Update trained model

README.md

@@ -2,10 +2,15 @@
 
 locimend is a tool that corrects DNA sequencing errors using Deep Learning.
 
+The goal is to provide a correct DNA sequence, when a sequence containing errors is provided.
+
+It provides both a command-line program and a REST API.
+
 ## Technologies
 
 - Tensorflow
 - Biopython
+- FastAPI
 
 ## Installation
 
@@ -37,13 +42,70 @@ cd locimend
 nix-shell
 ```
 
+5. Install the dependencies via poetry:
+
+```bash
+poetry install
+```
+
 After running these commands, you will find yourself in a shell that
 contains all the needed dependencies.
 
 ## Usage
 
-The following command creates the dataset, trains the Deep Learning model and shows the accuracy:
+### Training the model
+
+The following command creates the trains the Deep Learning model and shows the accuracy and AUC:
 
 ```bash
-poetry run python src/model.py
+poetry run python locimend/main.py train <data file> <label file>
 ```
+
+- <data file>: FASTQ file containing the sequences with errors
+- <label file>: FASTQ file containing the sequences without errors
+
+Both files must contain the canonical and read simulated sequences in the same positions (same row).
+
+A dataset is provided to train the model, in order to proceed execute the following command:
+
+```bash
+poetry run python locimend/main.py train data/curesim-HVR.fastq data/HVR.fastq
+```
+
+
+### Inference
+
+A trained model is provided, which can be used to infer the correct sequences. There are two ways to interact with it:
+
+- Command-line execution
+- REST API
+
+#### Command-line
+
+The following command will infer the correct sequence, and print it:
+
+```bash
+poetry run python locimend/main.py infer "<DNA sequence>"
+```
+
+#### REST API
+
+It is also possible to serve the model via a REST API, to start the web server run the following command:
+
+```bash
+poetry run api
+```
+
+The API can be accessed at http://localhost:8000, with either a GET or POST request:
+
+| Request | Endpoint | Payload |
+|:----:|:-----:|:-----:|
+| GET     | / | Sequence as a path parameter (in the URL) |
+| POST     | /| JSON |
+
+For a POST request the JSON must have the following structure:
+
+```json
+{"sequence": "<DNA sequence>"}
+```
+

default.nix

@@ -0,0 +1,5 @@
+{ sources ? import ./nix/sources.nix, pkgs ? import sources.nixpkgs { } }:
+
+with pkgs;
+
+poetry2nix.mkPoetryApplication { projectDir = ./.; }

docker.nix

@@ -0,0 +1,14 @@
+{ sources ? import ./nix/sources.nix, pkgs ? import sources.nixpkgs { } }:
+
+with pkgs;
+
+let locimend = callPackage ./default.nix { };
+
+in {
+  docker = dockerTools.streamLayeredImage {
+    name = "locimend";
+    contents = [ locimend ];
+    config.Cmd = [ "api" ];
+  };
+
+}

docs/locimend.ipynb

@@ -1,388 +0,0 @@
-{
-  "nbformat": 4,
-  "nbformat_minor": 0,
-  "metadata": {
-    "colab": {
-      "name": "locimend.ipynb",
-      "provenance": []
-    },
-    "kernelspec": {
-      "name": "python3",
-      "display_name": "Python 3"
-    },
-    "language_info": {
-      "name": "python"
-    }
-  },
-  "cells": [
-    {
-      "cell_type": "code",
-      "metadata": {
-        "id": "sRYtN362elcw"
-      },
-      "source": [
-        "# Constants\n",
-        "BASES = \"ACGT\"\n",
-        "TRAIN_DATASET = \"data/train_data.tfrecords\"\n",
-        "TEST_DATASET = \"data/test_data.tfrecords\"\n",
-        "EVAL_DATASET = \"data/eval_data.tfrecords\"\n",
-        "EPOCHS = 1000\n",
-        "BATCH_SIZE = 256\n",
-        "LEARNING_RATE = 0.004\n",
-        "L2 = 0.001\n",
-        "LOG_DIR = \"logs\""
-      ],
-      "execution_count": 4,
-      "outputs": []
-    },
-    {
-      "cell_type": "code",
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "mjwJOPSbvA0Y",
-        "outputId": "bb7fce1c-5758-4da8-e8a1-acd5275f979e"
-      },
-      "source": [
-        "!mkdir logs\n",
-        "!mkdir data\n",
-        "!curl -fL https://git.coolneng.duckdns.org/coolneng/locimend/raw/branch/master/data/HVR.fastq -o data/HVR.fastq\n",
-        "!curl -fL https://git.coolneng.duckdns.org/coolneng/locimend/raw/branch/master/data/curesim-HVR.fastq -o data/curesim-HVR.fastq"
-      ],
-      "execution_count": 3,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "text": [
-            "mkdir: cannot create directory ‘logs’: File exists\n",
-            "  % Total    % Received % Xferd  Average Speed   Time    Time     Time  Current\n",
-            "                                 Dload  Upload   Total   Spent    Left  Speed\n",
-            "100 1074k  100 1074k    0     0   804k      0  0:00:01  0:00:01 --:--:--  804k\n",
-            "  % Total    % Received % Xferd  Average Speed   Time    Time     Time  Current\n",
-            "                                 Dload  Upload   Total   Spent    Left  Speed\n",
-            "100 1484k  100 1484k    0     0   321k      0  0:00:04  0:00:04 --:--:--  321k\n"
-          ],
-          "name": "stdout"
-        }
-      ]
-    },
-    {
-      "cell_type": "code",
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "-uWm7bS7fkRE",
-        "outputId": "347d17aa-752e-425c-e727-71df2a32da67"
-      },
-      "source": [
-        "!pip install biopython"
-      ],
-      "execution_count": 5,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "text": [
-            "Collecting biopython\n",
-            "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/5a/42/de1ed545df624180b84c613e5e4de4848f72989ce5846a74af6baa0737b9/biopython-1.79-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.whl (2.3MB)\n",
-            "\u001b[K     |████████████████████████████████| 2.3MB 5.2MB/s \n",
-            "\u001b[?25hRequirement already satisfied: numpy in /usr/local/lib/python3.7/dist-packages (from biopython) (1.19.5)\n",
-            "Installing collected packages: biopython\n",
-            "Successfully installed biopython-1.79\n"
-          ],
-          "name": "stdout"
-        }
-      ]
-    },
-    {
-      "cell_type": "code",
-      "metadata": {
-        "id": "CKFwG1_afwFU"
-      },
-      "source": [
-        "from typing import List, Tuple\n",
-        "\n",
-        "from Bio.motifs import create\n",
-        "from Bio.SeqIO import parse\n",
-        "from numpy.random import random\n",
-        "from tensorflow import Tensor, int64, stack, cast, int32\n",
-        "from tensorflow.sparse import to_dense\n",
-        "from tensorflow.data import TFRecordDataset\n",
-        "from tensorflow.io import (\n",
-        "    FixedLenFeature,\n",
-        "    TFRecordWriter,\n",
-        "    VarLenFeature,\n",
-        "    parse_single_example,\n",
-        ")\n",
-        "from tensorflow.train import Example, Feature, Features, Int64List\n",
-        "\n",
-        "\n",
-        "\n",
-        "def generate_example(sequence, label, base_counts) -> bytes:\n",
-        "    \"\"\"\n",
-        "    Create a binary-string for each sequence containing the sequence and the bases' counts\n",
-        "    \"\"\"\n",
-        "    schema = {\n",
-        "        \"A_counts\": Feature(int64_list=Int64List(value=[sum(base_counts[\"A\"])])),\n",
-        "        \"C_counts\": Feature(int64_list=Int64List(value=[sum(base_counts[\"C\"])])),\n",
-        "        \"G_counts\": Feature(int64_list=Int64List(value=[sum(base_counts[\"G\"])])),\n",
-        "        \"T_counts\": Feature(int64_list=Int64List(value=[sum(base_counts[\"T\"])])),\n",
-        "        \"sequence\": Feature(int64_list=Int64List(value=encode_sequence(sequence))),\n",
-        "        \"label\": Feature(int64_list=Int64List(value=encode_sequence(label))),\n",
-        "    }\n",
-        "    example = Example(features=Features(feature=schema))\n",
-        "    return example.SerializeToString()\n",
-        "\n",
-        "\n",
-        "def encode_sequence(sequence) -> List[int]:\n",
-        "    \"\"\"\n",
-        "    Encode the DNA sequence using the indices of the BASES constant\n",
-        "    \"\"\"\n",
-        "    encoded_sequence = [BASES.index(element) for element in sequence]\n",
-        "    return encoded_sequence\n",
-        "\n",
-        "\n",
-        "def read_fastq(data_file, label_file) -> List[bytes]:\n",
-        "    \"\"\"\n",
-        "    Parses a data and a label FASTQ files and generates a List of serialized Examples\n",
-        "    \"\"\"\n",
-        "    examples = []\n",
-        "    with open(data_file) as data, open(label_file) as labels:\n",
-        "        for element, label in zip(parse(data, \"fastq\"), parse(labels, \"fastq\")):\n",
-        "            motifs = create([element.seq])\n",
-        "            example = generate_example(\n",
-        "                sequence=str(element.seq),\n",
-        "                label=str(label.seq),\n",
-        "                base_counts=motifs.counts,\n",
-        "            )\n",
-        "            examples.append(example)\n",
-        "    return examples\n",
-        "\n",
-        "\n",
-        "def create_dataset(\n",
-        "    data_file, label_file, train_eval_test_split=[0.8, 0.1, 0.1]\n",
-        ") -> None:\n",
-        "    \"\"\"\n",
-        "    Create a training, evaluation and test dataset with a 80/10/30 split respectively\n",
-        "    \"\"\"\n",
-        "    data = read_fastq(data_file, label_file)\n",
-        "    with TFRecordWriter(TRAIN_DATASET) as training, TFRecordWriter(\n",
-        "        TEST_DATASET\n",
-        "    ) as test, TFRecordWriter(EVAL_DATASET) as evaluation:\n",
-        "        for element in data:\n",
-        "            if random() < train_eval_test_split[0]:\n",
-        "                training.write(element)\n",
-        "            elif random() < train_eval_test_split[0] + train_eval_test_split[1]:\n",
-        "                evaluation.write(element)\n",
-        "            else:\n",
-        "                test.write(element)\n",
-        "\n",
-        "\n",
-        "def transform_features(parsed_features) -> List[Tensor]:\n",
-        "    \"\"\"\n",
-        "    Cast and transform the parsed features of an Example into a list of Tensors\n",
-        "    \"\"\"\n",
-        "    sparse_features = [\"sequence\", \"label\"]\n",
-        "    for feature in sparse_features:\n",
-        "        parsed_features[feature] = cast(parsed_features[feature], int32)\n",
-        "        parsed_features[feature] = to_dense(parsed_features[feature])\n",
-        "    for base in BASES:\n",
-        "        parsed_features[f\"{base}_counts\"] = cast(\n",
-        "            parsed_features[f\"{base}_counts\"], int32\n",
-        "        )\n",
-        "    features = list(parsed_features.values())[:-1]\n",
-        "    return features\n",
-        "\n",
-        "\n",
-        "def process_input(byte_string) -> Tuple[Tensor, Tensor]:\n",
-        "    \"\"\"\n",
-        "    Parse a byte-string into an Example object\n",
-        "    \"\"\"\n",
-        "    schema = {\n",
-        "        \"A_counts\": FixedLenFeature(shape=[1], dtype=int64),\n",
-        "        \"C_counts\": FixedLenFeature(shape=[1], dtype=int64),\n",
-        "        \"G_counts\": FixedLenFeature(shape=[1], dtype=int64),\n",
-        "        \"T_counts\": FixedLenFeature(shape=[1], dtype=int64),\n",
-        "        \"sequence\": VarLenFeature(dtype=int64),\n",
-        "        \"label\": VarLenFeature(dtype=int64),\n",
-        "    }\n",
-        "    parsed_features = parse_single_example(byte_string, features=schema)\n",
-        "    features = transform_features(parsed_features)\n",
-        "    return stack(features, axis=-1), parsed_features[\"label\"]\n",
-        "\n",
-        "\n",
-        "def read_dataset(filepath) -> TFRecordDataset:\n",
-        "    \"\"\"\n",
-        "    Read TFRecords files and generate a dataset\n",
-        "    \"\"\"\n",
-        "    data_input = TFRecordDataset(filenames=filepath)\n",
-        "    dataset = data_input.map(map_func=process_input)\n",
-        "    shuffled_dataset = dataset.shuffle(buffer_size=10000, seed=42)\n",
-        "    batched_dataset = shuffled_dataset.batch(batch_size=BATCH_SIZE).repeat(count=EPOCHS)\n",
-        "    return batched_dataset\n",
-        "\n",
-        "\n",
-        "def dataset_creation(\n",
-        "    data_file, label_file\n",
-        ") -> Tuple[TFRecordDataset, TFRecordDataset, TFRecordDataset]:\n",
-        "    \"\"\"\n",
-        "    Generate the TFRecord files and split them into training, validation and test data\n",
-        "    \"\"\"\n",
-        "    create_dataset(data_file, label_file)\n",
-        "    train_data = read_dataset(TRAIN_DATASET)\n",
-        "    eval_data = read_dataset(EVAL_DATASET)\n",
-        "    test_data = read_dataset(TEST_DATASET)\n",
-        "    return train_data, eval_data, test_data\n",
-        "\n"
-      ],
-      "execution_count": 6,
-      "outputs": []
-    },
-    {
-      "cell_type": "code",
-      "metadata": {
-        "id": "UXAAAVolf7GA"
-      },
-      "source": [
-        "from random import seed\n",
-        "\n",
-        "from tensorflow.keras import Model, Sequential, layers\n",
-        "from tensorflow.keras.callbacks import TensorBoard\n",
-        "from tensorflow.keras.losses import sparse_categorical_crossentropy\n",
-        "from tensorflow.keras.optimizers import Adam\n",
-        "from tensorflow.keras.regularizers import l2\n",
-        "from tensorflow.random import set_seed\n",
-        "\n",
-        "\n",
-        "def build_model() -> Model:\n",
-        "    \"\"\"\n",
-        "    Build the CNN model\n",
-        "    \"\"\"\n",
-        "    model = Sequential()\n",
-        "    model.add(\n",
-        "        layers.Conv1D(\n",
-        "            filters=16,\n",
-        "            kernel_size=5,\n",
-        "            activation=\"relu\",\n",
-        "            kernel_regularizer=l2(L2),\n",
-        "        )\n",
-        "    )\n",
-        "    model.add(layers.MaxPool1D(pool_size=3, strides=1))\n",
-        "    model.add(\n",
-        "        layers.Conv1D(\n",
-        "            filters=16,\n",
-        "            kernel_size=3,\n",
-        "            activation=\"relu\",\n",
-        "            kernel_regularizer=l2(L2),\n",
-        "        )\n",
-        "    )\n",
-        "    model.add(layers.MaxPool1D(pool_size=3, strides=1))\n",
-        "    model.add(layers.Flatten())\n",
-        "    model.add(\n",
-        "        layers.Dense(\n",
-        "            units=16,\n",
-        "            activation=\"relu\",\n",
-        "            kernel_regularizer=l2(L2),\n",
-        "        )\n",
-        "    )\n",
-        "    model.add(layers.Dropout(rate=0.3))\n",
-        "    model.add(\n",
-        "        layers.Dense(\n",
-        "            units=16,\n",
-        "            activation=\"relu\",\n",
-        "            kernel_regularizer=l2(L2),\n",
-        "        )\n",
-        "    )\n",
-        "    model.add(layers.Dropout(rate=0.3))\n",
-        "    # FIXME Change output size\n",
-        "    model.add(layers.Dense(units=len(BASES), activation=\"softmax\"))\n",
-        "    model.compile(\n",
-        "        optimizer=Adam(LEARNING_RATE),\n",
-        "        loss=sparse_categorical_crossentropy,\n",
-        "        metrics=[\"accuracy\"],\n",
-        "    )\n",
-        "    return model\n",
-        "\n",
-        "\n",
-        "def show_metrics(model, eval_dataset, test_dataset) -> None:\n",
-        "    \"\"\"\n",
-        "    Show the model metrics\n",
-        "    \"\"\"\n",
-        "    eval_metrics = model.evaluate(eval_dataset, verbose=0)\n",
-        "    test_metrics = model.evaluate(test_dataset, verbose=0)\n",
-        "    print(f\"Final eval metrics - loss: {eval_metrics[0]} - accuracy: {eval_metrics[1]}\")\n",
-        "    print(f\"Final test metrics - loss: {test_metrics[0]} - accuracy: {test_metrics[1]}\")\n",
-        "\n",
-        "\n",
-        "def run(data_file, label_file, seed_value=42) -> None:\n",
-        "    \"\"\"\n",
-        "    Create a dataset, a model and runs training and evaluation on it\n",
-        "    \"\"\"\n",
-        "    seed(seed_value)\n",
-        "    set_seed(seed_value)\n",
-        "    train_data, eval_data, test_data = dataset_creation(data_file, label_file)\n",
-        "    tensorboard = TensorBoard(log_dir=LOG_DIR, histogram_freq=1, profile_batch=0)\n",
-        "    model = build_model()\n",
-        "    print(\"Training the model\")\n",
-        "    model.fit(\n",
-        "        train_data,\n",
-        "        epochs=EPOCHS,\n",
-        "        validation_data=eval_data,\n",
-        "        callbacks=[tensorboard],\n",
-        "        verbose=0,\n",
-        "    )\n",
-        "    print(\"Training complete. Obtaining final metrics...\")\n",
-        "    show_metrics(model, eval_data, test_data)"
-      ],
-      "execution_count": 7,
-      "outputs": []
-    },
-    {
-      "cell_type": "code",
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 1000
-        },
-        "id": "V8BuUmpIgDqc",
-        "outputId": "e7f697dc-a459-4e4e-ed98-406b44e120fc"
-      },
-      "source": [
-        "run(data_file=\"data/curesim-HVR.fastq\", label_file=\"data/HVR.fastq\")"
-      ],
-      "execution_count": 8,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "text": [
-            "Training the model\n"
-          ],
-          "name": "stdout"
-        },
-        {
-          "output_type": "error",
-          "ename": "TypeError",
-          "evalue": "ignored",
-          "traceback": [
-            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-            "\u001b[0;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
-            "\u001b[0;32m<ipython-input-8-4b0e5d1da156>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mrun\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdata_file\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m\"data/curesim-HVR.fastq\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlabel_file\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m\"data/HVR.fastq\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
