pheval 0.6.2__py3-none-any.whl → 0.6.4__py3-none-any.whl

pheval/analyse/benchmark.py

@@ -1,6 +1,6 @@
+import sys
 import time
 from pathlib import Path
-from typing import List, Tuple
 
 import duckdb
 import polars as pl
@@ -53,8 +53,8 @@ def scan_directory(run: RunConfig, benchmark_type: BenchmarkOutputType) -> pl.La
 
 
 def process_stats(
-    runs: List[RunConfig], benchmark_type: BenchmarkOutputType
-) -> Tuple[pl.DataFrame, pl.DataFrame, pl.DataFrame]:
+    runs: list[RunConfig], benchmark_type: BenchmarkOutputType
+) -> tuple[pl.DataFrame, pl.DataFrame, pl.DataFrame]:
     """
     Processes stats outputs for specified runs to compare.
     Args:
@@ -74,9 +74,7 @@ def process_stats(
         curve_results.append(compute_curves(run.run_identifier, result_scan))
         true_positive_cases.append(
             result_scan.filter(pl.col("true_positive"))
-            .select(
-                ["result_file", *benchmark_type.columns, pl.col("rank").alias(run.run_identifier)]
-            )
+            .select(["result_file", *benchmark_type.columns, pl.col("rank").alias(run.run_identifier)])
             .sort(["result_file", *benchmark_type.columns])
         )
     return (
@@ -86,11 +84,7 @@ def process_stats(
             [true_positive_cases[0]]
             + [
                 df.select(
-                    [
-                        col
-                        for col in df.collect_schema().keys()
-                        if col not in ["result_file", *benchmark_type.columns]
-                    ]
+                    [col for col in df.collect_schema().keys() if col not in ["result_file", *benchmark_type.columns]]
                 )
                 for df in true_positive_cases[1:]
             ],
@@ -108,20 +102,14 @@ def benchmark(config: Config, benchmark_type: BenchmarkOutputType) -> None:
     """
     conn = duckdb.connect(f"{config.benchmark_name}.duckdb")
     stats, curve_results, true_positive_cases = process_stats(config.runs, benchmark_type)
-    write_table(
-        conn, stats, f"{config.benchmark_name}_{benchmark_type.prioritisation_type_string}_summary"
-    )
+    write_table(conn, stats, f"{config.benchmark_name}_{benchmark_type.prioritisation_type_string}_summary")
     write_table(
         conn,
         curve_results,
         f"{config.benchmark_name}_{benchmark_type.prioritisation_type_string}_binary_classification_curves",
     )
-    calculate_rank_changes(
-        conn, [run.run_identifier for run in config.runs], true_positive_cases, benchmark_type
-    )
-    generate_plots(
-        config.benchmark_name, stats, curve_results, benchmark_type, config.plot_customisation
-    )
+    calculate_rank_changes(conn, [run.run_identifier for run in config.runs], true_positive_cases, benchmark_type)
+    generate_plots(config.benchmark_name, stats, curve_results, benchmark_type, config.plot_customisation)
     conn.close()
 
 
@@ -135,6 +123,9 @@ def benchmark_runs(benchmark_config_file: Path) -> None:
     start_time = time.perf_counter()
     logger.info("Initiated benchmarking process.")
     config = parse_run_config(benchmark_config_file)
+    if Path(f"{config.benchmark_name}.duckdb").exists():
+        logger.error(f"{config.benchmark_name}.duckdb already exists! Exiting.")
+        sys.exit(1)
     gene_analysis_runs = [run for run in config.runs if run.gene_analysis]
     variant_analysis_runs = [run for run in config.runs if run.variant_analysis]
     disease_analysis_runs = [run for run in config.runs if run.disease_analysis]
@@ -171,6 +162,4 @@ def benchmark_runs(benchmark_config_file: Path) -> None:
             BenchmarkOutputTypeEnum.DISEASE.value,
         )
         logger.info("Finished benchmarking for disease results.")
-    logger.info(
-        f"Finished benchmarking! Total time: {time.perf_counter() - start_time:.2f} seconds."
-    )
+    logger.info(f"Finished benchmarking! Total time: {time.perf_counter() - start_time:.2f} seconds.")

