{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Colab initialization\n",
    "- install the pipeline in the colab runtime\n",
    "- download files neccessary for this example"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "!pip3 install -U pip > /dev/null\n",
    "!pip3 install -U bio_embeddings[all] > /dev/null"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "!wget http://data.bioembeddings.com/public/embeddings/notebooks/pipeline_output_example/mapping_file.csv --output-document mapping_file.csv\n",
    "!wget http://data.bioembeddings.com/public/embeddings/notebooks/pipeline_output_example/reduced_embeddings_file.h5 --output-document reduced_embeddings_file.h5\n",
    "!wget http://data.bioembeddings.com/public/embeddings/notebooks/custom_data/annotation_file.csv --output-document annotation_file.csv"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Visualize sequence spaces drawn by embeddings\n",
    "In this notebook, we use the output of the _embed_ stage to draw custom t-SNE sequence space plots."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "pycharm": {
     "is_executing": false
    }
   },
   "outputs": [],
   "source": [
    "import h5py\n",
    "import numpy as np\n",
    "from pandas import read_csv\n",
    "from bio_embeddings.project import tsne_reduce\n",
    "from bio_embeddings.visualize import render_3D_scatter_plotly"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "pycharm": {
     "is_executing": false
    }
   },
   "outputs": [],
   "source": [
    "mapping_file = read_csv('mapping_file.csv', index_col=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "pycharm": {
     "is_executing": false
    }
   },
   "outputs": [],
   "source": [
    "embeddings = []\n",
    "with h5py.File('reduced_embeddings_file.h5', 'r') as f:\n",
    "    for remapped_id in mapping_file.index:\n",
    "        embeddings.append(np.array(f[remapped_id]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "pycharm": {
     "is_executing": false
    }
   },
   "outputs": [],
   "source": [
    "options = {\n",
    "    'perplexity': 3,\n",
    "    'n_iter': 500\n",
    "}\n",
    "\n",
    "projected_embeddings = tsne_reduce(embeddings, **options)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "pycharm": {
     "is_executing": false
    }
   },
   "outputs": [],
   "source": [
    "mapping_file['component_0'] = projected_embeddings[:, 0]\n",
    "mapping_file['component_1'] = projected_embeddings[:, 1]\n",
    "mapping_file['component_2'] = projected_embeddings[:, 2]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "pycharm": {
     "is_executing": false
    }
   },
   "outputs": [],
   "source": [
    "annotation_file = read_csv('annotation_file.csv', index_col=0)\n",
    "\n",
    "merged_annotation_file = annotation_file.join(mapping_file.set_index('original_id'), how='outer')\n",
    "merged_annotation_file['label'].fillna('UNKNOWN', inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "pycharm": {
     "is_executing": false
    }
   },
   "outputs": [],
   "source": [
    "figure = render_3D_scatter_plotly(merged_annotation_file)\n",
    "figure.show()"
   ]
  }
 ],
 "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": "3.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}