diff --git a/deeprvat/data/dense_gt.py b/deeprvat/data/dense_gt.py index 16670651..bfe93c5c 100644 --- a/deeprvat/data/dense_gt.py +++ b/deeprvat/data/dense_gt.py @@ -73,6 +73,7 @@ def __init__( genes_to_keep: Optional[Set[str]] = None, gene_file: Optional[str] = None, gene_types_to_keep: Optional[List[str]] = None, + exclude_variant_cols: List[str] = [], ignore_by_annotation: Optional[List[Tuple[str, Any]]] = None, max_pval: Optional[Dict[str, float]] = None, variants: Optional[pd.DataFrame] = None, @@ -185,7 +186,9 @@ def __init__( ) self.transform_data() - self.setup_variants(min_common_variant_count, min_common_af, variants) + self.setup_variants( + min_common_variant_count, min_common_af, variants, exclude_variant_cols + ) self.get_variant_metadata(grouping_level) @@ -479,6 +482,7 @@ def setup_variants( min_common_variant_count: Optional[int], min_common_af: Optional[Dict[str, float]], train_variants: Optional[pd.DataFrame], + exclude_variant_cols: List[str], ): logger.debug("Setting up variants") if min_common_variant_count is None and min_common_af is None: diff --git a/dnanexus/config.yaml b/dnanexus/config.yaml index d140044c..7a5f5e4b 100644 --- a/dnanexus/config.yaml +++ b/dnanexus/config.yaml @@ -43,7 +43,7 @@ model: data: gt_file: /mnt/project/DeepRVAT/DeepRVAT/data/preprocessed/genotypes.h5 - variant_file: /mnt/project/DeepRVAT/DeepRVAT/data/variants.parquet + variant_file: /mnt/project/DeepRVAT/DeepRVAT/data/variants_90pct10dp_qc.parquet dataset_config: min_common_af: MAF: 0.01 @@ -110,6 +110,8 @@ data: - DeepRipe_plus_QKI_parclip - SpliceAI_delta_score gene_file: /mnt/project/DeepRVAT/DeepRVAT/data/protein_coding_genes.parquet + exclude_variant_cols: + - 90pct10dp_qc use_common_variants: False use_rare_variants: True rare_embedding: