasets #206

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

Closed
wants to merge 3 commits into from
Closed

Implement element filtering in the Ace datasets #206

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
223037f
Implement element filtering in the Ace datasets
Jul 19, 2023
0f171cc
Merge branch 'main' into ds_elements
Sep 29, 2023
6f5478b
Store seletected atomic_numbers as a set
Sep 29, 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
10 changes: 9 additions & 1 deletion torchmdnet/datasets/ace.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,12 +15,14 @@ def __init__(
pre_transform=None,
pre_filter=None,
paths=None,
atomic_numbers=None,
max_gradient=None,
subsample_molecules=1,
):
assert isinstance(paths, (str, list))

arg_hash = f"{paths}{max_gradient}{subsample_molecules}"
self.atomic_numbers = set([] if atomic_numbers is None else atomic_numbers)
arg_hash = f"{paths}{self.atomic_numbers}{max_gradient}{subsample_molecules}"
arg_hash = hashlib.md5(arg_hash.encode()).hexdigest()
self.name = f"{self.__class__.__name__}-{arg_hash}"
self.paths = paths
Expand Down Expand Up @@ -180,6 +182,11 @@ def sample_iter(self, mol_ids=False):
fq = pt.tensor(mol["formal_charges"], dtype=pt.long)
q = fq.sum()

# Keep molecules with specific elements
if self.atomic_numbers:
if not set(z.numpy()).issubset(self.atomic_numbers):
continue

for i_conf, (pos, y, neg_dy, pq, dp) in enumerate(load_confs(mol, n_atoms=len(z))):

# Skip samples with large forces
Expand Down Expand Up @@ -220,6 +227,7 @@ def processed_file_names(self):
def process(self):

print("Arguments")
print(f" atomic_numbers: {self.atomic_numbers}")
print(f" max_gradient: {self.max_gradient} eV/A")
print(f" subsample_molecules: {self.subsample_molecules}\n")

Expand Down