diff --git a/src/gentropy/dataset/dataset.py b/src/gentropy/dataset/dataset.py
index e56ef2ecc..c822b592a 100644
--- a/src/gentropy/dataset/dataset.py
+++ b/src/gentropy/dataset/dataset.py
@@ -352,3 +352,18 @@ def flag_duplicates(test_column: Column) -> Column:
             )
             > 1
         )
+
+    @staticmethod
+    def generate_identifier(uniqueness_defining_columns: list[str]) -> Column:
+        """Hashes the provided columns to generate a unique identifier.
+
+        Args:
+            uniqueness_defining_columns (list[str]): list of columns defining uniqueness
+
+        Returns:
+            Column: column with a unique identifier
+        """
+        hashable_columns = [f.when(f.col(column).cast("string").isNull(), f.lit("None"))
+                                 .otherwise(f.col(column).cast("string"))
+                                 for column in uniqueness_defining_columns]
+        return f.md5(f.concat(*hashable_columns))
diff --git a/src/gentropy/dataset/study_locus.py b/src/gentropy/dataset/study_locus.py
index 1b3473148..a4d35e7d5 100644
--- a/src/gentropy/dataset/study_locus.py
+++ b/src/gentropy/dataset/study_locus.py
@@ -447,24 +447,18 @@ def _align_overlapping_tags(
         )
 
     @staticmethod
-    def assign_study_locus_id(
-        study_id_col: Column,
-        variant_id_col: Column,
-        finemapping_col: Column = None,
-    ) -> Column:
-        """Hashes a column with a variant ID and a study ID to extract a consistent studyLocusId.
+    def assign_study_locus_id(uniqueness_defining_columns: list[str]) -> Column:
+        """Hashes the provided columns to extract a consistent studyLocusId.
 
         Args:
-            study_id_col (Column): column name with a study ID
-            variant_id_col (Column): column name with a variant ID
-            finemapping_col (Column, optional): column with fine mapping methodology
+            uniqueness_defining_columns (list[str]): list of columns defining uniqueness
 
         Returns:
             Column: column with a study locus ID
 
         Examples:
             >>> df = spark.createDataFrame([("GCST000001", "1_1000_A_C", "SuSiE-inf"), ("GCST000002", "1_1000_A_C", "pics")]).toDF("studyId", "variantId", "finemappingMethod")
-            >>> df.withColumn("study_locus_id", StudyLocus.assign_study_locus_id(f.col("studyId"), f.col("variantId"), f.col("finemappingMethod"))).show(truncate=False)
+            >>> df.withColumn("study_locus_id", StudyLocus.assign_study_locus_id(["studyId", "variantId", "finemappingMethod"])).show(truncate=False)
             +----------+----------+-----------------+--------------------------------+
             |studyId   |variantId |finemappingMethod|study_locus_id                  |
             +----------+----------+-----------------+--------------------------------+
@@ -473,15 +467,8 @@ def assign_study_locus_id(
             +----------+----------+-----------------+--------------------------------+
             <BLANKLINE>
         """
-        if finemapping_col is None:
-            finemapping_col = f.lit("None")
-        columns = [study_id_col, variant_id_col, finemapping_col]
-        hashable_columns = [f.when(column.cast("string").isNull(), f.lit("None"))
-                                 .otherwise(column.cast("string"))
-                                 for column in columns]
-        return f.md5(f.concat(*hashable_columns)).alias(
-            "studyLocusId"
-        )
+        return Dataset.generate_identifier(uniqueness_defining_columns).alias("studyLocusId")
+
 
     @classmethod
     def calculate_credible_set_log10bf(cls: type[StudyLocus], logbfs: Column) -> Column:
diff --git a/src/gentropy/datasource/eqtl_catalogue/finemapping.py b/src/gentropy/datasource/eqtl_catalogue/finemapping.py
index 11ec5bef1..0808b7016 100644
--- a/src/gentropy/datasource/eqtl_catalogue/finemapping.py
+++ b/src/gentropy/datasource/eqtl_catalogue/finemapping.py
@@ -260,7 +260,7 @@ def from_susie_results(
                 .select(
                     *study_locus_cols,
                     StudyLocus.assign_study_locus_id(
-                        f.col("studyId"), f.col("variantId"), f.col("finemappingMethod")
+                        ["studyId", "variantId", "finemappingMethod"]
                     ),
                     StudyLocus.calculate_credible_set_log10bf(
                         f.col("locus.logBF")
diff --git a/src/gentropy/datasource/finngen/finemapping.py b/src/gentropy/datasource/finngen/finemapping.py
index 092a79372..3c83ba8ff 100644
--- a/src/gentropy/datasource/finngen/finemapping.py
+++ b/src/gentropy/datasource/finngen/finemapping.py
@@ -471,7 +471,7 @@ def from_finngen_susie_finemapping(
         ).withColumn(
             "studyLocusId",
             StudyLocus.assign_study_locus_id(
-                f.col("studyId"), f.col("variantId"), f.col("finemappingMethod")
+                ["studyId", "variantId", "finemappingMethod"]
             ),
         )
 
