Convolutional variable length peptide network.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "from pepnet.encoder import Encoder\n",
    "encoder = Encoder()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 8,  5,  5,  1,  3, 18, 19, 11,  0,  0]])"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x_index = encoder.encode_index_array([\"SIINFEKL\"], max_peptide_length=10); x_index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[[False, False, False, False, False, False, False, False,  True,\n",
       "         False, False, False, False, False, False, False, False, False,\n",
       "         False, False, False],\n",
       "        [False, False, False, False, False,  True, False, False, False,\n",
       "         False, False, False, False, False, False, False, False, False,\n",
       "         False, False, False],\n",
       "        [False, False, False, False, False,  True, False, False, False,\n",
       "         False, False, False, False, False, False, False, False, False,\n",
       "         False, False, False],\n",
       "        [False,  True, False, False, False, False, False, False, False,\n",
       "         False, False, False, False, False, False, False, False, False,\n",
       "         False, False, False],\n",
       "        [False, False, False,  True, False, False, False, False, False,\n",
       "         False, False, False, False, False, False, False, False, False,\n",
       "         False, False, False],\n",
       "        [False, False, False, False, False, False, False, False, False,\n",
       "         False, False, False, False, False, False, False, False, False,\n",
       "          True, False, False],\n",
       "        [False, False, False, False, False, False, False, False, False,\n",
       "         False, False, False, False, False, False, False, False, False,\n",
       "         False,  True, False],\n",
       "        [False, False, False, False, False, False, False, False, False,\n",
       "         False, False,  True, False, False, False, False, False, False,\n",
       "         False, False, False],\n",
       "        [False, False, False, False, False, False, False, False, False,\n",
       "         False, False, False, False, False, False, False, False, False,\n",
       "         False, False, False],\n",
       "        [False, False, False, False, False, False, False, False, False,\n",
       "         False, False, False, False, False, False, False, False, False,\n",
       "         False, False, False]]], dtype=bool)"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x_binary = encoder.encode_onehot([\"SIINFEKL\"], max_peptide_length=10); x_binary"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 0.       ,  0.2401   ,  0.       ,  0.343    ,  0.       ,\n",
       "         0.285719 ,  0.       ,  0.       ,  0.0823543,  0.       ,\n",
       "         0.       ,  1.       ,  0.       ,  0.       ,  0.       ,\n",
       "         0.       ,  0.       ,  0.       ,  0.49     ,  0.7      ,  0.       ]])"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x_fofe = encoder.encode_FOFE([\"SIINFEKL\"]); x_fofe"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from pepnet.convolutional import make_variable_length_embedding_convolutional_model\n",
    "model_small = make_variable_length_embedding_convolutional_model(\n",
    "    max_peptide_length=30,\n",
    "    n_filters_per_size=32,\n",
    "    filter_sizes=[9],\n",
    "    n_conv_layers=1,\n",
    "    pool_size=3,\n",
    "    pool_stride=2,\n",
    "    dropout=0.25,\n",
    "    conv_dropout=0.1,\n",
    "    hidden_layer_sizes=[],\n",
    "    n_output=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "plot_model(model_small, to_file=\"conv_small.png\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "!open conv_small.png"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "from pepnet.convolutional import make_variable_length_embedding_convolutional_model\n",
    "model = make_variable_length_embedding_convolutional_model(\n",
    "    max_peptide_length=30,\n",
    "    n_filters_per_size=32,\n",
    "    filter_sizes=[3, 5, 9],\n",
    "    n_conv_layers=2,\n",
    "    pool_size=3,\n",
    "    pool_stride=2,\n",
    "    dropout=0.25,\n",
    "    conv_dropout=0.1,\n",
    "    hidden_layer_sizes=[100],\n",
    "    n_output=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "from keras.utils import plot_model\n",
    "from IPython.display import SVG\n",
    "from keras.utils.vis_utils import model_to_dot"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "plot_model(model, to_file=\"conv_large.png\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "!open conv_large.png"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "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": "3.5.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}