LucaCappelletti94/keras_synthetic_genome_sequence

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from keras_synthetic_genome_sequence.multivariate_gap_sequence import MultivariateGapSequence\n",
    "from ucsc_genomes_downloader import Genome\n",
    "from keras_synthetic_genome_sequence.utils import get_gaps_statistics\n",
    "import numpy as np\n",
    "from typing import Tuple\n",
    "from numba import njit, jit"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, description='Loading chromosomes for genome hg19', layout=Layout(flex='2')…"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, description='Rendering gaps in hg19', layout=Layout(flex='2'), max=3, styl…"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, description='Rendering sequences in hg19', layout=Layout(flex='2'), max=2,…"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r"
     ]
    }
   ],
   "source": [
    "hg19 = Genome(\"hg19\", chromosomes=[\"chr1\", \"chr2\", \"chr3\"])\n",
    "\n",
    "_, mean, covariance = get_gaps_statistics(\n",
    "    hg19,\n",
    "    100,\n",
    "    200\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, description='Rendering sequences in hg19', layout=Layout(flex='2'), max=1,…"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, description='Converting nucleotides to numeric classes', layout=Layout(fle…"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, description='Generating synthetic gaps', layout=Layout(flex='2'), max=1, s…"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r"
     ]
    }
   ],
   "source": [
    "gap_sequence = MultivariateGapSequence(\n",
    "    assembly=hg19,\n",
    "    bed=\"tests/utils/test.bed\",\n",
    "    gaps_mean=mean,\n",
    "    gaps_covariance=covariance,\n",
    "    batch_size=32\n",
    ")\n",
    "gap_sequence.on_train_start()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "@njit\n",
    "def add_gaps2(gaps_coordinates:dict, indices:np.ndarray, y:np.ndarray):\n",
    "    # Making a deep copy of y, since we are going to edit the copy.\n",
    "    x = np.copy(y)\n",
    "    for i in range(indices.shape[0]):\n",
    "        x[i][gaps_coordinates[indices[i]]] = 0.25\n",
    "    return x"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "def get4(self, idx: int) -> Tuple[np.ndarray, np.ndarray]:\n",
    "    # Retrieves the sequence from the bed generator\n",
    "    y = self.__getitem__(idx)\n",
    "    # For i-th row of current batch we apply the nucletides mask\n",
    "    x = add_gaps2(self._gaps_coordinates, self._gaps_index[idx], y)\n",
    "    return x, y"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "51.2 µs ± 4.48 µs per loop (mean ± std. dev. of 7 runs, 20000 loops each)\n"
     ]
    }
   ],
   "source": [
    "%%timeit -n 20000\n",
    "get4(gap_sequence, 1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "20.5 µs ± 222 ns per loop (mean ± std. dev. of 7 runs, 10000 loops each)\n"
     ]
    }
   ],
   "source": [
    "%%timeit -n 10000\n",
    "gap_sequence[0]"
   ]
  },
  {
   "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": "3.7.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}