pheval/analyse/benchmark_output_type.py

@@ -1,5 +1,5 @@
 from enum import Enum
-from typing import List, NamedTuple
+from typing import NamedTuple
 
 
 class BenchmarkOutputType(NamedTuple):
@@ -15,7 +15,7 @@ class BenchmarkOutputType(NamedTuple):
 
     prioritisation_type_string: str
     y_label: str
-    columns: List[str]
+    columns: list[str]
     result_directory: str
 
 
@@ -35,9 +35,7 @@ class BenchmarkOutputTypeEnum(Enum):
         ["gene_identifier", "gene_symbol"],
         "pheval_gene_results",
     )
-    VARIANT = BenchmarkOutputType(
-        "variant", "Disease-causing variants (%)", ["variant_id"], "pheval_variant_results"
-    )
+    VARIANT = BenchmarkOutputType("variant", "Disease-causing variants (%)", ["variant_id"], "pheval_variant_results")
     DISEASE = BenchmarkOutputType(
         "disease",
         "Known diseases (%)",

pheval/analyse/binary_classification_curves.py

@@ -1,5 +1,3 @@
-from typing import Tuple
-
 import numpy as np
 import polars as pl
 from sklearn.metrics import precision_recall_curve, roc_curve
@@ -11,7 +9,7 @@ class BinaryClassificationCurves:
     """Class for computing and storing ROC & Precision-Recall curves in Polars."""
 
     @staticmethod
-    def _compute_finite_bounds(result_scan: pl.LazyFrame) -> Tuple[float, float]:
+    def _compute_finite_bounds(result_scan: pl.LazyFrame) -> tuple[float, float]:
         """
         Compute min and max finite values in the 'score' column to handle NaN and Inf values.
         Args:
@@ -32,9 +30,7 @@ class BinaryClassificationCurves:
         )
 
     @staticmethod
-    def _clean_and_extract_data(
-        result_scan: pl.LazyFrame, max_finite: float, min_finite: float
-    ) -> pl.LazyFrame:
+    def _clean_and_extract_data(result_scan: pl.LazyFrame, max_finite: float, min_finite: float) -> pl.LazyFrame:
         """
         Normalise the 'score' column (handling NaNs and Inf values) and extract 'true_positive' labels.
 
@@ -64,9 +60,7 @@ class BinaryClassificationCurves:
         )
 
     @staticmethod
-    def _compute_roc_pr_curves(
-        run_identifier: str, labels: np.ndarray, scores: np.ndarray
-    ) -> pl.LazyFrame:
+    def _compute_roc_pr_curves(run_identifier: str, labels: np.ndarray, scores: np.ndarray) -> pl.LazyFrame:
         """
         Compute ROC and Precision-Recall curves.
 

pheval/analyse/binary_classification_stats.py

@@ -103,10 +103,7 @@ class BinaryClassificationStats:
     )
 
     F1_SCORE = (
-        pl.when(
-            2 * (pl.col("true_positives") + pl.col("false_positives") + pl.col("false_negatives"))
-            != 0
-        )
+        pl.when(2 * (pl.col("true_positives") + pl.col("false_positives") + pl.col("false_negatives")) != 0)
         .then(
             2
             * pl.col("true_positives")

pheval/analyse/generate_plots.py

@@ -1,5 +1,6 @@
 from enum import Enum
 from pathlib import Path
+from typing import ClassVar
 
 import duckdb
 import matplotlib
@@ -32,7 +33,7 @@ class PlotTypes(Enum):
 class PlotGenerator:
     """Class to generate plots."""
 
