random shuffle of sample

DeepDrug.ipynb

@@ -9,11 +9,28 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 1,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Using TensorFlow backend.\n"
+     ]
+    }
+   ],
    "source": [
-    "import numpy as np"
+    "import numpy as np\n",
+    "\n",
+    "from sklearn.preprocessing import LabelEncoder\n",
+    "from keras.models import Sequential\n",
+    "from keras import optimizers\n",
+    "from keras.layers import Dense, Flatten, TimeDistributedn, Dropout\n",
+    "from keras import Input, Model\n",
+    "from keras.layers import add, Activation\n",
+    "#from keras.utils import plot_model  # Needs pydot.\n",
+    "from keras.layers import Conv3D, MaxPooling3D"
    ]
   },
   {
@@ -30,7 +47,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [
     {
@@ -39,7 +56,7 @@
        "''"
       ]
      },
-     "execution_count": 3,
+     "execution_count": 2,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -66,19 +83,101 @@
     "nucleotide.pop()"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Creating input and ouputs"
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "data_onehot = np.ndarray(shape=(2219, 14, 32, 32, 32)) # initializing empty array\n",
+    "indices = np.random.permutation(2219)\n",
+    "output = np.ndarray(shape=(2219, 3)) # softmax 3, {steroid=1, heme=1, nucleotide=1}\n",
+    "lmin = len(steroid)\n",
+    "lmid = len(heme)\n",
+    "lmax = len(nucleotide)"
+   ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "n = -1\n",
+    "for i in indices:\n",
+    "    n += 1\n",
+    "    if i < lmin:\n",
+    "        data_onehot[n,] = np.load(\"deepdrug3d_voxel_data/\"+steroid[i]+\".npy\")\n",
+    "        output[n,] = [1,0,0]\n",
+    "    elif i > lmin and i < (lmin + lmid):\n",
+    "        data_onehot[n,] = np.load(\"deepdrug3d_voxel_data/\"+heme[i - lmin]+\".npy\")\n",
+    "        output[n,] = [0,1,0]\n",
+    "    else:\n",
+    "        data_onehot[n,] = np.load(\"deepdrug3d_voxel_data/\"+nucleotide[i - (lmin+lmid) - 1]+\".npy\")\n",
+    "        output[n,] = [0,0,1]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X_train = data_onehot[0:1664,]\n",
+    "Y_train = output[0:1664,]\n",
+    "X_test = data_onehot[1664:,]\n",
+    "Y_test = output[1664:,]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(1, 14, 32, 32, 32)"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "def model_sequential(): # créer un objet modèle\n",
+    "    \"\"\"\n",
+    "    Return a simple sequentiel model\n",
+    "    \n",
+    "    Returns :\n",
+    "        - model : keras.Model\n",
+    "    \"\"\"\n",
+    "    inputs = Input(shape=(32,32,32,14)) # 759 aa, 21 car onehot\n",
+    "    conv_1 = Conv3D(64, (28, 28, 28), padding=\"same\", activation=\"LeakyReLU\",\n",
+    "                        kernel_initializer=\"he_normal\")(inputs)\n",
+    "    conv_2 = Conv3D(64, (26, 26, 26), padding=\"same\", activation=\"LeakyReLU\",\n",
+    "                        kernel_initializer=\"he_normal\")(conv_1)\n",
+    "    drop_1 = Dropout(0.2)(conv_2)\n",
+    "    maxpool = MaxPooling3D()(drop_1)\n",
+    "    drop_2 = Dropout(0.4)(maxpool)\n",
+    "    dense = Dense(512)(drop_2)\n",
+    "    drop_3 = Dropout(0.4)(dense)\n",
+    "    output = TimeDistributed(Dense(3, activation='softmax'))(drop_3)\n",
+    "    model = Model(inputs=inputs, outputs=output)\n",
+    "    my_opt = optimizers.Adam(learning_rate=0.000001, beta_1=0.9, beta_2=0.999, amsgrad=False)\n",
+    "    print(model.summary)\n",
+    "    model.compile(optimizer=my_opt, loss=\"categorical_crossentropy\",\n",
+    "                  metrics=[\"accuracy\"])\n",
+    "    return model"
+   ]
   },
   {
    "cell_type": "code",