feat: adding foldx ingestion step

src/gentropy/config.py

@@ -112,6 +112,17 @@ class GWASCatalogSumstatsPreprocessConfig(StepConfig):
     )
 
 
+@dataclass
+class FoldXVariantAnnotationConfig(StepConfig):
+    """Step to ingest FoldX amino acid variation data."""
+
+    foldx_dataset_path: str = MISSING
+    plddt_threshold: float = 0.7
+    annotation_path: str = MISSING
+
+    _target_: str = "gentropy.foldx_ingestion.FoldXIngestionStep"
+
+
 @dataclass
 class EqtlCatalogueConfig(StepConfig):
     """eQTL Catalogue step configuration."""
@@ -767,3 +778,4 @@ def register_config() -> None:
     )
     cs.store(group="step", name="finngen_ukb_meta_ingestion", node=FinngenUkbMetaConfig)
     cs.store(group="step", name="credible_set_qc", node=CredibleSetQCStepConfig)
+    cs.store(group="step", name="foldx_integration", node=FoldXVariantAnnotationConfig)

src/gentropy/foldx_ingestion.py

@@ -0,0 +1,40 @@
+"""Ingest FoldX data from OTAR2081 project."""
+
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+
+from gentropy.common.session import Session
+from gentropy.datasource.open_targets.foldex_integration import OpenTargetsFoldX
+
+if TYPE_CHECKING:
+    from gentropy.dataset.amino_acid_variants import AminoAcidVariants
+
+
+class FoldXIngestionStep:
+    """Step to ingest proteome-wide FoldX dataset generated by the OTAR2081 project."""
+
+    def __init__(
+        self,
+        session: Session,
+        foldx_dataset_path: str,
+        plddt_threshold: float,
+        annotation_path: str,
+    ) -> None:
+        """Initialize step.
+
+        Args:
+            session (Session): Session object.
+            foldx_dataset_path (str): path to the FoldX dataset.
+            plddt_threshold (float): plddt threshold to filter amio acids in the structural model.
+            annotation_path (str): path of the output dataset.
+        """
+        fold_x_data = session.spark.read.parquet(foldx_dataset_path)
+        # Transform
+        gene_index: AminoAcidVariants = OpenTargetsFoldX.ingest_foldx_data(
+            fold_x_data, plddt_threshold
+        )
+        # Load
+        gene_index.df.coalesce(session.output_partitions).write.mode(
+            session.write_mode
+        ).parquet(annotation_path)