Added dinucl dist computation after meeting

Hugenotte585 · Jun 11, 2023 · 708ffe9 · 708ffe9
1 parent 63dc48b
commit 708ffe9
Show file tree

Hide file tree

Showing 3 changed files with 4,998 additions and 0 deletions.
diff --git a/notebooks/exploration_notebooks/explore_csv_from_paper_for_dinuc_dist.ipynb b/notebooks/exploration_notebooks/explore_csv_from_paper_for_dinuc_dist.ipynb
@@ -0,0 +1,214 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "csv_file = \"..\\\\..\\\\scer_half_life.csv\"\n",
+    "df = pd.read_csv(csv_file)\n",
+    "#print(list(df.columns))\n",
+    "df = df[df[\"UTR3_seq\"].notnull()].reset_index(drop=True)\n",
+    "\n",
+    "data = list(df[\"UTR3_seq\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "['AA', 'AC', 'AG', 'AT', 'AN', 'CA', 'CC', 'CG', 'CT', 'CN', 'GA', 'GC', 'GG', 'GT', 'GN', 'TA', 'TC', 'TG', 'TT', 'TN', 'NA', 'NC', 'NG', 'NT', 'NN']\n"
+     ]
+    }
+   ],
+   "source": [
+    "d = {}\n",
+    "nucleotides = \"ACGTN\"\n",
+    "pairs = []\n",
+    "for n1 in nucleotides:\n",
+    "    for n2 in nucleotides:\n",
+    "        pairs.append(n1+n2)\n",
+    "\n",
+    "print(pairs)\n",
+    "for seq in data:\n",
+    "    for n in pairs:\n",
+    "        tmp = d.get(n, 0)\n",
+    "        count = 0\n",
+    "        for i in range(len(seq)-1):\n",
+    "            pair=seq[i:i+2]\n",
+    "            if pair == n:\n",
+    "                count += 1\n",
+    "        d[n] = tmp + count"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'AA': 73552,\n",
+       " 'AC': 32728,\n",
+       " 'AG': 29334,\n",
+       " 'AT': 76731,\n",
+       " 'AN': 0,\n",
+       " 'CA': 34675,\n",
+       " 'CC': 16836,\n",
+       " 'CG': 14032,\n",
+       " 'CT': 33597,\n",
+       " 'CN': 0,\n",
+       " 'GA': 27438,\n",
+       " 'GC': 17562,\n",
+       " 'GG': 14076,\n",
+       " 'GT': 31294,\n",
+       " 'GN': 0,\n",
+       " 'TA': 75017,\n",
+       " 'TC': 34094,\n",
+       " 'TG': 33276,\n",
+       " 'TT': 87074,\n",
+       " 'TN': 0,\n",
+       " 'NA': 0,\n",
+       " 'NC': 0,\n",
+       " 'NG': 0,\n",
+       " 'NT': 0,\n",
+       " 'NN': 0}"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "d"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'A': 212345, 'C': 99140, 'G': 90370, 'T': 229461, 'N': 0}"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "count = {}\n",
+    "\n",
+    "for k in d.keys():\n",
+    "    tmp = count.get(k[0],0)\n",
+    "    count[k[0]] = tmp + d[k]\n",
+    "\n",
+    "count"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'AA': 0.34638071226070777,\n",
+       " 'AC': 0.15412753935812004,\n",
+       " 'AG': 0.1381441161553133,\n",
+       " 'AT': 0.3613516322258588,\n",
+       " 'AN': 1e-06,\n",
+       " 'CA': 0.3497589180956223,\n",
+       " 'CC': 0.1698214559209199,\n",
+       " 'CG': 0.14153822009279807,\n",
+       " 'CT': 0.33888540589065963,\n",
+       " 'CN': 1e-06,\n",
+       " 'GA': 0.3036194574526945,\n",
+       " 'GC': 0.1943354030098484,\n",
+       " 'GG': 0.15576065475268341,\n",
+       " 'GT': 0.3462884847847737,\n",
+       " 'GN': 1e-06,\n",
+       " 'TA': 0.32692801591991666,\n",
+       " 'TC': 0.14858398360069902,\n",
+       " 'TG': 0.1450191076522808,\n",
+       " 'TT': 0.3794728928271035,\n",
+       " 'TN': 1e-06,\n",
+       " 'NA': 1e-06,\n",
+       " 'NC': 1e-06,\n",
+       " 'NG': 1e-06,\n",
+       " 'NT': 1e-06,\n",
+       " 'NN': 1e-06}"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "{k: 0.000001 if count[k[0]] == 0 else (v / count[k[0]]) + 0.000001 for k, v in d.items()}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dist = torch.log(torch.tensor([[0.34638071226070777, 0.15412753935812004, 0.1381441161553133, 0.3613516322258588, 1e-06],\n",
+    "                               [0.3497589180956223, 0.1698214559209199, 0.14153822009279807, 0.33888540589065963, 1e-06],\n",
+    "                               [0.3036194574526945, 0.1943354030098484, 0.15576065475268341, 0.3462884847847737, 1e-06],\n",
+    "                               [0.32692801591991666, 0.14858398360069902, 0.1450191076522808, 0.3794728928271035, 1e-06]\n",
+    "                               [1e-06, 1e-06, 1e-06, 1e-06, 1e-06]]))"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3.11.3 64-bit",
+   "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": "3.8.10"
+  },
+  "orig_nbformat": 4,
+  "vscode": {
+   "interpreter": {
+    "hash": "767d51c1340bd893661ea55ea3124f6de3c7a262a8b4abca0554b478b1e2ff90"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}