test run

openproblems-bio · Nov 26, 2024 · b1a4b0c · b1a4b0c
1 parent 94c79b7
commit b1a4b0c
Show file tree

Hide file tree

Showing 3 changed files with 53 additions and 25 deletions.
diff --git a/runs.ipynb b/runs.ipynb
@@ -26,11 +26,23 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 7,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "upload: resources_test/datasets_raw/op_perturbation_sc_counts.h5ad to s3://openproblems-data/resources_test/grn/datasets_raw/op_perturbation_sc_counts.h5ad\n",
+      "upload: resources_test/datasets_raw/op_multiome_sc_counts.h5ad to s3://openproblems-data/resources_test/grn/datasets_raw/op_multiome_sc_counts.h5ad\n",
+      "upload: resources_test/inference_datasets/op_rna.h5ad to s3://openproblems-data/resources_test/grn/inference_datasets/op_rna.h5ad\n",
+      "upload: resources_test/evaluation_datasets/op_perturbation.h5ad to s3://openproblems-data/resources_test/grn/evaluation_datasets/op_perturbation.h5ad\n",
+      "upload: resources_test/inference_datasets/op_atac.h5ad to s3://openproblems-data/resources_test/grn/inference_datasets/op_atac.h5ad\n"
+     ]
+    }
+   ],
    "source": [
-    "# !aws s3 sync resources_test/ s3://openproblems-data/resources_test/grn/ --delete\n",
+    "!aws s3 sync resources_test/ s3://openproblems-data/resources_test/grn/ --delete\n",
     "# !aws s3 sync resources/ s3://openproblems-data/resources/grn/ --delete"
    ]
   },
@@ -43,7 +55,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -81,11 +93,25 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AnnData object with n_obs × n_vars = 25551 × 22787\n",
+       "    obs: 'cell_type', 'donor_id'\n",
+       "    var: 'gene_ids', 'interval'\n",
+       "    layers: 'X_norm', 'counts'"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
-    "ad.read('resources/')"
+    "ad.read('resources/inference_datasets/op_rna.h5ad')"
    ]
   },
   {
@@ -144,14 +170,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Submitted batch job 7845525\n"
+      "Submitted batch job 7849254\n"
      ]
     }
    ],
@@ -195,7 +221,7 @@
     }
    ],
    "source": [
-    "!ls output/temp/op/"
+    "!ls resources/scores/op/"
    ]
   },
   {
@@ -578,7 +604,7 @@
     }
    ],
    "source": [
-    "df_scores = pd.read_csv(f\"output/temp/op/50000-skeleton_False-binarize_True-ridge.csv\", index_col=0)\n",
+    "df_scores = pd.read_csv(f\"resources/scores/op/50000-skeleton_False-binarize_True-ridge.csv\", index_col=0)\n",
     "# df_scores[df_scores<0] = 0\n",
     "df_all_n = (df_scores-df_scores.min(axis=0))/(df_scores.max(axis=0)-df_scores.min(axis=0))\n",
     "df_scores['rank'] = df_all_n.mean(axis=1).rank(ascending=False).astype(int)\n",
@@ -935,7 +961,7 @@
     }
    ],
    "source": [
-    "df_scores = pd.read_csv(f\"output/temp/op/50000-skeleton_False-binarize_True-GB.csv\", index_col=0)\n",
+    "df_scores = pd.read_csv(f\"resources/scores/op/50000-skeleton_False-binarize_True-GB.csv\", index_col=0)\n",
     "# df_scores[df_scores<0] = 0\n",
     "df_all_n = (df_scores-df_scores.min(axis=0))/(df_scores.max(axis=0)-df_scores.min(axis=0))\n",
     "df_scores['rank'] = df_all_n.mean(axis=1).rank(ascending=False).astype(int)\n",
@@ -1164,7 +1190,7 @@
     }
    ],
    "source": [
-    "df_scores = pd.read_csv(f\"output/temp/replogle2/50000-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",
@@ -1403,7 +1429,7 @@
     }
    ],
    "source": [
-    "df_scores = pd.read_csv(f\"output/temp/nakatake/50000-skeleton_False-binarize_True-ridge.csv\", index_col=0)\n",
+    "df_scores = pd.read_csv(f\"resources/scores/nakatake/50000-skeleton_False-binarize_True-ridge.csv\", index_col=0)\n",
     "# df_scores[df_scores<0] = 0\n",
     "df_scores_f = df_scores[['static-theta-0.0', 'static-theta-0.5', 'static-theta-1.0']]\n",
     "df_all_n = (df_scores_f-df_scores_f.min(axis=0))/(df_scores_f.max(axis=0)-df_scores_f.min(axis=0))\n",
@@ -1649,7 +1675,7 @@
     }
    ],
    "source": [
-    "df_scores = pd.read_csv(f\"output/temp/norman/X_norm-50000-skeleton_False-binarize_True-ridge-global-False.csv\", index_col=0)\n",
+    "df_scores = pd.read_csv(f\"resources/scores/norman/X_norm-50000-skeleton_False-binarize_True-ridge-global-False.csv\", index_col=0)\n",
     "# df_scores[df_scores<0] = 0\n",
     "df_scores_f = df_scores[['static-theta-0.0', 'static-theta-0.5', 'static-theta-1.0']]\n",
     "df_all_n = (df_scores_f-df_scores_f.min(axis=0))/(df_scores_f.max(axis=0)-df_scores_f.min(axis=0))\n",
@@ -1684,7 +1710,7 @@
     }
    ],
    "source": [
-    "!ls output/temp/adamson/"
+    "!ls resources/scores/adamson/"
    ]
   },
   {
@@ -1884,7 +1910,7 @@
     }
    ],
    "source": [
-    "df_scores = pd.read_csv(f\"output/temp/adamson/X_norm-50000-skeleton_False-binarize_True-ridge-global-False.csv\", index_col=0)\n",
+    "df_scores = pd.read_csv(f\"resources/scores/adamson/X_norm-50000-skeleton_False-binarize_True-ridge-global-False.csv\", index_col=0)\n",
     "# df_scores[df_scores<0] = 0\n",
     "df_scores_f = df_scores[['static-theta-0.0', 'static-theta-0.5', 'static-theta-1.0']]\n",
     "df_all_n = (df_scores_f-df_scores_f.min(axis=0))/(df_scores_f.max(axis=0)-df_scores_f.min(axis=0))\n",
@@ -1930,7 +1956,7 @@
     }
    ],
    "source": [
-    "!ls output/temp/op/"
+    "!ls resources/scores/op/"
    ]
   },
   {
@@ -2511,8 +2537,8 @@
     }
    ],
    "source": [
-    "df_scores_gb = pd.read_csv(f\"output/temp/op/X_norm-50000-skeleton_False-binarize_True-ridge-global-True.csv\", index_col=0)\n",
-    "df_scores = pd.read_csv(f\"output/temp/op/X_norm-50000-skeleton_False-binarize_True-ridge-global-False.csv\", index_col=0)\n",
+    "df_scores_gb = pd.read_csv(f\"resources/scores/op/X_norm-50000-skeleton_False-binarize_True-ridge-global-True.csv\", index_col=0)\n",
+    "df_scores = pd.read_csv(f\"resources/scores/op/X_norm-50000-skeleton_False-binarize_True-ridge-global-False.csv\", index_col=0)\n",
     "\n",
     "df_scores = pd.concat([df_scores, df_scores_gb])\n",
     "# df_scores[df_scores<0] = 0\n",
@@ -2580,7 +2606,7 @@
    "source": [
     "# - collect all the scores\n",
     "for i, dataset in enumerate(datasets):\n",
-    "    df_scores = pd.read_csv(f\"output/temp/{dataset}/X_norm-50000-skeleton_False-binarize_True-ridge-global-False.csv\", index_col=0)\n",
+    "    df_scores = pd.read_csv(f\"resources/scores/{dataset}/X_norm-50000-skeleton_False-binarize_True-ridge-global-False.csv\", index_col=0)\n",
     "    # - normalize scores \n",
     "    df_scores = df_scores.fillna(0)\n",
     "    df_scores[df_scores < 0] = 0\n",

