k-mer counts as input feature vectors in Python

kmer_vector_example.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# k-mer count tables as input vectors\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [],
   "source": [
    "from typing import Sequence\n",
    "import collections\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "k = 3\n",
    "seq = \"AAABBBXXXYXXCCCXXXAAAXXXBCDEFXXYXXY\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Counter({'XXX': 3, 'AAA': 2, 'XXY': 2, 'XYX': 2, 'YXX': 2, 'AAB': 1, 'ABB': 1, 'BBB': 1, 'BBX': 1, 'BXX': 1, 'XXC': 1, 'XCC': 1, 'CCC': 1, 'CCX': 1, 'CXX': 1, 'XXA': 1, 'XAA': 1, 'AAX': 1, 'AXX': 1, 'XXB': 1, 'XBC': 1, 'BCD': 1, 'CDE': 1, 'DEF': 1, 'EFX': 1, 'FXX': 1})\n",
      "Counter({'XXYX': 2, 'XYXX': 2, 'AAAB': 1, 'AABB': 1, 'ABBB': 1, 'BBBX': 1, 'BBXX': 1, 'BXXX': 1, 'XXXY': 1, 'YXXC': 1, 'XXCC': 1, 'XCCC': 1, 'CCCX': 1, 'CCXX': 1, 'CXXX': 1, 'XXXA': 1, 'XXAA': 1, 'XAAA': 1, 'AAAX': 1, 'AAXX': 1, 'AXXX': 1, 'XXXB': 1, 'XXBC': 1, 'XBCD': 1, 'BCDE': 1, 'CDEF': 1, 'DEFX': 1, 'EFXX': 1, 'FXXY': 1})\n",
      "Counter({'XXYXX': 2, 'AAABB': 1, 'AABBB': 1, 'ABBBX': 1, 'BBBXX': 1, 'BBXXX': 1, 'BXXXY': 1, 'XXXYX': 1, 'XYXXC': 1, 'YXXCC': 1, 'XXCCC': 1, 'XCCCX': 1, 'CCCXX': 1, 'CCXXX': 1, 'CXXXA': 1, 'XXXAA': 1, 'XXAAA': 1, 'XAAAX': 1, 'AAAXX': 1, 'AAXXX': 1, 'AXXXB': 1, 'XXXBC': 1, 'XXBCD': 1, 'XBCDE': 1, 'BCDEF': 1, 'CDEFX': 1, 'DEFXX': 1, 'EFXXY': 1, 'FXXYX': 1})\n"
     ]
    }
   ],
   "source": [
    "def kmer_count(seq: Sequence, k=3) -> collections.Counter:\n",
    "    kmer_counts = collections.Counter()\n",
    "    for i in range(len(seq) - k):\n",
    "        kmer_counts.update([seq[i: i+k]])\n",
    "        \n",
    "    return kmer_counts\n",
    "\n",
    "print(kmer_count(seq, k=3))\n",
    "print(kmer_count(seq, k=4))\n",
    "print(kmer_count(seq, k=5))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Sort alphabetically by kmer\n",
    "ktuple = sorted(list(kmer_count(seq, k=3).items()), key = lambda x: x[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {},
   "outputs": [
    {
     "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>AAA</th>\n",
       "      <th>AAB</th>\n",
       "      <th>AAX</th>\n",
       "      <th>ABB</th>\n",
       "      <th>AXX</th>\n",
       "      <th>BBB</th>\n",
       "      <th>BBX</th>\n",
       "      <th>BCD</th>\n",
       "      <th>BXX</th>\n",
       "      <th>CCC</th>\n",
       "      <th>...</th>\n",
       "      <th>XAA</th>\n",
       "      <th>XBC</th>\n",
       "      <th>XCC</th>\n",
       "      <th>XXA</th>\n",
       "      <th>XXB</th>\n",
       "      <th>XXC</th>\n",
       "      <th>XXX</th>\n",
       "      <th>XXY</th>\n",
       "      <th>XYX</th>\n",
       "      <th>YXX</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>my_seq_id1</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1 rows × 26 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "            AAA  AAB  AAX  ABB  AXX  BBB  BBX  BCD  BXX  CCC  ...  XAA  XBC  \\\n",
       "my_seq_id1    2    1    1    1    1    1    1    1    1    1  ...    1    1   \n",
       "\n",
       "            XCC  XXA  XXB  XXC  XXX  XXY  XYX  YXX  \n",
       "my_seq_id1    1    1    1    1    3    2    2    2  \n",
       "\n",
       "[1 rows x 26 columns]"
      ]
     },
     "execution_count": 51,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Convert into a DataFrame\n",
    "\n",
    "kmerseqs = []\n",
    "counts = []\n",
    "for ks, c in ktuple:\n",
    "    kmerseqs.append(ks)\n",
    "    counts.append(c)\n",
    "    \n",
    "pd.DataFrame([counts], columns=kmerseqs, index=['my_seq_id1'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.7.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}