add node_group_dict back to the vis module; revert the example in the…

… doc website
TuftsBCB · May 11, 2024 · 25b57c6 · 25b57c6
1 parent 44b2c56
commit 25b57c6
Show file tree

Hide file tree

Showing 4 changed files with 39 additions and 111 deletions.
diff --git a/docs/quick_tour.md b/docs/quick_tour.md
@@ -162,11 +162,9 @@ You can also apply the clustering information to your visual.
 
 ```python
 >>> gene_group_dict = dict()
->>> gene_group_dict = {g:[
->>>     'red', 'blue', 'yellow', 'green'
->>> ][c] for g, c in zip(nxg.nodes(), node_labels)}
+>>> gene_group_dict = {g:str(c) for g, c in zip(nxg.nodes(), node_labels)}
 >>> g = grn.visualize_local_neighborhood(
->>>     'HIST1H1D', k=40, node_color_dict=gene_group_dict
+>>>     'HIST1H1D', k=40, node_group_dict=gene_group_dict
 >>>     )
 >>> g.show('view.html')
 ```

diff --git a/example.ipynb b/example.ipynb
@@ -132,15 +132,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 3,
    "id": "bc3a63a5-b5dc-4ec3-82b6-b8cb2dd341b1",
    "metadata": {},
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "Training loss: 0.233, Change on Adj: -0.000: 100%|███████████████████████████████████████████████████████████████| 1000/1000 [00:06<00:00, 149.83it/s]\n"
+      "Training loss: 0.208, Change on Adj: -0.000: 100%|████████████████████████████████████████████████████████| 1000/1000 [00:07<00:00, 131.75it/s]\n"
      ]
     }
    ],
@@ -161,21 +161,21 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 4,
    "id": "31bd6acc-bf8f-4e67-a0e7-fdc85ed1abde",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "{'AUROC': 0.6132166098363903,\n",
-       " 'AUPR': 0.05205800776865746,\n",
-       " 'AUPRR': 2.447880617451527,\n",
-       " 'EP': 748,\n",
-       " 'EPR': 4.148199666781842}"
+       "{'AUROC': 0.6121613001722375,\n",
+       " 'AUPR': 0.05236067534187729,\n",
+       " 'AUPRR': 2.462112704267227,\n",
+       " 'EP': 761,\n",
+       " 'EPR': 4.220294046017355}"
       ]
      },
-     "execution_count": 21,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -198,7 +198,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 4,
    "id": "52ea6e49-9f2e-4662-914d-c6f5c9d92a85",
    "metadata": {},
    "outputs": [
@@ -208,7 +208,7 @@
        "Inferred GRN: 1,620 TFs x 1,620 Target Genes"
       ]
      },
-     "execution_count": 22,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -280,7 +280,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 7,
    "id": "1d5bac96-23f4-4aa8-87b9-f5ecd6362e60",
    "metadata": {},
    "outputs": [
@@ -290,7 +290,7 @@
        "'HIST1H1D'"
       ]
      },
-     "execution_count": 23,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -311,7 +311,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 5,
    "id": "6c64e64a-9d05-41b2-ad8e-611347dcc074",
    "metadata": {},
    "outputs": [
@@ -337,10 +337,10 @@
        "        "
       ],
       "text/plain": [
-       "<IPython.lib.display.IFrame at 0x2afeaaa89a50>"
+       "<IPython.lib.display.IFrame at 0x2b4caf056150>"
       ]
      },
-     "execution_count": 24,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -360,7 +360,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": 6,
    "id": "48469757-7d04-4daf-88ea-b3ff34000190",
    "metadata": {},
    "outputs": [
@@ -370,11 +370,11 @@
      "text": [
       "/cluster/tufts/slonimlab/hzhu07/miniconda3/envs/grn/lib/python3.11/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
       "  from .autonotebook import tqdm as notebook_tqdm\n",
-      "Computing transition probabilities: 100%|███████████████████████████████████████████████████████████████████████████| 52/52 [00:00<00:00, 1973.90it/s]\n",
-      "Generating walks (CPU: 3): 100%|█████████████████████████████████████████████████████████████████████████████████████| 50/50 [00:00<00:00, 172.69it/s]\n",
-      "Generating walks (CPU: 1): 100%|█████████████████████████████████████████████████████████████████████████████████████| 50/50 [00:00<00:00, 172.33it/s]\n",
-      "Generating walks (CPU: 2): 100%|█████████████████████████████████████████████████████████████████████████████████████| 50/50 [00:00<00:00, 170.24it/s]\n",
-      "Generating walks (CPU: 4): 100%|█████████████████████████████████████████████████████████████████████████████████████| 50/50 [00:00<00:00, 169.11it/s]\n",
+      "Computing transition probabilities: 100%|████████████████████████████████████████████████████████████████████| 49/49 [00:00<00:00, 2035.81it/s]\n",
+      "Generating walks (CPU: 2): 100%|██████████████████████████████████████████████████████████████████████████████| 50/50 [00:00<00:00, 201.35it/s]\n",
+      "Generating walks (CPU: 4): 100%|██████████████████████████████████████████████████████████████████████████████| 50/50 [00:00<00:00, 206.38it/s]\n",
+      "Generating walks (CPU: 1): 100%|██████████████████████████████████████████████████████████████████████████████| 50/50 [00:00<00:00, 177.20it/s]\n",
+      "Generating walks (CPU: 3): 100%|██████████████████████████████████████████████████████████████████████████████| 50/50 [00:00<00:00, 155.50it/s]\n",
       "/cluster/tufts/slonimlab/hzhu07/miniconda3/envs/grn/lib/python3.11/site-packages/sklearn/cluster/_kmeans.py:1416: FutureWarning: The default value of `n_init` will change from 10 to 'auto' in 1.4. Set the value of `n_init` explicitly to suppress the warning\n",
       "  super()._check_params_vs_input(X, default_n_init=10)\n"
      ]
@@ -384,10 +384,10 @@
      "output_type": "stream",
      "text": [
       "Clusters:\n",
-      "Cluster 0: RBL1,H1F0,KAT2B\n",
-      "Cluster 1: MCM6,MCM4,RBBP4,SP1,RRM2,EZH2,MCM10,UNG,RAD51,UHRF1,E2F1,MCM3,PCNA,MCM7,BARD1,ABTB1\n",
-      "Cluster 2: GM44335,TOP2A,KPNA2,GM10184,POLR3B,FZR1,ATF4\n",
-      "Cluster 3: FBXO5,HIST1H1D,KNTC1,BRCA1,RAD54B,HIST1H2BL,HIST1H2BB,HIST1H3H,HIST1H2AC,HIST1H2BF,HIST1H1A,DNMT1,HIST1H4K,HIST1H1B,HIST1H2AK,HIST1H2BN,HIST1H2AI,HIST1H2BK,HIST1H2AG,HIST1H2AF,EGR1,GM26448,TAF1,DEK,GM9531,GM37404\n"
+      "Cluster 0: FBXO5,HIST1H1D,GM44335,KNTC1,RAD54B,BRCA1,DNMT1,HIST1H1B,HIST1H2BN,HIST1H2BK,HIST1H2BL,HIST1H2AC,HIST1H1A,HIST1H2BB,HIST1H3H,HIST1H2AK,HIST1H2AF,HIST1H2AG,HIST1H2AI,HIST1H2BF,HIST1H4K,TAF1,DEK,GM9531,ABTB1,GM26448,EGR1\n",
+      "Cluster 1: MAZ,GM37404,RBL1,STAG3\n",
+      "Cluster 2: RRM2,PCNA,MCM6,RAD51,MCM10,MCM7,UHRF1,BARD1,E2F1,MCM4,RBBP4,ZFP367,UNG,MCM3\n",
+      "Cluster 3: TOP2A,GM10184,KANK3,POLR3B\n"
      ]
     }
    ],
@@ -417,79 +417,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 28,
-   "id": "1497f58c-4619-4eaf-ace3-176a4ad858aa",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'FBXO5': '3',\n",
-       " 'HIST1H1D': '3',\n",
-       " 'KNTC1': '3',\n",
-       " 'BRCA1': '3',\n",
-       " 'GM44335': '2',\n",
-       " 'RAD54B': '3',\n",
-       " 'HIST1H2BL': '3',\n",
-       " 'HIST1H2BB': '3',\n",
-       " 'HIST1H3H': '3',\n",
-       " 'HIST1H2AC': '3',\n",
-       " 'HIST1H2BF': '3',\n",
-       " 'HIST1H1A': '3',\n",
-       " 'DNMT1': '3',\n",
-       " 'HIST1H4K': '3',\n",
-       " 'HIST1H1B': '3',\n",
-       " 'HIST1H2AK': '3',\n",
-       " 'HIST1H2BN': '3',\n",
-       " 'HIST1H2AI': '3',\n",
-       " 'HIST1H2BK': '3',\n",
-       " 'HIST1H2AG': '3',\n",
-       " 'HIST1H2AF': '3',\n",
-       " 'EGR1': '3',\n",
-       " 'GM26448': '3',\n",
-       " 'TAF1': '3',\n",
-       " 'MCM6': '1',\n",
-       " 'DEK': '3',\n",
-       " 'MCM4': '1',\n",
-       " 'RBBP4': '1',\n",
-       " 'RBL1': '0',\n",
-       " 'SP1': '1',\n",
-       " 'RRM2': '1',\n",
-       " 'EZH2': '1',\n",
-       " 'MCM10': '1',\n",
-       " 'UNG': '1',\n",
-       " 'RAD51': '1',\n",
-       " 'UHRF1': '1',\n",
-       " 'E2F1': '1',\n",
-       " 'MCM3': '1',\n",
-       " 'PCNA': '1',\n",
-       " 'MCM7': '1',\n",
-       " 'TOP2A': '2',\n",
-       " 'BARD1': '1',\n",
-       " 'H1F0': '0',\n",
-       " 'KPNA2': '2',\n",
-       " 'GM10184': '2',\n",
-       " 'POLR3B': '2',\n",
-       " 'FZR1': '2',\n",
-       " 'ATF4': '2',\n",
-       " 'GM9531': '3',\n",
-       " 'KAT2B': '0',\n",
-       " 'ABTB1': '1',\n",
-       " 'GM37404': '3'}"
-      ]
-     },
-     "execution_count": 28,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "gene_group_dict"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 29,
+   "execution_count": 7,
    "id": "a22e59ec-33a2-4560-86e0-67cc5725e4b5",
    "metadata": {},
    "outputs": [
@@ -515,21 +443,19 @@
        "        "
       ],
       "text/plain": [
-       "<IPython.lib.display.IFrame at 0x2afefb4b45d0>"
+       "<IPython.lib.display.IFrame at 0x2b4d66fb7290>"
       ]
      },
-     "execution_count": 29,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
     "gene_group_dict = dict()\n",
-    "gene_group_dict = {g:[\n",
-    "    'red', 'blue', 'yellow', 'green'\n",
-    "][c] for g, c in zip(nxg.nodes(), node_labels)}\n",
+    "gene_group_dict = {g:str(c) for g, c in zip(nxg.nodes(), node_labels)}\n",
     "g = grn.visualize_local_neighborhood(\n",
-    "    'HIST1H1D', k=40, node_color_dict=gene_group_dict\n",
+    "    'HIST1H1D', k=40, node_group_dict=gene_group_dict\n",
     "    )\n",
     "g.show('view.html')"
    ]

