scope: add more scope details to tutorial

Author: aditya0by0

tutorials/data_exploration_scope.ipynb

@@ -17,6 +17,96 @@
     "---\n"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "f6c25706-251c-438c-9915-e8002647eb94",
+   "metadata": {},
+   "source": [
+    "### Understanding [SCOPe](https://scop.berkeley.edu/) and [PDB](https://www.rcsb.org/)  \n",
+    "\n",
+    "\n",
+    "1. **Protein domains form chains.**  \n",
+    "2. **Chains form complexes** (protein complexes or structures).  \n",
+    "3. These **complexes are the entries in PDB**, represented by unique identifiers like `\"1A3N\"`.  \n",
+    "\n",
+    "---\n",
+    "\n",
+    "#### **Protein Domain**  \n",
+    "A **protein domain** is a **structural and functional unit** of a protein.  \n",
+    "\n",
+    "\n",
+    "##### Key Characteristics:\n",
+    "- **Domains are part of a protein chain.**  \n",
+    "- A domain can span:  \n",
+    "  1. **The entire chain** (single-domain protein):  \n",
+    "     - In this case, the protein domain is equivalent to the chain itself.  \n",
+    "     - Example:  \n",
+    "       - All chains of the **PDB structure \"1A3N\"** are single-domain proteins.  \n",
+    "       - Each chain has a SCOPe domain identifier. \n",
+    "       - For example, Chain **A**:  \n",
+    "         - Domain identifier: `d1a3na_`  \n",
+    "         - Breakdown of the identifier:  \n",
+    "           - `d`: Denotes domain.  \n",
+    "           - `1a3n`: Refers to the PDB protein structure identifier.  \n",
+    "           - `a`: Specifies the chain within the structure.  (`_` for None and `.` for multiple chains)\n",
+    "           - `_`: Indicates the domain spans the entire chain (single-domain protein).  \n",
+    "         - Example: [PDB Structure 1A3N - Chain A](https://www.rcsb.org/sequence/1A3N#A)\n",
+    "  2. **A specific portion of the chain** (multi-domain protein):  \n",
+    "     - Here, a single chain contains multiple domains.  \n",
+    "     - Example: Chain **A** of the **PDB structure \"1PKN\"** contains three domains: `d1pkna1`, `d1pkna2`, `d1pkna3`.  \n",
+    "     - Example: [PDB Structure 1PKN - Chain A](https://www.rcsb.org/annotations/1PKN).  \n",
+    "\n",
+    "---\n",
+    "\n",
+    "#### **Protein Chain**  \n",
+    "A **protein chain** refers to the entire **polypeptide chain** observed in a protein's 3D structure (as described in PDB files).  \n",
+    "\n",
+    "##### Key Points:\n",
+    "- A chain can consist of **one or multiple domains**:\n",
+    "  - **Single-domain chain**: The chain and domain are identical.  \n",
+    "    - Example: Myoglobin.  \n",
+    "  - **Multi-domain chain**: Contains several domains, each with distinct structural and functional roles.  \n",
+    "- Chains assemble to form **protein complexes** or **structures**.  \n",
+    "\n",
+    "\n",
+    "---\n",
+    "\n",
+    "#### **Key Observations About SCOPe**  \n",
+    "- The **fundamental classification unit** in SCOPe is the **protein domain**, not the entire protein.  \n",
+    "- _**The taxonomy in SCOPe is not for the entire protein (i.e., the full-length amino acid sequence as encoded by a gene) but for protein domains, which are smaller, structurally and functionally distinct regions of the protein.**_\n",
+    "\n",
+    "\n",
+    "--- \n",
+    "\n",
+    "**SCOPe 2.08 Data Analysis:**\n",
+    "\n",
+    "The current SCOPe version (2.08) includes the following statistics based on analysis for relevant data:\n",
+    "\n",
+    "- **Classes**: 12\n",
+    "- **Folds**: 1485\n",
+    "- **Superfamilies**: 2368\n",
+    "- **Families**: 5431\n",
+    "- **Proteins**: 13,514\n",
+    "- **Species**: 30,294\n",
+    "- **Domains**: 344,851\n",
+    "\n",
+    "For more detailed statistics, please refer to the official SCOPe website:\n",
+    "\n",
+    "- [SCOPe 2.08 Statistics](https://scop.berkeley.edu/statistics/ver=2.08)\n",
+    "- [SCOPe 2.08 Release](https://scop.berkeley.edu/ver=2.08)\n",
+    "\n",
+    "---\n",
+    "\n",
+    "## SCOPe Labeling \n",
+    "\n",
+    "- Use SCOPe labels for protein domains.\n",
+    "- Map them back to their **protein-chain** sequences (protein sequence label = sum of all domain labels).\n",
+    "- Train on protein sequences.\n",
+    "- This pretraining task would be comparable to GO-based training.\n",
+    "\n",
+    "--- "
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 1,
@@ -171,25 +261,25 @@
      "text": [
       "Checking for processed data in data\\SCOPe\\version_2.08\\SCOPe2000\\processed\n",
       "Missing processed data file (`data.pkl` file)\n",
-	  "Missing PDB raw data, Downloading PDB sequence data....\n",
-	  "Downloading to temporary file C:\\Users\\HP\\AppData\\Local\\Temp\\tmpsif7r129\n",
-	  "Downloaded to C:\\Users\\HP\\AppData\\Local\\Temp\\tmpsif7r129\n",
-	  "Unzipping the file....\n",
+      "Missing PDB raw data, Downloading PDB sequence data....\n",
+      "Downloading to temporary file C:\\Users\\HP\\AppData\\Local\\Temp\\tmpsif7r129\n",
+      "Downloaded to C:\\Users\\HP\\AppData\\Local\\Temp\\tmpsif7r129\n",
+      "Unzipping the file....\n",
       "Unpacked and saved to data\\SCOPe\\pdb_sequences.txt\n",
       "Removed temporary file C:\\Users\\HP\\AppData\\Local\\Temp\\tmpsif7r129\n",
-	  "Missing Scope: cla.txt raw data, Downloading...\n"
-	  ]
-	},
-	{
-	 "name": "stderr",
+      "Missing Scope: cla.txt raw data, Downloading...\n"
+     ]
+    },
+    {
+     "name": "stderr",
      "output_type": "stream",
      "text": [
       "G:\\anaconda3\\envs\\env_chebai\\lib\\site-packages\\urllib3\\connectionpool.py:1099: InsecureRequestWarning: Unverified HTTPS request is being made to host 'scop.berkeley.edu'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings\n",
       "warnings.warn(\n"
-	  ]
-	},
-	{
-	 "name": "stdout",
+     ]
+    },
+    {
+     "name": "stdout",
      "output_type": "stream",
      "text": [
       "Missing Scope: hie.txt raw data, Downloading...\n",