diff --git a/README.md b/README.md
index 21d1e372a..eee10a646 100644
--- a/README.md
+++ b/README.md
@@ -71,7 +71,8 @@ flowchart TB
 
 Chromatin accessibility data
 
-Example file: `resources_test/grn_benchmark/inference_datasets//op_atac.h5ad`
+Example file:
+`resources_test/grn_benchmark/inference_data//op_atac.h5ad`
 
 Format:
 
@@ -120,7 +121,7 @@ Arguments:
 
 File indicating the inferred GRN.
 
-Example file: `resources/grn_models/op/collectri.h5ad`
+Example file: `resources_test/grn_models/op/collectri.h5ad`
 
 Format:
 
@@ -139,7 +140,7 @@ Data structure:
 |:---|:---|:---|
 | `uns["dataset_id"]` | `string` | A unique identifier for the dataset. |
 | `uns["method_id"]` | `string` | A unique identifier for the inference method. |
-| `uns["prediction"]` | `DataFrame` | Inferred GRNs in the format of source, target, weight. |
+| `uns["prediction"]` | `object` | Inferred GRNs in the format of source, target, weight. |
 
 </div>
 
@@ -245,7 +246,8 @@ Data structure:
 
 Perturbation dataset for benchmarking.
 
-Example file: `resources_test/grn_benchmark/evaluation_data//op.h5ad`
+Example file:
+`resources_test/grn_benchmark/evaluation_data/op_bulk.h5ad`
 
 Format:
 
@@ -275,7 +277,8 @@ Data structure:
 
 RNA expression data.
 
-Example file: `resources_test/grn_benchmark/inference_datasets//op_rna.h5ad`
+Example file:
+`resources_test/grn_benchmark/inference_data/op_rna.h5ad`
 
 Format:
 
diff --git a/_viash.yaml b/_viash.yaml
index 11c4a0779..a2016b10c 100644
--- a/_viash.yaml
+++ b/_viash.yaml
@@ -59,7 +59,7 @@ info:
 
     ```bash
     viash run src/control_methods/pearson_corr/config.vsh.yaml -- \
-              --rna resources/grn_benchmark/inference_datasets/norman_rna.h5ad --prediction output/net.h5ad
+              --rna resources/grn_benchmark/inference_data/norman_rna.h5ad --prediction output/net.h5ad
     ```
 