diff --git a/src/gentropy/datasource/gwas_catalog/associations.py b/src/gentropy/datasource/gwas_catalog/associations.py
index 5e84079a1..b34944b11 100644
--- a/src/gentropy/datasource/gwas_catalog/associations.py
+++ b/src/gentropy/datasource/gwas_catalog/associations.py
@@ -1188,7 +1188,7 @@ def update_study_id(
             .drop("subStudyDescription", "updatedStudyId")
         ).withColumn(
             "studyLocusId",
-            StudyLocus.assign_study_locus_id(f.col("studyId"), f.col("variantId")),
+            StudyLocus.assign_study_locus_id(["studyId", "variantId"]),
         )
         return self
 
diff --git a/src/gentropy/datasource/open_targets/l2g_gold_standard.py b/src/gentropy/datasource/open_targets/l2g_gold_standard.py
index 2cfcd62f8..26d5a0253 100644
--- a/src/gentropy/datasource/open_targets/l2g_gold_standard.py
+++ b/src/gentropy/datasource/open_targets/l2g_gold_standard.py
@@ -52,7 +52,7 @@ def parse_positive_curation(
             )
             .withColumn(
                 "studyLocusId",
-                StudyLocus.assign_study_locus_id(f.col("studyId"), f.col("variantId")),
+                StudyLocus.assign_study_locus_id(["studyId", "variantId"]),
             )
             .groupBy("studyLocusId", "studyId", "variantId", "geneId")
             .agg(f.collect_set("source").alias("sources"))
diff --git a/src/gentropy/l2g.py b/src/gentropy/l2g.py
index 6f80d826e..ff8c6c8ff 100644
--- a/src/gentropy/l2g.py
+++ b/src/gentropy/l2g.py
@@ -207,17 +207,22 @@ def _generate_feature_matrix(self, write_feature_matrix: bool) -> L2GFeatureMatr
             study_locus_overlap = StudyLocus(
                 _df=self.credible_set.df.join(
                     f.broadcast(
-                        self.gs_curation.select(
-                            StudyLocus.assign_study_locus_id(
-                                f.col("association_info.otg_id"),  # studyId
-                                f.concat_ws(  # variantId
+                        self.gs_curation
+                        .withColumn(
+                            "variantId",
+                            f.concat_ws(
                                     "_",
                                     f.col("sentinel_variant.locus_GRCh38.chromosome"),
                                     f.col("sentinel_variant.locus_GRCh38.position"),
                                     f.col("sentinel_variant.alleles.reference"),
                                     f.col("sentinel_variant.alleles.alternative"),
-                                ),
-                            ).alias("studyLocusId"),
+                            )
+                        )
+                        .select(
+                            StudyLocus.assign_study_locus_id(
+                                ["association_info.otg_id",  # studyId
+                                "variantId"]
+                            ),
                         )
                     ),
                     "studyLocusId",
diff --git a/src/gentropy/method/locus_breaker_clumping.py b/src/gentropy/method/locus_breaker_clumping.py
index 0ca7ae29b..fd7661a22 100644
--- a/src/gentropy/method/locus_breaker_clumping.py
+++ b/src/gentropy/method/locus_breaker_clumping.py
@@ -112,8 +112,8 @@ def locus_breaker(
                     .cast(t.ArrayType(t.StringType()))
                     .alias("qualityControls"),
                     StudyLocus.assign_study_locus_id(
-                        f.col("studyId"), f.col("variantId")
-                    ).alias("studyLocusId"),
+                        ["studyId", "variantId"]
+                    ),
                 )
             ),
             _schema=StudyLocus.get_schema(),
diff --git a/src/gentropy/method/pics.py b/src/gentropy/method/pics.py
index 6889aaa26..5fd084efd 100644
--- a/src/gentropy/method/pics.py
+++ b/src/gentropy/method/pics.py
@@ -257,7 +257,7 @@ def finemap(
                 .withColumn(
                     "studyLocusId",
                     StudyLocus.assign_study_locus_id(
-                        f.col("studyId"), f.col("variantId"), f.col("finemappingMethod")
+                        ["studyId", "variantId", "finemappingMethod"]
                     ),
                 )
                 .drop("neglog_pvalue")
diff --git a/src/gentropy/method/window_based_clumping.py b/src/gentropy/method/window_based_clumping.py
index 9ef747abf..3ab15d42f 100644
--- a/src/gentropy/method/window_based_clumping.py
+++ b/src/gentropy/method/window_based_clumping.py
@@ -247,7 +247,7 @@ def clump(
                 .withColumn(
                     "studyLocusId",
                     StudyLocus.assign_study_locus_id(
-                        f.col("studyId"), f.col("variantId")
+                        ["studyId", "variantId"]
                     ),
                 )
                 # Initialize QC column as array of strings:
diff --git a/src/gentropy/susie_finemapper.py b/src/gentropy/susie_finemapper.py
index a80591c60..26c73e20f 100644
--- a/src/gentropy/susie_finemapper.py
+++ b/src/gentropy/susie_finemapper.py
@@ -95,7 +95,7 @@ def __init__(
             .df.withColumn(
                 "studyLocusId",
                 StudyLocus.assign_study_locus_id(
-                    f.col("studyId"), f.col("variantId"), f.col("finemappingMethod")
+                    ["studyId", "variantId", "finemappingMethod"]
                 ),
             )
             .collect()[0]
@@ -247,7 +247,7 @@ def susie_inf_to_studylocus(
                 .withColumn(
                     "studyLocusId",
                     StudyLocus.assign_study_locus_id(
-                        f.col("studyId"), f.col("variantId"), f.col("finemappingMethod")
+                        ["studyId", "variantId", "finemappingMethod"]
                     ),
                 )
                 .select(