Skip to content
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.

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

[cleanup] change logging levels to debug to declutter output #391

Merged
merged 4 commits into from
May 1, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
1 change: 1 addition & 0 deletions CHANGELOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,7 @@
* Fix bug where the `deprotonate` argument is not wired up to `graphein.protein.graphs.construct_graphs`. [#375](https://github.com/a-r-j/graphein/pull/375)

#### Misc
* bumped logging level down from `INFO` to `DEBUG` at several places to reduced output length [#391](https://github.com/a-r-j/graphein/pull/391)
* exposed `fill_value` and `bfactor` option to `protein_to_pyg` function. [#385](https://github.com/a-r-j/graphein/pull/385) and [#388](https://github.com/a-r-j/graphein/pull/388)
* Updated Foldcomp datasets with improved setup function and updated database choices such as ESMAtlas. [#382](https://github.com/a-r-j/graphein/pull/382)
* Resolve issue with notebook version and `pluggy` in Dockerfile. [#372](https://github.com/a-r-j/graphein/pull/372)
Expand Down
18 changes: 9 additions & 9 deletions graphein/ml/datasets/pdb_data.py
Original file line number Diff line number Diff line change
Expand Up @@ -341,7 +341,7 @@ def _download_pdb_sequences(self):
):
log.info("Downloading PDB sequences...")
wget.download(self.pdb_sequences_url, out=str(self.root_dir))
log.info("Downloaded sequences")
log.debug("Downloaded sequences")

# Unzip all collected sequences
if not os.path.exists(self.root_dir / self.pdb_seqres_filename):
Expand All @@ -353,7 +353,7 @@ def _download_pdb_sequences(self):
self.root_dir / self.pdb_seqres_filename, "wb"
) as f_out:
shutil.copyfileobj(f_in, f_out)
log.info("Unzipped sequences")
log.debug("Unzipped sequences")

def _download_ligand_map(self):
"""Download ligand map from
Expand All @@ -362,7 +362,7 @@ def _download_ligand_map(self):
if not os.path.exists(self.root_dir / self.ligand_map_filename):
log.info("Downloading ligand map...")
wget.download(self.ligand_map_url, out=str(self.root_dir))
log.info("Downloaded ligand map")
log.debug("Downloaded ligand map")

def _download_source_map(self):
"""Download source map from
Expand All @@ -371,7 +371,7 @@ def _download_source_map(self):
if not os.path.exists(self.root_dir / self.source_map_filename):
log.info("Downloading source map...")
wget.download(self.source_map_url, out=str(self.root_dir))
log.info("Downloaded source map")
log.debug("Downloaded source map")

def _download_resolution(self):
"""Download source map from
Expand All @@ -380,7 +380,7 @@ def _download_resolution(self):
if not os.path.exists(self.root_dir / self.resolution_filename):
log.info("Downloading resolution map...")
wget.download(self.resolution_url, out=str(self.root_dir))
log.info("Downloaded resolution map")
log.debug("Downloaded resolution map")

def _download_entry_metadata(self):
"""Download PDB entry metadata from
Expand All @@ -391,7 +391,7 @@ def _download_entry_metadata(self):
):
log.info("Downloading entry metadata...")
wget.download(self.pdb_deposition_date_url, out=str(self.root_dir))
log.info("Downloaded entry metadata")
log.debug("Downloaded entry metadata")

def _download_exp_type(self):
"""Download PDB experiment metadata from
Expand All @@ -400,7 +400,7 @@ def _download_exp_type(self):
if not os.path.exists(self.root_dir / self.pdb_entry_type_filename):
log.info("Downloading experiment type map...")
wget.download(self.pdb_entry_type_url, out=str(self.root_dir))
log.info("Downloaded experiment type map")
log.debug("Downloaded experiment type map")

def _download_pdb_availability(self):
"""Download PDB availability metadata from
Expand All @@ -409,7 +409,7 @@ def _download_pdb_availability(self):
if not os.path.exists(self.root_dir / self.pdb_availability_filename):
log.info("Downloading PDB availability map...")
wget.download(self.pdb_availability_url, out=str(self.root_dir))
log.info("Downloaded PDB availability map")
log.debug("Downloaded PDB availability map")

def _parse_ligand_map(self) -> Dict[str, List[str]]:
"""Parse the ligand maps for all PDB records.
Expand Down Expand Up @@ -1300,7 +1300,7 @@ def split_clusters(
self.split_ratios,
self.assign_leftover_rows_to_split_n,
)
log.info("Done splitting clusters")
log.debug("Done splitting clusters")