     ## Evaluate a GRN
diff --git a/runs.ipynb b/runs.ipynb
index 63654579d..2f2d09bbd 100644
--- a/runs.ipynb
+++ b/runs.ipynb
@@ -14,40 +14,73 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "download: s3://openproblems-data/resources/grn/grn_benchmark/evaluation_datasets/adamson_bulk.h5ad to resources/grn_benchmark/evaluation_datasets/adamson_bulk.h5ad\n",
+      "download: s3://openproblems-data/resources/grn/grn_benchmark/evaluation_datasets/norman_bulk.h5ad to resources/grn_benchmark/evaluation_datasets/norman_bulk.h5ad\n",
+      "download: s3://openproblems-data/resources/grn/grn_benchmark/evaluation_datasets/replogle_bulk.h5ad to resources/grn_benchmark/evaluation_datasets/replogle_bulk.h5ad\n",
+      "download: s3://openproblems-data/resources/grn/grn_benchmark/evaluation_datasets/nakatake_bulk.h5ad to resources/grn_benchmark/evaluation_datasets/nakatake_bulk.h5ad\n",
+      "download: s3://openproblems-data/resources/grn/grn_benchmark/inference_datasets/adamson_rna.h5ad to resources/grn_benchmark/inference_datasets/adamson_rna.h5ad\n",
+      "download: s3://openproblems-data/resources/grn/grn_benchmark/evaluation_datasets/op_bulk.h5ad to resources/grn_benchmark/evaluation_datasets/op_bulk.h5ad\n",
+      "download: s3://openproblems-data/resources/grn/grn_benchmark/inference_datasets/nakatake_rna.h5ad to resources/grn_benchmark/inference_datasets/nakatake_rna.h5ad\n",
+      "download: s3://openproblems-data/resources/grn/grn_benchmark/evaluation_datasets/adamson_sc.h5ad to resources/grn_benchmark/evaluation_datasets/adamson_sc.h5ad\n",
+      "download: s3://openproblems-data/resources/grn/grn_benchmark/inference_datasets/op_atac.rds to resources/grn_benchmark/inference_datasets/op_atac.rds\n",
+      "download: s3://openproblems-data/resources/grn/grn_benchmark/inference_datasets/norman_rna.h5ad to resources/grn_benchmark/inference_datasets/norman_rna.h5ad\n",
+      "download: s3://openproblems-data/resources/grn/grn_benchmark/inference_datasets/op_rna.rds to resources/grn_benchmark/inference_datasets/op_rna.rds\n",
+      "download: s3://openproblems-data/resources/grn/grn_benchmark/evaluation_datasets/norman_sc.h5ad to resources/grn_benchmark/evaluation_datasets/norman_sc.h5ad\n",
+      "download: s3://openproblems-data/resources/grn/grn_benchmark/prior/op/annot_peak_database.csv to resources/grn_benchmark/prior/op/annot_peak_database.csv\n",
+      "download: s3://openproblems-data/resources/grn/grn_benchmark/prior/op/cell_topic.csv to resources/grn_benchmark/prior/op/cell_topic.csv\n",
+      "download: s3://openproblems-data/resources/grn/grn_benchmark/prior/op/peaks.bed to resources/grn_benchmark/prior/op/peaks.bed\n",
+      "download: s3://openproblems-data/resources/grn/grn_benchmark/prior/op/peak_annotation.csv to resources/grn_benchmark/prior/op/peak_annotation.csv\n",
+      "download: s3://openproblems-data/resources/grn/grn_benchmark/prior/op/peaks.txt to resources/grn_benchmark/prior/op/peaks.txt\n",
+      "download: s3://openproblems-data/resources/grn/grn_benchmark/prior/regulators_consensus_adamson.json to resources/grn_benchmark/prior/regulators_consensus_adamson.json\n",
+      "download: s3://openproblems-data/resources/grn/grn_benchmark/prior/regulators_consensus_nakatake.json to resources/grn_benchmark/prior/regulators_consensus_nakatake.json\n",
+      "download: s3://openproblems-data/resources/grn/grn_benchmark/prior/regulators_consensus_norman.json to resources/grn_benchmark/prior/regulators_consensus_norman.json\n",
+      "download: s3://openproblems-data/resources/grn/grn_benchmark/prior/regulators_consensus_op.json to resources/grn_benchmark/prior/regulators_consensus_op.json\n",
+      "download: s3://openproblems-data/resources/grn/grn_benchmark/prior/regulators_consensus_replogle2.json to resources/grn_benchmark/prior/regulators_consensus_replogle2.json\n",
+      "download: s3://openproblems-data/resources/grn/grn_benchmark/prior/tf_all.csv to resources/grn_benchmark/prior/tf_all.csv\n",
+      "download: s3://openproblems-data/resources/grn/grn_benchmark/prior/skeleton.csv to resources/grn_benchmark/prior/skeleton.csv\n",
+      "download: s3://openproblems-data/resources/grn/grn_benchmark/prior/ws_consensus_adamson.csv to resources/grn_benchmark/prior/ws_consensus_adamson.csv\n",
+      "download: s3://openproblems-data/resources/grn/grn_benchmark/prior/ws_consensus_norman.csv to resources/grn_benchmark/prior/ws_consensus_norman.csv\n",
+      "download: s3://openproblems-data/resources/grn/grn_benchmark/prior/ws_distance_background_adamson.csv to resources/grn_benchmark/prior/ws_distance_background_adamson.csv\n",
+      "download: s3://openproblems-data/resources/grn/grn_benchmark/prior/ws_distance_background_norman.csv to resources/grn_benchmark/prior/ws_distance_background_norman.csv\n",
+      "download: s3://openproblems-data/resources/grn/grn_benchmark/inference_datasets/op_rna.h5ad to resources/grn_benchmark/inference_datasets/op_rna.h5ad\n",
+      "download: s3://openproblems-data/resources/grn/grn_benchmark/inference_datasets/replogle_rna.h5ad to resources/grn_benchmark/inference_datasets/replogle_rna.h5ad\n",
+      "download: s3://openproblems-data/resources/grn/grn_benchmark/inference_datasets/op_atac.h5ad to resources/grn_benchmark/inference_datasets/op_atac.h5ad\n",
+      "download: s3://openproblems-data/resources/grn/grn_benchmark/evaluation_datasets/replogle_sc.h5ad to resources/grn_benchmark/evaluation_datasets/replogle_sc.h5ad\n"
