tutorials/protein_protein_interaction.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Protein-Protein Interaction (PPI)\n",
    "\n",
    "After you finding your modules, you can recover if any pair of genes within each module are confirmed to have known functional PPIs using [STRING](https://string-db.org/)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[1m\u001b[94mReading 5xFAD WGCNA done!\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>dynamicColors</th>\n",
       "      <th>moduleColors</th>\n",
       "      <th>moduleLabels</th>\n",
       "      <th>gene_name</th>\n",
       "      <th>gene_biotype</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>ENSMUSG00000000028</th>\n",
       "      <td>darkred</td>\n",
       "      <td>darkred</td>\n",
       "      <td>4.0</td>\n",
       "      <td>Cdc45</td>\n",
       "      <td>protein_coding</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ENSMUSG00000000049</th>\n",
       "      <td>darkred</td>\n",
       "      <td>darkred</td>\n",
       "      <td>4.0</td>\n",
       "      <td>Apoh</td>\n",
       "      <td>protein_coding</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ENSMUSG00000000056</th>\n",
       "      <td>darkgrey</td>\n",
       "      <td>darkgrey</td>\n",
       "      <td>3.0</td>\n",
       "      <td>Narf</td>\n",
       "      <td>protein_coding</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ENSMUSG00000000058</th>\n",
       "      <td>coral</td>\n",
       "      <td>coral</td>\n",
       "      <td>2.0</td>\n",
       "      <td>Cav2</td>\n",
       "      <td>protein_coding</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ENSMUSG00000000078</th>\n",
       "      <td>gainsboro</td>\n",
       "      <td>gainsboro</td>\n",
       "      <td>7.0</td>\n",
       "      <td>Klf6</td>\n",
       "      <td>protein_coding</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                   dynamicColors moduleColors  moduleLabels gene_name  \\\n",
       "ENSMUSG00000000028       darkred      darkred           4.0     Cdc45   \n",
       "ENSMUSG00000000049       darkred      darkred           4.0      Apoh   \n",
       "ENSMUSG00000000056      darkgrey     darkgrey           3.0      Narf   \n",
       "ENSMUSG00000000058         coral        coral           2.0      Cav2   \n",
       "ENSMUSG00000000078     gainsboro    gainsboro           7.0      Klf6   \n",
       "\n",
       "                      gene_biotype  \n",
       "ENSMUSG00000000028  protein_coding  \n",
       "ENSMUSG00000000049  protein_coding  \n",
       "ENSMUSG00000000056  protein_coding  \n",
       "ENSMUSG00000000058  protein_coding  \n",
       "ENSMUSG00000000078  protein_coding  "
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import PyWGCNA\n",
    "pyWGCNA_5xFAD = PyWGCNA.readWGCNA(\"5xFAD.p\")\n",
    "pyWGCNA_5xFAD.datExpr.var.head(5)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## PPI genes\n",
    "\n",
    "If you are interested in the genes with PPI within modules/gene list, you can use the `request_PPI()` function to give you all the possible PPIs with their scores."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1179 genes out of 1335 genes have PPI.\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>gene1</th>\n",
       "      <th>gene2</th>\n",
       "      <th>score</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Cav2</td>\n",
       "      <td>Cav1</td>\n",
       "      <td>0.995</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Cav2</td>\n",
       "      <td>Cacna1c</td>\n",
       "      <td>0.975</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Cav2</td>\n",
       "      <td>Egfr</td>\n",
       "      <td>0.958</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Cav2</td>\n",
       "      <td>Src</td>\n",
       "      <td>0.921</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Cav2</td>\n",
       "      <td>Nos3</td>\n",
       "      <td>0.921</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5860</th>\n",
       "      <td>Soat1</td>\n",
       "      <td>Dhcr24</td>\n",
       "      <td>0.943</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5861</th>\n",
       "      <td>Soat1</td>\n",
       "      <td>Dhcr7</td>\n",
       "      <td>0.942</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5862</th>\n",
       "      <td>Soat1</td>\n",
       "      <td>Cyp46a1</td>\n",
       "      <td>0.891</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5863</th>\n",
       "      <td>Soat1</td>\n",
       "      <td>Ch25h</td>\n",
       "      <td>0.87</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5864</th>\n",
       "      <td>Soat1</td>\n",
       "      <td>Cyp7a1</td>\n",
       "      <td>0.855</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5865 rows × 3 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      gene1    gene2  score\n",
       "0      Cav2     Cav1  0.995\n",
       "1      Cav2  Cacna1c  0.975\n",
       "2      Cav2     Egfr  0.958\n",
       "3      Cav2      Src  0.921\n",
       "4      Cav2     Nos3  0.921\n",
       "...     ...      ...    ...\n",
       "5860  Soat1   Dhcr24  0.943\n",
       "5861  Soat1    Dhcr7  0.942\n",
       "5862  Soat1  Cyp46a1  0.891\n",
       "5863  Soat1    Ch25h   0.87\n",
       "5864  Soat1   Cyp7a1  0.855\n",
       "\n",