-            "\u001b[0;32m<ipython-input-7-d8ed7ecffd74>\u001b[0m in \u001b[0;36mrun\u001b[0;34m(data_file, label_file, seed_value)\u001b[0m\n\u001b[1;32m     84\u001b[0m         \u001b[0mvalidation_data\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0meval_data\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     85\u001b[0m         \u001b[0mcallbacks\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mtensorboard\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 86\u001b[0;31m         \u001b[0mverbose\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     87\u001b[0m     )\n\u001b[1;32m     88\u001b[0m     \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"Training complete. Obtaining final metrics...\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-            "\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training.py\u001b[0m in \u001b[0;36mfit\u001b[0;34m(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_batch_size, validation_freq, max_queue_size, workers, use_multiprocessing)\u001b[0m\n\u001b[1;32m   1181\u001b[0m                 _r=1):\n\u001b[1;32m   1182\u001b[0m               \u001b[0mcallbacks\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mon_train_batch_begin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mstep\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1183\u001b[0;31m               \u001b[0mtmp_logs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtrain_function\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0miterator\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1184\u001b[0m               \u001b[0;32mif\u001b[0m \u001b[0mdata_handler\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mshould_sync\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1185\u001b[0m                 \u001b[0mcontext\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0masync_wait\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-            "\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/def_function.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, *args, **kwds)\u001b[0m\n\u001b[1;32m    887\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    888\u001b[0m       \u001b[0;32mwith\u001b[0m \u001b[0mOptionalXlaContext\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_jit_compile\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 889\u001b[0;31m         \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwds\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    890\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    891\u001b[0m       \u001b[0mnew_tracing_count\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mexperimental_get_tracing_count\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-            "\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/def_function.py\u001b[0m in \u001b[0;36m_call\u001b[0;34m(self, *args, **kwds)\u001b[0m\n\u001b[1;32m    931\u001b[0m       \u001b[0;31m# This is the first call of __call__, so we have to initialize.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    932\u001b[0m       \u001b[0minitializers\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 933\u001b[0;31m       \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_initialize\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkwds\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0madd_initializers_to\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0minitializers\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    934\u001b[0m     \u001b[0;32mfinally\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    935\u001b[0m       \u001b[0;31m# At this point we know that the initialization is complete (or less\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-            "\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/def_function.py\u001b[0m in \u001b[0;36m_initialize\u001b[0;34m(self, args, kwds, add_initializers_to)\u001b[0m\n\u001b[1;32m    762\u001b[0m     self._concrete_stateful_fn = (\n\u001b[1;32m    763\u001b[0m         self._stateful_fn._get_concrete_function_internal_garbage_collected(  # pylint: disable=protected-access\n\u001b[0;32m--> 764\u001b[0;31m             *args, **kwds))\n\u001b[0m\u001b[1;32m    765\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    766\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0minvalid_creator_scope\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0munused_args\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0munused_kwds\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-            "\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/function.py\u001b[0m in \u001b[0;36m_get_concrete_function_internal_garbage_collected\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   3048\u001b[0m       \u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkwargs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   3049\u001b[0m     \u001b[0;32mwith\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_lock\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 3050\u001b[0;31m       \u001b[0mgraph_function\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0m_\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_maybe_define_function\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   3051\u001b[0m     \u001b[0;32mreturn\u001b[0m \u001b[0mgraph_function\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   3052\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
-            "\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/function.py\u001b[0m in \u001b[0;36m_maybe_define_function\u001b[0;34m(self, args, kwargs)\u001b[0m\n\u001b[1;32m   3442\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   3443\u001b[0m           \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_function_cache\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmissed\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0madd\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcall_context_key\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 3444\u001b[0;31m           \u001b[0mgraph_function\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_create_graph_function\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   3445\u001b[0m           \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_function_cache\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mprimary\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mcache_key\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mgraph_function\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   3446\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
-            "\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/function.py\u001b[0m in \u001b[0;36m_create_graph_function\u001b[0;34m(self, args, kwargs, override_flat_arg_shapes)\u001b[0m\n\u001b[1;32m   3287\u001b[0m             \u001b[0marg_names\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0marg_names\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   3288\u001b[0m             \u001b[0moverride_flat_arg_shapes\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0moverride_flat_arg_shapes\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 3289\u001b[0;31m             capture_by_value=self._capture_by_value),\n\u001b[0m\u001b[1;32m   3290\u001b[0m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_function_attributes\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   3291\u001b[0m         \u001b[0mfunction_spec\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfunction_spec\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-            "\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/func_graph.py\u001b[0m in \u001b[0;36mfunc_graph_from_py_func\u001b[0;34m(name, python_func, args, kwargs, signature, func_graph, autograph, autograph_options, add_control_dependencies, arg_names, op_return_value, collections, capture_by_value, override_flat_arg_shapes)\u001b[0m\n\u001b[1;32m    997\u001b[0m         \u001b[0m_\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0moriginal_func\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtf_decorator\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0munwrap\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mpython_func\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    998\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 999\u001b[0;31m       \u001b[0mfunc_outputs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpython_func\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0mfunc_args\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mfunc_kwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1000\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1001\u001b[0m       \u001b[0;31m# invariant: `func_outputs` contains only Tensors, CompositeTensors,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-            "\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/def_function.py\u001b[0m in \u001b[0;36mwrapped_fn\u001b[0;34m(*args, **kwds)\u001b[0m\n\u001b[1;32m    670\u001b[0m         \u001b[0;31m# the function a weak reference to itself to avoid a reference cycle.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    671\u001b[0m         \u001b[0;32mwith\u001b[0m \u001b[0mOptionalXlaContext\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcompile_with_xla\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 672\u001b[0;31m           \u001b[0mout\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mweak_wrapped_fn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__wrapped__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwds\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    673\u001b[0m         \u001b[0;32mreturn\u001b[0m \u001b[0mout\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    674\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
-            "\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/func_graph.py\u001b[0m in \u001b[0;36mwrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m    984\u001b[0m           \u001b[0;32mexcept\u001b[0m \u001b[0mException\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m  \u001b[0;31m# pylint:disable=broad-except\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    985\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0mhasattr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0me\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m\"ag_error_metadata\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 986\u001b[0;31m               \u001b[0;32mraise\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mag_error_metadata\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mto_exception\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0me\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    987\u001b[0m             \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    988\u001b[0m               \u001b[0;32mraise\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-            "\u001b[0;31mTypeError\u001b[0m: in user code:\n\n    /usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training.py:855 train_function  *\n        return step_function(self, iterator)\n    /usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training.py:845 step_function  **\n        outputs = model.distribute_strategy.run(run_step, args=(data,))\n    /usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/distribute_lib.py:1285 run\n        return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)\n    /usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/distribute_lib.py:2833 call_for_each_replica\n        return self._call_for_each_replica(fn, args, kwargs)\n    /usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/distribute_lib.py:3608 _call_for_each_replica\n        return fn(*args, **kwargs)\n    /usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training.py:838 run_step  **\n        outputs = model.train_step(data)\n    /usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training.py:795 train_step\n        y_pred = self(x, training=True)\n    /usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/base_layer.py:1030 __call__\n        outputs = call_fn(inputs, *args, **kwargs)\n    /usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/sequential.py:394 call\n        outputs = layer(inputs, **kwargs)\n    /usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/base_layer.py:1030 __call__\n        outputs = call_fn(inputs, *args, **kwargs)\n    /usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/layers/convolutional.py:249 call\n        outputs = self._convolution_op(inputs, self.kernel)\n    /usr/local/lib/python3.7/dist-packages/tensorflow/python/util/dispatch.py:206 wrapper\n        return target(*args, **kwargs)\n    /usr/local/lib/python3.7/dist-packages/tensorflow/python/ops/nn_ops.py:1019 convolution_v2\n        name=name)\n    /usr/local/lib/python3.7/dist-packages/tensorflow/python/ops/nn_ops.py:1149 convolution_internal\n        name=name)\n    /usr/local/lib/python3.7/dist-packages/tensorflow/python/util/dispatch.py:206 wrapper\n        return target(*args, **kwargs)\n    /usr/local/lib/python3.7/dist-packages/tensorflow/python/util/deprecation.py:602 new_func\n        return func(*args, **kwargs)\n    /usr/local/lib/python3.7/dist-packages/tensorflow/python/util/deprecation.py:602 new_func\n        return func(*args, **kwargs)\n    /usr/local/lib/python3.7/dist-packages/tensorflow/python/ops/nn_ops.py:1892 conv1d\n        name=name)\n    /usr/local/lib/python3.7/dist-packages/tensorflow/python/ops/gen_nn_ops.py:973 conv2d\n        data_format=data_format, dilations=dilations, name=name)\n    /usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/op_def_library.py:558 _apply_op_helper\n        inferred_from[input_arg.type_attr]))\n\n    TypeError: Input 'filter' of 'Conv2D' Op has type float32 that does not match type int32 of argument 'input'.\n"
-          ]
-        }
-      ]
-    }
-  ]
-}

locimend/api.py

@@ -0,0 +1,27 @@
+from fastapi import FastAPI
+from pydantic import BaseModel
+from uvicorn import run
+
+from locimend.model import infer_sequence
+
+app = FastAPI()
+
+
+class Input(BaseModel):
+    sequence: str
+
+
+@app.get("/{sequence}")
+async def get_sequence_path(sequence: str):
+    correct_sequence = await infer_sequence(sequence)
+    return {"sequence": correct_sequence}
+
+
+@app.post("/")
+async def get_sequence_body(sequence: Input):
+    correct_sequence = await infer_sequence(sequence.sequence)
+    return {"sequence": correct_sequence}
+
+
+def main():
+    run(app, host="0.0.0.0")

locimend/hyperparameters.py

@@ -0,0 +1,24 @@
+class Hyperparameters:
+    def __init__(
+        self,
+        data_file,
+        label_file,
+        train_dataset="data/train_data.tfrecords",
+        test_dataset="data/test_data.tfrecords",
+        eval_dataset="data/eval_data.tfrecords",
+        epochs=100,
+        batch_size=64,
+        learning_rate=0.004,
+        l2_rate=0.001,
+        max_length=80,
+    ):
+        self.data_file = data_file
+        self.label_file = label_file
+        self.train_dataset = train_dataset
+        self.eval_dataset = eval_dataset
+        self.test_dataset = test_dataset
+        self.epochs = epochs
+        self.batch_size = batch_size
+        self.learning_rate = learning_rate
+        self.l2_rate = l2_rate
+        self.max_length = max_length

locimend/main.py

@@ -0,0 +1,40 @@
+from asyncio import run
+from argparse import ArgumentParser, Namespace
+from time import time
+
+from locimend.model import infer_sequence, train_model
+
+
+def parse_arguments() -> Namespace:
+    parser = ArgumentParser()
+    subparsers = parser.add_subparsers(dest="task")
+    parser_train = subparsers.add_parser("train")
+    parser_infer = subparsers.add_parser("infer")
+    parser_train.add_argument(
+        "data_file", help="FASTQ file containing the sequences with errors"
+    )
+    parser_train.add_argument(
+        "label_file", help="FASTQ file containing the sequences without errors"
+    )
+    parser_infer.add_argument("sequence", help="DNA sequence with errors")
+    return parser.parse_args()
+
+
+async def execute_task(args):
+    if args.task == "train":
+        start_time = time()
+        train_model(data_file=args.data_file, label_file=args.label_file)
+        end_time = time()
+        print(f"Training time: {end_time - start_time}")
+    else:
+        prediction = await infer_sequence(sequence=args.sequence)
+        print(f"Error-corrected sequence: {prediction}")
+
+
+def main() -> None:
+    args = parse_arguments()
+    run(execute_task(args))
+
+
+if __name__ == "__main__":
+    main()

locimend/model.py

@@ -0,0 +1,89 @@
+from random import seed
+
+from numpy import argmax
+from tensorflow import one_hot
+from tensorflow.keras import Model, Sequential
+from tensorflow.keras.layers import Dense, Dropout, Input, Masking
+from tensorflow.keras.losses import categorical_crossentropy
+from tensorflow.keras.models import load_model
+from tensorflow.keras.optimizers import Adam
+from tensorflow.keras.regularizers import l2
+from tensorflow.random import set_seed
+
+from locimend.hyperparameters import Hyperparameters
+from locimend.preprocessing import (
+    BASES,
+    dataset_creation,
+    decode_sequence,
+    encode_sequence,
+)
+
+
+def build_model(hyperparams) -> Model:
+    """
+    Build the CNN model
+    """
+    model = Sequential(
+        [
+            Input(shape=(hyperparams.max_length, len(BASES))),
+            Masking(mask_value=-1),
+            Dense(
+                units=256, activation="relu", kernel_regularizer=l2(hyperparams.l2_rate)
+            ),
+            Dropout(rate=0.3),
+            Dense(
+                units=128, activation="relu", kernel_regularizer=l2(hyperparams.l2_rate)
+            ),
+            Dropout(rate=0.3),
+            Dense(
+                units=64, activation="relu", kernel_regularizer=l2(hyperparams.l2_rate)
+            ),
+            Dropout(rate=0.3),
+            Dense(units=len(BASES), activation="softmax"),
+        ]
+    )
+    model.compile(
+        optimizer=Adam(hyperparams.learning_rate),
+        loss=categorical_crossentropy,
+        metrics=["accuracy", "AUC"],
+    )
+    return model
+
+
+def show_metrics(model, eval_dataset, test_dataset) -> None:
+    """
+    Show the model metrics
+    """
+    eval_metrics = model.evaluate(eval_dataset, verbose=0)
+    test_metrics = model.evaluate(test_dataset, verbose=0)
+    print(f"Eval metrics {eval_metrics}")
+    print(f"Test metrics {test_metrics}")
+
+
+def train_model(data_file, label_file, seed_value=42) -> None:
+    """
+    Create a dataset, a model and runs training and evaluation on it
+    """
+    seed(seed_value)
+    set_seed(seed_value)
+    hyperparams = Hyperparameters(data_file=data_file, label_file=label_file)
+    train_data, eval_data, test_data = dataset_creation(hyperparams)
+    model = build_model(hyperparams)
+    print("Training the model")
+    model.fit(train_data, epochs=hyperparams.epochs, validation_data=eval_data)
+    print("Training complete. Obtaining the model's metrics...")
+    show_metrics(model, eval_data, test_data)
+    model.save("trained_model")
+
+
+async def infer_sequence(sequence) -> str:
+    """
+    Predict the correct sequence, using the trained model
+    """
+    model = load_model("trained_model")
+    encoded_sequence = encode_sequence(sequence)
+    one_hot_encoded_sequence = one_hot(encoded_sequence, depth=len(BASES))
+    prediction = model.predict(one_hot_encoded_sequence)
+    encoded_prediction = argmax(prediction, axis=1)
+    final_prediction = decode_sequence(encoded_prediction)
+    return final_prediction

locimend/preprocessing.py

@@ -3,14 +3,13 @@ from typing import Dict, List, Tuple
 from Bio.pairwise2 import align
 from Bio.SeqIO import parse
 from numpy.random import random
-from tensorflow import Tensor, int64
+from tensorflow import Tensor, int64, one_hot
-from tensorflow.data import TFRecordDataset
 from tensorflow.data import AUTOTUNE, TFRecordDataset
 from tensorflow.io import TFRecordWriter, VarLenFeature, parse_single_example
 from tensorflow.sparse import to_dense
 from tensorflow.train import Example, Feature, Features, Int64List
 
-from constants import *
+BASES = "ACGT-"
 
 
 def align_sequences(sequence, label) -> Tuple[str, str]:
@@ -23,19 +22,6 @@ def align_sequences(sequence, label) -> Tuple[str, str]:
     return aligned_seq, aligned_label
 
 
-def generate_example(sequence, label) -> bytes:
-    """
-    Create a binary-string for each sequence containing the sequence and the bases' counts
-    """
-    aligned_seq, aligned_label = align_sequences(sequence, label)
-    schema = {
-        "sequence": Feature(int64_list=Int64List(value=encode_sequence(aligned_seq))),
-        "label": Feature(int64_list=Int64List(value=encode_sequence(aligned_label))),
-    }
-    example = Example(features=Features(feature=schema))
-    return example.SerializeToString()
-
-
 def encode_sequence(sequence) -> List[int]:
     """
     Encode the DNA sequence using the indices of the BASES constant
@@ -44,29 +30,59 @@ def encode_sequence(sequence) -> List[int]:
     return encoded_sequence
 
 
-def read_fastq(data_file, label_file) -> List[bytes]:
+def decode_sequence(sequence) -> str:
+    """
+    Decode an index encoded sequence back to the human readable format
+    """
+    decoded_list = [BASES[element] for element in sequence]
+    sequence = "".join(decoded_list)
+    return sequence
+
+
+def prepare_sequences(sequence, label):
+    """
+    Align and encode the sequences to obtain a fixed length output in order to perform batching
+    """
+    encoded_sequences = []
+    aligned_seq, aligned_label = align_sequences(sequence, label)
+    for item in [aligned_seq, aligned_label]:
+        encoded_sequences.append(encode_sequence(item))
+    return encoded_sequences[0], encoded_sequences[1]
+
+
+def generate_example(sequence, label) -> bytes:
+    """
+    Create a binary-string for each sequence containing the sequence and the bases' counts
+    """
+    processed_seq, processed_label = prepare_sequences(sequence, label)
+    schema = {
+        "sequence": Feature(int64_list=Int64List(value=processed_seq)),
+        "label": Feature(int64_list=Int64List(value=processed_label)),
+    }
+    example = Example(features=Features(feature=schema))
+    return example.SerializeToString()
+
+
+def read_fastq(hyperparams) -> List[bytes]:
     """
     Parses a data and a label FASTQ files and generates a List of serialized Examples
     """
     examples = []
-    with open(data_file) as data, open(label_file) as labels:
+    with open(hyperparams.data_file) as data, open(hyperparams.label_file) as labels:
         for element, label in zip(parse(data, "fastq"), parse(labels, "fastq")):
-            example = generate_example(
+            example = generate_example(sequence=str(element.seq), label=str(label.seq))
-                sequence=str(element.seq),
-                label=str(label.seq),
-            )
             examples.append(example)
     return examples
 
 
-def create_dataset(data_file, label_file, dataset_split=[0.8, 0.1, 0.1]) -> None:
+def create_dataset(hyperparams, dataset_split=[0.8, 0.1, 0.1]) -> None:
     """
     Create a training, evaluation and test dataset with a 80/10/10 split respectively
     """
-    data = read_fastq(data_file, label_file)
+    data = read_fastq(hyperparams)
-    with TFRecordWriter(TRAIN_DATASET) as training, TFRecordWriter(
+    with TFRecordWriter(hyperparams.train_dataset) as training, TFRecordWriter(
-        TEST_DATASET
+        hyperparams.test_dataset
-    ) as test, TFRecordWriter(EVAL_DATASET) as evaluation:
+    ) as test, TFRecordWriter(hyperparams.eval_dataset) as evaluation:
         for element in data:
             if random() < dataset_split[0]:
                 training.write(element)
@@ -78,12 +94,13 @@ def create_dataset(data_file, label_file, dataset_split=[0.8, 0.1, 0.1]) -> None
 
 def transform_features(parsed_features) -> Dict[str, Tensor]:
     """
-    Transform the parsed features of an Example into a list of dense Tensors
+    Transform the parsed features of an Example into a list of dense one hot encoded Tensors
     """
     features = {}
     sparse_features = ["sequence", "label"]
     for element in sparse_features:
         features[element] = to_dense(parsed_features[element])
+        features[element] = one_hot(features[element], depth=len(BASES))
     return features
 
 
@@ -100,25 +117,32 @@ def process_input(byte_string) -> Tuple[Tensor, Tensor]:
     return features["sequence"], features["label"]
 
 
-def read_dataset(filepath) -> TFRecordDataset:
+def read_dataset(filepath, hyperparams) -> TFRecordDataset:
     """
     Read TFRecords files and generate a dataset
     """
     data_input = TFRecordDataset(filenames=filepath)
     dataset = data_input.map(map_func=process_input, num_parallel_calls=AUTOTUNE)
     shuffled_dataset = dataset.shuffle(buffer_size=10000, seed=42)
-    batched_dataset = shuffled_dataset.batch(batch_size=BATCH_SIZE).repeat(count=EPOCHS)
+    batched_dataset = shuffled_dataset.padded_batch(
+        batch_size=hyperparams.batch_size,
+        padded_shapes=(
+            [hyperparams.max_length, len(BASES)],
+            [hyperparams.max_length, len(BASES)],
+        ),
+        padding_values=-1.0,
+    )
     return batched_dataset
 
 
 def dataset_creation(
-    data_file, label_file
+    hyperparams,
 ) -> Tuple[TFRecordDataset, TFRecordDataset, TFRecordDataset]:
     """
     Generate the TFRecord files and split them into training, validation and test data
     """
-    create_dataset(data_file, label_file)
+    create_dataset(hyperparams)
-    train_data = read_dataset(TRAIN_DATASET)
+    train_data = read_dataset(hyperparams.train_dataset, hyperparams)
-    eval_data = read_dataset(EVAL_DATASET)
+    eval_data = read_dataset(hyperparams.eval_dataset, hyperparams)
-    test_data = read_dataset(TEST_DATASET)
+    test_data = read_dataset(hyperparams.test_dataset, hyperparams)
     return train_data, eval_data, test_data

nix/sources.json

@@ -17,10 +17,10 @@
         "homepage": "",
         "owner": "NixOS",
         "repo": "nixpkgs",
-        "rev": "0d337eb6b77c8911cd02ed92e63fcc2a8949b404",
+        "rev": "f930ea227cecaed1f1bdb047fef54fe4f0721c8c",
-        "sha256": "1xm6ss7j3zscpiczz3kxjad3jd1qvy5zpm35kqri6p9mp4jzna1x",
+        "sha256": "04khbc44lppzz0m2g56zr7vafv4fvnb7rfbz7c03dqw6k99svj1c",
         "type": "tarball",
-        "url": "https://github.com/NixOS/nixpkgs/archive/0d337eb6b77c8911cd02ed92e63fcc2a8949b404.tar.gz",
+        "url": "https://github.com/NixOS/nixpkgs/archive/f930ea227cecaed1f1bdb047fef54fe4f0721c8c.tar.gz",
         "url_template": "https://github.com/<owner>/<repo>/archive/<rev>.tar.gz"
     }
 }

poetry.lock

@@ -0,0 +1,913 @@
+[[package]]
+name = "absl-py"
+version = "0.12.0"
+description = "Abseil Python Common Libraries, see https://github.com/abseil/abseil-py."
+category = "main"
+optional = false
+python-versions = "*"
+
+[package.dependencies]
+six = "*"
+
+[[package]]
+name = "asgiref"
+version = "3.4.1"
+description = "ASGI specs, helper code, and adapters"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
+[package.extras]
+tests = ["pytest", "pytest-asyncio", "mypy (>=0.800)"]
+
+[[package]]
+name = "astunparse"
+version = "1.6.3"
+description = "An AST unparser for Python"
+category = "main"
+optional = false
+python-versions = "*"
+
+[package.dependencies]
+six = ">=1.6.1,<2.0"
+
+[[package]]
+name = "biopython"
+version = "1.78"
+description = "Freely available tools for computational molecular biology."
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
+[package.dependencies]
+numpy = "*"
+
+[[package]]
+name = "cachetools"
+version = "4.2.2"
+description = "Extensible memoizing collections and decorators"
+category = "main"
+optional = false
+python-versions = "~=3.5"
+
+[[package]]
+name = "certifi"
+version = "2020.12.5"
+description = "Python package for providing Mozilla's CA Bundle."
+category = "main"
+optional = false
+python-versions = "*"
+
+[[package]]
+name = "chardet"
+version = "4.0.0"
+description = "Universal encoding detector for Python 2 and 3"
+category = "main"
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*"
+
+[[package]]
+name = "click"
+version = "8.0.1"
+description = "Composable command line interface toolkit"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
+[package.dependencies]
+colorama = {version = "*", markers = "platform_system == \"Windows\""}
+
+[[package]]
+name = "colorama"
+version = "0.4.4"
+description = "Cross-platform colored terminal text."
+category = "main"
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*"
+
+[[package]]
+name = "fastapi"
+version = "0.66.0"
+description = "FastAPI framework, high performance, easy to learn, fast to code, ready for production"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
+[package.dependencies]
+pydantic = ">=1.6.2,<1.7 || >1.7,<1.7.1 || >1.7.1,<1.7.2 || >1.7.2,<1.7.3 || >1.7.3,<1.8 || >1.8,<1.8.1 || >1.8.1,<2.0.0"
+starlette = "0.14.2"
+
+[package.extras]
+all = ["requests (>=2.24.0,<3.0.0)", "aiofiles (>=0.5.0,<0.6.0)", "jinja2 (>=2.11.2,<3.0.0)", "python-multipart (>=0.0.5,<0.0.6)", "itsdangerous (>=1.1.0,<2.0.0)", "pyyaml (>=5.3.1,<6.0.0)", "graphene (>=2.1.8,<3.0.0)", "ujson (>=4.0.1,<5.0.0)", "orjson (>=3.2.1,<4.0.0)", "email_validator (>=1.1.1,<2.0.0)", "uvicorn[standard] (>=0.12.0,<0.14.0)", "async_exit_stack (>=1.0.1,<2.0.0)", "async_generator (>=1.10,<2.0.0)"]
+dev = ["python-jose[cryptography] (>=3.1.0,<4.0.0)", "passlib[bcrypt] (>=1.7.2,<2.0.0)", "autoflake (>=1.3.1,<2.0.0)", "flake8 (>=3.8.3,<4.0.0)", "uvicorn[standard] (>=0.12.0,<0.14.0)", "graphene (>=2.1.8,<3.0.0)"]
+doc = ["mkdocs (>=1.1.2,<2.0.0)", "mkdocs-material (>=7.1.9,<8.0.0)", "markdown-include (>=0.6.0,<0.7.0)", "mkdocs-markdownextradata-plugin (>=0.1.7,<0.2.0)", "typer-cli (>=0.0.12,<0.0.13)", "pyyaml (>=5.3.1,<6.0.0)"]
+test = ["pytest (==5.4.3)", "pytest-cov (==2.10.0)", "pytest-asyncio (>=0.14.0,<0.15.0)", "mypy (==0.812)", "flake8 (>=3.8.3,<4.0.0)", "black (==20.8b1)", "isort (>=5.0.6,<6.0.0)", "requests (>=2.24.0,<3.0.0)", "httpx (>=0.14.0,<0.15.0)", "email_validator (>=1.1.1,<2.0.0)", "sqlalchemy (>=1.3.18,<1.4.0)", "peewee (>=3.13.3,<4.0.0)", "databases[sqlite] (>=0.3.2,<0.4.0)", "orjson (>=3.2.1,<4.0.0)", "ujson (>=4.0.1,<5.0.0)", "async_exit_stack (>=1.0.1,<2.0.0)", "async_generator (>=1.10,<2.0.0)", "python-multipart (>=0.0.5,<0.0.6)", "aiofiles (>=0.5.0,<0.6.0)", "flask (>=1.1.2,<2.0.0)"]
+
+[[package]]
+name = "flatbuffers"
+version = "1.12"
+description = "The FlatBuffers serialization format for Python"
+category = "main"
+optional = false
+python-versions = "*"
+
+[[package]]
+name = "gast"
+version = "0.3.3"
+description = "Python AST that abstracts the underlying Python version"
+category = "main"
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
+
+[[package]]
+name = "google-auth"
+version = "1.30.0"
+description = "Google Authentication Library"
+category = "main"
+optional = false
+python-versions = ">=2.7,!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*"
+
+[package.dependencies]
+cachetools = ">=2.0.0,<5.0"
+pyasn1-modules = ">=0.2.1"
+rsa = {version = ">=3.1.4,<5", markers = "python_version >= \"3.6\""}
+six = ">=1.9.0"
+
+[package.extras]
+aiohttp = ["aiohttp (>=3.6.2,<4.0.0dev)"]
+pyopenssl = ["pyopenssl (>=20.0.0)"]
+reauth = ["pyu2f (>=0.1.5)"]
+
+[[package]]
+name = "google-auth-oauthlib"
+version = "0.4.4"
+description = "Google Authentication Library"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
+[package.dependencies]
+google-auth = ">=1.0.0"
+requests-oauthlib = ">=0.7.0"
+
+[package.extras]
+tool = ["click (>=6.0.0)"]
+
+[[package]]
+name = "google-pasta"
+version = "0.2.0"
+description = "pasta is an AST-based Python refactoring library"
+category = "main"
+optional = false
+python-versions = "*"
+
+[package.dependencies]
+six = "*"
+
+[[package]]
+name = "grpcio"
+version = "1.32.0"
+description = "HTTP/2-based RPC framework"
+category = "main"
+optional = false
+python-versions = "*"
+
+[package.dependencies]
+six = ">=1.5.2"
+
+[package.extras]
+protobuf = ["grpcio-tools (>=1.32.0)"]
+
+[[package]]
+name = "h11"
+version = "0.12.0"
+description = "A pure-Python, bring-your-own-I/O implementation of HTTP/1.1"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
+[[package]]
+name = "h5py"
+version = "2.10.0"
+description = "Read and write HDF5 files from Python"
+category = "main"
+optional = false
+python-versions = "*"
+
+[package.dependencies]
+numpy = ">=1.7"
+six = "*"
+
+[[package]]
+name = "idna"
+version = "2.10"
+description = "Internationalized Domain Names in Applications (IDNA)"
+category = "main"
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
+
+[[package]]
+name = "isort"
+version = "5.8.0"
+description = "A Python utility / library to sort Python imports."
+category = "dev"
+optional = false
+python-versions = ">=3.6,<4.0"
+
+[package.extras]
+pipfile_deprecated_finder = ["pipreqs", "requirementslib"]
+requirements_deprecated_finder = ["pipreqs", "pip-api"]
+colors = ["colorama (>=0.4.3,<0.5.0)"]
+
+[[package]]
+name = "keras-preprocessing"
+version = "1.1.2"
+description = "Easy data preprocessing and data augmentation for deep learning models"
+category = "main"
+optional = false
+python-versions = "*"
+
+[package.dependencies]
+numpy = ">=1.9.1"
+six = ">=1.9.0"
+
+[package.extras]
+image = ["scipy (>=0.14)", "Pillow (>=5.2.0)"]
+pep8 = ["flake8"]
+tests = ["pandas", "pillow", "tensorflow", "keras", "pytest", "pytest-xdist", "pytest-cov"]
+
+[[package]]
+name = "markdown"
+version = "3.3.4"
+description = "Python implementation of Markdown."
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
+[package.extras]
+testing = ["coverage", "pyyaml"]
+
+[[package]]
+name = "numpy"
+version = "1.19.5"
+description = "NumPy is the fundamental package for array computing with Python."
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
+[[package]]
+name = "oauthlib"
+version = "3.1.0"
+description = "A generic, spec-compliant, thorough implementation of the OAuth request-signing logic"
+category = "main"
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
+
+[package.extras]
+rsa = ["cryptography"]
+signals = ["blinker"]
+signedtoken = ["cryptography", "pyjwt (>=1.0.0)"]
+
+[[package]]
+name = "opt-einsum"
+version = "3.3.0"
+description = "Optimizing numpys einsum function"
+category = "main"
+optional = false
+python-versions = ">=3.5"
+
+[package.dependencies]
+numpy = ">=1.7"
+
+[package.extras]
+docs = ["sphinx (==1.2.3)", "sphinxcontrib-napoleon", "sphinx-rtd-theme", "numpydoc"]
+tests = ["pytest", "pytest-cov", "pytest-pep8"]
+
+[[package]]
+name = "protobuf"
+version = "3.15.8"
+description = "Protocol Buffers"
+category = "main"
+optional = false
+python-versions = "*"
+
+[package.dependencies]
+six = ">=1.9"
+
+[[package]]
+name = "pyasn1"
+version = "0.4.8"
+description = "ASN.1 types and codecs"
+category = "main"
+optional = false
+python-versions = "*"
+
+[[package]]
+name = "pyasn1-modules"
+version = "0.2.8"
+description = "A collection of ASN.1-based protocols modules."
+category = "main"
+optional = false
+python-versions = "*"
+
+[package.dependencies]
+pyasn1 = ">=0.4.6,<0.5.0"
+
+[[package]]
+name = "pydantic"
+version = "1.8.2"
+description = "Data validation and settings management using python 3.6 type hinting"
+category = "main"
+optional = false
+python-versions = ">=3.6.1"
+
+[package.dependencies]
+typing-extensions = ">=3.7.4.3"
+
+[package.extras]
+dotenv = ["python-dotenv (>=0.10.4)"]
+email = ["email-validator (>=1.0.3)"]
+
+[[package]]
+name = "pyflakes"
+version = "2.3.1"
+description = "passive checker of Python programs"
+category = "dev"
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
+
+[[package]]
+name = "requests"
+version = "2.25.1"
+description = "Python HTTP for Humans."
+category = "main"
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*"
+
+[package.dependencies]
+certifi = ">=2017.4.17"
+chardet = ">=3.0.2,<5"
+idna = ">=2.5,<3"
+urllib3 = ">=1.21.1,<1.27"
+
+[package.extras]
+security = ["pyOpenSSL (>=0.14)", "cryptography (>=1.3.4)"]
+socks = ["PySocks (>=1.5.6,!=1.5.7)", "win-inet-pton"]
+
+[[package]]
+name = "requests-oauthlib"
+version = "1.3.0"
+description = "OAuthlib authentication support for Requests."
+category = "main"
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
+
+[package.dependencies]
+oauthlib = ">=3.0.0"
+requests = ">=2.0.0"
+
+[package.extras]
+rsa = ["oauthlib[signedtoken] (>=3.0.0)"]
+
+[[package]]
+name = "rsa"
+version = "4.7.2"
+description = "Pure-Python RSA implementation"
+category = "main"
+optional = false
+python-versions = ">=3.5, <4"
+
+[package.dependencies]
+pyasn1 = ">=0.1.3"
+
+[[package]]
+name = "six"
+version = "1.15.0"
+description = "Python 2 and 3 compatibility utilities"
+category = "main"
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*"
+
+[[package]]
+name = "starlette"
+version = "0.14.2"
+description = "The little ASGI library that shines."
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
+[package.extras]
+full = ["aiofiles", "graphene", "itsdangerous", "jinja2", "python-multipart", "pyyaml", "requests"]
+
+[[package]]
+name = "tensorboard"
+version = "2.5.0"
+description = "TensorBoard lets you watch Tensors Flow"
+category = "main"
+optional = false
+python-versions = ">= 2.7, != 3.0.*, != 3.1.*"
+
+[package.dependencies]
+absl-py = ">=0.4"
+google-auth = ">=1.6.3,<2"
+google-auth-oauthlib = ">=0.4.1,<0.5"
+grpcio = ">=1.24.3"
+markdown = ">=2.6.8"
+numpy = ">=1.12.0"
+protobuf = ">=3.6.0"
+requests = ">=2.21.0,<3"
+tensorboard-data-server = ">=0.6.0,<0.7.0"
+tensorboard-plugin-wit = ">=1.6.0"
+werkzeug = ">=0.11.15"
+
+[[package]]
+name = "tensorboard-data-server"
+version = "0.6.1"
+description = "Fast data loading for TensorBoard"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
+[[package]]
+name = "tensorboard-plugin-wit"
+version = "1.8.0"
+description = "What-If Tool TensorBoard plugin."
+category = "main"
+optional = false
+python-versions = "*"
+
+[[package]]
+name = "tensorflow"
+version = "2.4.1"
+description = "TensorFlow is an open source machine learning framework for everyone."
+category = "main"
+optional = false
+python-versions = "*"
+
+[package.dependencies]
+absl-py = ">=0.10,<1.0"
+astunparse = ">=1.6.3,<1.7.0"
+flatbuffers = ">=1.12.0,<1.13.0"
+gast = "0.3.3"
+google-pasta = ">=0.2,<1.0"
+grpcio = ">=1.32.0,<1.33.0"
+h5py = ">=2.10.0,<2.11.0"
+keras-preprocessing = ">=1.1.2,<1.2.0"
+numpy = ">=1.19.2,<1.20.0"
+opt-einsum = ">=3.3.0,<3.4.0"
+protobuf = ">=3.9.2"
+six = ">=1.15.0,<1.16.0"
+tensorboard = ">=2.4,<3.0"
+tensorflow-estimator = ">=2.4.0,<2.5.0"
+termcolor = ">=1.1.0,<1.2.0"
+typing-extensions = ">=3.7.4,<3.8.0"
+wrapt = ">=1.12.1,<1.13.0"
+
+[[package]]
+name = "tensorflow-estimator"
+version = "2.4.0"
+description = "TensorFlow Estimator."
+category = "main"
+optional = false
+python-versions = "*"
+
+[[package]]
+name = "termcolor"
+version = "1.1.0"
+description = "ANSII Color formatting for output in terminal."
+category = "main"
+optional = false
+python-versions = "*"
+
+[[package]]
+name = "typing-extensions"
+version = "3.7.4.3"
+description = "Backported and Experimental Type Hints for Python 3.5+"
+category = "main"
+optional = false
+python-versions = "*"
+
+[[package]]
+name = "urllib3"
+version = "1.26.4"
+description = "HTTP library with thread-safe connection pooling, file post, and more."
+category = "main"
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*, <4"
+
+[package.extras]
+secure = ["pyOpenSSL (>=0.14)", "cryptography (>=1.3.4)", "idna (>=2.0.0)", "certifi", "ipaddress"]
+socks = ["PySocks (>=1.5.6,!=1.5.7,<2.0)"]
+brotli = ["brotlipy (>=0.6.0)"]
+
+[[package]]
+name = "uvicorn"
+version = "0.14.0"
+description = "The lightning-fast ASGI server."
+category = "main"
+optional = false
+python-versions = "*"
+
+[package.dependencies]
+asgiref = ">=3.3.4"
+click = ">=7"
+h11 = ">=0.8"
+
+[package.extras]
+standard = ["websockets (>=9.1)", "httptools (>=0.2.0,<0.3.0)", "watchgod (>=0.6)", "python-dotenv (>=0.13)", "PyYAML (>=5.1)", "uvloop (>=0.14.0,!=0.15.0,!=0.15.1)", "colorama (>=0.4)"]
+
+[[package]]
+name = "werkzeug"
+version = "1.0.1"
+description = "The comprehensive WSGI web application library."
+category = "main"
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*"
+
+[package.extras]
+dev = ["pytest", "pytest-timeout", "coverage", "tox", "sphinx", "pallets-sphinx-themes", "sphinx-issues"]
+watchdog = ["watchdog"]
+
+[[package]]
+name = "wrapt"
+version = "1.12.1"
+description = "Module for decorators, wrappers and monkey patching."
+category = "main"
+optional = false
+python-versions = "*"
+
+[metadata]
+lock-version = "1.1"
+python-versions = "3.8.*"
+content-hash = "65002195ba305cb44acdd69909b86b82b0c837fbdcccc755ccc235c84f057a1c"
+
+[metadata.files]
+absl-py = [
+    {file = "absl-py-0.12.0.tar.gz", hash = "sha256:b44f68984a5ceb2607d135a615999b93924c771238a63920d17d3387b0d229d5"},
+    {file = "absl_py-0.12.0-py3-none-any.whl", hash = "sha256:afe94e3c751ff81aad55d33ab6e630390da32780110b5af72ae81ecff8418d9e"},
+]
+asgiref = [
+    {file = "asgiref-3.4.1-py3-none-any.whl", hash = "sha256:ffc141aa908e6f175673e7b1b3b7af4fdb0ecb738fc5c8b88f69f055c2415214"},
+    {file = "asgiref-3.4.1.tar.gz", hash = "sha256:4ef1ab46b484e3c706329cedeff284a5d40824200638503f5768edb6de7d58e9"},
+]
+astunparse = [
+    {file = "astunparse-1.6.3-py2.py3-none-any.whl", hash = "sha256:c2652417f2c8b5bb325c885ae329bdf3f86424075c4fd1a128674bc6fba4b8e8"},
+    {file = "astunparse-1.6.3.tar.gz", hash = "sha256:5ad93a8456f0d084c3456d059fd9a92cce667963232cbf763eac3bc5b7940872"},
+]
+biopython = [
+    {file = "biopython-1.78-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:0b9fbb0d3022dc22716da108b8a81b80d952cd97ac1f106de491dce850f92f62"},
+    {file = "biopython-1.78-cp36-cp36m-manylinux1_i686.whl", hash = "sha256:f5021a398c898b9cf6815cc5171c146a601b935b55364c53e6516a2545ab740c"},
+    {file = "biopython-1.78-cp36-cp36m-manylinux1_x86_64.whl", hash = "sha256:195f099c2c0c39518b6df921ab2b3cc43a601896018fc61909ac8385d5878866"},
+    {file = "biopython-1.78-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cfb93842501ebc0e0ef6520daddcbeeefc9b61736972580917dafd5c8a5a8041"},
+    {file = "biopython-1.78-cp36-cp36m-win32.whl", hash = "sha256:75b55000793f6b76334b8e80dc7e6d8cd2b019af917aa431cea6646e8e696c7f"},
+    {file = "biopython-1.78-cp36-cp36m-win_amd64.whl", hash = "sha256:f1076653937947773768455556b1d24acad9575759e9089082f32636b09add54"},
+    {file = "biopython-1.78-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:e0af107cc62a905d13d35dd7b38f335a37752ede45e4617139e84409a6a88dc4"},
+    {file = "biopython-1.78-cp37-cp37m-manylinux1_i686.whl", hash = "sha256:4565c97fab16c5697d067b821b6a1da0ec3ef36a9c96cf103ac7b4a94eb9f9ba"},
+    {file = "biopython-1.78-cp37-cp37m-manylinux1_x86_64.whl", hash = "sha256:0df5cddef2819c975e6508adf5d85aa046e449df5420d02b04871c7836b41273"},
+    {file = "biopython-1.78-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1df0bce7fd5e2414d6e18c9229fa0056914d2b9041531c71cac48f38a622142d"},
+    {file = "biopython-1.78-cp37-cp37m-win32.whl", hash = "sha256:5c0b369f91a76b8e5e36624d075585c3f0f088ea4a6e3d015c48f08e48ce0114"},
+    {file = "biopython-1.78-cp37-cp37m-win_amd64.whl", hash = "sha256:cc3b0b78022d14f11d508038a288a189d03c97c476d6636c7b6f98bd8bc8462b"},
+    {file = "biopython-1.78-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:010142a8ec2549ff0649edd497658964ef1a18eefdb9fd942ec1e81b292ce2d9"},
+    {file = "biopython-1.78-cp38-cp38-manylinux1_i686.whl", hash = "sha256:194528eda6856a4c68f840ca0bcc9b544a5edee3548b97521084e7ac38c833ca"},
+    {file = "biopython-1.78-cp38-cp38-manylinux1_x86_64.whl", hash = "sha256:ada611f12ee3b0bef7308ef41ee7b94898613b369ab44e0268d74bd1d6a06920"},
+    {file = "biopython-1.78-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d15d09bfe0d3a8a416a596a3909d9718c811df852d969592b4fa9e0da9cf7375"},
+    {file = "biopython-1.78-cp38-cp38-win32.whl", hash = "sha256:48d424453a5512a1d1d41a4acabdfe5291da1f491a2d3606f2b0e4fbd63aeda6"},
+    {file = "biopython-1.78-cp38-cp38-win_amd64.whl", hash = "sha256:2bd5a630be2a8e593094f7b1717fc962eda8931b68542b97fbf9bd8e2ac1e08d"},
+    {file = "biopython-1.78-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:b470c44d7a04e40a0cfc65853b1a5a6bf506a130c334cf4cffa05df07dbda366"},
+    {file = "biopython-1.78-cp39-cp39-manylinux1_i686.whl", hash = "sha256:c130c8e64ae2e4c7c73f0c24974ac8a832190cc3cf3c3c7b4aaffc974effc993"},
+    {file = "biopython-1.78-cp39-cp39-manylinux1_x86_64.whl", hash = "sha256:9b4374a47d924d4d4ffe2fea010ce75427bbfd92e45d50d5b1213a478baf680f"},
+    {file = "biopython-1.78-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:639461a1ac5765406ec8ab8ed619845351f2ff22fed734d86e09e4a7b7719a08"},
+    {file = "biopython-1.78-cp39-cp39-win32.whl", hash = "sha256:fe2bcf85d0f5f1888ed7d86c139e9d4e7d54e036c8ac54e929663d63548046a1"},
+    {file = "biopython-1.78-cp39-cp39-win_amd64.whl", hash = "sha256:6ed345b1ef100d58d8376e31c280b13fc87bb8f73ccc447f8140344991b61459"},
+    {file = "biopython-1.78.tar.gz", hash = "sha256:1ee0a0b6c2376680fea6642d5080baa419fd73df104a62d58a8baf7a8bbe4564"},
+]
+cachetools = [
+    {file = "cachetools-4.2.2-py3-none-any.whl", hash = "sha256:2cc0b89715337ab6dbba85b5b50effe2b0c74e035d83ee8ed637cf52f12ae001"},
+    {file = "cachetools-4.2.2.tar.gz", hash = "sha256:61b5ed1e22a0924aed1d23b478f37e8d52549ff8a961de2909c69bf950020cff"},
+]
+certifi = [
+    {file = "certifi-2020.12.5-py2.py3-none-any.whl", hash = "sha256:719a74fb9e33b9bd44cc7f3a8d94bc35e4049deebe19ba7d8e108280cfd59830"},
+    {file = "certifi-2020.12.5.tar.gz", hash = "sha256:1a4995114262bffbc2413b159f2a1a480c969de6e6eb13ee966d470af86af59c"},
+]
+chardet = [
+    {file = "chardet-4.0.0-py2.py3-none-any.whl", hash = "sha256:f864054d66fd9118f2e67044ac8981a54775ec5b67aed0441892edb553d21da5"},
+    {file = "chardet-4.0.0.tar.gz", hash = "sha256:0d6f53a15db4120f2b08c94f11e7d93d2c911ee118b6b30a04ec3ee8310179fa"},
+]
+click = [
+    {file = "click-8.0.1-py3-none-any.whl", hash = "sha256:fba402a4a47334742d782209a7c79bc448911afe1149d07bdabdf480b3e2f4b6"},
+    {file = "click-8.0.1.tar.gz", hash = "sha256:8c04c11192119b1ef78ea049e0a6f0463e4c48ef00a30160c704337586f3ad7a"},
+]
+colorama = [
+    {file = "colorama-0.4.4-py2.py3-none-any.whl", hash = "sha256:9f47eda37229f68eee03b24b9748937c7dc3868f906e8ba69fbcbdd3bc5dc3e2"},
+    {file = "colorama-0.4.4.tar.gz", hash = "sha256:5941b2b48a20143d2267e95b1c2a7603ce057ee39fd88e7329b0c292aa16869b"},
+]
+fastapi = [
+    {file = "fastapi-0.66.0-py3-none-any.whl", hash = "sha256:85d8aee8c3c46171f4cb7bb3651425a42c07cb9183345d100ef55d88ca2ce15f"},
+    {file = "fastapi-0.66.0.tar.gz", hash = "sha256:6ea4225448786f3d6fae737713789f87631a7455f65580de0a4a2e50471060d9"},
+]
+flatbuffers = [
+    {file = "flatbuffers-1.12-py2.py3-none-any.whl", hash = "sha256:9e9ef47fa92625c4721036e7c4124182668dc6021d9e7c73704edd395648deb9"},
+    {file = "flatbuffers-1.12.tar.gz", hash = "sha256:63bb9a722d5e373701913e226135b28a6f6ac200d5cc7b4d919fa38d73b44610"},
+]
+gast = [
+    {file = "gast-0.3.3-py2.py3-none-any.whl", hash = "sha256:8f46f5be57ae6889a4e16e2ca113b1703ef17f2b0abceb83793eaba9e1351a45"},
+    {file = "gast-0.3.3.tar.gz", hash = "sha256:b881ef288a49aa81440d2c5eb8aeefd4c2bb8993d5f50edae7413a85bfdb3b57"},
+]
+google-auth = [
+    {file = "google-auth-1.30.0.tar.gz", hash = "sha256:9ad25fba07f46a628ad4d0ca09f38dcb262830df2ac95b217f9b0129c9e42206"},
+    {file = "google_auth-1.30.0-py2.py3-none-any.whl", hash = "sha256:588bdb03a41ecb4978472b847881e5518b5d9ec6153d3d679aa127a55e13b39f"},
+]
+google-auth-oauthlib = [
+    {file = "google-auth-oauthlib-0.4.4.tar.gz", hash = "sha256:09832c6e75032f93818edf1affe4746121d640c625a5bef9b5c96af676e98eee"},
+    {file = "google_auth_oauthlib-0.4.4-py2.py3-none-any.whl", hash = "sha256:0e92aacacfb94978de3b7972cf4b0f204c3cd206f74ddd0dc0b31e91164e6317"},
+]
+google-pasta = [
+    {file = "google-pasta-0.2.0.tar.gz", hash = "sha256:c9f2c8dfc8f96d0d5808299920721be30c9eec37f2389f28904f454565c8a16e"},
+    {file = "google_pasta-0.2.0-py2-none-any.whl", hash = "sha256:4612951da876b1a10fe3960d7226f0c7682cf901e16ac06e473b267a5afa8954"},
+    {file = "google_pasta-0.2.0-py3-none-any.whl", hash = "sha256:b32482794a366b5366a32c92a9a9201b107821889935a02b3e51f6b432ea84ed"},
+]
+grpcio = [
+    {file = "grpcio-1.32.0-cp27-cp27m-macosx_10_9_x86_64.whl", hash = "sha256:3afb058b6929eba07dba9ae6c5b555aa1d88cb140187d78cc510bd72d0329f28"},
+    {file = "grpcio-1.32.0-cp27-cp27m-manylinux2010_i686.whl", hash = "sha256:a8004b34f600a8a51785e46859cd88f3386ef67cccd1cfc7598e3d317608c643"},
+    {file = "grpcio-1.32.0-cp27-cp27m-manylinux2010_x86_64.whl", hash = "sha256:e6786f6f7be0937614577edcab886ddce91b7c1ea972a07ef9972e9f9ecbbb78"},
+    {file = "grpcio-1.32.0-cp27-cp27m-win32.whl", hash = "sha256:e467af6bb8f5843f5a441e124b43474715cfb3981264e7cd227343e826dcc3ce"},
+    {file = "grpcio-1.32.0-cp27-cp27m-win_amd64.whl", hash = "sha256:1376a60f9bfce781b39973f100b5f67e657b5be479f2fd8a7d2a408fc61c085c"},
+    {file = "grpcio-1.32.0-cp27-cp27mu-linux_armv7l.whl", hash = "sha256:ce617e1c4a39131f8527964ac9e700eb199484937d7a0b3e52655a3ba50d5fb9"},
+    {file = "grpcio-1.32.0-cp27-cp27mu-manylinux2010_i686.whl", hash = "sha256:99bac0e2c820bf446662365df65841f0c2a55b0e2c419db86eaf5d162ddae73e"},
+    {file = "grpcio-1.32.0-cp27-cp27mu-manylinux2010_x86_64.whl", hash = "sha256:6d869a3e8e62562b48214de95e9231c97c53caa7172802236cd5d60140d7cddd"},
+    {file = "grpcio-1.32.0-cp35-cp35m-linux_armv7l.whl", hash = "sha256:182c64ade34c341398bf71ec0975613970feb175090760ab4f51d1e9a5424f05"},
+    {file = "grpcio-1.32.0-cp35-cp35m-macosx_10_7_intel.whl", hash = "sha256:9c0d8f2346c842088b8cbe3e14985b36e5191a34bf79279ba321a4bf69bd88b7"},
+    {file = "grpcio-1.32.0-cp35-cp35m-manylinux2010_i686.whl", hash = "sha256:4775bc35af9cd3b5033700388deac2e1d611fa45f4a8dcb93667d94cb25f0444"},
+    {file = "grpcio-1.32.0-cp35-cp35m-manylinux2010_x86_64.whl", hash = "sha256:be98e3198ec765d0a1e27f69d760f69374ded8a33b953dcfe790127731f7e690"},
+    {file = "grpcio-1.32.0-cp35-cp35m-manylinux2014_i686.whl", hash = "sha256:378fe80ec5d9353548eb2a8a43ea03747a80f2e387c4f177f2b3ff6c7d898753"},
+    {file = "grpcio-1.32.0-cp35-cp35m-manylinux2014_x86_64.whl", hash = "sha256:f7d508691301027033215d3662dab7e178f54d5cca2329f26a71ae175d94b83f"},
+    {file = "grpcio-1.32.0-cp35-cp35m-win32.whl", hash = "sha256:25959a651420dd4a6fd7d3e8dee53f4f5fd8c56336a64963428e78b276389a59"},
+    {file = "grpcio-1.32.0-cp35-cp35m-win_amd64.whl", hash = "sha256:ac7028d363d2395f3d755166d0161556a3f99500a5b44890421ccfaaf2aaeb08"},
+    {file = "grpcio-1.32.0-cp36-cp36m-linux_armv7l.whl", hash = "sha256:c31e8a219650ddae1cd02f5a169e1bffe66a429a8255d3ab29e9363c73003b62"},
+    {file = "grpcio-1.32.0-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:e28e4c0d4231beda5dee94808e3a224d85cbaba3cfad05f2192e6f4ec5318053"},
+    {file = "grpcio-1.32.0-cp36-cp36m-manylinux2010_i686.whl", hash = "sha256:f03dfefa9075dd1c6c5cc27b1285c521434643b09338d8b29e1d6a27b386aa82"},
+    {file = "grpcio-1.32.0-cp36-cp36m-manylinux2010_x86_64.whl", hash = "sha256:c4966d746dccb639ef93f13560acbe9630681c07f2b320b7ec03fe2c8f0a1f15"},
+    {file = "grpcio-1.32.0-cp36-cp36m-manylinux2014_i686.whl", hash = "sha256:ec10d5f680b8e95a06f1367d73c5ddcc0ed04a3f38d6e4c9346988fb0cea2ffa"},
+    {file = "grpcio-1.32.0-cp36-cp36m-manylinux2014_x86_64.whl", hash = "sha256:28677f057e2ef11501860a7bc15de12091d40b95dd0fddab3c37ff1542e6b216"},
+    {file = "grpcio-1.32.0-cp36-cp36m-win32.whl", hash = "sha256:0f3f09269ffd3fded430cd89ba2397eabbf7e47be93983b25c187cdfebb302a7"},
+    {file = "grpcio-1.32.0-cp36-cp36m-win_amd64.whl", hash = "sha256:4396b1d0f388ae875eaf6dc05cdcb612c950fd9355bc34d38b90aaa0665a0d4b"},
+    {file = "grpcio-1.32.0-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:1ada89326a364a299527c7962e5c362dbae58c67b283fe8383c4d952b26565d5"},
+    {file = "grpcio-1.32.0-cp37-cp37m-manylinux2010_i686.whl", hash = "sha256:1d384a61f96a1fc6d5d3e0b62b0a859abc8d4c3f6d16daba51ebf253a3e7df5d"},
+    {file = "grpcio-1.32.0-cp37-cp37m-manylinux2010_x86_64.whl", hash = "sha256:e811ce5c387256609d56559d944a974cc6934a8eea8c76e7c86ec388dc06192d"},
+    {file = "grpcio-1.32.0-cp37-cp37m-manylinux2014_i686.whl", hash = "sha256:07b430fa68e5eecd78e2ad529ab80f6a234b55fc1b675fe47335ccbf64c6c6c8"},
+    {file = "grpcio-1.32.0-cp37-cp37m-manylinux2014_x86_64.whl", hash = "sha256:0e3edd8cdb71809d2455b9dbff66b4dd3d36c321e64bfa047da5afdfb0db332b"},
+    {file = "grpcio-1.32.0-cp37-cp37m-win32.whl", hash = "sha256:6f7947dad606c509d067e5b91a92b250aa0530162ab99e4737090f6b17eb12c4"},
+    {file = "grpcio-1.32.0-cp37-cp37m-win_amd64.whl", hash = "sha256:7cda998b7b551503beefc38db9be18c878cfb1596e1418647687575cdefa9273"},
+    {file = "grpcio-1.32.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:c58825a3d8634cd634d8f869afddd4d5742bdb59d594aea4cea17b8f39269a55"},
+    {file = "grpcio-1.32.0-cp38-cp38-manylinux2010_i686.whl", hash = "sha256:ef9bd7fdfc0a063b4ed0efcab7906df5cae9bbcf79d05c583daa2eba56752b00"},
+    {file = "grpcio-1.32.0-cp38-cp38-manylinux2010_x86_64.whl", hash = "sha256:1ce6f5ff4f4a548c502d5237a071fa617115df58ea4b7bd41dac77c1ab126e9c"},
+    {file = "grpcio-1.32.0-cp38-cp38-manylinux2014_i686.whl", hash = "sha256:f12900be4c3fd2145ba94ab0d80b7c3d71c9e6414cfee2f31b1c20188b5c281f"},
+    {file = "grpcio-1.32.0-cp38-cp38-manylinux2014_x86_64.whl", hash = "sha256:f53f2dfc8ff9a58a993e414a016c8b21af333955ae83960454ad91798d467c7b"},
+    {file = "grpcio-1.32.0-cp38-cp38-win32.whl", hash = "sha256:5bddf9d53c8df70061916c3bfd2f468ccf26c348bb0fb6211531d895ed5e4c72"},
+    {file = "grpcio-1.32.0-cp38-cp38-win_amd64.whl", hash = "sha256:14c0f017bfebbc18139551111ac58ecbde11f4bc375b73a53af38927d60308b6"},
+    {file = "grpcio-1.32.0.tar.gz", hash = "sha256:01d3046fe980be25796d368f8fc5ff34b7cf5e1444f3789a017a7fe794465639"},
+]
+h11 = [
+    {file = "h11-0.12.0-py3-none-any.whl", hash = "sha256:36a3cb8c0a032f56e2da7084577878a035d3b61d104230d4bd49c0c6b555a9c6"},
+    {file = "h11-0.12.0.tar.gz", hash = "sha256:47222cb6067e4a307d535814917cd98fd0a57b6788ce715755fa2b6c28b56042"},
+]
+h5py = [
+    {file = "h5py-2.10.0-cp27-cp27m-macosx_10_6_intel.whl", hash = "sha256:ecf4d0b56ee394a0984de15bceeb97cbe1fe485f1ac205121293fc44dcf3f31f"},
+    {file = "h5py-2.10.0-cp27-cp27m-manylinux1_i686.whl", hash = "sha256:86868dc07b9cc8cb7627372a2e6636cdc7a53b7e2854ad020c9e9d8a4d3fd0f5"},
+    {file = "h5py-2.10.0-cp27-cp27m-manylinux1_x86_64.whl", hash = "sha256:aac4b57097ac29089f179bbc2a6e14102dd210618e94d77ee4831c65f82f17c0"},
+    {file = "h5py-2.10.0-cp27-cp27m-win32.whl", hash = "sha256:7be5754a159236e95bd196419485343e2b5875e806fe68919e087b6351f40a70"},
+    {file = "h5py-2.10.0-cp27-cp27m-win_amd64.whl", hash = "sha256:13c87efa24768a5e24e360a40e0bc4c49bcb7ce1bb13a3a7f9902cec302ccd36"},
+    {file = "h5py-2.10.0-cp27-cp27mu-manylinux1_i686.whl", hash = "sha256:79b23f47c6524d61f899254f5cd5e486e19868f1823298bc0c29d345c2447172"},
+    {file = "h5py-2.10.0-cp27-cp27mu-manylinux1_x86_64.whl", hash = "sha256:cbf28ae4b5af0f05aa6e7551cee304f1d317dbed1eb7ac1d827cee2f1ef97a99"},
+    {file = "h5py-2.10.0-cp34-cp34m-manylinux1_i686.whl", hash = "sha256:c0d4b04bbf96c47b6d360cd06939e72def512b20a18a8547fa4af810258355d5"},
+    {file = "h5py-2.10.0-cp34-cp34m-manylinux1_x86_64.whl", hash = "sha256:549ad124df27c056b2e255ea1c44d30fb7a17d17676d03096ad5cd85edb32dc1"},
+    {file = "h5py-2.10.0-cp35-cp35m-macosx_10_6_intel.whl", hash = "sha256:a5f82cd4938ff8761d9760af3274acf55afc3c91c649c50ab18fcff5510a14a5"},
+    {file = "h5py-2.10.0-cp35-cp35m-manylinux1_i686.whl", hash = "sha256:3dad1730b6470fad853ef56d755d06bb916ee68a3d8272b3bab0c1ddf83bb99e"},
+    {file = "h5py-2.10.0-cp35-cp35m-manylinux1_x86_64.whl", hash = "sha256:063947eaed5f271679ed4ffa36bb96f57bc14f44dd4336a827d9a02702e6ce6b"},
+    {file = "h5py-2.10.0-cp35-cp35m-win32.whl", hash = "sha256:c54a2c0dd4957776ace7f95879d81582298c5daf89e77fb8bee7378f132951de"},
+    {file = "h5py-2.10.0-cp35-cp35m-win_amd64.whl", hash = "sha256:6998be619c695910cb0effe5eb15d3a511d3d1a5d217d4bd0bebad1151ec2262"},
+    {file = "h5py-2.10.0-cp36-cp36m-macosx_10_6_intel.whl", hash = "sha256:ff7d241f866b718e4584fa95f520cb19405220c501bd3a53ee11871ba5166ea2"},
+    {file = "h5py-2.10.0-cp36-cp36m-manylinux1_i686.whl", hash = "sha256:54817b696e87eb9e403e42643305f142cd8b940fe9b3b490bbf98c3b8a894cf4"},
+    {file = "h5py-2.10.0-cp36-cp36m-manylinux1_x86_64.whl", hash = "sha256:d3c59549f90a891691991c17f8e58c8544060fdf3ccdea267100fa5f561ff62f"},
+    {file = "h5py-2.10.0-cp36-cp36m-win32.whl", hash = "sha256:d7ae7a0576b06cb8e8a1c265a8bc4b73d05fdee6429bffc9a26a6eb531e79d72"},
+    {file = "h5py-2.10.0-cp36-cp36m-win_amd64.whl", hash = "sha256:bffbc48331b4a801d2f4b7dac8a72609f0b10e6e516e5c480a3e3241e091c878"},
+    {file = "h5py-2.10.0-cp37-cp37m-macosx_10_6_intel.whl", hash = "sha256:51ae56894c6c93159086ffa2c94b5b3388c0400548ab26555c143e7cfa05b8e5"},
+    {file = "h5py-2.10.0-cp37-cp37m-manylinux1_i686.whl", hash = "sha256:16ead3c57141101e3296ebeed79c9c143c32bdd0e82a61a2fc67e8e6d493e9d1"},
+    {file = "h5py-2.10.0-cp37-cp37m-manylinux1_x86_64.whl", hash = "sha256:f0e25bb91e7a02efccb50aba6591d3fe2c725479e34769802fcdd4076abfa917"},
+    {file = "h5py-2.10.0-cp37-cp37m-win32.whl", hash = "sha256:f23951a53d18398ef1344c186fb04b26163ca6ce449ebd23404b153fd111ded9"},
+    {file = "h5py-2.10.0-cp37-cp37m-win_amd64.whl", hash = "sha256:8bb1d2de101f39743f91512a9750fb6c351c032e5cd3204b4487383e34da7f75"},
+    {file = "h5py-2.10.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:64f74da4a1dd0d2042e7d04cf8294e04ddad686f8eba9bb79e517ae582f6668d"},
+    {file = "h5py-2.10.0-cp38-cp38-manylinux1_x86_64.whl", hash = "sha256:d35f7a3a6cefec82bfdad2785e78359a0e6a5fbb3f605dd5623ce88082ccd681"},
+    {file = "h5py-2.10.0-cp38-cp38-win32.whl", hash = "sha256:6ef7ab1089e3ef53ca099038f3c0a94d03e3560e6aff0e9d6c64c55fb13fc681"},
+    {file = "h5py-2.10.0-cp38-cp38-win_amd64.whl", hash = "sha256:769e141512b54dee14ec76ed354fcacfc7d97fea5a7646b709f7400cf1838630"},
+    {file = "h5py-2.10.0.tar.gz", hash = "sha256:84412798925dc870ffd7107f045d7659e60f5d46d1c70c700375248bf6bf512d"},
+]
+idna = [
+    {file = "idna-2.10-py2.py3-none-any.whl", hash = "sha256:b97d804b1e9b523befed77c48dacec60e6dcb0b5391d57af6a65a312a90648c0"},
+    {file = "idna-2.10.tar.gz", hash = "sha256:b307872f855b18632ce0c21c5e45be78c0ea7ae4c15c828c20788b26921eb3f6"},
+]
+isort = [
+    {file = "isort-5.8.0-py3-none-any.whl", hash = "sha256:2bb1680aad211e3c9944dbce1d4ba09a989f04e238296c87fe2139faa26d655d"},
+    {file = "isort-5.8.0.tar.gz", hash = "sha256:0a943902919f65c5684ac4e0154b1ad4fac6dcaa5d9f3426b732f1c8b5419be6"},
+]
+keras-preprocessing = [
+    {file = "Keras_Preprocessing-1.1.2-py2.py3-none-any.whl", hash = "sha256:7b82029b130ff61cc99b55f3bd27427df4838576838c5b2f65940e4fcec99a7b"},
+    {file = "Keras_Preprocessing-1.1.2.tar.gz", hash = "sha256:add82567c50c8bc648c14195bf544a5ce7c1f76761536956c3d2978970179ef3"},
+]
+markdown = [
+    {file = "Markdown-3.3.4-py3-none-any.whl", hash = "sha256:96c3ba1261de2f7547b46a00ea8463832c921d3f9d6aba3f255a6f71386db20c"},
+    {file = "Markdown-3.3.4.tar.gz", hash = "sha256:31b5b491868dcc87d6c24b7e3d19a0d730d59d3e46f4eea6430a321bed387a49"},
+]
+numpy = [
+    {file = "numpy-1.19.5-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:cc6bd4fd593cb261332568485e20a0712883cf631f6f5e8e86a52caa8b2b50ff"},
+    {file = "numpy-1.19.5-cp36-cp36m-manylinux1_i686.whl", hash = "sha256:aeb9ed923be74e659984e321f609b9ba54a48354bfd168d21a2b072ed1e833ea"},
+    {file = "numpy-1.19.5-cp36-cp36m-manylinux1_x86_64.whl", hash = "sha256:8b5e972b43c8fc27d56550b4120fe6257fdc15f9301914380b27f74856299fea"},
+    {file = "numpy-1.19.5-cp36-cp36m-manylinux2010_i686.whl", hash = "sha256:43d4c81d5ffdff6bae58d66a3cd7f54a7acd9a0e7b18d97abb255defc09e3140"},
+    {file = "numpy-1.19.5-cp36-cp36m-manylinux2010_x86_64.whl", hash = "sha256:a4646724fba402aa7504cd48b4b50e783296b5e10a524c7a6da62e4a8ac9698d"},
+    {file = "numpy-1.19.5-cp36-cp36m-manylinux2014_aarch64.whl", hash = "sha256:2e55195bc1c6b705bfd8ad6f288b38b11b1af32f3c8289d6c50d47f950c12e76"},
+    {file = "numpy-1.19.5-cp36-cp36m-win32.whl", hash = "sha256:39b70c19ec771805081578cc936bbe95336798b7edf4732ed102e7a43ec5c07a"},
+    {file = "numpy-1.19.5-cp36-cp36m-win_amd64.whl", hash = "sha256:dbd18bcf4889b720ba13a27ec2f2aac1981bd41203b3a3b27ba7a33f88ae4827"},
+    {file = "numpy-1.19.5-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:603aa0706be710eea8884af807b1b3bc9fb2e49b9f4da439e76000f3b3c6ff0f"},
+    {file = "numpy-1.19.5-cp37-cp37m-manylinux1_i686.whl", hash = "sha256:cae865b1cae1ec2663d8ea56ef6ff185bad091a5e33ebbadd98de2cfa3fa668f"},
+    {file = "numpy-1.19.5-cp37-cp37m-manylinux1_x86_64.whl", hash = "sha256:36674959eed6957e61f11c912f71e78857a8d0604171dfd9ce9ad5cbf41c511c"},
+    {file = "numpy-1.19.5-cp37-cp37m-manylinux2010_i686.whl", hash = "sha256:06fab248a088e439402141ea04f0fffb203723148f6ee791e9c75b3e9e82f080"},
+    {file = "numpy-1.19.5-cp37-cp37m-manylinux2010_x86_64.whl", hash = "sha256:6149a185cece5ee78d1d196938b2a8f9d09f5a5ebfbba66969302a778d5ddd1d"},
+    {file = "numpy-1.19.5-cp37-cp37m-manylinux2014_aarch64.whl", hash = "sha256:50a4a0ad0111cc1b71fa32dedd05fa239f7fb5a43a40663269bb5dc7877cfd28"},
+    {file = "numpy-1.19.5-cp37-cp37m-win32.whl", hash = "sha256:d051ec1c64b85ecc69531e1137bb9751c6830772ee5c1c426dbcfe98ef5788d7"},
+    {file = "numpy-1.19.5-cp37-cp37m-win_amd64.whl", hash = "sha256:a12ff4c8ddfee61f90a1633a4c4afd3f7bcb32b11c52026c92a12e1325922d0d"},
+    {file = "numpy-1.19.5-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:cf2402002d3d9f91c8b01e66fbb436a4ed01c6498fffed0e4c7566da1d40ee1e"},
+    {file = "numpy-1.19.5-cp38-cp38-manylinux1_i686.whl", hash = "sha256:1ded4fce9cfaaf24e7a0ab51b7a87be9038ea1ace7f34b841fe3b6894c721d1c"},
+    {file = "numpy-1.19.5-cp38-cp38-manylinux1_x86_64.whl", hash = "sha256:012426a41bc9ab63bb158635aecccc7610e3eff5d31d1eb43bc099debc979d94"},
+    {file = "numpy-1.19.5-cp38-cp38-manylinux2010_i686.whl", hash = "sha256:759e4095edc3c1b3ac031f34d9459fa781777a93ccc633a472a5468587a190ff"},
+    {file = "numpy-1.19.5-cp38-cp38-manylinux2010_x86_64.whl", hash = "sha256:a9d17f2be3b427fbb2bce61e596cf555d6f8a56c222bd2ca148baeeb5e5c783c"},
+    {file = "numpy-1.19.5-cp38-cp38-manylinux2014_aarch64.whl", hash = "sha256:99abf4f353c3d1a0c7a5f27699482c987cf663b1eac20db59b8c7b061eabd7fc"},
+    {file = "numpy-1.19.5-cp38-cp38-win32.whl", hash = "sha256:384ec0463d1c2671170901994aeb6dce126de0a95ccc3976c43b0038a37329c2"},
+    {file = "numpy-1.19.5-cp38-cp38-win_amd64.whl", hash = "sha256:811daee36a58dc79cf3d8bdd4a490e4277d0e4b7d103a001a4e73ddb48e7e6aa"},
+    {file = "numpy-1.19.5-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:c843b3f50d1ab7361ca4f0b3639bf691569493a56808a0b0c54a051d260b7dbd"},
+    {file = "numpy-1.19.5-cp39-cp39-manylinux1_i686.whl", hash = "sha256:d6631f2e867676b13026e2846180e2c13c1e11289d67da08d71cacb2cd93d4aa"},
+    {file = "numpy-1.19.5-cp39-cp39-manylinux1_x86_64.whl", hash = "sha256:7fb43004bce0ca31d8f13a6eb5e943fa73371381e53f7074ed21a4cb786c32f8"},
+    {file = "numpy-1.19.5-cp39-cp39-manylinux2010_i686.whl", hash = "sha256:2ea52bd92ab9f768cc64a4c3ef8f4b2580a17af0a5436f6126b08efbd1838371"},
+    {file = "numpy-1.19.5-cp39-cp39-manylinux2010_x86_64.whl", hash = "sha256:400580cbd3cff6ffa6293df2278c75aef2d58d8d93d3c5614cd67981dae68ceb"},
+    {file = "numpy-1.19.5-cp39-cp39-manylinux2014_aarch64.whl", hash = "sha256:df609c82f18c5b9f6cb97271f03315ff0dbe481a2a02e56aeb1b1a985ce38e60"},
+    {file = "numpy-1.19.5-cp39-cp39-win32.whl", hash = "sha256:ab83f24d5c52d60dbc8cd0528759532736b56db58adaa7b5f1f76ad551416a1e"},
+    {file = "numpy-1.19.5-cp39-cp39-win_amd64.whl", hash = "sha256:0eef32ca3132a48e43f6a0f5a82cb508f22ce5a3d6f67a8329c81c8e226d3f6e"},
+    {file = "numpy-1.19.5-pp36-pypy36_pp73-manylinux2010_x86_64.whl", hash = "sha256:a0d53e51a6cb6f0d9082decb7a4cb6dfb33055308c4c44f53103c073f649af73"},
+    {file = "numpy-1.19.5.zip", hash = "sha256:a76f502430dd98d7546e1ea2250a7360c065a5fdea52b2dffe8ae7180909b6f4"},
+]
+oauthlib = [
+    {file = "oauthlib-3.1.0-py2.py3-none-any.whl", hash = "sha256:df884cd6cbe20e32633f1db1072e9356f53638e4361bef4e8b03c9127c9328ea"},
+    {file = "oauthlib-3.1.0.tar.gz", hash = "sha256:bee41cc35fcca6e988463cacc3bcb8a96224f470ca547e697b604cc697b2f889"},
+]
+opt-einsum = [
+    {file = "opt_einsum-3.3.0-py3-none-any.whl", hash = "sha256:2455e59e3947d3c275477df7f5205b30635e266fe6dc300e3d9f9646bfcea147"},
+    {file = "opt_einsum-3.3.0.tar.gz", hash = "sha256:59f6475f77bbc37dcf7cd748519c0ec60722e91e63ca114e68821c0c54a46549"},
+]
+protobuf = [
+    {file = "protobuf-3.15.8-cp27-cp27m-macosx_10_9_x86_64.whl", hash = "sha256:fad4f971ec38d8df7f4b632c819bf9bbf4f57cfd7312cf526c69ce17ef32436a"},
+    {file = "protobuf-3.15.8-cp27-cp27mu-manylinux1_x86_64.whl", hash = "sha256:f17b352d7ce33c81773cf81d536ca70849de6f73c96413f17309f4b43ae7040b"},
+    {file = "protobuf-3.15.8-cp35-cp35m-macosx_10_9_intel.whl", hash = "sha256:4a054b0b5900b7ea7014099e783fb8c4618e4209fffcd6050857517b3f156e18"},
+    {file = "protobuf-3.15.8-cp35-cp35m-manylinux1_x86_64.whl", hash = "sha256:efa4c4d4fc9ba734e5e85eaced70e1b63fb3c8d08482d839eb838566346f1737"},
+    {file = "protobuf-3.15.8-cp35-cp35m-win32.whl", hash = "sha256:07eec4e2ccbc74e95bb9b3afe7da67957947ee95bdac2b2e91b038b832dd71f0"},
+    {file = "protobuf-3.15.8-cp35-cp35m-win_amd64.whl", hash = "sha256:f9cadaaa4065d5dd4d15245c3b68b967b3652a3108e77f292b58b8c35114b56c"},
+    {file = "protobuf-3.15.8-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:2dc0e8a9e4962207bdc46a365b63a3f1aca6f9681a5082a326c5837ef8f4b745"},
+    {file = "protobuf-3.15.8-cp36-cp36m-manylinux1_x86_64.whl", hash = "sha256:f80afc0a0ba13339bbab25ca0409e9e2836b12bb012364c06e97c2df250c3343"},
+    {file = "protobuf-3.15.8-cp36-cp36m-win32.whl", hash = "sha256:c5566f956a26cda3abdfacc0ca2e21db6c9f3d18f47d8d4751f2209d6c1a5297"},
+    {file = "protobuf-3.15.8-cp36-cp36m-win_amd64.whl", hash = "sha256:dab75b56a12b1ceb3e40808b5bd9dfdaef3a1330251956e6744e5b6ed8f8830b"},
+    {file = "protobuf-3.15.8-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:3053f13207e7f13dc7be5e9071b59b02020172f09f648e85dc77e3fcb50d1044"},
+    {file = "protobuf-3.15.8-cp37-cp37m-manylinux1_x86_64.whl", hash = "sha256:1f0b5d156c3df08cc54bc2c8b8b875648ea4cd7ebb2a9a130669f7547ec3488c"},
+    {file = "protobuf-3.15.8-cp37-cp37m-win32.whl", hash = "sha256:90270fe5732c1f1ff664a3bd7123a16456d69b4e66a09a139a00443a32f210b8"},
+    {file = "protobuf-3.15.8-cp37-cp37m-win_amd64.whl", hash = "sha256:f42c2f5fb67da5905bfc03733a311f72fa309252bcd77c32d1462a1ad519521e"},
+    {file = "protobuf-3.15.8-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:f6077db37bfa16494dca58a4a02bfdacd87662247ad6bc1f7f8d13ff3f0013e1"},
+    {file = "protobuf-3.15.8-cp38-cp38-manylinux1_x86_64.whl", hash = "sha256:510e66491f1a5ac5953c908aa8300ec47f793130097e4557482803b187a8ee05"},
+    {file = "protobuf-3.15.8-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:5ff9fa0e67fcab442af9bc8d4ec3f82cb2ff3be0af62dba047ed4187f0088b7d"},
+    {file = "protobuf-3.15.8-cp39-cp39-manylinux1_x86_64.whl", hash = "sha256:1c0e9e56202b9dccbc094353285a252e2b7940b74fdf75f1b4e1b137833fabd7"},
+    {file = "protobuf-3.15.8-py2.py3-none-any.whl", hash = "sha256:a0a08c6b2e6d6c74a6eb5bf6184968eefb1569279e78714e239d33126e753403"},
+    {file = "protobuf-3.15.8.tar.gz", hash = "sha256:0277f62b1e42210cafe79a71628c1d553348da81cbd553402a7f7549c50b11d0"},
+]
+pyasn1 = [
+    {file = "pyasn1-0.4.8-py2.4.egg", hash = "sha256:fec3e9d8e36808a28efb59b489e4528c10ad0f480e57dcc32b4de5c9d8c9fdf3"},
+    {file = "pyasn1-0.4.8-py2.5.egg", hash = "sha256:0458773cfe65b153891ac249bcf1b5f8f320b7c2ce462151f8fa74de8934becf"},
+    {file = "pyasn1-0.4.8-py2.6.egg", hash = "sha256:5c9414dcfede6e441f7e8f81b43b34e834731003427e5b09e4e00e3172a10f00"},
+    {file = "pyasn1-0.4.8-py2.7.egg", hash = "sha256:6e7545f1a61025a4e58bb336952c5061697da694db1cae97b116e9c46abcf7c8"},
+    {file = "pyasn1-0.4.8-py2.py3-none-any.whl", hash = "sha256:39c7e2ec30515947ff4e87fb6f456dfc6e84857d34be479c9d4a4ba4bf46aa5d"},
+    {file = "pyasn1-0.4.8-py3.1.egg", hash = "sha256:78fa6da68ed2727915c4767bb386ab32cdba863caa7dbe473eaae45f9959da86"},
+    {file = "pyasn1-0.4.8-py3.2.egg", hash = "sha256:08c3c53b75eaa48d71cf8c710312316392ed40899cb34710d092e96745a358b7"},
+    {file = "pyasn1-0.4.8-py3.3.egg", hash = "sha256:03840c999ba71680a131cfaee6fab142e1ed9bbd9c693e285cc6aca0d555e576"},
+    {file = "pyasn1-0.4.8-py3.4.egg", hash = "sha256:7ab8a544af125fb704feadb008c99a88805126fb525280b2270bb25cc1d78a12"},
+    {file = "pyasn1-0.4.8-py3.5.egg", hash = "sha256:e89bf84b5437b532b0803ba5c9a5e054d21fec423a89952a74f87fa2c9b7bce2"},
+    {file = "pyasn1-0.4.8-py3.6.egg", hash = "sha256:014c0e9976956a08139dc0712ae195324a75e142284d5f87f1a87ee1b068a359"},
+    {file = "pyasn1-0.4.8-py3.7.egg", hash = "sha256:99fcc3c8d804d1bc6d9a099921e39d827026409a58f2a720dcdb89374ea0c776"},
+    {file = "pyasn1-0.4.8.tar.gz", hash = "sha256:aef77c9fb94a3ac588e87841208bdec464471d9871bd5050a287cc9a475cd0ba"},
+]
+pyasn1-modules = [
+    {file = "pyasn1-modules-0.2.8.tar.gz", hash = "sha256:905f84c712230b2c592c19470d3ca8d552de726050d1d1716282a1f6146be65e"},
+    {file = "pyasn1_modules-0.2.8-py2.4.egg", hash = "sha256:0fe1b68d1e486a1ed5473f1302bd991c1611d319bba158e98b106ff86e1d7199"},
+    {file = "pyasn1_modules-0.2.8-py2.5.egg", hash = "sha256:fe0644d9ab041506b62782e92b06b8c68cca799e1a9636ec398675459e031405"},
+    {file = "pyasn1_modules-0.2.8-py2.6.egg", hash = "sha256:a99324196732f53093a84c4369c996713eb8c89d360a496b599fb1a9c47fc3eb"},
+    {file = "pyasn1_modules-0.2.8-py2.7.egg", hash = "sha256:0845a5582f6a02bb3e1bde9ecfc4bfcae6ec3210dd270522fee602365430c3f8"},
+    {file = "pyasn1_modules-0.2.8-py2.py3-none-any.whl", hash = "sha256:a50b808ffeb97cb3601dd25981f6b016cbb3d31fbf57a8b8a87428e6158d0c74"},
+    {file = "pyasn1_modules-0.2.8-py3.1.egg", hash = "sha256:f39edd8c4ecaa4556e989147ebf219227e2cd2e8a43c7e7fcb1f1c18c5fd6a3d"},
+    {file = "pyasn1_modules-0.2.8-py3.2.egg", hash = "sha256:b80486a6c77252ea3a3e9b1e360bc9cf28eaac41263d173c032581ad2f20fe45"},
+    {file = "pyasn1_modules-0.2.8-py3.3.egg", hash = "sha256:65cebbaffc913f4fe9e4808735c95ea22d7a7775646ab690518c056784bc21b4"},
+    {file = "pyasn1_modules-0.2.8-py3.4.egg", hash = "sha256:15b7c67fabc7fc240d87fb9aabf999cf82311a6d6fb2c70d00d3d0604878c811"},
+    {file = "pyasn1_modules-0.2.8-py3.5.egg", hash = "sha256:426edb7a5e8879f1ec54a1864f16b882c2837bfd06eee62f2c982315ee2473ed"},
+    {file = "pyasn1_modules-0.2.8-py3.6.egg", hash = "sha256:cbac4bc38d117f2a49aeedec4407d23e8866ea4ac27ff2cf7fb3e5b570df19e0"},
+    {file = "pyasn1_modules-0.2.8-py3.7.egg", hash = "sha256:c29a5e5cc7a3f05926aff34e097e84f8589cd790ce0ed41b67aed6857b26aafd"},
+]
+pydantic = [
+    {file = "pydantic-1.8.2-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:05ddfd37c1720c392f4e0d43c484217b7521558302e7069ce8d318438d297739"},
+    {file = "pydantic-1.8.2-cp36-cp36m-manylinux1_i686.whl", hash = "sha256:a7c6002203fe2c5a1b5cbb141bb85060cbff88c2d78eccbc72d97eb7022c43e4"},
+    {file = "pydantic-1.8.2-cp36-cp36m-manylinux2014_i686.whl", hash = "sha256:589eb6cd6361e8ac341db97602eb7f354551482368a37f4fd086c0733548308e"},
+    {file = "pydantic-1.8.2-cp36-cp36m-manylinux2014_x86_64.whl", hash = "sha256:10e5622224245941efc193ad1d159887872776df7a8fd592ed746aa25d071840"},
+    {file = "pydantic-1.8.2-cp36-cp36m-win_amd64.whl", hash = "sha256:99a9fc39470010c45c161a1dc584997f1feb13f689ecf645f59bb4ba623e586b"},
+    {file = "pydantic-1.8.2-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:a83db7205f60c6a86f2c44a61791d993dff4b73135df1973ecd9eed5ea0bda20"},
+    {file = "pydantic-1.8.2-cp37-cp37m-manylinux1_i686.whl", hash = "sha256:41b542c0b3c42dc17da70554bc6f38cbc30d7066d2c2815a94499b5684582ecb"},
+    {file = "pydantic-1.8.2-cp37-cp37m-manylinux2014_i686.whl", hash = "sha256:ea5cb40a3b23b3265f6325727ddfc45141b08ed665458be8c6285e7b85bd73a1"},
+    {file = "pydantic-1.8.2-cp37-cp37m-manylinux2014_x86_64.whl", hash = "sha256:18b5ea242dd3e62dbf89b2b0ec9ba6c7b5abaf6af85b95a97b00279f65845a23"},
+    {file = "pydantic-1.8.2-cp37-cp37m-win_amd64.whl", hash = "sha256:234a6c19f1c14e25e362cb05c68afb7f183eb931dd3cd4605eafff055ebbf287"},
+    {file = "pydantic-1.8.2-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:021ea0e4133e8c824775a0cfe098677acf6fa5a3cbf9206a376eed3fc09302cd"},
