reformat code using black

Author: inodb

src/cbiohub/analyze.py

@@ -99,8 +99,12 @@ def find_variant(
 
 
 def variant_frequency_per_clinical_attribute(
-    variant: Union[GenomicVariant, ProteinVariant], clinical_attribute,
-    directory=None, group_by_study_id=False, count_samples=False, sql=False
+    variant: Union[GenomicVariant, ProteinVariant],
+    clinical_attribute,
+    directory=None,
+    group_by_study_id=False,
+    count_samples=False,
+    sql=False,
 ):
     """Check how frequently a particular variant occurs per cancer type."""
     if directory is None:
@@ -136,8 +140,12 @@ def variant_frequency_per_clinical_attribute(
     """
     group_by_clause = f"clinical.{clinical_attribute}, TotalPerAttribute.total"
     total_group_by = f"clinical.{clinical_attribute}"
-    total_join = f"clinical.{clinical_attribute} = TotalPerAttribute.{clinical_attribute}"
-    total_select = f"clinical.{clinical_attribute}, COUNT(DISTINCT {count_attribute}) AS total"
+    total_join = (
+        f"clinical.{clinical_attribute} = TotalPerAttribute.{clinical_attribute}"
+    )
+    total_select = (
+        f"clinical.{clinical_attribute}, COUNT(DISTINCT {count_attribute}) AS total"
+    )
 
     if group_by_study_id:
         total_select = f"clinical.STUDY_ID, {total_select}"

src/cbiohub/cli.py

@@ -46,6 +46,7 @@ def cli():
 
 cli.add_command(data)
 
+
 @cli.command()
 def config():
     """Display the current configuration settings."""
@@ -86,11 +87,18 @@ def find(arg1, arg2, arg3, arg4, arg5, processed_dir, sql):
     if arg1 and arg2 and arg3 and arg4:
         # assuming chrom/pos/start/end
         exists, unique_ids = find_variant(
-            chrom=arg1, start=arg2, end=arg3, ref=arg4, alt=arg5, directory=processed_dir
+            chrom=arg1,
+            start=arg2,
+            end=arg3,
+            ref=arg4,
+            alt=arg5,
+            directory=processed_dir,
         )
     elif arg1 and arg2:
         # assuming gene/protein_change
-        exists, unique_ids = find_variant(hugo_symbol=arg1, protein_change=arg2, directory=processed_dir)
+        exists, unique_ids = find_variant(
+            hugo_symbol=arg1, protein_change=arg2, directory=processed_dir
+        )
     else:
         click.echo(click.style("❌ Invalid arguments.", fg="red"))
         return
@@ -108,6 +116,7 @@ def find(arg1, arg2, arg3, arg4, arg5, processed_dir, sql):
     else:
         click.echo(click.style("❌ Variant not found.", fg="red"))
 
+
 def detect_variant_type(args):
     """
     Detects the variant type based on the number and structure of arguments.
@@ -121,10 +130,13 @@ def detect_variant_type(args):
     elif len(args) == 2:
         return ProteinVariant(*args)
     else:
-        raise click.UsageError("Could not detect variant type. Ensure arguments match either chrom/start/end/ref/alt or gene/protein_change format.")
+        raise click.UsageError(
+            "Could not detect variant type. Ensure arguments match either chrom/start/end/ref/alt or gene/protein_change format."
+        )
+
 
 @cli.command(help="Check how frequently a particular variant occurs per cancer type.")
-@click.argument('args', nargs=-1, required=True)
+@click.argument("args", nargs=-1, required=True)
 @click.option(
     "--clinical-attribute",
     default="CANCER_TYPE",
@@ -143,14 +155,20 @@ def detect_variant_type(args):
     help="Count samples instead of patients",
 )
 @common_options
-def variant_frequency(args, clinical_attribute, processed_dir, sql, group_by_study_id, count_samples):
+def variant_frequency(
+    args, clinical_attribute, processed_dir, sql, group_by_study_id, count_samples
+):
     """Check how frequently a particular variant occurs per cancer type (or
     other clinical sample attributes)."""
     variant = detect_variant_type(args)
 
     result = variant_frequency_per_clinical_attribute(
-        variant, clinical_attribute, directory=processed_dir, sql=sql, group_by_study_id=group_by_study_id,
-        count_samples=count_samples
+        variant,
+        clinical_attribute,
+        directory=processed_dir,
+        sql=sql,
+        group_by_study_id=group_by_study_id,
+        count_samples=count_samples,
     )
     if sql:
         return print(result)

src/cbiohub/data_commands.py

@@ -167,7 +167,9 @@ def combine(output_dir):
                 )
 
                 for mutation_file in MUTATION_DATA_FILES:
-                    mutation_file = study.processed_path / mutation_file.replace("txt","parquet")
+                    mutation_file = study.processed_path / mutation_file.replace(
+                        "txt", "parquet"
+                    )
                     if mutation_file.exists():
                         table = pq.read_table(mutation_file)
                         # Select only specific columns and adjust their types

src/cbiohub/study.py

@@ -5,7 +5,12 @@
     settings,
 )  # Assuming settings is a module with PROCESSED_PATH defined
 
-MUTATION_DATA_FILES = ["data_mutations.txt", "data_mutations_extended.txt", "data_nonsignedout_mutations.txt"]
+MUTATION_DATA_FILES = [
+    "data_mutations.txt",
+    "data_mutations_extended.txt",
+    "data_nonsignedout_mutations.txt",
+]
+
 
 class Study:
     def __init__(self, study_path: Path):
@@ -16,7 +21,9 @@ def __init__(self, study_path: Path):
         self.patient_data_file = "data_clinical_patient.txt"
         # mutation data can have multiple names
         self.mutation_data_files = [
-            mut_file for mut_file in MUTATION_DATA_FILES if (self.study_path / mut_file).exists()
+            mut_file
+            for mut_file in MUTATION_DATA_FILES
+            if (self.study_path / mut_file).exists()
         ]
         # all mutation data files are combined into this file
         self.mutation_parquet_file = "data_mutations.parquet"
@@ -180,7 +187,10 @@ def is_processed(self):
         source_files = [
             self.study_path / self.sample_data_file,
             self.study_path / self.patient_data_file,
-            *[self.study_path / mutation_data_file for mutation_data_file in self.mutation_data_files],
+            *[
+                self.study_path / mutation_data_file
+                for mutation_data_file in self.mutation_data_files
+            ],
             self.study_path / "meta_study.txt",
         ]
 

src/cbiohub/variant.py

@@ -10,4 +10,6 @@ def __init__(self, chrom, start, end, ref, alt):
 class ProteinVariant:
     def __init__(self, gene, protein_change):
         self.gene = gene
-        self.protein_change = protein_change if protein_change.startswith("p.") else f"p.{protein_change}"
+        self.protein_change = (
+            protein_change if protein_change.startswith("p.") else f"p.{protein_change}"
+        )