# Update splits
for split in self.splits:
Expand Down
4 changes: 2 additions & 2 deletions graphein/protein/features/sequence/embeddings.py
Original file line number Diff line number Diff line change
Expand Up @@ -31,7 +31,7 @@
pip_install=True,
conda_channel="pytorch",
)
log.warning(message)
log.debug(message)

try:
import biovec
Expand All @@ -42,7 +42,7 @@
pip_install=True,
extras=True,
)
log.warning(message)
log.debug(message)


@lru_cache()
Expand Down
2 changes: 1 addition & 1 deletion graphein/protein/meshes.py
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@
conda_channel="pytorch3d",
pip_install=True,
)
log.warning(message)
log.debug(message)


def check_for_pymol_installation():
Expand Down
4 changes: 2 additions & 2 deletions graphein/protein/tensor/io.py
Original file line number Diff line number Diff line change
Expand Up @@ -49,7 +49,7 @@
conda_channel="pyg",
pip_install=True,
)
log.warning(message)
log.debug(message)

try:
import torch
Expand All @@ -60,7 +60,7 @@
conda_channel="pytorch",
pip_install=True,
)
log.warning(message)
log.debug(message)


def get_protein_length(df: pd.DataFrame, insertions: bool = True) -> int:
Expand Down
2 changes: 1 addition & 1 deletion graphein/protein/tensor/representation.py
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,7 @@
conda_channel="pytorch",
pip_install=True,
)
log.warning(message)
log.debug(message)


def get_full_atom_coords(
Expand Down
2 changes: 1 addition & 1 deletion graphein/protein/tensor/sequence.py
Original file line number Diff line number Diff line change
Expand Up @@ -31,7 +31,7 @@
conda_channel="pytorch",
pip_install=True,
)
log.warning(message)
log.debug(message)


def get_sequence(
Expand Down
12 changes: 6 additions & 6 deletions graphein/protein/utils.py
Original file line number Diff line number Diff line change
Expand Up @@ -205,7 +205,7 @@ def download_pdb(

# Check if PDB already exists
if os.path.exists(out_dir / f"{pdb_code}{extension}") and not overwrite:
log.info(
log.debug(
f"{pdb_code} already exists: {out_dir / f'{pdb_code}{extension}'}"
)
return out_dir / f"{pdb_code}{extension}"
Expand All @@ -224,7 +224,7 @@ def download_pdb(
assert os.path.exists(
out_dir / f"{pdb_code}{extension}"
), f"{pdb_code} download failed. Not found in {out_dir}"
log.info(f"{pdb_code} downloaded to {out_dir}")
log.debug(f"{pdb_code} downloaded to {out_dir}")
return out_dir / f"{pdb_code}{extension}"


Expand Down Expand Up @@ -346,7 +346,7 @@ def download_alphafold_structure(
(Path(out_dir) / f"{uniprot_id}{extension}").resolve()
)

log.info(f"Downloaded AlphaFold PDB file for: {uniprot_id}")
log.debug(f"Downloaded AlphaFold PDB file for: {uniprot_id}")
if aligned_score:
score_query = (
BASE_URL
Expand Down Expand Up @@ -412,7 +412,7 @@ def save_graph_to_pdb(
if hetatms:
ppd.df["HETATM"] = hetatm_df
ppd.to_pdb(path=path, records=None, gz=gz, append_newline=True)
log.info(f"Successfully saved graph to {path}")
log.debug(f"Successfully saved graph to {path}")


def save_pdb_df_to_pdb(
Expand All @@ -439,7 +439,7 @@ def save_pdb_df_to_pdb(
if hetatms:
ppd.df["HETATM"] = hetatm_df
ppd.to_pdb(path=path, records=None, gz=gz, append_newline=True)
log.info(f"Successfully saved PDB dataframe to {path}")
log.debug(f"Successfully saved PDB dataframe to {path}")


def save_rgroup_df_to_pdb(
Expand Down Expand Up @@ -475,7 +475,7 @@ def save_rgroup_df_to_pdb(
if hetatms:
ppd.df["HETATM"] = hetatm_df
ppd.to_pdb(path=path, records=None, gz=gz, append_newline=True)
log.info(f"Successfully saved rgroup data to {path}")
log.debug(f"Successfully saved rgroup data to {path}")


def esmfold(
Expand Down
3 changes: 2 additions & 1 deletion graphein/protein/visualisation.py
Original file line number Diff line number Diff line change
Expand Up @@ -33,7 +33,7 @@
package="pytorch3d",
conda_channel="pytorch3d",
)
log.warning(message)
log.debug(message)

try:
from mpl_chord_diagram import chord_diagram
Expand All @@ -44,6 +44,7 @@
pip_install=True,
extras=True,
)
log.debug(message)


def plot_pointcloud(mesh: Meshes, title: str = "") -> Axes3D:
Expand Down