diff --git a/pyproject.toml b/pyproject.toml
@@ -13,7 +13,7 @@ maintainers = [
 ]
 readme = "README.md"
 license = {file = "LICENSE"}
-version = "0.0.7"
+version = "0.0.8"
 description = "Gene Regulatory Networks Inference using diffusion model"
 
 classifiers = ["License :: OSI Approved :: Apache Software License"]

diff --git a/regdiffusion/plot/pyvis.py b/regdiffusion/plot/pyvis.py
@@ -7,6 +7,7 @@ def plot_pyvis(
     node_size: int = 8, 
     font_size: int = 30,
     node_color_dict: Dict = None, 
+    node_group_dict: Dict = None,
     cdn_resources: str = 'remote', notebook: bool = True):
     """
     Generate a vis.js network visualization given an edge list 
@@ -21,6 +22,8 @@ def plot_pyvis(
         font_size (int): The font size for nodes labels.
         node_color_dict (dict): A dictionary with keys being the names of 
             genes and values being the color. 
+        node_group_dict (dict): A dictionary with keys being the names of 
+            genes and values being the group. 
         cdn_resources (str): Where to load vis.js resources. Default is
             'remote'.
         notebook (bool): Boolean value indicating whether the visualization
@@ -41,8 +44,9 @@ def plot_pyvis(
             node_shape = 'star' if node in star_genes else 'dot'
             this_node_size = 2 * node_size if node in star_genes else node_size
         node_color = None if node_color_dict is None else node_color_dict[node]
+        node_group = None if node_group_dict is None else node_group_dict[node]
         g.add_node(node, label=node, size=this_node_size, 
-                   shape=node_shape, color=node_color, 
+                   shape=node_shape, color=node_color, group=node_group,
                    font={"size": font_size})
 
     if 'edge_width' in pandas_edgelist.columns: