initial commit

.ipynb_checkpoints/DeepDrug-checkpoint.ipynb

@@ -0,0 +1,101 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# DeepDrug3D"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create pocket lists\n",
+    "4 pockets are created :\n",
+    "  + control\n",
+    "  + steroid\n",
+    "  + heme\n",
+    "  + nucleotide"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open(\"control.list\", \"r\") as filin:\n",
+    "    control = filin.read()\n",
+    "control = control.split(\"\\n\")\n",
+    "control.pop()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open(\"steroid.list\", \"r\") as filin:\n",
+    "    steroid = filin.read()\n",
+    "steroid = steroid.split(\"\\n\")\n",
+    "steroid.pop()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open(\"heme.list\", \"r\") as filin:\n",
+    "    heme = filin.read()\n",
+    "heme = heme.split(\"\\n\")\n",
+    "heme.pop()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open(\"nucleotide.list\", \"r\") as filin:\n",
+    "    nucleotide = filin.read()\n",
+    "nucleotide = nucleotide.split(\"\\n\")\n",
+    "nucleotide.pop()"
+   ]
+  }
+ ],
+ "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": 4
+}

.ipynb_checkpoints/secondary_struct-checkpoint.ipynb

@@ -0,0 +1,387 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import keras\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "\n",
+    "from sklearn.preprocessing import LabelEncoder\n",
+    "from keras.models import Sequential\n",
+    "from keras.layers import Dense, Flatten, TimeDistributed\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 Conv1D, AveragePooling1D"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def file_to_dataframe(filename):\n",
+    "    \"\"\"\n",
+    "    Returns a pandas dataframe ncol = len(longest_sequence),\n",
+    "                               nrow = number of sequences\n",
+    "                               \n",
+    "    Arguments :\n",
+    "        - filename : str\n",
+    "            path to file\n",
+    "    Takes a path to a files containing any sequences, must be 1 sequence\n",
+    "    per line.\n",
+    "    \n",
+    "    Sequences shorter than longest_sequence are completed with '0' char.\n",
+    "    \"\"\"\n",
+    "    filin = open(filename)\n",
+    "    fastas0 = filin.read()\n",
+    "    fastas0 = fastas0.split('\\n')\n",
+    "    nmax = len(max(fastas0, key=len))\n",
+    "    fastas = []\n",
+    "    for fasta in fastas0:\n",
+    "        fastas.append(fasta + (nmax - len(fasta)) * '0')\n",
+    "    \n",
+    "    seqs = pd.DataFrame(index=range(len(fastas)), columns=range(nmax))\n",
+    "    \n",
+    "    for i, fasta in enumerate(fastas):\n",
+    "        seqs.loc[i] = pd.Series(list(fasta))\n",
+    "    \n",
+    "    return seqs"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [],
+   "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=(759,21)) # 759 aa, 21 car onehot\n",
+    "    conv_1 = Conv1D(25, (5), padding=\"same\", activation=\"relu\",\n",
+    "                        kernel_initializer=\"he_normal\")(inputs)\n",
+    "    conv_2 = Conv1D(35, (5), padding=\"same\", activation=\"relu\",\n",
+    "                        kernel_initializer=\"he_normal\")(conv_1)\n",
+    "    output = TimeDistributed(Dense(4, activation='softmax'))(conv_2)\n",
+    "    model = Model(inputs=inputs, outputs=output)\n",
+    "    print(model.summary)\n",
+    "    model.compile(optimizer=\"adam\", loss=\"categorical_crossentropy\",\n",
+    "                  metrics=[\"accuracy\"])\n",
+    "    return model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def char_to_onehot(df, ncol=0):\n",
+    "    \"\"\"\n",
+    "    Returns the given str-encoded dataframe into a onehot encoded dataframe as an array object\n",
+    "    \n",
+    "    * Arguments:\n",
+    "        - df : pandas.DataFrame, the dataframe containing the sequences, cell \n",
+    "                               containing strings.\n",
+    "        - ncol : int, Optionnal. the number of col used to build the LabelEncoder\n",
+    "                    which will transform the df cells into int(categorical).\n",
+    "    \"\"\"\n",
+    "    classes = LabelEncoder()\n",
+    "    classes.fit(df[ncol])\n",
+    "    df_categorical = df.apply(func=classes.transform, axis=0)\n",
+    "    df_onehot = keras.utils.to_categorical(df_categorical)\n",
+    "    return df_onehot"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def true_accuracy(predictions, onehot_Y_test):\n",
+    "    \"\"\"\n",
+    "    Computes the accuracy ignoring the \"0\" of the DataFrame.\n",
+    "    \n",
+    "    * Arguments :\n",
+    "        - predictions : numpy.array, output of the model, onehot encoded.\n",
+    "        - onehot_Y_test : numpy.array, the true values, onehot encoded.\n",
+    "        \n",
+    "    * Returns :\n",
+    "        - acc_coor : int, accuracy corrected, not considering '0' predictions\n",
+    "    \"\"\"\n",
+    "    tp = 0\n",
+    "    tn = 0\n",
+    "    fn = 0\n",
+    "    fp = 0\n",
+    "    tot = 0\n",
+    "\n",
+    "    for i in range(len(predictions)):\n",
+    "        for j in range(len(predictions[i])):\n",
+    "            if onehot_Y_test[i, j, 3] != 0.:\n",
+    "                predmax = -1\n",
+    "                predict_class = -1\n",
+    "                true_class = -1\n",
+    "                for k in range(len(predictions[i, j])):\n",
+    "                    if predmax < predictions[i, j, k]:\n",
+    "                        predmax = predictions[i, j, k]\n",
+    "                        predict_class = k\n",
+    "                    if onehot_Y_test[i, j, k] == 1.:\n",
+    "                        true_class = k\n",
+    "                if predict_class == true_class:\n",
+    "                    tp = tp+1\n",
+    "                tot = tot + 1\n",
+    "    acc_corr = tp/tot*100\n",
+    "    return acc_corr"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Create dataframe from files\n",
+    "fasta = file_to_dataframe(\"data/train.fasta\")\n",
+    "fasta = fasta.replace(\"X\", \"A\") # 'X' in fasta sequences are replace with 'A'\n",
+    "dssp = file_to_dataframe(\"data/train.dssp\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Writes Dataframes to csv files\n",
+    "fasta.to_csv(path_or_buf=\"data/train_fasta.csv\")\n",
+    "dssp.to_csv(path_or_buf=\"data/train_dssp.csv\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# To onehot\n",
+    "fasta_onehot = char_to_onehot(fasta, 0)\n",
+    "dssp_onehot = char_to_onehot(dssp, 2)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Divides the dataset in train and test subsets\n",
+    "fasta_train = fasta_onehot[0:1000,]\n",
+    "dssp_train = dssp_onehot[0:1000,]\n",
+    "fasta_test = fasta_onehot[1000:,]\n",
+    "dssp_test = dssp_onehot[1000:]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<bound method Network.summary of <keras.engine.training.Model object at 0x7f68cfb7b0d0>>\n",
+      "Epoch 1/30\n",
+      "1000/1000 [==============================] - 2s 2ms/step - loss: 0.7467 - acc: 0.7447\n",
+      "Epoch 2/30\n",
+      "1000/1000 [==============================] - 1s 974us/step - loss: 0.2610 - acc: 0.8944\n",
+      "Epoch 3/30\n",
+      "1000/1000 [==============================] - 1s 964us/step - loss: 0.2053 - acc: 0.9086\n",
+      "Epoch 4/30\n",
+      "1000/1000 [==============================] - 1s 994us/step - loss: 0.1899 - acc: 0.9154\n",
+      "Epoch 5/30\n",
+      "1000/1000 [==============================] - 1s 986us/step - loss: 0.1817 - acc: 0.9193\n",
+      "Epoch 6/30\n",
+      "1000/1000 [==============================] - 1s 1ms/step - loss: 0.1790 - acc: 0.9201\n",
+      "Epoch 7/30\n",
+      "1000/1000 [==============================] - 1s 1ms/step - loss: 0.1759 - acc: 0.9217\n",
+      "Epoch 8/30\n",
+      "1000/1000 [==============================] - 1s 960us/step - loss: 0.1743 - acc: 0.9222\n",
+      "Epoch 9/30\n",
+      "1000/1000 [==============================] - 1s 977us/step - loss: 0.1735 - acc: 0.9226\n",
+      "Epoch 10/30\n",
+      "1000/1000 [==============================] - 1s 963us/step - loss: 0.1727 - acc: 0.9228\n",
+      "Epoch 11/30\n",
+      "1000/1000 [==============================] - 1s 999us/step - loss: 0.1712 - acc: 0.9239\n",
+      "Epoch 12/30\n",
+      "1000/1000 [==============================] - 1s 963us/step - loss: 0.1702 - acc: 0.9243\n",
+      "Epoch 13/30\n",
+      "1000/1000 [==============================] - 1s 1ms/step - loss: 0.1695 - acc: 0.9249\n",
+      "Epoch 14/30\n",
+      "1000/1000 [==============================] - 1s 978us/step - loss: 0.1687 - acc: 0.9252\n",
+      "Epoch 15/30\n",
+      "1000/1000 [==============================] - 1s 981us/step - loss: 0.1678 - acc: 0.9257\n",
+      "Epoch 16/30\n",
+      "1000/1000 [==============================] - 1s 985us/step - loss: 0.1669 - acc: 0.9260\n",
+      "Epoch 17/30\n",
+      "1000/1000 [==============================] - 1s 1ms/step - loss: 0.1661 - acc: 0.9267\n",
+      "Epoch 18/30\n",
+      "1000/1000 [==============================] - 1s 1000us/step - loss: 0.1656 - acc: 0.9269\n",
+      "Epoch 19/30\n",
+      "1000/1000 [==============================] - 1s 1ms/step - loss: 0.1650 - acc: 0.9273\n",
+      "Epoch 20/30\n",
+      "1000/1000 [==============================] - 1s 1ms/step - loss: 0.1640 - acc: 0.9277\n",
+      "Epoch 21/30\n",
+      "1000/1000 [==============================] - 1s 1ms/step - loss: 0.1637 - acc: 0.9281\n",
+      "Epoch 22/30\n",
+      "1000/1000 [==============================] - 1s 1ms/step - loss: 0.1630 - acc: 0.9285\n",
+      "Epoch 23/30\n",
+      "1000/1000 [==============================] - 1s 1ms/step - loss: 0.1621 - acc: 0.9289\n",
+      "Epoch 24/30\n",
+      "1000/1000 [==============================] - 1s 992us/step - loss: 0.1619 - acc: 0.9289\n",
+      "Epoch 25/30\n",
+      "1000/1000 [==============================] - 1s 1ms/step - loss: 0.1616 - acc: 0.9291\n",
+      "Epoch 26/30\n",
+      "1000/1000 [==============================] - 1s 1ms/step - loss: 0.1616 - acc: 0.9291\n",
+      "Epoch 27/30\n",
+      "1000/1000 [==============================] - 1s 1ms/step - loss: 0.1608 - acc: 0.9296\n",
+      "Epoch 28/30\n",
+      "1000/1000 [==============================] - 1s 1ms/step - loss: 0.1604 - acc: 0.9297\n",
+      "Epoch 29/30\n",
+      "1000/1000 [==============================] - 1s 1ms/step - loss: 0.1601 - acc: 0.9298\n",
+      "Epoch 30/30\n",
+      "1000/1000 [==============================] - 1s 1ms/step - loss: 0.1597 - acc: 0.9300\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<keras.callbacks.History at 0x7f68cfcf6050>"
+      ]
+     },
+     "execution_count": 27,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "model = model_sequential()\n",
+    "model.fit(fasta_train, dssp_train, epochs=30, batch_size=30)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "predictions = model.predict(fasta_test, batch_size=30)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "accuracy : 68.06409539780138\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(\"accuracy : {}\".format(true_accuracy(predictions, dssp_test)))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "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": 4
+}

DeepDrug.ipynb

@@ -0,0 +1,112 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# DeepDrug3D"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create pocket lists\n",
+    "4 pockets are created :\n",
+    "  + control\n",
+    "  + steroid\n",
+    "  + heme\n",
+    "  + nucleotide"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "''"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "with open(\"control.list\", \"r\") as filin:\n",
+    "    control = filin.read()\n",
+    "control = control.split(\"\\n\")\n",
+    "control.pop()\n",
+    "\n",
+    "with open(\"steroid.list\", \"r\") as filin:\n",
+    "    steroid = filin.read()\n",
