Skip to content

Fix/column annotation #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

Merged
zhu0619 merged 2 commits into from
Aug 27, 2024
Merged

Fix/column annotation #184

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
6b866b9
content type validator and serializer
zhu0619 Aug 27, 2024
fcb3474
add pdb content type
zhu0619 Aug 27, 2024
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
16 changes: 15 additions & 1 deletion polaris/dataset/_column.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,7 @@ class Modality(enum.Enum):
IMAGE = "image"


class KnownContentType(str, enum.Enum):
class KnownContentType(enum.Enum):
"""Used to specify column's IANA content type in a dataset."""

SMILES = "chemical/x-smiles"
Expand Down Expand Up @@ -57,6 +57,13 @@ def _validate_modality(cls, v, values):
v = Modality[v.upper()]
return v

@field_validator("content_type")
def _validate_content_type(cls, v, values):
"""Tries to convert a string to the Enum"""
if isinstance(v, str):
v = KnownContentType[v.upper()]
return v

@field_validator("dtype")
def _validate_dtype(cls, v):
"""Tries to convert a string to the Enum"""
Expand All @@ -69,6 +76,13 @@ def _serialize_modality(self, v: Modality):
"""Return the modality as a string, keeping it serializable"""
return v.name

@field_serializer("content_type")
def _serialize_content_type(self, v: KnownContentType):
"""Return the content_type as a string, keeping it serializable"""
if v is not None:
v = v.name
return v

@field_serializer("dtype")
def _serialize_dtype(self, v: Optional[DTypeLike]):
"""Return the dtype as a string, keeping it serializable"""
Expand Down
8 changes: 6 additions & 2 deletions polaris/dataset/converters/_pdb.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@
import zarr
from fastpdb import struc

from polaris.dataset import ColumnAnnotation, Modality
from polaris.dataset import ColumnAnnotation, Modality, KnownContentType
from polaris.dataset._adapters import Adapter
from polaris.dataset.converters._base import Converter, FactoryProduct

Expand Down Expand Up @@ -188,7 +188,11 @@ def convert(self, path, factory: "DatasetFactory", append: bool = False) -> Fact
df[self.pdb_column] = pd.Series(pointers)

# Set the annotations
annotations = {self.pdb_column: ColumnAnnotation(is_pointer=True, modality=Modality.PROTEIN_3D)}
annotations = {
self.pdb_column: ColumnAnnotation(
is_pointer=True, modality=Modality.PROTEIN_3D, content_type=KnownContentType.PDB
)
}

# Return the dataframe and the annotations
return df, annotations, {self.pdb_column: Adapter.ARRAY_TO_PDB}