-    palette_hex_codes = [
+    palette_hex_codes: ClassVar[list[str]] = [
         "#f4ae3d",
         "#ee5825",
         "#2b7288",
@@ -91,9 +92,7 @@ class PlotGenerator:
             {"run_identifier": "Run", "mrr": "Percentage"}
         )
 
-    def _save_fig(
-        self, benchmark_output_type: BenchmarkOutputType, y_lower_limit: int, y_upper_limit: int
-    ) -> None:
+    def _save_fig(self, benchmark_output_type: BenchmarkOutputType, y_lower_limit: int, y_upper_limit: int) -> None:
         """
         Save the generated figure.
         Args:
@@ -140,9 +139,7 @@ class PlotGenerator:
             legend=False,
             edgecolor="white",
         )
-        plt.title(
-            f"{benchmark_output_type.prioritisation_type_string.capitalize()} results - mean reciprocal rank"
-        )
+        plt.title(f"{benchmark_output_type.prioritisation_type_string.capitalize()} results - mean reciprocal rank")
         self._save_fig(benchmark_output_type, 0, 1)
 
     @staticmethod
@@ -189,17 +186,13 @@ class PlotGenerator:
         plt.title(plot_customisation.rank_plot_title, loc="center", fontsize=15)
         self._save_fig(benchmark_output_type, 0, 1)
 
-    def _generate_non_cumulative_bar_plot_data(
-        self, benchmarking_results_df: pl.DataFrame
-    ) -> pl.DataFrame:
+    def _generate_non_cumulative_bar_plot_data(self, benchmarking_results_df: pl.DataFrame) -> pl.DataFrame:
         """
         Generate data in the correct format for dataframe creation for a non-cumulative bar plot,
         appending to the self.stats attribute of the class.
         """
         return self._generate_stacked_data(benchmarking_results_df).hstack(
-            self._extract_mrr_data(benchmarking_results_df).select(
-                pl.col("Percentage").alias("MRR")
-            )
+            self._extract_mrr_data(benchmarking_results_df).select(pl.col("Percentage").alias("MRR"))
         )
 
     def generate_cumulative_bar(
@@ -309,9 +302,7 @@ def generate_plots(
     This method generates summary statistics bar plots based on the provided benchmarking results and plot type.
     """
     plot_generator = PlotGenerator(benchmark_name)
-    plot_customisation_type = getattr(
-        plot_customisation, f"{benchmark_output_type.prioritisation_type_string}_plots"
-    )
+    plot_customisation_type = getattr(plot_customisation, f"{benchmark_output_type.prioritisation_type_string}_plots")
     logger.info("Generating ROC curve visualisations.")
     plot_generator.generate_roc_curve(curves, benchmark_output_type, plot_customisation_type)
     logger.info("Generating Precision-Recall curves visualisations.")
@@ -355,8 +346,7 @@ def generate_plots_from_db(db_path: Path, config: Path) -> None:
     }
     for benchmark_output_type in BenchmarkOutputTypeEnum:
         summary_table = (
-            f"{benchmark_config_file.benchmark_name}_"
-            f"{benchmark_output_type.value.prioritisation_type_string}_summary"
+            f"{benchmark_config_file.benchmark_name}_{benchmark_output_type.value.prioritisation_type_string}_summary"
         )
         curve_table = (
             f"{benchmark_config_file.benchmark_name}_"

pheval/analyse/generate_rank_comparisons.py

@@ -1,5 +1,4 @@
 from itertools import combinations
-from typing import List
 
 import polars as pl
 from duckdb.duckdb import DuckDBPyConnection
@@ -11,7 +10,7 @@ from pheval.utils.logger import get_logger
 
 def calculate_rank_changes(
     conn: DuckDBPyConnection,
-    run_identifiers: List[str],
+    run_identifiers: list[str],
     true_positive_cases: pl.DataFrame,
     benchmark_type: BenchmarkOutputType,
 ) -> None:

pheval/analyse/rank_stats.py

@@ -1,5 +1,4 @@
 from dataclasses import dataclass
-from typing import List
 
 import numpy as np
 import polars as pl
@@ -81,11 +80,7 @@ class Ranks:
         """
         precision_expr = pl.col(f"top{k}") / (pl.col("number_of_samples") * k)
         recall_expr = pl.col(f"top{k}") / pl.col("total")
-        return (
-            ((2 * precision_expr * recall_expr) / (precision_expr + recall_expr))
-            .fill_nan(0)
-            .alias(f"f_beta@{k}")
-        )
+        return ((2 * precision_expr * recall_expr) / (precision_expr + recall_expr)).fill_nan(0).alias(f"f_beta@{k}")
 