+    "steroid = steroid.split(\"\\n\")\n",
+    "steroid.pop()\n",
+    "\n",
+    "with open(\"heme.list\", \"r\") as filin:\n",
+    "    heme = filin.read()\n",
+    "heme = heme.split(\"\\n\")\n",
+    "heme.pop()\n",
+    "\n",
+    "with open(\"nucleotide.list\", \"r\") as filin:\n",
+    "    nucleotide = filin.read()\n",
+    "nucleotide = nucleotide.split(\"\\n\")\n",
+    "nucleotide.pop()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "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": 4
+}

config.yml

@@ -0,0 +1,120 @@
+name: projet-dl
+channels:
+  - defaults
+dependencies:
+  - _libgcc_mutex=0.1=main
+  - attrs=19.1.0=py37_1
+  - backcall=0.1.0=py37_0
+  - blas=1.0=mkl
+  - bleach=3.1.0=py37_0
+  - ca-certificates=2019.5.15=1
+  - certifi=2019.6.16=py37_1
+  - dbus=1.13.6=h746ee38_0
+  - decorator=4.4.0=py37_1
+  - defusedxml=0.6.0=py_0
+  - entrypoints=0.3=py37_0
+  - expat=2.2.6=he6710b0_0
+  - fontconfig=2.13.0=h9420a91_0
+  - freetype=2.9.1=h8a8886c_1
+  - glib=2.56.2=hd408876_0
+  - gmp=6.1.2=h6c8ec71_1
+  - gst-plugins-base=1.14.0=hbbd80ab_1
+  - gstreamer=1.14.0=hb453b48_1
+  - icu=58.2=h9c2bf20_1
+  - intel-openmp=2019.4=243
+  - ipykernel=5.1.2=py37h39e3cac_0
+  - ipython=7.8.0=py37h39e3cac_0
+  - ipython_genutils=0.2.0=py37_0
+  - ipywidgets=7.5.1=py_0
+  - jedi=0.15.1=py37_0
+  - jinja2=2.10.1=py37_0
+  - jpeg=9b=h024ee3a_2
+  - json5=0.8.5=py_0
+  - jsonschema=3.0.2=py37_0
+  - jupyter=1.0.0=py37_7
+  - jupyter_client=5.3.1=py_0
+  - jupyter_console=6.0.0=py37_0
+  - jupyter_core=4.5.0=py_0
+  - jupyterlab=1.1.3=pyhf63ae98_0
+  - jupyterlab_server=1.0.0=py_1
+  - libedit=3.1.20181209=hc058e9b_0
+  - libffi=3.2.1=hd88cf55_4
+  - libgcc-ng=9.1.0=hdf63c60_0
+  - libgfortran-ng=7.3.0=hdf63c60_0
+  - libpng=1.6.37=hbc83047_0
+  - libsodium=1.0.16=h1bed415_0
+  - libstdcxx-ng=9.1.0=hdf63c60_0
+  - libuuid=1.0.3=h1bed415_2
+  - libxcb=1.13=h1bed415_1
+  - libxml2=2.9.9=hea5a465_1
+  - markupsafe=1.1.1=py37h7b6447c_0
+  - mistune=0.8.4=py37h7b6447c_0
+  - mkl=2019.4=243
+  - mkl-service=2.3.0=py37he904b0f_0
+  - mkl_fft=1.0.14=py37ha843d7b_0
+  - mkl_random=1.0.2=py37hd81dba3_0
+  - nbconvert=5.5.0=py_0
+  - nbformat=4.4.0=py37_0
+  - ncurses=6.1=he6710b0_1
+  - notebook=6.0.1=py37_0
+  - numpy=1.16.5=py37h7e9f1db_0
+  - numpy-base=1.16.5=py37hde5b4d6_0
+  - openssl=1.1.1d=h7b6447c_1
+  - pandas=0.25.1=py37he6710b0_0
+  - pandoc=2.2.3.2=0
+  - pandocfilters=1.4.2=py37_1
+  - parso=0.5.1=py_0
+  - pcre=8.43=he6710b0_0
+  - pexpect=4.7.0=py37_0
+  - pickleshare=0.7.5=py37_0
+  - pip=19.2.2=py37_0
+  - prometheus_client=0.7.1=py_0
+  - prompt_toolkit=2.0.9=py37_0
+  - ptyprocess=0.6.0=py37_0
+  - pygments=2.4.2=py_0
+  - pyqt=5.9.2=py37h05f1152_2
+  - pyrsistent=0.14.11=py37h7b6447c_0
+  - python=3.7.4=h265db76_1
+  - python-dateutil=2.8.0=py37_0
+  - pytz=2019.2=py_0
+  - pyzmq=18.1.0=py37he6710b0_0
+  - qt=5.9.7=h5867ecd_1
+  - qtconsole=4.5.5=py_0
+  - readline=7.0=h7b6447c_5
+  - scipy=1.3.1=py37h7c811a0_0
+  - send2trash=1.5.0=py37_0
+  - setuptools=41.0.1=py37_0
+  - sip=4.19.8=py37hf484d3e_0
+  - six=1.12.0=py37_0
+  - sqlite=3.29.0=h7b6447c_0
+  - terminado=0.8.2=py37_0
+  - testpath=0.4.2=py37_0
+  - tk=8.6.8=hbc83047_0
+  - tornado=6.0.3=py37h7b6447c_0
+  - traitlets=4.3.2=py37_0
+  - wcwidth=0.1.7=py37_0
+  - webencodings=0.5.1=py37_1
+  - wheel=0.33.4=py37_0
+  - widgetsnbextension=3.5.1=py37_0
+  - xz=5.2.4=h14c3975_4
+  - zeromq=4.3.1=he6710b0_3
+  - zlib=1.2.11=h7b6447c_3
+  - pip:
+    - biopython==1.74
+    - cycler==0.10.0
+    - griddataformats==0.5.0
+    - gsd==1.8.1
+    - joblib==0.13.2
+    - kiwisolver==1.1.0
+    - matplotlib==3.1.1
+    - mdanalysis==0.20.1
+    - mmtf-python==1.1.2
+    - mock==3.0.5
+    - msgpack==0.6.1
+    - networkx==2.3
+    - pbxplore==1.3.8
+    - pillow==6.1.0
+    - pyclustering==0.9.1
+    - pyparsing==2.4.2
+    - keras
+    - sklearn

heme.list

@@ -0,0 +1,596 @@
+101mA00
+1a2sA00
+1a4eD00
+1a4fA00
+1a4fB00
+1a56A00
+1a7vA00
+1a9wB00
+1akkA00
+1allA00
+1aqeA00
