clustering tab working

pomegranate/app.py

@@ -7,7 +7,7 @@
 import dash
 from dash import Dash, dcc, html, Input, Output
 from tabs.seeMotif import motifVisualisationTab
-from tabs.clustering import clustering_tab
+from tabs.clustering import clustering_tab, update_graph, update_vis_1
 
 PROTEIN_ID = "default"
 

pomegranate/definitions.py

@@ -7,8 +7,19 @@
 
 SAVED_GRAPHS_DIR = os.path.join(ROOT_DIR, "graphs")
 
+SAVED_CLUSTER_GRAPHS_PATH = os.path.join(ROOT_DIR, "clustering_saved_graphs")
+
 STRUCTURE_HUMAN_PATH = os.path.join(STRUCTURE_PATH, 'human')
+STRUCTURE_YEAST_PATH = os.path.join(STRUCTURE_PATH, 'yeast')
+
+
 
 EMBEDDINGS_FILENAME = "embeddings_output.csv" #'embeddings.csv'
+n = 60
+n = 61
+EMBEDDINGS_FILENAME = f"EM_gcn_E{n}.csv"
+EMBEDDINGS_FILENAME = f"ALL_CURRENT.csv"
 EMBEDDINGS_PATH = os.path.join(os.path.join(ROOT_DIR, 'embeddings'), EMBEDDINGS_FILENAME)
 
+
+

pomegranate/interactive.ipynb

@@ -0,0 +1,152 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "To use the Graphein submodule graphein.protein.visualisation, you need to install: pytorch3d \n",
+      "To do so, use the following command: conda install -c pytorch3d pytorch3d\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #7fbfbf; text-decoration-color: #7fbfbf\">[08/02/22 12:11:29] </span><span style=\"color: #800000; text-decoration-color: #800000\">WARNING </span> To use the Graphein submodule                       <a href=\"file:///home/cam/mambaforge/lib/python3.9/site-packages/graphein/protein/meshes.py\"><span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">meshes.py</span></a><span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">:</span><a href=\"file:///home/cam/mambaforge/lib/python3.9/site-packages/graphein/protein/meshes.py#29\"><span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">29</span></a>\n",
+       "                             graphein.protein.meshes, you need to install:                   \n",
+       "                             pytorch3d                                                       \n",
+       "                             To do so, use the following command: conda install              \n",
+       "                             -c pytorch3d pytorch3d                                          \n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[2;36m[08/02/22 12:11:29]\u001b[0m\u001b[2;36m \u001b[0m\u001b[31mWARNING \u001b[0m To use the Graphein submodule                       \u001b]8;id=645620;file:///home/cam/mambaforge/lib/python3.9/site-packages/graphein/protein/meshes.py\u001b\\\u001b[2mmeshes.py\u001b[0m\u001b]8;;\u001b\\\u001b[2m:\u001b[0m\u001b]8;id=336006;file:///home/cam/mambaforge/lib/python3.9/site-packages/graphein/protein/meshes.py#29\u001b\\\u001b[2m29\u001b[0m\u001b]8;;\u001b\\\n",
+       "                             graphein.protein.meshes, you need to install:                   \n",
+       "                             pytorch3d                                                       \n",
+       "                             To do so, use the following command: conda install              \n",
+       "                             -c pytorch3d pytorch3d                                          \n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "from graphein.protein.config import ProteinGraphConfig\n",
+    "\n",
+    "config = ProteinGraphConfig()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "9889db684b504c10b7e76c5a34eab4e3",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Output()"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"></pre>\n"
+      ],
+      "text/plain": []
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "from graphein.protein.graphs import construct_graph\n",
+    "\n",
+    "g = construct_graph(config=config, pdb_code=\"3eiy\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "KeyError",
+     "evalue": "'rsa'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mKeyError\u001b[0m                                  Traceback (most recent call last)",
+      "\u001b[1;32m/mnt/home2nd/pomegranate/pomegranate/interactive.ipynb Cell 3\u001b[0m in \u001b[0;36m<cell line: 9>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      <a href='vscode-notebook-cell:/mnt/home2nd/pomegranate/pomegranate/interactive.ipynb#ch0000002?line=7'>8</a>\u001b[0m avg_rsa \u001b[39m=\u001b[39m \u001b[39m0\u001b[39m\n\u001b[1;32m      <a href='vscode-notebook-cell:/mnt/home2nd/pomegranate/pomegranate/interactive.ipynb#ch0000002?line=8'>9</a>\u001b[0m \u001b[39mfor\u001b[39;00m k, n \u001b[39min\u001b[39;00m g\u001b[39m.\u001b[39mnodes(data\u001b[39m=\u001b[39m\u001b[39mTrue\u001b[39;00m):\n\u001b[0;32m---> <a href='vscode-notebook-cell:/mnt/home2nd/pomegranate/pomegranate/interactive.ipynb#ch0000002?line=10'>11</a>\u001b[0m     \u001b[39mprint\u001b[39m(n[\u001b[39m'\u001b[39;49m\u001b[39mrsa\u001b[39;49m\u001b[39m'\u001b[39;49m])\n",
+      "\u001b[0;31mKeyError\u001b[0m: 'rsa'"
+     ]
+    }
+   ],
+   "source": [
+    "from graphein.protein.subgraphs import extract_subgraph_from_point\n",
+    "#from protein.phosphosite import get_protein_subgraph_radius\n",
+    "\n",
+    "site = list(g.nodes())[10]\n",
+    "\n",
+    "#g = get_protein_subgraph_radius(g=g, site=site, r=r)\n",
+    "\n",
+    "avg_rsa = 0\n",
+    "for k, n in g.nodes(data=True):\n",
+    "    \n",
+    "    print(n['meiler'])\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3.9.7 ('base')",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.13"
+  },
+  "orig_nbformat": 4,
+  "vscode": {
+   "interpreter": {
+    "hash": "dba50d74266ba8c3f81eac460edffb71d253875af3f2e47df42dacc524c6cffc"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

