chore: merge dev

src/gentropy/dataset/study_index.py

@@ -30,14 +30,12 @@ class StudyQualityCheck(Enum):
         UNRESOLVED_DISEASE (str): Disease identifier could not match to referece or retired identifier - labelling failing disease
         UNKNOWN_STUDY_TYPE (str): Indicating the provided type of study is not supported.
         DUPLICATED_STUDY (str): Flagging if a study identifier is not unique.
-        NO_GENE_PROVIDED (str): Flagging QTL studies if the measured
     """
 
     UNRESOLVED_TARGET = "Target/gene identifier could not match to reference."
     UNRESOLVED_DISEASE = "No valid disease identifier found."
     UNKNOWN_STUDY_TYPE = "This type of study is not supported."
     DUPLICATED_STUDY = "The identifier of this study is not unique."
-    NO_GENE_PROVIDED = "QTL study doesn't have gene assigned."
 
 
 @dataclass

src/gentropy/study_locus_validation.py

@@ -41,14 +41,11 @@ def __init__(
         # Running validation then writing output:
         study_locus_with_qc = (
             StudyLocus.from_parquet(session, list(study_locus_path))
-            # Flagging study locus with subsignificant p-values
-            .validate_lead_pvalue(pvalue_cutoff=gwas_significance)
             # Add flag for MHC region
             .qc_MHC_region()
             .validate_study(study_index)  # Flagging studies not in study index
-            .annotate_study_type(study_index) # Add study type to study locus
+            .annotate_study_type(study_index)  # Add study type to study locus
             .qc_redundant_top_hits_from_PICS()  # Flagging top hits from studies with PICS summary statistics
-            .validate_unique_study_locus_id()  # Flagging duplicated study locus ids
             # Annotates credible intervals and filter to only keep 99% credible sets
             .filter_credible_set(credible_interval=CredibleInterval.IS99)
         ).persist()  # we will need this for 2 types of outputs

src/gentropy/study_validation.py

@@ -58,8 +58,7 @@ def __init__(
 
         # Running validation:
         study_index_with_qc = (
-            study_index.validate_disease(disease_index)
-            .validate_unique_study_id()  # Flagging duplicated study ids
+            study_index.validate_unique_study_id()  # Flagging duplicated study ids
             .validate_study_type()  # Flagging non-supported study types.
             .validate_target(target_index)  # Flagging QTL studies with invalid targets
             .validate_disease(disease_index)  # Flagging invalid EFOs