+     ]
+    }
+   ],
+   "source": [
+    "!aws s3 sync  s3://openproblems-data/resources/grn/grn_benchmark resources/grn_benchmark --delete\n",
+    "!aws s3 sync  s3://openproblems-data/resources/grn/grn_models resources/grn_models --delete"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "upload: resources/grn_benchmark/inference_datasets/op_rna.rds to s3://openproblems-data/resources/grn/grn_benchmark/inference_datasets/op_rna.rds\n",
-      "upload: resources/grn_benchmark/inference_datasets/op_atac.rds to s3://openproblems-data/resources/grn/grn_benchmark/inference_datasets/op_atac.rds\n",
-      "upload: resources/grn_benchmark/prior/op/annot_peak_database.csv to s3://openproblems-data/resources/grn/grn_benchmark/prior/op/annot_peak_database.csv\n",
-      "upload: resources/grn_benchmark/prior/op/cell_topic.csv to s3://openproblems-data/resources/grn/grn_benchmark/prior/op/cell_topic.csv\n",
-      "upload: resources/grn_benchmark/prior/op/peaks.bed to s3://openproblems-data/resources/grn/grn_benchmark/prior/op/peaks.bed\n",
-      "upload: resources/grn_benchmark/prior/op/peak_annotation.csv to s3://openproblems-data/resources/grn/grn_benchmark/prior/op/peak_annotation.csv\n",
-      "upload: resources/grn_benchmark/prior/op/peaks.txt to s3://openproblems-data/resources/grn/grn_benchmark/prior/op/peaks.txt\n",
-      "upload: resources/grn_benchmark/prior/regulators_consensus_adamson.json to s3://openproblems-data/resources/grn/grn_benchmark/prior/regulators_consensus_adamson.json\n",
-      "upload: resources/grn_benchmark/prior/regulators_consensus_nakatake.json to s3://openproblems-data/resources/grn/grn_benchmark/prior/regulators_consensus_nakatake.json\n",
-      "upload: resources/grn_benchmark/prior/regulators_consensus_norman.json to s3://openproblems-data/resources/grn/grn_benchmark/prior/regulators_consensus_norman.json\n",
-      "upload: resources/grn_benchmark/prior/regulators_consensus_op.json to s3://openproblems-data/resources/grn/grn_benchmark/prior/regulators_consensus_op.json\n",
-      "upload: resources/grn_benchmark/prior/regulators_consensus_replogle2.json to s3://openproblems-data/resources/grn/grn_benchmark/prior/regulators_consensus_replogle2.json\n",
-      "upload: resources/grn_benchmark/prior/tf_all.csv to s3://openproblems-data/resources/grn/grn_benchmark/prior/tf_all.csv\n",
-      "upload: resources/grn_benchmark/inference_datasets/replogle_rna.h5ad to s3://openproblems-data/resources/grn/grn_benchmark/inference_datasets/replogle_rna.h5ad\n",
-      "upload: resources/grn_benchmark/prior/ws_consensus_adamson.csv to s3://openproblems-data/resources/grn/grn_benchmark/prior/ws_consensus_adamson.csv\n",
-      "upload: resources/grn_benchmark/prior/ws_consensus_norman.csv to s3://openproblems-data/resources/grn/grn_benchmark/prior/ws_consensus_norman.csv\n",
-      "upload: resources/grn_benchmark/prior/ws_distance_background_adamson.csv to s3://openproblems-data/resources/grn/grn_benchmark/prior/ws_distance_background_adamson.csv\n",
-      "upload: resources/grn_benchmark/prior/ws_distance_background_norman.csv to s3://openproblems-data/resources/grn/grn_benchmark/prior/ws_distance_background_norman.csv\n",
-      "upload: resources/grn_benchmark/prior/skeleton.csv to s3://openproblems-data/resources/grn/grn_benchmark/prior/skeleton.csv\n",
-      "upload: resources/grn_benchmark/inference_datasets/op_rna.h5ad to s3://openproblems-data/resources/grn/grn_benchmark/inference_datasets/op_rna.h5ad\n",
-      "upload: resources/grn_benchmark/inference_datasets/op_atac.h5ad to s3://openproblems-data/resources/grn/grn_benchmark/inference_datasets/op_atac.h5ad\n",
-      "upload: resources/grn_benchmark/evaluation_datasets/replogle_sc.h5ad to s3://openproblems-data/resources/grn/grn_benchmark/evaluation_datasets/replogle_sc.h5ad\n"
+      "delete: s3://openproblems-data/resources_test/grn/grn_benchmark/evaluation_datasets/op_perturbation.h5ad\n",
+      "delete: s3://openproblems-data/resources_test/grn/grn_benchmark/inference_datasets/op_atac.h5ad\n",
+      "delete: s3://openproblems-data/resources_test/grn/grn_benchmark/inference_datasets/op_rna.h5ad\n",
+      "upload: resources_test/grn_benchmark/inference_data/op_atac.h5ad to s3://openproblems-data/resources_test/grn/grn_benchmark/inference_data/op_atac.h5ad\n",
+      "upload: resources_test/grn_benchmark/inference_data/op_rna.h5ad to s3://openproblems-data/resources_test/grn/grn_benchmark/inference_data/op_rna.h5ad\n",
+      "upload: resources_test/grn_benchmark/evaluation_data/op_bulk.h5ad to s3://openproblems-data/resources_test/grn/grn_benchmark/evaluation_data/op_bulk.h5ad\n"
      ]
     }
    ],
    "source": [
-    "!aws s3 sync resources/grn_benchmark s3://openproblems-data/resources/grn/grn_benchmark --delete"
+    "!aws s3 sync   resources_test s3://openproblems-data/resources_test/grn/ --delete"
    ]
   },
   {
@@ -62,7 +95,7 @@
     "# !aws s3 sync resources/results/ s3://openproblems-data/resources/grn/results --delete\n",
     "# !aws s3 sync resources/scores/ s3://openproblems-data/resources/grn/scores --delete\n",
     "# !aws s3 sync  resources/grn_benchmark/evaluation_data// s3://openproblems-data/resources/grn/evaluation_data/ --delete\n",
-    "# !aws s3 sync  resources/grn_benchmark/inference_datasets/ s3://openproblems-data/resources/grn/inference_datasets/ --delete"