+    {file = "pydantic-1.8.2-cp38-cp38-manylinux1_i686.whl", hash = "sha256:e710876437bc07bd414ff453ac8ec63d219e7690128d925c6e82889d674bb505"},
+    {file = "pydantic-1.8.2-cp38-cp38-manylinux2014_i686.whl", hash = "sha256:ac8eed4ca3bd3aadc58a13c2aa93cd8a884bcf21cb019f8cfecaae3b6ce3746e"},
+    {file = "pydantic-1.8.2-cp38-cp38-manylinux2014_x86_64.whl", hash = "sha256:4a03cbbe743e9c7247ceae6f0d8898f7a64bb65800a45cbdc52d65e370570820"},
+    {file = "pydantic-1.8.2-cp38-cp38-win_amd64.whl", hash = "sha256:8621559dcf5afacf0069ed194278f35c255dc1a1385c28b32dd6c110fd6531b3"},
+    {file = "pydantic-1.8.2-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:8b223557f9510cf0bfd8b01316bf6dd281cf41826607eada99662f5e4963f316"},
+    {file = "pydantic-1.8.2-cp39-cp39-manylinux1_i686.whl", hash = "sha256:244ad78eeb388a43b0c927e74d3af78008e944074b7d0f4f696ddd5b2af43c62"},
+    {file = "pydantic-1.8.2-cp39-cp39-manylinux2014_i686.whl", hash = "sha256:05ef5246a7ffd2ce12a619cbb29f3307b7c4509307b1b49f456657b43529dc6f"},
+    {file = "pydantic-1.8.2-cp39-cp39-manylinux2014_x86_64.whl", hash = "sha256:54cd5121383f4a461ff7644c7ca20c0419d58052db70d8791eacbbe31528916b"},
+    {file = "pydantic-1.8.2-cp39-cp39-win_amd64.whl", hash = "sha256:4be75bebf676a5f0f87937c6ddb061fa39cbea067240d98e298508c1bda6f3f3"},
+    {file = "pydantic-1.8.2-py3-none-any.whl", hash = "sha256:fec866a0b59f372b7e776f2d7308511784dace622e0992a0b59ea3ccee0ae833"},
+    {file = "pydantic-1.8.2.tar.gz", hash = "sha256:26464e57ccaafe72b7ad156fdaa4e9b9ef051f69e175dbbb463283000c05ab7b"},
+]
+pyflakes = [
+    {file = "pyflakes-2.3.1-py2.py3-none-any.whl", hash = "sha256:7893783d01b8a89811dd72d7dfd4d84ff098e5eed95cfa8905b22bbffe52efc3"},
+    {file = "pyflakes-2.3.1.tar.gz", hash = "sha256:f5bc8ecabc05bb9d291eb5203d6810b49040f6ff446a756326104746cc00c1db"},
+]
+requests = [
+    {file = "requests-2.25.1-py2.py3-none-any.whl", hash = "sha256:c210084e36a42ae6b9219e00e48287def368a26d03a048ddad7bfee44f75871e"},
+    {file = "requests-2.25.1.tar.gz", hash = "sha256:27973dd4a904a4f13b263a19c866c13b92a39ed1c964655f025f3f8d3d75b804"},
+]
+requests-oauthlib = [
+    {file = "requests-oauthlib-1.3.0.tar.gz", hash = "sha256:b4261601a71fd721a8bd6d7aa1cc1d6a8a93b4a9f5e96626f8e4d91e8beeaa6a"},
+    {file = "requests_oauthlib-1.3.0-py2.py3-none-any.whl", hash = "sha256:7f71572defaecd16372f9006f33c2ec8c077c3cfa6f5911a9a90202beb513f3d"},
+    {file = "requests_oauthlib-1.3.0-py3.7.egg", hash = "sha256:fa6c47b933f01060936d87ae9327fead68768b69c6c9ea2109c48be30f2d4dbc"},
+]
+rsa = [
+    {file = "rsa-4.7.2-py3-none-any.whl", hash = "sha256:78f9a9bf4e7be0c5ded4583326e7461e3a3c5aae24073648b4bdfa797d78c9d2"},
+    {file = "rsa-4.7.2.tar.gz", hash = "sha256:9d689e6ca1b3038bc82bf8d23e944b6b6037bc02301a574935b2dd946e0353b9"},
+]
+six = [
+    {file = "six-1.15.0-py2.py3-none-any.whl", hash = "sha256:8b74bedcbbbaca38ff6d7491d76f2b06b3592611af620f8426e82dddb04a5ced"},
+    {file = "six-1.15.0.tar.gz", hash = "sha256:30639c035cdb23534cd4aa2dd52c3bf48f06e5f4a941509c8bafd8ce11080259"},
+]
+starlette = [
+    {file = "starlette-0.14.2-py3-none-any.whl", hash = "sha256:3c8e48e52736b3161e34c9f0e8153b4f32ec5d8995a3ee1d59410d92f75162ed"},
+    {file = "starlette-0.14.2.tar.gz", hash = "sha256:7d49f4a27f8742262ef1470608c59ddbc66baf37c148e938c7038e6bc7a998aa"},
+]
+tensorboard = [
+    {file = "tensorboard-2.5.0-py3-none-any.whl", hash = "sha256:e167460085b6528956b33bab1c970c989cdce47a6616273880733f5e7bde452e"},
+]
+tensorboard-data-server = [
+    {file = "tensorboard_data_server-0.6.1-py3-none-any.whl", hash = "sha256:809fe9887682d35c1f7d1f54f0f40f98bb1f771b14265b453ca051e2ce58fca7"},
+    {file = "tensorboard_data_server-0.6.1-py3-none-macosx_10_9_x86_64.whl", hash = "sha256:fa8cef9be4fcae2f2363c88176638baf2da19c5ec90addb49b1cde05c95c88ee"},
+    {file = "tensorboard_data_server-0.6.1-py3-none-manylinux2010_x86_64.whl", hash = "sha256:d8237580755e58eff68d1f3abefb5b1e39ae5c8b127cc40920f9c4fb33f4b98a"},
+]
+tensorboard-plugin-wit = [
+    {file = "tensorboard_plugin_wit-1.8.0-py3-none-any.whl", hash = "sha256:2a80d1c551d741e99b2f197bb915d8a133e24adb8da1732b840041860f91183a"},
+]
+tensorflow = [
+    {file = "tensorflow-2.4.1-cp36-cp36m-macosx_10_11_x86_64.whl", hash = "sha256:e1f2799cc86861680d8515167f103e2207a8cab92a4afe5471e4839330591f08"},
+    {file = "tensorflow-2.4.1-cp36-cp36m-manylinux2010_x86_64.whl", hash = "sha256:55368ba0bedb513ba0e36a2543a588b5276e9b2ca99fa3232a9a176601a7bab5"},
+    {file = "tensorflow-2.4.1-cp36-cp36m-win_amd64.whl", hash = "sha256:0e427b1350be6dbe572f971947c5596fdbb152081f227808d8becd894bf40282"},
+    {file = "tensorflow-2.4.1-cp37-cp37m-macosx_10_11_x86_64.whl", hash = "sha256:36d5acd60aac48e34bd545d0ce1fb8b3fceebff6b8782436defd0f71c12203bd"},
+    {file = "tensorflow-2.4.1-cp37-cp37m-manylinux2010_x86_64.whl", hash = "sha256:22723b8e1fa83b34f56c349b16a57aaff913b404451fcf70981f2b1d6e0c64fc"},
+    {file = "tensorflow-2.4.1-cp37-cp37m-win_amd64.whl", hash = "sha256:2357112319303da1b5459a621fd0503c2b2cd97b6c33c4903abd46b3c3e380e2"},
+    {file = "tensorflow-2.4.1-cp38-cp38-macosx_10_11_x86_64.whl", hash = "sha256:4a04081647b89a8fb602895b29ffc559e3c20aac8bde1d4c5ecd2a65adce5d35"},
+    {file = "tensorflow-2.4.1-cp38-cp38-manylinux2010_x86_64.whl", hash = "sha256:efa9daa4b3701a4e439b24b74c1e4b66844aee8ae5263fb3cc12281ac9cc9f67"},
+    {file = "tensorflow-2.4.1-cp38-cp38-win_amd64.whl", hash = "sha256:eedcf578afde5e6e69c75d796bed41093451cd1ab54afb438760e40fb74a09de"},
+]
+tensorflow-estimator = [
+    {file = "tensorflow_estimator-2.4.0-py2.py3-none-any.whl", hash = "sha256:5b7b7bf2debe19a8794adacc43e8ba6459daa4efaf54d3302623994a359b17f0"},
+]
+termcolor = [
+    {file = "termcolor-1.1.0.tar.gz", hash = "sha256:1d6d69ce66211143803fbc56652b41d73b4a400a2891d7bf7a1cdf4c02de613b"},
+]
+typing-extensions = [
+    {file = "typing_extensions-3.7.4.3-py2-none-any.whl", hash = "sha256:dafc7639cde7f1b6e1acc0f457842a83e722ccca8eef5270af2d74792619a89f"},
+    {file = "typing_extensions-3.7.4.3-py3-none-any.whl", hash = "sha256:7cb407020f00f7bfc3cb3e7881628838e69d8f3fcab2f64742a5e76b2f841918"},
+    {file = "typing_extensions-3.7.4.3.tar.gz", hash = "sha256:99d4073b617d30288f569d3f13d2bd7548c3a7e4c8de87db09a9d29bb3a4a60c"},
+]
+urllib3 = [
+    {file = "urllib3-1.26.4-py2.py3-none-any.whl", hash = "sha256:2f4da4594db7e1e110a944bb1b551fdf4e6c136ad42e4234131391e21eb5b0df"},
+    {file = "urllib3-1.26.4.tar.gz", hash = "sha256:e7b021f7241115872f92f43c6508082facffbd1c048e3c6e2bb9c2a157e28937"},
+]
+uvicorn = [
+    {file = "uvicorn-0.14.0-py3-none-any.whl", hash = "sha256:2a76bb359171a504b3d1c853409af3adbfa5cef374a4a59e5881945a97a93eae"},
+    {file = "uvicorn-0.14.0.tar.gz", hash = "sha256:45ad7dfaaa7d55cab4cd1e85e03f27e9d60bc067ddc59db52a2b0aeca8870292"},
+]
+werkzeug = [
+    {file = "Werkzeug-1.0.1-py2.py3-none-any.whl", hash = "sha256:2de2a5db0baeae7b2d2664949077c2ac63fbd16d98da0ff71837f7d1dea3fd43"},
+    {file = "Werkzeug-1.0.1.tar.gz", hash = "sha256:6c80b1e5ad3665290ea39320b91e1be1e0d5f60652b964a3070216de83d2e47c"},
+]
+wrapt = [
+    {file = "wrapt-1.12.1.tar.gz", hash = "sha256:b62ffa81fb85f4332a4f609cab4ac40709470da05643a082ec1eb88e6d9b97d7"},
+]

pyproject.toml

@@ -9,11 +9,16 @@ license = "GPL-3.0-or-later"
 python = "3.8.*"
 tensorflow = "^2.4.1"
 biopython = "^1.78"
+fastapi = "^0.66.0"
+uvicorn = "^0.14.0"
 
 [tool.poetry.dev-dependencies]
 isort = "^5.8.0"
 pyflakes = "^2.3.1"
 
+[tool.poetry.scripts]
+api = "locimend.api:main"
+
 [build-system]
 requires = ["poetry-core>=1.0.0"]
 build-backend = "poetry.core.masonry.api"

src/constants.py

@@ -1,9 +0,0 @@
-BASES = "ACGT-"
-TRAIN_DATASET = "data/train_data.tfrecords"
-TEST_DATASET = "data/test_data.tfrecords"
-EVAL_DATASET = "data/eval_data.tfrecords"
-EPOCHS = 1000
-BATCH_SIZE = 256
-LEARNING_RATE = 0.004
-L2 = 0.001
-LOG_DIR = "logs"

src/model.py

@@ -1,95 +0,0 @@
-from random import seed
-
-from tensorflow.keras import Model, Sequential, layers
-from tensorflow.keras.callbacks import TensorBoard
-from tensorflow.keras.losses import sparse_categorical_crossentropy
-from tensorflow.keras.optimizers import Adam
-from tensorflow.keras.regularizers import l2
-from tensorflow.random import set_seed
-
-from constants import *
-from preprocessing import dataset_creation
-
-
-def build_model() -> Model:
-    """
-    Build the CNN model
-    """
-    model = Sequential()
-    model.add(
-        layers.Conv1D(
-            filters=16,
-            kernel_size=5,
-            activation="relu",
-            kernel_regularizer=l2(L2),
-        )
-    )
-    model.add(layers.MaxPool1D(pool_size=3, strides=1))
-    model.add(
-        layers.Conv1D(
-            filters=16,
-            kernel_size=3,
-            activation="relu",
-            kernel_regularizer=l2(L2),
-        )
-    )
-    model.add(layers.MaxPool1D(pool_size=3, strides=1))
-    model.add(layers.Flatten())
-    model.add(
-        layers.Dense(
-            units=16,
-            activation="relu",
-            kernel_regularizer=l2(L2),
-        )
-    )
-    model.add(layers.Dropout(rate=0.3))
-    model.add(
-        layers.Dense(
-            units=16,
-            activation="relu",
-            kernel_regularizer=l2(L2),
-        )
-    )
-    model.add(layers.Dropout(rate=0.3))
-    # FIXME Change output size
-    model.add(layers.Dense(units=len(BASES), activation="softmax"))
-    model.compile(
-        optimizer=Adam(LEARNING_RATE),
-        loss=sparse_categorical_crossentropy,
-        metrics=["accuracy"],
-    )
-    return model
-
-
-def show_metrics(model, eval_dataset, test_dataset) -> None:
-    """
-    Show the model metrics
-    """
-    eval_metrics = model.evaluate(eval_dataset, verbose=0)
-    test_metrics = model.evaluate(test_dataset, verbose=0)
-    print(f"Final eval metrics - loss: {eval_metrics[0]} - accuracy: {eval_metrics[1]}")
-    print(f"Final test metrics - loss: {test_metrics[0]} - accuracy: {test_metrics[1]}")
-
-
-def run(data_file, label_file, seed_value=42) -> None:
-    """
-    Create a dataset, a model and runs training and evaluation on it
-    """
-    seed(seed_value)
-    set_seed(seed_value)
-    train_data, eval_data, test_data = dataset_creation(data_file, label_file)
-    tensorboard = TensorBoard(log_dir=LOG_DIR, histogram_freq=1, profile_batch=0)
-    model = build_model()
-    print("Training the model")
-    model.fit(
-        train_data,
-        epochs=EPOCHS,
-        validation_data=eval_data,
-        callbacks=[tensorboard],
-    )
-    print("Training complete. Obtaining final metrics...")
-    show_metrics(model, eval_data, test_data)
-
-
-if __name__ == "__main__":
-    run(data_file="data/curesim-HVR.fastq", label_file="data/HVR.fastq")