+1ashA00
+1b7vA00
+1b82A00
+1b8dA01
+1bbhA00
+1bbpA00
+1bccD01
+1be3C00
+1binA00
+1bvbA03
+1bz1A00
+1c2nA00
+1c52A00
+1c6oA00
+1c6sA00
+1c7dA00
+1cc5A00
+1cchA00
+1ccrA00
+1cg5A00
+1cg5B00
+1ci3A00
+1cl6A00
+1cnoG00
+1co6A00
+1cpcA00
+1cpcB00
+1cpqA00
+1ctmA00
+1cxaA00
+1cxyA00
+1cyfA00
+1cyjA00
+1d06A00
+1d1vA00
+1d4cA02
+1d7cA01
+1d8uA00
+1dlwA00
+1dm1A00
+1drmA00
+1dvhA00
+1dvvA00
+1dw0A00
+1dxtB00
+1e29A00
+1ebtA00
+1ecaA00
+1egyA00
+1etpA01
+1euoA00
+1ew6A00
+1ezvC00
+1f1cA00
+1f4uA00
+1f5oA00
+1f99A00
+1f99B00
+1fcbA00
+1fcdD01
+1fdhB00
+1fftE01
+1fhfA00
+1fj0A00
+1fs7A01
+1ft9A00
+1gcvA00
+1gcvB00
+1gdiA00
+1gdvA00
+1gjqA00
+1gksA00
+1gm4A02
+1gqaA00
+1gu2A00
+1gu6B01
+1gwsA14
+1gyoA03
+1h1oB02
+1h21A01
+1h31A01
+1h31B00
+1h97A00
+1hbgA00
+1hbhA00
+1hbhB00
+1hbrA00
+1hdsD00
+1he2A01
+1hlbA00
+1hlmA00
+1hroA00
+1i7yA00
+1iqcB01
+1it2A00
+1ithA00
+1iw1A01
+1ix3A00
+1izoA00
+1j0pA00
+1j77A00
+1jdlA00
+1jebA00
+1jjuA01
+1jmxA01
+1jniA01
+1jrxA02
+1kibA00
+1kn1B00
+1kqgC00
+1kr7A00
+1kwjA00
+1kx2A00
+1lhsA00
+1liaB00
+1ls9A00
+1ly8B03
+1m1pA01
+1m56A01
+1m7sA00
+1mg2D00
+1mhlB04
+1mj4A00
+1mjtA01
+1mqfA00
+1mwbA00
+1mytA00
+1n5uA05
+1ngkB00
+1nr6A00
+1ntfA00
+1oagA00
+1oahB02
+1ofwA09
+1ogyB01
+1oj6B00
+1or4A00
+1os6A02
+1outA00
+1outB00
+1prhA00
+1q90A00
+1qdbC04
+1qgwA00
+1qgwD02
+1qjsA00
+1qksA00
+1qn1A01
+1qn2A00
+1qwlA00
+1r3qA00
+1rz6A00
+1s56B00
+1s5lP00
+1s66A00
+1schB00
+1si8A00
+1sk7A00
+1soxA01
+1sp3A07
+1spgA00
+1spgB00
+1suoA00
+1sy7B00
+1t88A00
+1tguC00
+1tu9A00
+1u17A00
+1uvxA00
+1ux8A00
+1v4uA00
+1v4wB00
+1v75A00
+1w2lA00
+1w5cB14
+1w7oA03
+1we1A00
+1wmuB00
+1woxB00
+1wveB00
+1x3kA00
+1x3xA00
+1x9fA00
+1x9fB00
+1x9fD00
+1x9fG00
+1xbnA00
+1xf6B01
+1xq5A00
+1xq5B00
+1yeaA00
+1yhuA00
+1yhuB00
+1yhuC00
+1yiqA01
+1yq4D00
+1z1nA16
+1z24A00
+1zrtB00
+1zzhB01
+2a3mA03
+2amoB00
+2bh4A00
+2bk9A00
+2bkmA00
+2blfB00
+2bq4B03
+2bz9A00
+2c0kA00
+2c1dA00
+2c1dB00
+2c1vA01
+2c2cA00
+2c7jA00
+2c7jB01
+2c8sA00
+2ccyA00
+2civA01
+2czsA00
+2d09A00
+2d0sA00
+2d0wA00
+2d1eA00
+2d2mA00
+2d2mB00
+2d2mD00
+2dc3A00
+2dgeA00
+2e74A01
+2e84A14
+2eimA03
+2flqB01
+2fmyA00
+2fw5A01
+2fynA01
+2fynB00
+2hpdB00
+2hreA00
+2i89A00
+2i96A00
+2ibjA00
+2ig3A00
+2iufA00
+2ivfC00
+2j0pA00
+2j8wA00
+2je2A00
+2jxmB00
+2k2nA00
+2k3vA03
+2k78A00
+2l4dA00
+2noxB00
+2nwbA00
+2nzaA00
+2olpA00
+2oolA00
+2oyyA00
+2ozyA04
+2pbjD00
+2q2oA00
+2q7aA01
+2q8qA00
+2qppB00
+2r1hA00
+2r1hB00
+2r4zB00
+2r79A00
+2rfbA00
+2ri4D00
+2uulA00
+2uulB00
+2uydA00
+2v7iA00
+2vgrC00
+2vhdA00
+2vjhA01
+2vjhB00
+2vjrA00
+2vjrB01
+2vjtB00
+2vr0A06
+2vr0F03
+2vywA00
+2vzwB00
+2w31A00
+2wh8B00
+2wtgA00
+2wy4A00
+2x9oA00
+2xkrA00
+2xleA00
+2xq1O00
+2xtsB00
+2xykB00
+2y4eB01
+2y8hA00
+2ybqA01
+2yevB02
+2yiuB00
+2yk3A00
+2ynmC00
+2yp1C01
+2zboA00
+2zdoD00
+2zdpA00
+2zfoC00
+2zonD00
+2zooA00
+2zt9C01
+2zzsA00
+3a15B00
+3a4hA00
+3a9fA00
+3ae3D00
+3aeqA00
+3aq5A00
+3at5A00
+3at5B00
+3awmA00
+3ayfA01
+3b42A00
+3bcqA00
+3bcqB00
+3bk9A01
+3bxuB02
+3caoA03
+3cp5A00
+3cslB00
+3cwbC03
+3cx5D00
+3czhA01
+3dbmA00
+3dmiA00
+3dp5A00
+3dr0A00
+3dsjA00
+3e4wA00
+3e65B00
+3egwC00
+3ej6B03
+3ejeH01
+3ellA00
+3emmA00
+3fjwA00
+3gasA00
+3gm6A04
+3gw9A00
+3h4nB00
+3h8tA00
+3hf4A00
+3hq8A01
+3hx9A00
+3hyuA00
+3hyuB00
+3ia8A00
+3jbbI00
+3lf5A00
+3lxiB00
+3m5qA02
+3m97A00
+3mgxA00
+3mk7A01
+3mk7B01
+3mk7C01
+3mkbB00
+3ml1B01
+3mvcA00
+3nerB00
+3nn2B00
+3notA00
+3nu1A01
+3o0rC00
+3o0rD00
+3o5cA00
+3oa8B00
+3ocdA00
+3ov0A02
+3p3zA00
+3pc3A00
+3ph2A00
+3pmqA04
+3pt7B00
+3q08A00
+3qjtA00
+3qnsA00
+3qpiB00
+3qqrB00
+3qugA00
+3qzpB00
+3r9cA00
+3rivA00
+3rtlB01
+3rwlA00
+3s1iA00
+3sikB00
+3swjA01
+3t3zB00
+3t6dA01
+3tf8B00
+3tktA00
+3tm9A00
+3u8pB00
+3ubrA01
+3ucpA02
+3ut2A00
+3vliA00
+3vlmA00
+3volA00
+3vp5A00
+3vreB00
+3w2zA00
+3wctA00
+3wctB00
+3wctC00
+3wcuD00
+3wfxA00
+3wmmA00
+3x15A00
+3zbyB00
+3zhwA00
+3ziyA00
+3zjhB00
+4aamA00
+4atjB00
+4b2nA01
+4b2yA00
+4b4yA00
+4b7fA01
+4b8nB00
+4bf4D00
+4bjaA00
+4bwiA01
+4c0nA00
+4cabA00
+4cdpA00
+4cx9A00
+4czoA00
+4d1nC01
+4e04B00
+4e37B00
+4egnB00
+4eieA00
+4ejgE00
+4f0tB01
+4fa4B00
+4fofA00
+4g1bA00