+    "# !aws s3 sync  resources/grn_benchmark/inference_data/ s3://openproblems-data/resources/grn/inference_data/ --delete"
    ]
   },
   {
@@ -199,7 +232,7 @@
     "!aws s3 sync  s3://openproblems-data/resources/grn/ resources/ --delete\n",
     "# aws s3 sync s3://openproblems-data/resources/grn/results  resources/results/ --delete\n",
     "# aws s3 sync  s3://openproblems-data/resources/grn/grn_models resources/grn_models/\n",
-    "# aws s3 sync  s3://openproblems-data/resources/grn/inference_datasets/ resources/grn_benchmark/inference_datasets/\n",
+    "# aws s3 sync  s3://openproblems-data/resources/grn/inference_data/ resources/grn_benchmark/inference_data/\n",
     "# aws s3 sync  s3://openproblems-data/resources/grn/evaluation_data/ resources/grn_benchmark/evaluation_data//"
    ]
   },
@@ -210,7 +243,7 @@
    "outputs": [],
    "source": [
     "# !aws s3 sync resources_test/ s3://openproblems-data/resources_test/grn/ --delete\n",
-    "# !aws s3 sync resources/grn_benchmark/inference_datasets/ s3://openproblems-data/resources/grn/inference_datasets/ --delete"
+    "# !aws s3 sync resources/grn_benchmark/inference_data/ s3://openproblems-data/resources/grn/inference_data/ --delete"
    ]
   },
   {
@@ -222,7 +255,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -257,14 +290,26 @@
     "    'scores_dir': 'resources/scores'\n",
     "}\n",
     "\n",
-    "datasets = ['op', 'replogle', 'nakatake', 'norman', 'adamson']"
+    "datasets = ['op', 'replogle2', 'nakatake', 'norman', 'adamson']"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 3,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "ename": "NameError",
+     "evalue": "name 'datasets' is not defined",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[3], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m dataset \u001b[38;5;129;01min\u001b[39;00m \u001b[43mdatasets\u001b[49m:\n\u001b[1;32m      2\u001b[0m     \u001b[38;5;28;01mfor\u001b[39;00m method \u001b[38;5;129;01min\u001b[39;00m par[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mmethods\u001b[39m\u001b[38;5;124m'\u001b[39m]:\n\u001b[1;32m      3\u001b[0m         file_name \u001b[38;5;241m=\u001b[39m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mresources/grn_models/\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mdataset\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m/\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mmethod\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m.csv\u001b[39m\u001b[38;5;124m'\u001b[39m\n",
+      "\u001b[0;31mNameError\u001b[0m: name 'datasets' is not defined"
+     ]
+    }
+   ],
    "source": [
     "for dataset in datasets:\n",
     "    for method in par['methods']:\n",
@@ -278,46 +323,33 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 2,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/home/jnourisa/miniconda3/envs/py10/lib/python3.10/site-packages/anndata/_core/aligned_df.py:68: ImplicitModificationWarning: Transforming to str index.\n",
-      "  warnings.warn(\"Transforming to str index.\", ImplicitModificationWarning)\n",
-      "/home/jnourisa/miniconda3/envs/py10/lib/python3.10/site-packages/anndata/_core/aligned_df.py:68: ImplicitModificationWarning: Transforming to str index.\n",
-      "  warnings.warn(\"Transforming to str index.\", ImplicitModificationWarning)\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "import anndata as ad\n",
-    "adata = ad.read_h5ad('output/score_op_scprint.h5ad')"
+    "adata = ad.read_h5ad('K562_gwps_raw_singlecell.h5ad', backed='r')"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [
     {
-     "data": {
-      "text/plain": [
-       "{'dataset_id': 'op',\n",
-       " 'method_id': 'reg2-scprint',\n",
-       " 'metric_ids': array(['reg2-theta-0.0', 'reg2-theta-0.5', 'reg2-theta-1.0'], dtype=object),\n",
-       " 'metric_values': array([0.23660427, 0.28158203, 0.31389769])}"
-      ]
-     },
-     "execution_count": 5,
-     "metadata": {},
-     "output_type": "execute_result"
+     "ename": "NameError",
+     "evalue": "name 'adata' is not defined",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[1], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43madata\u001b[49m\u001b[38;5;241m.\u001b[39mobs\n",
+      "\u001b[0;31mNameError\u001b[0m: name 'adata' is not defined"
+     ]
     }
    ],
    "source": [
-    "adata.uns"
+    "adata.obs"
    ]
   },
   {
@@ -1069,7 +1101,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "### replogle"
+    "### replogle2"
    ]
   },
   {
@@ -1287,7 +1319,7 @@
     }
    ],
    "source": [
-    "df_scores = pd.read_csv(f\"resources/scores/replogle/50000-skeleton_False-binarize_True-ridge.csv\", index_col=0)\n",
+    "df_scores = pd.read_csv(f\"resources/scores/replogle2/50000-skeleton_False-binarize_True-ridge.csv\", index_col=0)\n",
     "# df_scores[df_scores<0] = 0\n",
     "\n",
     "df_scores_f = df_scores[['static-theta-0.0', 'static-theta-0.5', 'static-theta-1.0']]\n",
@@ -3831,7 +3863,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "base",
+   "display_name": "py10",
    "language": "python",
    "name": "python3"
   },
@@ -3845,7 +3877,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.15"
+   "version": "3.10.14"
   }
  },
  "nbformat": 4,
diff --git a/scripts/add_a_method.sh b/scripts/add_a_method.sh
index e697fbf71..209e1e9a6 100644
--- a/scripts/add_a_method.sh
+++ b/scripts/add_a_method.sh
@@ -27,7 +27,7 @@ viash run src/methods/$method_id/config.vsh.yaml -- \
 
 # run the inference using the method for op dataset using only RNA data. Add more aurguments if needed.
 viash run src/methods/$method_id/config.vsh.yaml -- \
-  --rna "resources/grn_benchmark/inference_datasets/op_rna.h5ad" \
+  --rna "resources/grn_benchmark/inference_data/op_rna.h5ad" \
   --prediction "output/prediction.h5ad"
 
 # run evaluation metrics
diff --git a/scripts/download_resources.sh b/scripts/download_resources.sh
index 9bf81a885..0fe90771e 100755
--- a/scripts/download_resources.sh
+++ b/scripts/download_resources.sh
@@ -4,4 +4,4 @@ set -e
 
 # common/scripts/sync_resources
 
-aws s3 sync  s3://openproblems-data/resources/grn/grn_benchmark resources/grn_benchmark --delete --no-sign-request
\ No newline at end of file
+aws s3 sync  s3://openproblems-data/resources/grn/grn_benchmark resources/grn_benchmark --delete --no-sign-request
diff --git a/scripts/run_benchmark_all.sh b/scripts/run_benchmark_all.sh
index 01b96b479..4bab0fff5 100644
--- a/scripts/run_benchmark_all.sh
+++ b/scripts/run_benchmark_all.sh
@@ -22,8 +22,8 @@ param_list:
     metric_ids: $metric_ids
     method_ids: $method_ids
     evaluation_data: ${resources_dir}/evaluation_data/${dataset}.h5ad
-    rna: ${resources_dir}/inference_datasets/${dataset}_rna.h5ad
-    atac: ${resources_dir}/inference_datasets/${dataset}_atac.h5ad
+    rna: ${resources_dir}/inference_data/${dataset}_rna.h5ad
+    atac: ${resources_dir}/inference_data/${dataset}_atac.h5ad
     reg_type: $reg_type
     subsample: $subsample
     num_workers: $num_workers
diff --git a/scripts/run_grn_evaluation.sh b/scripts/run_grn_evaluation.sh
index 3032d7a58..ed3d918f3 100644
--- a/scripts/run_grn_evaluation.sh
+++ b/scripts/run_grn_evaluation.sh
@@ -57,15 +57,16 @@ append_entry() {
   cat >> $param_file << HERE
   - id: ${reg_type}_${1}
     metric_ids: ${metric_ids}
-    evaluation_data: ${resources_dir}/evaluation_data/${dataset}.h5ad
-    evaluation_data_sc: ${resources_dir}/evaluation_data/${dataset}_sc_counts.h5ad
+    evaluation_data: ${resources_dir}/grn_benchmark/evaluation_data/${dataset}.h5ad
+    evaluation_data_sc: ${resources_dir}/grn_benchmark/evaluation_data/${dataset}_sc.h5ad
     reg_type: $reg_type
     method_id: $1
+    dataset_id: $dataset
     num_workers: $num_workers
-    tf_all: ${resources_dir}/prior/tf_all.csv
-    regulators_consensus: ${resources_dir}/prior/regulators_consensus_${dataset}.json
-    ws_consensus: ${resources_dir}/prior/ws_consensus_${dataset}.json
-    ws_distance_background: ${resources_dir}/prior/ws_distance_background_${dataset}.json
+    tf_all: ${resources_dir}/grn_benchmark/prior/tf_all.csv
+    regulators_consensus: ${resources_dir}/grn_benchmark/prior/regulators_consensus_${dataset}.json
+    ws_consensus: ${resources_dir}/grn_benchmark/prior/ws_consensus_${dataset}.csv
+    ws_distance_background: ${resources_dir}/grn_benchmark/prior/ws_distance_background_${dataset}.csv
     prediction: ${grn_models_folder}/${dataset}/$1.h5ad
     layer: "X_norm"
 HERE
diff --git a/src/api/file_atac_h5ad.yaml b/src/api/file_atac_h5ad.yaml
index e0a4aefd0..21f34423c 100644
--- a/src/api/file_atac_h5ad.yaml
+++ b/src/api/file_atac_h5ad.yaml
@@ -1,5 +1,5 @@
 type: file
-example: resources_test/grn_benchmark/inference_datasets//op_atac.h5ad
+example: resources_test/grn_benchmark/inference_data//op_atac.h5ad
 label:  chromatin accessibility data
 summary: "Chromatin accessibility data"
 info:
diff --git a/src/api/file_rna_h5ad.yaml b/src/api/file_rna_h5ad.yaml
index 74e981370..9be9167ac 100644
--- a/src/api/file_rna_h5ad.yaml
+++ b/src/api/file_rna_h5ad.yaml
@@ -1,5 +1,5 @@
 type: file
-example: resources_test/grn_benchmark/inference_datasets/op_rna.h5ad
+example: resources_test/grn_benchmark/inference_data/op_rna.h5ad
 label: gene expression data
 summary: "RNA expression data."
 info:
diff --git a/src/helper.py b/src/helper.py
index 6dc454835..7056439c4 100644
--- a/src/helper.py
+++ b/src/helper.py
@@ -40,7 +40,7 @@ def analyse_meta_cells(task_grn_inference_dir):
 