pomegranate/json_conversion/graphein_to_json.py

@@ -1,5 +1,5 @@
 import os
-from typing import Dict
+from typing import Dict, Union
 import graphein.protein as gp
 
 import networkx as nx
@@ -84,18 +84,22 @@ def g_to_json(g, prot_id, db_name='PDB', save_path=SAVED_GRAPHS_DIR):
 Get graph back from json
 '''
 def load_prot_graph (
-    json_graph: Dict, 
+    json_graph: Union[Dict, str], 
 ) -> nx.Graph:
 
     """
-    :param json_graph: JSON object that represents a NetworkX graph.  Can be loaded in from a JSON file. 
+    :param json_graph: JSON string or JSON object that represents a NetworkX graph.  Can be loaded in from a JSON file. 
     :type json_graph: Dict
     :return: NetworkX protein graph
     :rtype: nx.Graph 
     """
 
     # Load general graph
-    g: nx.Graph = nx.readwrite.json_graph.node_link_graph(json.loads(json_graph))
+
+    if type(json_graph) == str: 
+        json_graph = json.loads(json_graph)
+
+    g: nx.Graph = nx.readwrite.json_graph.node_link_graph(json_graph)
 
     # Convert specific fields from strings
     g.graph["pdb_df"] = pd.read_json(g.graph["pdb_df"])

pomegranate/load.py

@@ -62,6 +62,25 @@ class GraphDict:
     pass
 
 
+"""
+Get average RSA for a graph (or subgraph)
+"""
+def get_avg_rsa(
+    g: nx.Graph, 
+) -> float:
+
+    sum = 0
+    num = len(list(g.nodes()))
+    for k, n in g.nodes(data=True):
+        sum += float(n['rsa'])
+
+    return sum / num
+
+
+
+
+
+
 """
 String printing functions
 """
@@ -225,7 +244,7 @@ def load_graphs(
             if verbose:
                 print(f"[{index:4d}] Constructing graph from {acc}...", end=" ")
 
-            try:
+            if True:
                 g = construct_graph(config, pdb_path=pdb_path) 
 
                 pos: int = int(res_pos)
@@ -238,6 +257,8 @@ def load_graphs(
 
                 g = get_surface_motif(g, site=res, r=radius_threshold, asa_threshold=rsa_threshold) 
 
+                avg_rsa = get_avg_rsa(g)
+
                 # Assert that phosphosite residue is same as what we expected 
                 assert aa3to1(psite_res) == res_code, f"Residue mismatch {psite_res} and {res_code}"
                 assert aa3to1(res.split(':')[1]) == res_code, f"Residue mismatch {res} and {res_code} {pos}"
@@ -249,8 +270,15 @@ def load_graphs(
                 # Assert that phosphosiste is included in the graph.  
                 # TODO: display green on the terminal output if it is included; 
                 # Display red on terminal if it is excluded (and --force was used.)
+            try:
 
-                graph = {'graph': g, 'kinase': kinase, 'psite': psite, 'res': res}
+                graph = {
+                    'graph': g, 
+                    'kinase': kinase, 
+                    'psite': psite, 
+                    'res': res, 
+                    'average_rsa': avg_rsa,
+                }
                 graphs[index] = graph
 
                 psite_contained = res in list(g.nodes())
@@ -293,7 +321,7 @@ def load_graphs(
         print(f"{stats['num_fail']} graph constructions failed")
         print("")
 
-    return graphs
+    return graphs   
 
 
 '''