       "[5865 rows x 3 columns]"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "genes = pyWGCNA_5xFAD.datExpr.var[pyWGCNA_5xFAD.datExpr.var.moduleColors == \"coral\"]\n",
    "genes = genes.index.astype(str).tolist()\n",
    "PPI = pyWGCNA_5xFAD.request_PPI(genes=genes, species=10090)\n",
    "PPI"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## PPI netwroks\n",
    "\n",
    "If you want to recover networks of PPI you can use `PPI_network()` function.\n",
    "You can pass a list of modules or genes to restrict it to."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[93mPPI directory does not exist!\n",
      "Creating PPI directory!\u001b[0m\n",
      "4 genes out of 4 genes have PPI.\n",
      "Saving interaction network to figures/PPI/Cav2_PPI.png\n",
      "For having interactive network, click line below:\n",
      "https://string-db.org/api/tsv/get_link?identifiers=Cav1%0dCacna1c%0dEgfr%0dSrc%0dNos3%0dCav2&species=10090\n",
      "Saving interaction network to figures/PPI/Ccl12_PPI.png\n",
      "For having interactive network, click line below:\n",
      "https://string-db.org/api/tsv/get_link?identifiers=Ccl2%0dCcl7%0dJun%0dCcl6%0dCcr2%0dCcl12&species=10090\n",
      "Saving interaction network to figures/PPI/Ccl2_PPI.png\n",
      "For having interactive network, click line below:\n",
      "https://string-db.org/api/tsv/get_link?identifiers=Jun%0dCcr1%0dCcl7%0dCcr5%0dCcr2%0dCcl2&species=10090\n",
      "Saving interaction network to figures/PPI/Scpep1_PPI.png\n",
      "For having interactive network, click line below:\n",
      "https://string-db.org/api/tsv/get_link?identifiers=Lactb2%0dTwf2%0dStk24%0dTbcb%0dAldh7a1%0dScpep1&species=10090\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>gene1</th>\n",
       "      <th>gene2</th>\n",
       "      <th>score</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Cav2</td>\n",
       "      <td>Cav1</td>\n",
       "      <td>0.995</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Cav2</td>\n",
       "      <td>Cacna1c</td>\n",
       "      <td>0.975</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Cav2</td>\n",
       "      <td>Egfr</td>\n",
       "      <td>0.958</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Cav2</td>\n",
       "      <td>Src</td>\n",
       "      <td>0.921</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Cav2</td>\n",
       "      <td>Nos3</td>\n",
       "      <td>0.921</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>Ccl12</td>\n",
       "      <td>Ccl2</td>\n",
       "      <td>0.883</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>Ccl12</td>\n",
       "      <td>Ccl7</td>\n",
       "      <td>0.884</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>Ccl12</td>\n",
       "      <td>Jun</td>\n",
       "      <td>0.912</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>Ccl12</td>\n",
       "      <td>Ccl6</td>\n",
       "      <td>0.943</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>Ccl12</td>\n",
       "      <td>Ccr2</td>\n",
       "      <td>0.997</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>Ccl2</td>\n",
       "      <td>Jun</td>\n",
       "      <td>0.969</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>Ccl2</td>\n",
       "      <td>Ccr1</td>\n",
       "      <td>0.977</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Ccl2</td>\n",
       "      <td>Ccl7</td>\n",
       "      <td>0.987</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Ccl2</td>\n",
       "      <td>Ccr5</td>\n",
       "      <td>0.989</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Ccl2</td>\n",
       "      <td>Ccr2</td>\n",
       "      <td>0.999</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>Scpep1</td>\n",
       "      <td>Lactb2</td>\n",
       "      <td>0.767</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>Scpep1</td>\n",
       "      <td>Twf2</td>\n",
       "      <td>0.726</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>Scpep1</td>\n",
       "      <td>Stk24</td>\n",
       "      <td>0.693</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>Scpep1</td>\n",
       "      <td>Tbcb</td>\n",
       "      <td>0.693</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>Scpep1</td>\n",
       "      <td>Aldh7a1</td>\n",
       "      <td>0.666</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     gene1    gene2  score\n",
       "0     Cav2     Cav1  0.995\n",
       "1     Cav2  Cacna1c  0.975\n",
       "2     Cav2     Egfr  0.958\n",
       "3     Cav2      Src  0.921\n",
       "4     Cav2     Nos3  0.921\n",
       "14   Ccl12     Ccl2  0.883\n",
       "13   Ccl12     Ccl7  0.884\n",
       "12   Ccl12      Jun  0.912\n",
       "11   Ccl12     Ccl6  0.943\n",
       "10   Ccl12     Ccr2  0.997\n",
       "9     Ccl2      Jun  0.969\n",
       "8     Ccl2     Ccr1  0.977\n",
       "7     Ccl2     Ccl7  0.987\n",
       "6     Ccl2     Ccr5  0.989\n",
       "5     Ccl2     Ccr2  0.999\n",
       "15  Scpep1   Lactb2  0.767\n",
       "16  Scpep1     Twf2  0.726\n",
       "17  Scpep1    Stk24  0.693\n",
       "18  Scpep1     Tbcb  0.693\n",
       "19  Scpep1  Aldh7a1  0.666"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "geneList = PPI.gene1[:20].unique().tolist()\n",
    "pyWGCNA_5xFAD.PPI_network(species=10090, geneList=geneList)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.10.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}