+4g1xA00
+4gd3I00
+4gl5A00
+4gu7A00
+4gydA00
+4h0mA01
+4h2lB00
+4h8qA00
+4hkaA00
+4hrrA00
+4hrrB00
+4i3bA00
+4i8vC00
+4i91A00
+4j20A00
+4j6dB00
+4jetA00
+4jj0A01
+4jouA00
+4kmgA00
+4l0dA01
+4l2mA00
+4l6gA00
+4l6vS19
+4ljiA00
+4lm6A00
+4lm6B01
+4lm8A04
+4lmhD09
+4lmsA00
+4lmsC01
+4lmxC01
+4n4jA07
+4n4oA00
+4n73A00
+4nk2A00
+4o1wA00
+4o4sG00
+4o7gB00
+4oqrA00
+4ourB01
+4pwaD01
+4pwvA00
+4qi3A00
+4qi7A00
+4qoqA00
+4r1zA00
+4rknA08
+4rlrA00
+4rm4A00
+4tx3A00
+4u72A00
+4u8uA00
+4u8uB00
+4u8uC00
+4u8uD00
+4u99A00
+4ubsA06
+4uc1A05
+4uiiA00
+4uiqA00
+4uurA00
+4uylB00
+4uzvA00
+4v2kA00
+4w7jC00
+4wnuB00
+4x8yA00
+4xdiA00
+4xe3A00
+4xkbA00
+4xmhA01
+4xtqA00
+4xxiA00
+4xxlA00
+4xydB00
+4y7sA00
+4ympB00
+4yt3A00
+4zgxJ00
+4zvbA00
+5a13B00
+5akpA00
+5aqdA01
+5aqdM03
+5aurA00
+5b3iA00
+5b3vB01
+5b50A00
+5b6qA00
+5bv2B00
+5bv5A00
+5c2vC01
+5cx7E00
+5d1vA00
+5de0C00
+5dfxA00
+5f1aA01
+5f6zA00
+5ff1B05
+5foiA00
+5fujA00
+5fygA00
+5gj3A00
+5gweA00
+5hh3B00
+5irvC00
+5jggA00
+5jnzB00
+5k8zB01
+5kyoA00
+5kzlA00
+5l8rE04
+5l91A00
+5llyC00
+5lo9A02
+5loqC01
+5lthA00
+5mapB00
+5mg1A00
+5o0tA01
+5o1lB00
+5oheF00
+5t2kB00
+5ti9C00
+5tiaD00
+5v3uA00
+5vbuA00
+5vcgA00
+5x24A00
+5xnlC16
+5xnlD16
+5xnlV04
+5xnlW16
+5xnmA18
+5y1iA00
+5y8aA00

secondary_struct.ipynb

@@ -0,0 +1,387 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import keras\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "\n",
+    "from sklearn.preprocessing import LabelEncoder\n",
+    "from keras.models import Sequential\n",
+    "from keras.layers import Dense, Flatten, TimeDistributed\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 Conv1D, AveragePooling1D"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def file_to_dataframe(filename):\n",
+    "    \"\"\"\n",
+    "    Returns a pandas dataframe ncol = len(longest_sequence),\n",
+    "                               nrow = number of sequences\n",
+    "                               \n",
+    "    Arguments :\n",
+    "        - filename : str\n",
+    "            path to file\n",
+    "    Takes a path to a files containing any sequences, must be 1 sequence\n",
+    "    per line.\n",
+    "    \n",
+    "    Sequences shorter than longest_sequence are completed with '0' char.\n",
+    "    \"\"\"\n",
+    "    filin = open(filename)\n",
+    "    fastas0 = filin.read()\n",
+    "    fastas0 = fastas0.split('\\n')\n",
+    "    nmax = len(max(fastas0, key=len))\n",
+    "    fastas = []\n",
+    "    for fasta in fastas0:\n",
+    "        fastas.append(fasta + (nmax - len(fasta)) * '0')\n",
+    "    \n",
+    "    seqs = pd.DataFrame(index=range(len(fastas)), columns=range(nmax))\n",
+    "    \n",
+    "    for i, fasta in enumerate(fastas):\n",
+    "        seqs.loc[i] = pd.Series(list(fasta))\n",
+    "    \n",
+    "    return seqs"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [],
+   "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=(759,21)) # 759 aa, 21 car onehot\n",
+    "    conv_1 = Conv1D(25, (5), padding=\"same\", activation=\"relu\",\n",
+    "                        kernel_initializer=\"he_normal\")(inputs)\n",
+    "    conv_2 = Conv1D(35, (5), padding=\"same\", activation=\"relu\",\n",
+    "                        kernel_initializer=\"he_normal\")(conv_1)\n",
+    "    output = TimeDistributed(Dense(4, activation='softmax'))(conv_2)\n",
+    "    model = Model(inputs=inputs, outputs=output)\n",
+    "    print(model.summary)\n",
+    "    model.compile(optimizer=\"adam\", loss=\"categorical_crossentropy\",\n",
+    "                  metrics=[\"accuracy\"])\n",
+    "    return model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def char_to_onehot(df, ncol=0):\n",
+    "    \"\"\"\n",
+    "    Returns the given str-encoded dataframe into a onehot encoded dataframe as an array object\n",
+    "    \n",
+    "    * Arguments:\n",
+    "        - df : pandas.DataFrame, the dataframe containing the sequences, cell \n",
+    "                               containing strings.\n",