diff --git a/src/metrics/script_all.py b/src/metrics/script_all.py
@@ -69,7 +69,7 @@ def define_par(dataset):
 global_models = False
 
 # - run metrics 
-for dataset in ['adamson']: #'op', 'replogle2', 'nakatake', 'norman', 'adamson'
+for dataset in ['op']: #'op', 'replogle2', 'nakatake', 'norman', 'adamson'
   print('------ ', dataset, '------')
   par = define_par(dataset)
   os.makedirs(par['scores_dir'], exist_ok=True)
@@ -78,7 +78,7 @@ def define_par(dataset):
     par['binarize'] = binarize
     for max_n_links in [50000]:
       par['max_n_links'] = max_n_links
-      for apply_skeleton in [False]:
+      for apply_skeleton in [True]:
         par['apply_skeleton'] = apply_skeleton
         # - determines models to run 
         grn_files_dict = {}

diff --git a/src/process_data/multiomics/format_data/script.py b/src/process_data/multiomics/format_data/script.py
@@ -16,8 +16,6 @@
 multiomics.X = multiomics.layers['counts']
 del multiomics.layers
 multiomics.layers['counts'] = multiomics.X.copy()
-X_norm = sc.pp.normalize_total(multiomics, inplace=False)['X']
-multiomics.layers['X_norm'] = sc.pp.log1p(X_norm, copy=True)
 
 multiomics.var.index.name='location'
 multiomics.obs.index.name='obs_id'
@@ -58,5 +56,9 @@
 multiomics_rna.obs['donor_id'] = multiomics_rna.obs['donor_id'].map(donor_map)
 multiomics_atac.obs['donor_id'] = multiomics_atac.obs['donor_id'].map(donor_map)
 
+# normalize rna 
+X_norm = sc.pp.normalize_total(multiomics_rna, inplace=False)['X']
+multiomics_rna.layers['X_norm'] = sc.pp.log1p(X_norm, copy=True)
+
 multiomics_rna.write(par['multiomics_rna'])
 multiomics_atac.write(par['multiomics_atac'])