baseline models are structured. util added

runs.ipynb

@@ -9,7 +9,28 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Collecting PyYAML\n",
+      "  Downloading PyYAML-6.0.2-cp310-cp310-macosx_11_0_arm64.whl.metadata (2.1 kB)\n",
+      "Downloading PyYAML-6.0.2-cp310-cp310-macosx_11_0_arm64.whl (171 kB)\n",
+      "Installing collected packages: PyYAML\n",
+      "Successfully installed PyYAML-6.0.2\n"
+     ]
+    }
+   ],
+   "source": [
+    "!pip install PyYAML"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -110,9 +131,24 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AnnData object with n_obs × n_vars = 8133 × 22787\n",
+       "    obs: 'cell_type', 'donor_id'\n",
+       "    var: 'gene_ids', 'interval', 'mean', 'std'\n",
+       "    uns: 'log1p'\n",
+       "    layers: 'lognorm'"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": []
   },
   {
@@ -126,7 +162,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "### Baseline scores on donor 0. Normalized, non cell type specific"
+    "### Baseline scores on donor 0. Normalized, non cell type specific, full "
    ]
   },
   {
@@ -357,6 +393,57 @@
     "!aws s3 sync resources/grn-benchmark s3://openproblems-data/resources/grn/grn-benchmark --delete"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "delete: resources/grn-benchmark/multiomics_rna_qc.h5ad\n",
+      "download: s3://openproblems-data/resources/grn/grn-benchmark/multiomics_rna.h5ad to resources/grn-benchmark/multiomics_rna.h5ad\n",
+      "download: s3://openproblems-data/resources/grn/grn-benchmark/multiomics_rna_0.h5ad to resources/grn-benchmark/multiomics_rna_0.h5ad\n"
+     ]
+    }
+   ],
+   "source": [
+    "!aws s3 sync  s3://openproblems-data/resources/grn/grn-benchmark resources/grn-benchmark --delete"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# To be categorized"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "if par['metacell']:\n",
+    "    print('metacell')\n",
+    "    def create_meta_cells(df, n_cells=15):\n",
+    "        meta_x = []\n",
+    "        for i in range(0, df.shape[0], n_cells):\n",
+    "            meta_x.append(df.iloc[i:i+n_cells, :].sum(axis=0).values)\n",
+    "        df = pd.DataFrame(meta_x, columns=df.columns)\n",
+    "        return df\n",
+    "            \n",
+    "    adata_df = pd.DataFrame(multiomics_rna.X.todense(), columns=multiomics_rna.var_names)\n",
+    "    adata_df['cell_type'] = multiomics_rna.obs['cell_type'].values\n",
+    "    adata_df['donor_id'] = multiomics_rna.obs['donor_id'].values\n",
+    "    df = adata_df.groupby(['cell_type','donor_id']).apply(lambda df: create_meta_cells(df))\n",
+    "    X = df.values\n",
+    "    var = pd.DataFrame(index=df.columns)\n",
+    "    obs = df.reset_index()[['cell_type','donor_id']]\n",
+    "    multiomics_rna = ad.AnnData(X=X, obs=obs, var=var)"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},

src/api/comp_method.yaml

@@ -58,11 +58,8 @@ functionality:
       default: false
       description: subset rna seq data to only 7000 hvgs to reduce dimensionality
 
-
-
-
   resources:
-    - path: ../utils/util.py
+    - path: /src/utils/util.py
 
   test_resources:
     - type: python_script

src/control_methods/pearson/script.py

@@ -1,18 +1,8 @@
-import os
-import pandas as pd
-import numpy as np
-import anndata as ad
-import scanpy as sc
-from tqdm import tqdm
-from scipy.stats import spearmanr
-from sklearn.preprocessing import StandardScaler
-from utils.util import process_data, create_corr_net
 
 ## VIASH START
 par = {
     'multiomics_rna': 'resources/grn-benchmark/multiomics_rna_0.h5ad',
     'tf_all': 'resources/prior/tf_all.csv',
-    'causal': False,
     'cell_type_specific': True,
     'max_n_links': 50000,
     'prediction': 'resources/grn_models/donor_0_default/pearson.csv',
@@ -22,20 +12,11 @@
 }
 ## VIASH END
 print(par)
+import sys
+sys.path.append('./src/utils')
+from util import create_corr_net
 
-print('Read data')
-multiomics_rna = ad.read_h5ad(par["multiomics_rna"])
-process_data(multiomics_rna)
-
-gene_names = multiomics_rna.var_names.to_numpy()
-tf_all = np.loadtxt(par['tf_all'], dtype=str)
-groups = multiomics_rna.obs.cell_type
-tf_all = np.intersect1d(tf_all, gene_names)
-n_tfs = len(tf_all)
-
-
-print('Create corr net')
-net = create_corr_net(multiomics_rna.X, multiomics_rna.var_names, groups, par, tf_all=None)
-
+par['causal'] = False
+net = create_corr_net(par)
 print('Output GRN')
 net.to_csv(par['prediction'])

src/control_methods/pearson/test.sh

@@ -1,5 +1,4 @@
-viash run src/control_methods/baseline_corr/config.vsh.yaml -- \
+viash run src/control_methods/pearson/config.vsh.yaml -- \
   --prediction output/baseline_corr.csv \
   --multiomics_rna resources/grn-benchmark/multiomics_rna.h5ad \
-  --tf_all resources/prior/tf_all.csv \
-  --causal true
+  --tf_all resources/prior/tf_all.csv