+    "        - ncol : int, Optionnal. the number of col used to build the LabelEncoder\n",
+    "                    which will transform the df cells into int(categorical).\n",
+    "    \"\"\"\n",
+    "    classes = LabelEncoder()\n",
+    "    classes.fit(df[ncol])\n",
+    "    df_categorical = df.apply(func=classes.transform, axis=0)\n",
+    "    df_onehot = keras.utils.to_categorical(df_categorical)\n",
+    "    return df_onehot"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def true_accuracy(predictions, onehot_Y_test):\n",
+    "    \"\"\"\n",
+    "    Computes the accuracy ignoring the \"0\" of the DataFrame.\n",
+    "    \n",
+    "    * Arguments :\n",
+    "        - predictions : numpy.array, output of the model, onehot encoded.\n",
+    "        - onehot_Y_test : numpy.array, the true values, onehot encoded.\n",
+    "        \n",
+    "    * Returns :\n",
+    "        - acc_coor : int, accuracy corrected, not considering '0' predictions\n",
+    "    \"\"\"\n",
+    "    tp = 0\n",
+    "    tn = 0\n",
+    "    fn = 0\n",
+    "    fp = 0\n",
+    "    tot = 0\n",
+    "\n",
+    "    for i in range(len(predictions)):\n",
+    "        for j in range(len(predictions[i])):\n",
+    "            if onehot_Y_test[i, j, 3] != 0.:\n",
+    "                predmax = -1\n",
+    "                predict_class = -1\n",
+    "                true_class = -1\n",
+    "                for k in range(len(predictions[i, j])):\n",
+    "                    if predmax < predictions[i, j, k]:\n",
+    "                        predmax = predictions[i, j, k]\n",
+    "                        predict_class = k\n",
+    "                    if onehot_Y_test[i, j, k] == 1.:\n",
+    "                        true_class = k\n",
+    "                if predict_class == true_class:\n",
+    "                    tp = tp+1\n",
+    "                tot = tot + 1\n",
+    "    acc_corr = tp/tot*100\n",
+    "    return acc_corr"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Create dataframe from files\n",
+    "fasta = file_to_dataframe(\"data/train.fasta\")\n",
+    "fasta = fasta.replace(\"X\", \"A\") # 'X' in fasta sequences are replace with 'A'\n",
+    "dssp = file_to_dataframe(\"data/train.dssp\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Writes Dataframes to csv files\n",
+    "fasta.to_csv(path_or_buf=\"data/train_fasta.csv\")\n",
+    "dssp.to_csv(path_or_buf=\"data/train_dssp.csv\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# To onehot\n",
+    "fasta_onehot = char_to_onehot(fasta, 0)\n",
+    "dssp_onehot = char_to_onehot(dssp, 2)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Divides the dataset in train and test subsets\n",
+    "fasta_train = fasta_onehot[0:1000,]\n",
+    "dssp_train = dssp_onehot[0:1000,]\n",
+    "fasta_test = fasta_onehot[1000:,]\n",
+    "dssp_test = dssp_onehot[1000:]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<bound method Network.summary of <keras.engine.training.Model object at 0x7f68cfb7b0d0>>\n",
+      "Epoch 1/30\n",
+      "1000/1000 [==============================] - 2s 2ms/step - loss: 0.7467 - acc: 0.7447\n",
+      "Epoch 2/30\n",
+      "1000/1000 [==============================] - 1s 974us/step - loss: 0.2610 - acc: 0.8944\n",
+      "Epoch 3/30\n",
+      "1000/1000 [==============================] - 1s 964us/step - loss: 0.2053 - acc: 0.9086\n",
+      "Epoch 4/30\n",
+      "1000/1000 [==============================] - 1s 994us/step - loss: 0.1899 - acc: 0.9154\n",
+      "Epoch 5/30\n",
+      "1000/1000 [==============================] - 1s 986us/step - loss: 0.1817 - acc: 0.9193\n",
+      "Epoch 6/30\n",
+      "1000/1000 [==============================] - 1s 1ms/step - loss: 0.1790 - acc: 0.9201\n",
+      "Epoch 7/30\n",
+      "1000/1000 [==============================] - 1s 1ms/step - loss: 0.1759 - acc: 0.9217\n",
+      "Epoch 8/30\n",
+      "1000/1000 [==============================] - 1s 960us/step - loss: 0.1743 - acc: 0.9222\n",
+      "Epoch 9/30\n",