 
     par = {
-        'rna': f'{task_grn_inference_dir}/resources/grn_benchmark/inference_datasets/{dataset}_rna.h5ad',
+        'rna': f'{task_grn_inference_dir}/resources/grn_benchmark/inference_data/{dataset}_rna.h5ad',
         "evaluation_data": f"{task_grn_inference_dir}/resources/grn_benchmark/evaluation_data//{dataset}.h5ad",
 
         'layer': 'X_norm',
@@ -123,7 +123,7 @@ def analyse_imputation(task_grn_inference_dir):
 
 
     par = {
-        'rna': f'{task_grn_inference_dir}/resources/grn_benchmark/inference_datasets/{dataset}_rna.h5ad',
+        'rna': f'{task_grn_inference_dir}/resources/grn_benchmark/inference_data/{dataset}_rna.h5ad',
         "evaluation_data": f"{task_grn_inference_dir}/resources/grn_benchmark/evaluation_data//{dataset}.h5ad",
 
         'layer': 'X_norm',
@@ -204,7 +204,7 @@ def analyse_imputation(task_grn_inference_dir):
 def analyse_corr_vs_tfmasked_corr(task_grn_inference_dir):
     for i_run, dataset in enumerate(['op', 'replogle', 'nakatake', 'norman', 'adamson']):
         par = {
-            'rna': f'{task_grn_inference_dir}/resources/grn_benchmark/inference_datasets/{dataset}_rna.h5ad',
+            'rna': f'{task_grn_inference_dir}/resources/grn_benchmark/inference_data/{dataset}_rna.h5ad',
             "evaluation_data": f"{task_grn_inference_dir}/resources/grn_benchmark/evaluation_data//{dataset}.h5ad",
 
             'layer': 'X_norm',
diff --git a/src/methods/multi_omics/celloracle/script.py b/src/methods/multi_omics/celloracle/script.py
index 0ca2676b8..6b0ccdbf3 100644
--- a/src/methods/multi_omics/celloracle/script.py
+++ b/src/methods/multi_omics/celloracle/script.py
@@ -6,8 +6,8 @@
 
 ## VIASH START
 par = {
-  "rna": "resources/grn_benchmark/inference_datasets/op_rna.h5ad",
-  "atac": "resources/grn_benchmark/inference_datasets/op_atac.h5ad",
+  "rna": "resources/grn_benchmark/inference_data/op_rna.h5ad",
+  "atac": "resources/grn_benchmark/inference_data/op_atac.h5ad",
   "base_grn": 'output/celloracle/base_grn.csv',
   "temp_dir": 'output/celloracle/',
   "num_workers": 10,
diff --git a/src/methods/single_omics/scgpt/run.sh b/src/methods/single_omics/scgpt/run.sh
index 7b409ad1f..b833dd98c 100644
--- a/src/methods/single_omics/scgpt/run.sh
+++ b/src/methods/single_omics/scgpt/run.sh
@@ -1,4 +1,4 @@
 viash run src/methods/single_omics/scgpt/config.vsh.yaml -- \
-    --rna resources_test/grn_benchmark/inference_datasets//op_rna.h5ad \
+    --rna resources_test/grn_benchmark/inference_data//op_rna.h5ad \
     --tf_all resources/grn_benchmark/prior/tf_all.csv \
     --prediction output/prediction.h5ad
\ No newline at end of file
diff --git a/src/methods/single_omics/scprint/run.sh b/src/methods/single_omics/scprint/run.sh
index e8988169d..31c97b8a1 100644
--- a/src/methods/single_omics/scprint/run.sh
+++ b/src/methods/single_omics/scprint/run.sh
@@ -13,13 +13,13 @@
 
 
 # viash run src/methods/single_omics/scprint/config.vsh.yaml -- \
-#     --rna resources_test/grn_benchmark/inference_datasets//op_rna.h5ad \
+#     --rna resources_test/grn_benchmark/inference_data//op_rna.h5ad \
 #     --tf_all resources/grn_benchmark/prior/tf_all.csv \
 #     --prediction output/prediction.h5ad
 
 
 # python src/methods/single_omics/scprint/script.py  \
-#     --rna resources/grn_benchmark/inference_datasets/op_rna.h5ad \
+#     --rna resources/grn_benchmark/inference_data/op_rna.h5ad \
 #     --tf_all resources/grn_benchmark/prior/tf_all.csv \
 #     --prediction output/prediction.h5ad
 
diff --git a/src/methods/single_omics/scprint/script.py b/src/methods/single_omics/scprint/script.py
index 6ff098cf1..4b791612e 100644
--- a/src/methods/single_omics/scprint/script.py
+++ b/src/methods/single_omics/scprint/script.py
@@ -28,7 +28,7 @@
 