     @classmethod
     def _average_precision_at_k(cls, df: pl.LazyFrame, k: int) -> pl.LazyFrame:
@@ -103,9 +98,7 @@ class Ranks:
         filtered_df = cls._filter_results(df, k)
         df_grouped = filtered_df.with_columns(
             pl.struct("ranks")
-            .map_elements(
-                lambda row: cls._compute_ap_k(np.array(row["ranks"])), return_dtype=pl.Float64
-            )
+            .map_elements(lambda row: cls._compute_ap_k(np.array(row["ranks"])), return_dtype=pl.Float64)
             .alias(f"ap@{k}")
         )
         return df_grouped.select(["file_path", f"ap@{k}"])
@@ -131,7 +124,7 @@ class Ranks:
         return ap_sum / num_samples
 
     @classmethod
-    def _calculate_ndcg_at_k(cls, ranks: List[int], k: int) -> float:
+    def _calculate_ndcg_at_k(cls, ranks: list[int], k: int) -> float:
         """
         Compute NDCG@K for a single query.
         Args:
@@ -146,9 +139,7 @@ class Ranks:
         result_ranks[valid_indices] = 3
         ideal_ranking = np.sort(result_ranks)[::-1]
         return (
-            ndcg_score(result_ranks.reshape(1, -1), ideal_ranking.reshape(1, -1))
-            if np.sum(result_ranks) > 0
-            else 0.0
+            ndcg_score(result_ranks.reshape(1, -1), ideal_ranking.reshape(1, -1)) if np.sum(result_ranks) > 0 else 0.0
         )
 
     @classmethod
@@ -156,9 +147,7 @@ class Ranks:
         filtered_df = cls._filter_results(df, k)
         ndcg_df = filtered_df.with_columns(
             pl.struct("ranks")
-            .map_elements(
-                lambda row: cls._calculate_ndcg_at_k(row["ranks"], k), return_dtype=pl.Float64
-            )
+            .map_elements(lambda row: cls._calculate_ndcg_at_k(row["ranks"], k), return_dtype=pl.Float64)
             .alias(f"NDCG@{k}")
         )
         ndcg_sum = ndcg_df.select(pl.col(f"NDCG@{k}").sum()).collect().item()
@@ -218,14 +207,8 @@ def compute_rank_stats(run_identifier: str, result_scan: pl.LazyFrame) -> pl.Laz
             pl.lit(Ranks.mean_average_precision_at_k(true_positive_scan, 3)).alias("MAP@3"),
             pl.lit(Ranks.mean_average_precision_at_k(true_positive_scan, 5)).alias("MAP@5"),
             pl.lit(Ranks.mean_average_precision_at_k(true_positive_scan, 10)).alias("MAP@10"),
-            pl.lit(Ranks.mean_normalised_discounted_cumulative_gain(true_positive_scan, 3)).alias(
-                "NDCG@3"
-            ),
-            pl.lit(Ranks.mean_normalised_discounted_cumulative_gain(true_positive_scan, 5)).alias(
-                "NDCG@5"
-            ),
-            pl.lit(Ranks.mean_normalised_discounted_cumulative_gain(true_positive_scan, 10)).alias(
-                "NDCG@10"
-            ),
+            pl.lit(Ranks.mean_normalised_discounted_cumulative_gain(true_positive_scan, 3)).alias("NDCG@3"),
+            pl.lit(Ranks.mean_normalised_discounted_cumulative_gain(true_positive_scan, 5)).alias("NDCG@5"),
+            pl.lit(Ranks.mean_normalised_discounted_cumulative_gain(true_positive_scan, 10)).alias("NDCG@10"),
         ]
     )