+      "1000/1000 [==============================] - 1s 977us/step - loss: 0.1735 - acc: 0.9226\n",
+      "Epoch 10/30\n",
+      "1000/1000 [==============================] - 1s 963us/step - loss: 0.1727 - acc: 0.9228\n",
+      "Epoch 11/30\n",
+      "1000/1000 [==============================] - 1s 999us/step - loss: 0.1712 - acc: 0.9239\n",
+      "Epoch 12/30\n",
+      "1000/1000 [==============================] - 1s 963us/step - loss: 0.1702 - acc: 0.9243\n",
+      "Epoch 13/30\n",
+      "1000/1000 [==============================] - 1s 1ms/step - loss: 0.1695 - acc: 0.9249\n",
+      "Epoch 14/30\n",
+      "1000/1000 [==============================] - 1s 978us/step - loss: 0.1687 - acc: 0.9252\n",
+      "Epoch 15/30\n",
+      "1000/1000 [==============================] - 1s 981us/step - loss: 0.1678 - acc: 0.9257\n",
+      "Epoch 16/30\n",
+      "1000/1000 [==============================] - 1s 985us/step - loss: 0.1669 - acc: 0.9260\n",
+      "Epoch 17/30\n",
+      "1000/1000 [==============================] - 1s 1ms/step - loss: 0.1661 - acc: 0.9267\n",
+      "Epoch 18/30\n",
+      "1000/1000 [==============================] - 1s 1000us/step - loss: 0.1656 - acc: 0.9269\n",
+      "Epoch 19/30\n",
+      "1000/1000 [==============================] - 1s 1ms/step - loss: 0.1650 - acc: 0.9273\n",
+      "Epoch 20/30\n",
+      "1000/1000 [==============================] - 1s 1ms/step - loss: 0.1640 - acc: 0.9277\n",
+      "Epoch 21/30\n",
+      "1000/1000 [==============================] - 1s 1ms/step - loss: 0.1637 - acc: 0.9281\n",
+      "Epoch 22/30\n",
+      "1000/1000 [==============================] - 1s 1ms/step - loss: 0.1630 - acc: 0.9285\n",
+      "Epoch 23/30\n",
+      "1000/1000 [==============================] - 1s 1ms/step - loss: 0.1621 - acc: 0.9289\n",
+      "Epoch 24/30\n",
+      "1000/1000 [==============================] - 1s 992us/step - loss: 0.1619 - acc: 0.9289\n",
+      "Epoch 25/30\n",
+      "1000/1000 [==============================] - 1s 1ms/step - loss: 0.1616 - acc: 0.9291\n",
+      "Epoch 26/30\n",
+      "1000/1000 [==============================] - 1s 1ms/step - loss: 0.1616 - acc: 0.9291\n",
+      "Epoch 27/30\n",
+      "1000/1000 [==============================] - 1s 1ms/step - loss: 0.1608 - acc: 0.9296\n",
+      "Epoch 28/30\n",
+      "1000/1000 [==============================] - 1s 1ms/step - loss: 0.1604 - acc: 0.9297\n",
+      "Epoch 29/30\n",
+      "1000/1000 [==============================] - 1s 1ms/step - loss: 0.1601 - acc: 0.9298\n",
+      "Epoch 30/30\n",
+      "1000/1000 [==============================] - 1s 1ms/step - loss: 0.1597 - acc: 0.9300\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<keras.callbacks.History at 0x7f68cfcf6050>"
+      ]
+     },
+     "execution_count": 27,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "model = model_sequential()\n",
+    "model.fit(fasta_train, dssp_train, epochs=30, batch_size=30)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "predictions = model.predict(fasta_test, batch_size=30)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "accuracy : 68.06409539780138\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(\"accuracy : {}\".format(true_accuracy(predictions, dssp_test)))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "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": 4
+}

steroid.list

@@ -0,0 +1,69 @@
+1a28A00
+1afsA01
+1aquA01
+1coyA00
+1dbbB00
+1dbjA00
+1eupA02
+1fdtA00
+1h60A01
+1hv5E01
+1i7gA01
+1jnhB00
+1kdkA00
+1nfqA01
+1ogzA00
+1oh0B00
+1q13A01
+1q20A01
+1vpoB00
+1x8jA01
+1xj7A01
+1xnxA00
+1xv9B00
+1y5rA01
+1yb1A00
+2aaxA00
+2d06A01
+2hzqA00
+2ipgA01
+2o5yB00
+2qp4A00
+2v95A00
+2vctA00
+3burA01
+3eauA02
+3gn8A01
+3kdmB00
+3mnpA01
+3oikA00
+3ollA00
+3q95B00
+3rukD01
+3s79A01
+3wo2C02
+4c3yH02
+4c49A00
+4dvqA01
+4j6cA00
+4jvlA01
+4l1wA01
+4ltwA00
+4pleA02
+4qckA00
+4qdcA00
+4qdfB00
+4qf7A00
+4r1zA01
+4r21B01
+4ubtA01
+4x1gA00
+4y8wC01
+5a1pA01
+5hgcA00
+5hs6A01
+5if6A00
+5l91A04
+5lurA00
+5vb2D05
+6f88A01