 ## VIASH START
 par = {
-    'rna': 'resources/grn_benchmark/inference_datasets/op_rna.h5ad',
+    'rna': 'resources/grn_benchmark/inference_data/op_rna.h5ad',
     'tf_all': 'resources/grn_benchmark/prior/tf_all.csv',
     'prediction': 'output/grn.h5ad',
     'filtration': 'top-k',
diff --git a/src/process_data/explanatory_analysis/peak_annotation/script.R b/src/process_data/explanatory_analysis/peak_annotation/script.R
index e3cda8e0f..bed2e4dac 100644
--- a/src/process_data/explanatory_analysis/peak_annotation/script.R
+++ b/src/process_data/explanatory_analysis/peak_annotation/script.R
@@ -11,7 +11,7 @@ library(tibble)
 
 ## VIASH START
 par <- list(
-  multiomics_atac = "resources/grn_benchmark/inference_datasets/op_atac.h5ad",
+  multiomics_atac = "resources/grn_benchmark/inference_data/op_atac.h5ad",
   annot_peak_database = "resources/grn_benchmark/prior/peak_annotation.csv"
 )
 ## VIASH END
diff --git a/src/process_data/op_multiomics/format_data/script.py b/src/process_data/op_multiomics/format_data/script.py
index 7031a712d..a644f5705 100644
--- a/src/process_data/op_multiomics/format_data/script.py
+++ b/src/process_data/op_multiomics/format_data/script.py
@@ -4,8 +4,8 @@
 ## VIASH START
 par = {
     'multiome_counts': 'resources/datasets_raw/op_multiome_sc_counts.h5ad',
-    'multiomics_rna': 'resources/grn_benchmark/inference_datasets/op_rna.h5ad',
-    'multiomics_atac': 'resources/grn_benchmark/inference_datasets/op_atac.h5ad'
+    'multiomics_rna': 'resources/grn_benchmark/inference_data/op_rna.h5ad',
+    'multiomics_atac': 'resources/grn_benchmark/inference_data/op_atac.h5ad'
 }
 ## VIASH END
 
diff --git a/src/process_data/pereggrn/script.py b/src/process_data/pereggrn/script.py
index bb2c109ce..740cea933 100644
--- a/src/process_data/pereggrn/script.py
+++ b/src/process_data/pereggrn/script.py
@@ -105,7 +105,7 @@ def process_dataset(file_name):
         adata.write(f'resources/grn_benchmark/evaluation_data/{file_name}_sc.h5ad')
 
     adata_bulked.write(f'resources/extended_data/{file_name}_bulk.h5ad')
-    adata_train.write(f'resources/grn_benchmark/inference_datasets/{file_name}_rna.h5ad')
+    adata_train.write(f'resources/grn_benchmark/inference_data/{file_name}_rna.h5ad')
     adata_test.write(f'resources/grn_benchmark/evaluation_data/{file_name}_bulk.h5ad')
     
 
diff --git a/src/process_data/replogle_k562_gwps/run.sh b/src/process_data/replogle_k562_gwps/run.sh
index 4364003a3..8790f731f 100644
--- a/src/process_data/replogle_k562_gwps/run.sh
+++ b/src/process_data/replogle_k562_gwps/run.sh
@@ -18,5 +18,5 @@ python src/process_data/replogle_k562_gwps/script.py \
         --adata_bulk resources/extended_data/replogle_bulk.h5ad \
         --adata_test_sc resources/grn_benchmark/evaluation_data/replogle_sc.h5ad \
         --adata_test_bulk resources/grn_benchmark/evaluation_data/replogle_bulk.h5ad \
-        --adata_train_bulk resources/grn_benchmark/inference_datasets/replogle_rna.h5ad \
+        --adata_train_bulk resources/grn_benchmark/inference_data/replogle_rna.h5ad \
         --adata_train_sc resources/extended_data/replogle_train_sc.h5ad \
\ No newline at end of file
diff --git a/src/process_data/test_data/run.sh b/src/process_data/test_data/run.sh
index 0e0af2bb9..918b276df 100644
--- a/src/process_data/test_data/run.sh
+++ b/src/process_data/test_data/run.sh
@@ -1,6 +1,6 @@
 viash run src/process_data/test_data/config.novsh.yaml -- \
-    --rna resources/grn_benchmark/inference_datasets/op_rna.h5ad --rna_test resources_test/grn_benchmark/inference_datasets//op_rna.h5ad \
-    --atac resources/grn_benchmark/inference_datasets/op_atac.h5ad --atac_test resources_test/grn_benchmark/inference_datasets//op_atac.h5ad \
+    --rna resources/grn_benchmark/inference_data/op_rna.h5ad --rna_test resources_test/grn_benchmark/inference_data//op_rna.h5ad \
+    --atac resources/grn_benchmark/inference_data/op_atac.h5ad --atac_test resources_test/grn_benchmark/inference_data//op_atac.h5ad \
     --perturbation_data resources/grn_benchmark/evaluation_data/op.h5ad --perturbation_data_test resources_test/grn_benchmark/evaluation_data/op.h5ad \
     --multiomics_counts resources/grn_benchmark/datasets_raw/op_multiome_sc_counts.h5ad --multiomics_counts_test resources_test/grn_benchmark/datasets_raw/op_multiome_sc_counts.h5ad \
     # --perturbation_counts resources/datasets_raw/op_perturbation_sc_counts.h5ad --perturbation_counts_test resources_test/datasets_raw/op_perturbation_sc_counts.h5ad \
diff --git a/src/process_data/test_data/script.py b/src/process_data/test_data/script.py
index 6588565bd..83b915a97 100644
--- a/src/process_data/test_data/script.py
+++ b/src/process_data/test_data/script.py
@@ -12,11 +12,11 @@
 ## VIASH START
 
