Remove to-dos, handle lint warnings and run notebooks

gnomad_toolbox/analysis/general.py

@@ -1,6 +1,6 @@
 """Set of general functions for gnomAD analysis."""
 
-from typing import Dict, List, Optional, Tuple, Union
+from typing import Dict, List, Optional
 
 import hail as hl
 from gnomad.assessment.summary_stats import freq_bin_expr
@@ -9,7 +9,7 @@
 
 
 def get_variant_count_by_freq_bin(
-    af_cutoffs: List[float] = [0.001, 0.01],
+    af_cutoffs: Optional[List[float]] = None,
     singletons: bool = False,
     doubletons: bool = False,
     pass_only: bool = True,
@@ -37,6 +37,10 @@ def get_variant_count_by_freq_bin(
         'data_type', and 'version'.
     :return: Dictionary with counts.
     """
+    # Initialize af_cutoffs if not provided
+    if af_cutoffs is None:
+        af_cutoffs = [0.001, 0.01]
+
     # Load the Hail Table if not provided
     ht = _get_dataset(dataset="variant", **kwargs)
 

gnomad_toolbox/filtering/vep.py

@@ -13,8 +13,6 @@
 from gnomad_toolbox.load_data import _get_dataset, get_compatible_dataset_versions
 
 
-# TODO: Check these csq sets, the ones in the code don't match what is listed on the
-#  browser. We should make sure they are consistent.
 def filter_by_consequence_category(
     plof: bool = False,
     missense: bool = False,
@@ -52,31 +50,7 @@ def filter_by_consequence_category(
 
         Other:
 
-            - protein_altering_variant
-            - incomplete_terminal_codon_variant
-            - stop_retained_variant
-            - coding_sequence_variant
-            - mature_miRNA_variant
-            - 5_prime_UTR_variant
-            - 3_prime_UTR_variant
-            - non_coding_transcript_exon_variant
-            - non_coding_exon_variant
-            - NMD_transcript_variant
-            - non_coding_transcript_variant
-            - nc_transcript_variant
-            - downstream_gene_variant
-            - TFBS_ablation
-            - TFBS_amplification
-            - TF_binding_site_variant
-            - regulatory_region_ablation
-            - regulatory_region_amplification
-            - feature_elongation
-            - regulatory_region_variant
-            - feature_truncation
-            - intergenic_variant
-            - intron_variant
-            - splice_region_variant
-            - upstream_gene_variant
+            - All other consequences not included in the above categories.
 
     :param plof: Whether to include pLoF variants.
     :param missense: Whether to include missense variants.
@@ -94,8 +68,14 @@ def filter_by_consequence_category(
     # Load the Hail Table if not provided
     ht = _get_dataset(dataset="variant", **kwargs)
 
-    lof_csqs = list(LOF_CSQ_SET)
-    missense_csqs = ["missense_variant", "inframe_insertion", "inframe_deletion"]
+    lof_csqs = list(LOF_CSQ_SET + ["transcript_ablation"])
+    missense_csqs = [
+        "missense_variant",
+        "inframe_insertion",
+        "inframe_deletion",
+        "stop_lost",
+        "start_lost",
+    ]
     synonymous_csqs = ["synonymous_variant"]
     other_csqs = lof_csqs + missense_csqs + synonymous_csqs
 
@@ -165,6 +145,7 @@ def filter_to_high_confidence_loftee(
         is False.
     :param canonical_only: Whether to include only canonical transcripts. Default is
         False.
+    :param version: Optional version of the dataset to use.
     :param kwargs: Additional arguments to pass to `_get_dataset`.
     :return: Table with high-confidence LOFTEE variants.
     """

gnomad_toolbox/load_data.py

@@ -115,8 +115,6 @@
 }
 
 
-# TODO: Are there other things we want to store in a session? Like a PASS variants only
-#  variable?
 class GnomADSession:
     """Class to manage the default data type and version for a gnomAD session."""
 

gnomad_toolbox/notebooks/dive_into_secondary_analyses.ipynb

@@ -1872,14 +1872,6 @@
    "source": [
     "get_observed_plofs_for_gene_constraint('drd2').show(-1)"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "3c2212f4-a7cf-45bc-930d-aa18cebff7a3",
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {

gnomad_toolbox/scripts.py

@@ -27,7 +27,7 @@ def load_config(config_file: str = CONFIG_FILE) -> dict:
     :return: The configuration dictionary.
     """
     if os.path.exists(config_file):
-        with open(config_file, "r") as f:
+        with open(config_file, "r", encoding="utf-8") as f:
             return json.load(f)
     return {}
 
@@ -40,7 +40,7 @@ def save_config(config: dict, config_file: str = CONFIG_FILE) -> None:
     :param config_file: Path to the configuration file.
     :return: None.
     """
-    with open(config_file, "w") as f:
+    with open(config_file, "w", encoding="utf-8") as f:
         json.dump(config, f, indent=4)
 
 
@@ -159,8 +159,12 @@ def copy_notebooks_cli(destination: str, overwrite: bool) -> None:
     try:
         copy_notebooks(destination, overwrite)
         logger.info("Notebooks successfully copied to %s.", destination)
-    except Exception as e:
-        logger.error("Error during notebook copy: %s", e)
+    except FileNotFoundError:
+        logger.error("The destination directory %s does not exist.", destination)
+    except PermissionError:
+        logger.error("Permission denied while accessing %s.", destination)
+    except OSError as e:
+        logger.error("OS error during notebook copy: %s", e)
 
 
 def run_jupyter_cli() -> None:
@@ -185,4 +189,7 @@ def run_jupyter_cli() -> None:
 
     # Launch Jupyter.
     command = sys.argv[1] if len(sys.argv) > 1 else "lab"
-    subprocess.run(["jupyter", command])
+    try:
+        subprocess.run(["jupyter", command], check=True)
+    except subprocess.CalledProcessError as e:
+        logger.error("Failed to launch Jupyter: %s", e)