pheval/analyse/run_data_parser.py

@@ -1,5 +1,4 @@
 from pathlib import Path
-from typing import List, Optional
 
 import yaml
 from pydantic import BaseModel, field_validator
@@ -28,8 +27,8 @@ class RunConfig(BaseModel):
     gene_analysis: bool
     variant_analysis: bool
     disease_analysis: bool
-    threshold: Optional[float]
-    score_order: Optional[str]
+    threshold: float | None
+    score_order: str | None
 
     @field_validator("threshold", mode="before")
     @classmethod
@@ -41,6 +40,13 @@ class RunConfig(BaseModel):
     def set_score_order(cls, score_order):
         return score_order or "descending"
 
+    @field_validator("results_dir", mode="after")
+    @classmethod
+    def check_results_dir_exists(cls, results_dir: Path):
+        if not results_dir.exists():
+            raise FileNotFoundError(f"The specified results directory does not exist: {results_dir}")
+        return results_dir
+
 
 class SinglePlotCustomisation(BaseModel):
     """
@@ -53,10 +59,10 @@ class SinglePlotCustomisation(BaseModel):
         precision_recall_title (str): The title for the precision-recall plot.
     """
 
-    plot_type: Optional[str] = "bar_cumulative"
-    rank_plot_title: Optional[str]
-    roc_curve_title: Optional[str]
-    precision_recall_title: Optional[str]
+    plot_type: str | None = "bar_cumulative"
+    rank_plot_title: str | None
+    roc_curve_title: str | None
+    precision_recall_title: str | None
 
     @field_validator("plot_type", mode="before")
     @classmethod
@@ -86,7 +92,7 @@ class Config(BaseModel):
     """
 
     benchmark_name: str
-    runs: List[RunConfig]
+    runs: list[RunConfig]
     plot_customisation: PlotCustomisation
 
 
@@ -100,7 +106,7 @@ def parse_run_config(run_config: Path) -> Config:
     """
     logger = get_logger()
     logger.info(f"Loading benchmark configuration from {run_config}")
-    with open(run_config, "r") as f:
+    with open(run_config) as f:
         config_data = yaml.safe_load(f)
     f.close()
     config = Config(**config_data)

pheval/cli.py

@@ -29,7 +29,7 @@ def main(ctx, verbose=1, quiet=False):
     """Main CLI method for PhEval."""
     initialise_context(ctx)
 
-    if verbose >= 2:
+    if verbose >= 2:  # noqa
         logger.setLevel(logging.DEBUG)
     elif verbose == 1:
         logger.setLevel(logging.INFO)

pheval/cli_pheval_utils.py

@@ -1,7 +1,6 @@
 """PhEval utils Command Line Interface"""
 
 from pathlib import Path
-from typing import List
 
 import click
 
@@ -39,9 +38,7 @@ from pheval.utils.utils import semsim_scramble
     "-c",
     required=True,
     multiple=True,
-    type=click.Choice(
-        ["jaccard_similarity", "dice_similarity", "phenodigm_score"], case_sensitive=False
-    ),
+    type=click.Choice(["jaccard_similarity", "dice_similarity", "phenodigm_score"], case_sensitive=False),
     help="Score column that will be scrambled",
 )
 @click.option(
@@ -54,9 +51,7 @@ from pheval.utils.utils import semsim_scramble
     help="""Scramble Magnitude (noise)
     that will be applied to semantic similarity score column (e.g. jaccard similarity).""",
 )
-def semsim_scramble_command(
-    input: Path, output: Path, score_column: List[str], scramble_factor: float
-):
+def semsim_scramble_command(input: Path, output: Path, score_column: list[str], scramble_factor: float):
     """Scrambles semsim profile multiplying score value by scramble factor
     Args:
         input (Path): Path file that points out to the semsim profile
@@ -125,9 +120,7 @@ def scramble_phenopackets_command(
     if phenopacket_path is None and phenopacket_dir is None:
         raise InputError("Either a phenopacket or phenopacket directory must be specified")
     else:
-        scramble_phenopackets(
-            output_dir, phenopacket_path, phenopacket_dir, scramble_factor, local_ontology_cache
-        )
+        scramble_phenopackets(output_dir, phenopacket_path, phenopacket_dir, scramble_factor, local_ontology_cache)
 