 par = {
-    'rna': 'resources/grn_benchmark/inference_datasets/op_rna.h5ad',
-    'rna_test': 'resources_test/grn_benchmark/inference_datasets//op_rna.h5ad',
+    'rna': 'resources/grn_benchmark/inference_data/op_rna.h5ad',
+    'rna_test': 'resources_test/grn_benchmark/inference_data//op_rna.h5ad',
 
-    'atac': 'resources/grn_benchmark/inference_datasets/op_atac.h5ad',
-    'atac_test': 'resources_test/grn_benchmark/inference_datasets//op_atac.h5ad',
+    'atac': 'resources/grn_benchmark/inference_data/op_atac.h5ad',
+    'atac_test': 'resources_test/grn_benchmark/inference_data//op_atac.h5ad',
 
     'perturbation_data': 'resources/grn_benchmark/evaluation_data//op.h5ad',
     'perturbation_data_test': 'resources_test/grn_benchmark/evaluation_data//op.h5ad',
diff --git a/src/workflows/run_grn_evaluation/config.vsh.yaml b/src/workflows/run_grn_evaluation/config.vsh.yaml
index fca0a232b..a504673ed 100644
--- a/src/workflows/run_grn_evaluation/config.vsh.yaml
+++ b/src/workflows/run_grn_evaluation/config.vsh.yaml
@@ -25,6 +25,10 @@ argument_groups:
         type: string
         required: true
         direction: input
+      - name: --dataset_id
+        type: string
+        required: true
+        direction: input
       - name: --tf_all
         type: file
         direction: input
diff --git a/src/workflows/run_grn_evaluation/main.nf b/src/workflows/run_grn_evaluation/main.nf
index 164a9bb3c..ac3551587 100644
--- a/src/workflows/run_grn_evaluation/main.nf
+++ b/src/workflows/run_grn_evaluation/main.nf
@@ -39,11 +39,13 @@ workflow run_wf {
       // use 'fromState' to fetch the arguments the component requires from the overall state
       fromState: [
         evaluation_data: "evaluation_data",
+        evaluation_data_sc: "evaluation_data_sc",
         prediction: "prediction",
         ws_distance_background: "ws_distance_background",
         subsample: "subsample",
         reg_type: "reg_type",
         method_id: "method_id",
+        dataset_id: "method_id",
         num_workers: "num_workers",
         regulators_consensus: "regulators_consensus",
         ws_consensus: "ws_consensus",
diff --git a/src/workflows_local/benchmark/methods/script.py b/src/workflows_local/benchmark/methods/script.py
index 9c32eb2ff..eb630ba9b 100644
--- a/src/workflows_local/benchmark/methods/script.py
+++ b/src/workflows_local/benchmark/methods/script.py
@@ -20,8 +20,8 @@
 def run_grn_inference(par, dataset='op', subsample=None):
     par_local = {
         'models_dir': f'resources/grn_models/{dataset}/',
-        'rna': f'resources/grn_benchmark/inference_datasets/{dataset}_rna.h5ad',
-        'atac': f'resources/grn_benchmark/inference_datasets/{dataset}_atac.h5ad', 
+        'rna': f'resources/grn_benchmark/inference_data/{dataset}_rna.h5ad',
+        'atac': f'resources/grn_benchmark/inference_data/{dataset}_atac.h5ad', 
         'rna_positive_control': f'resources/datasets_raw/{dataset}.h5ad', 
         'num_workers': 10,
         'tmp_dir': 'output/grn_inference'
diff --git a/test.ipynb b/test.ipynb
index 63c2aa963..af308d81a 100644
--- a/test.ipynb
+++ b/test.ipynb
@@ -50,7 +50,7 @@
     }
    ],
    "source": [
-    "adata = ad.read_h5ad('resources/grn_benchmark/inference_datasets/replogle_rna.h5ad')\n",
+    "adata = ad.read_h5ad('resources/grn_benchmark/inference_data/replogle_rna.h5ad')\n",
     "adata[adata.obs['is_control']]"
    ]
   }