notebooks/01_protein_interaction_dataset.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Imports"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/strokach/env/lib/python3.7/site-packages/Bio/KDTree/__init__.py:27: BiopythonDeprecationWarning: Bio.KDTree has been deprecated, and we intend to remove it in a future release of Biopython. Please use Bio.PDB.kdtrees instead, which is functionally very similar.\n",
      "  BiopythonDeprecationWarning,\n"
     ]
    }
   ],
   "source": [
    "import os\n",
    "from pathlib import Path\n",
    "\n",
    "from tqdm.notebook import tqdm\n",
    "\n",
    "import proteinsolver\n",
    "import torch"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "if \"DATAPKG_DATA_DIR\" in os.environ:\n",
    "    DATAPKG_DATA_DIR = Path(os[\"DATAPKG_DATA_DIR\"]).resolve(strict=True)\n",
    "else:\n",
    "    DATAPKG_DATA_DIR = Path(\"/home/kimlab4/strokach/datapkg_output_dir\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Workspace"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "pdb_interaction_files = sorted([\n",
    "    file\n",
    "    for file in DATAPKG_DATA_DIR.joinpath(\"adjacency-net-v2\", \"v0.3\", \"pdb-interface\").glob(\"*.arrow\")\n",
    "    if file.with_suffix(\".SUCCESS\").is_file()\n",
    "])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "assert len(pdb_interaction_files) == 300"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "/home/kimlab4/strokach/datapkg_output_dir/adjacency-net-v2/v0.3/pdb-interface/pdb-interface-1-300.arrow\n"
     ]
    }
   ],
   "source": [
    "print(pdb_interaction_files[0])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Examine the loaded data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "protein_interaction_dataset = proteinsolver.datasets.ProteinInteractionDataset(pdb_interaction_files)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "data = protein_interaction_dataset[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Data(edge_attr=[172640, 2], edge_index=[2, 172640], sequence_1_length=[1], x=[416])\n"
     ]
    }
   ],
   "source": [
    "print(data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "197339"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(protein_interaction_dataset)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Compare sequential vs. random access reading speed"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "5ec89aed2f314286abf398d74f3d00f8",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(FloatProgress(value=0.0, max=200.0), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    }
   ],
   "source": [
    "for idx in tqdm(range(len(protein_interaction_dataset))[:200]):\n",
    "    _ = protein_interaction_dataset[idx]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "3b410cd7524e411aa9ccc23eaf5b37b0",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(FloatProgress(value=0.0, max=200.0), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    }
   ],
   "source": [
    "for idx in tqdm(torch.randperm(len(protein_interaction_dataset))[:200]):\n",
    "    _ = protein_interaction_dataset[idx]"
   ]
  },
  {
   "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": "3.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}