 
 @click.command("semsim-comparison")
@@ -149,9 +142,7 @@ def scramble_phenopackets_command(
     "--score-column",
     "-c",
     required=True,
-    type=click.Choice(
-        ["jaccard_similarity", "dice_similarity", "phenodigm_score"], case_sensitive=False
-    ),
+    type=click.Choice(["jaccard_similarity", "dice_similarity", "phenodigm_score"], case_sensitive=False),
     help="Score column that will be used in comparison",
 )
 @click.option(
@@ -232,9 +223,7 @@ def semsim_comparison(
     help="Gene identifier to add to phenopacket",
     type=click.Choice(["ensembl_id", "entrez_id", "hgnc_id"]),
 )
-def update_phenopackets_command(
-    phenopacket_path: Path, phenopacket_dir: Path, output_dir: Path, gene_identifier: str
-):
+def update_phenopackets_command(phenopacket_path: Path, phenopacket_dir: Path, output_dir: Path, gene_identifier: str):
     """Update gene symbols and identifiers for phenopackets."""
     if phenopacket_path is None and phenopacket_dir is None:
         raise InputError("Either a phenopacket or phenopacket directory must be specified")
@@ -313,10 +302,10 @@ def create_spiked_vcfs_command(
     phenopacket_path: Path,
     phenopacket_dir: Path,
     output_dir: Path,
-    hg19_template_vcf: Path = None,
-    hg38_template_vcf: Path = None,
-    hg19_vcf_dir: Path = None,
-    hg38_vcf_dir: Path = None,
+    hg19_template_vcf: Path | None = None,
+    hg38_template_vcf: Path | None = None,
+    hg19_vcf_dir: Path | None = None,
+    hg38_vcf_dir: Path | None = None,
 ):
     """
     Create spiked VCF from either a Phenopacket or a Phenopacket directory.
@@ -394,9 +383,7 @@ def benchmark(
     This is the path where the phenotypic database folder will be written out.""",
     type=Path,
 )
-def semsim_to_exomiserdb_command(
-    input_file: Path, object_prefix: str, subject_prefix: str, db_path: Path
-):
+def semsim_to_exomiserdb_command(input_file: Path, object_prefix: str, subject_prefix: str, db_path: Path):
     """ingests semsim file into exomiser phenotypic database
 
     Args:

pheval/config_parser.py

@@ -39,7 +39,7 @@ class InputDirConfig:
 def parse_input_dir_config(input_dir: Path) -> InputDirConfig:
     """Reads the config file."""
     logger.info(f"Parsing config.yaml located in {input_dir}.")
-    with open(Path(input_dir).joinpath("config.yaml"), "r") as config_file:
+    with open(Path(input_dir).joinpath("config.yaml")) as config_file:
         config = yaml.safe_load(config_file)
     config_file.close()
     return from_yaml(InputDirConfig, yaml.dump(config))

pheval/implementations/__init__.py

@@ -15,11 +15,9 @@ def get_implementation_resolver() -> ClassResolver[PhEvalRunner]:
     Returns:
         ClassResolver[PhEvalRunner]: _description_
     """
-    implementation_resolver: PhevalClassResolver[PhEvalRunner] = (
-        PhevalClassResolver.from_subclasses(
-            PhEvalRunner,
-            suffix="Implementation",
-        )
+    implementation_resolver: PhevalClassResolver[PhEvalRunner] = PhevalClassResolver.from_subclasses(
+        PhEvalRunner,
+        suffix="Implementation",
     )
 
     # implementation_resolver.synonyms.update(

pheval/infra/exomiserdb.py

@@ -12,9 +12,7 @@ info_debug = log.getLogger("debug")
 
 
 class DBConnector:
-    def __init__(
-        self, jar: Path, driver: str, server: str, database: str, user: str, password: str
-    ):
+    def __init__(self, jar: Path, driver: str, server: str, database: str, user: str, password: str):
         self.jar = jar
         self.driver = driver
         self.server = server
@@ -63,7 +61,7 @@ class DBConnection:
 class ExomiserDB:
     def __init__(self, db_path: Path):
         try:
-            self.connector = DBConnector(  # noqa
+            self.connector = DBConnector(
                 jar=os.path.join(os.path.dirname(__file__), "../../../lib/h2-1.4.199.jar"),
                 driver="org.h2.Driver",
                 server=f"jdbc:h2:{db_path}",
@@ -89,7 +87,7 @@ class ExomiserDB:
             batches = reader.next_batches(batch_length)
             cursor = conn.get_cursor()
             # # TODO: Refactor this
-            with open(input_file, "r") as f:
+            with open(input_file) as f:
                 total = sum(1 for line in f)
             pbar = tqdm(total=total - 1)
             mapping_id = 1
@@ -112,12 +110,10 @@ def _format_row(mapping_id, data):
         data (_type_): row data
     """
     # TODO:Improve string escaping. Replace this code with parametrised query
-    return f"""({mapping_id}, '{data['subject_id']}', '{data['subject_label'].replace("'", "")}', '{data['object_id']}', '{data['object_label'].replace("'", "")}', {data['jaccard_similarity']}, {data['ancestor_information_content']}, {data['phenodigm_score']}, '{data['ancestor_id'].split(",")[0]}', '{data['ancestor_label'].replace("'", "")}')"""  # noqa
+    return f"""({mapping_id}, '{data["subject_id"]}', '{data["subject_label"].replace("'", "")}', '{data["object_id"]}', '{data["object_label"].replace("'", "")}', {data["jaccard_similarity"]}, {data["ancestor_information_content"]}, {data["phenodigm_score"]}, '{data["ancestor_id"].split(",")[0]}', '{data["ancestor_label"].replace("'", "")}')"""  # noqa
 
 
-def _semsim2h2(
-    input_data: pl.DataFrame, subject_prefix: str, object_prefix: str, mapping_id=1
-) -> None:
+def _semsim2h2(input_data: pl.DataFrame, subject_prefix: str, object_prefix: str, mapping_id=1) -> None:
     """This function is responsible for generate sql insertion query for each semsim profile row
 
     Args:
@@ -130,12 +126,8 @@ def _semsim2h2(
     if mapping_id == 1:
         sql += f"TRUNCATE TABLE EXOMISER.{subject_prefix}_{object_prefix}_MAPPINGS;\n"
 
-    object_id = (
-        f"{object_prefix}_ID_HIT" if subject_prefix == object_prefix else f"{object_prefix}_ID"
-    )
-    object_term = (
-        f"{object_prefix}_HIT_TERM" if subject_prefix == object_prefix else f"{object_prefix}_TERM"
-    )
+    object_id = f"{object_prefix}_ID_HIT" if subject_prefix == object_prefix else f"{object_prefix}_ID"
+    object_term = f"{object_prefix}_HIT_TERM" if subject_prefix == object_prefix else f"{object_prefix}_TERM"
     sql += f"""INSERT INTO EXOMISER.{subject_prefix}_{object_prefix}_MAPPINGS
 (MAPPING_ID, {subject_prefix}_ID, {subject_prefix}_TERM, {object_id}, {object_term}, SIMJ, IC, SCORE, LCS_ID, LCS_TERM)
 VALUES"""