Parallelize dataset transformations

README.md

@@ -2,15 +2,10 @@
 
 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
 
@@ -42,70 +37,13 @@ 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
 
-### Training the model
+The following command creates the dataset, trains the Deep Learning model and shows the accuracy:
-
-The following command creates the trains the Deep Learning model and shows the accuracy and AUC:
 
 ```bash
-poetry run python locimend/main.py train <data file> <label file>
+poetry run python src/model.py
 ```
-
-- <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

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

docker.nix

@@ -1,14 +0,0 @@
-{ 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

@@ -0,0 +1,388 @@
+{
+  "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"
+          ]
+        }
+      ]
+    }
+  ]
+}

flake.lock

@@ -1,41 +0,0 @@
-{
-  "nodes": {
-    "flake-utils": {
-      "locked": {
-        "lastModified": 1631561581,
-        "narHash": "sha256-3VQMV5zvxaVLvqqUrNz3iJelLw30mIVSfZmAaauM3dA=",
-        "owner": "numtide",
-        "repo": "flake-utils",
-        "rev": "7e5bf3925f6fbdfaf50a2a7ca0be2879c4261d19",
-        "type": "github"
-      },
-      "original": {
-        "owner": "numtide",
-        "repo": "flake-utils",
-        "type": "github"
-      }
-    },
-    "nixpkgs": {
-      "locked": {
-        "lastModified": 1634044603,
-        "narHash": "sha256-JX9/U/ci9Gw1fhWjEB3HfzDK8bAbcfQcTO6fEJmgFfo=",
-        "owner": "NixOS",
-        "repo": "nixpkgs",
-        "rev": "15847b4b4fc260fb400880aa3cbee65a65f252c5",
-        "type": "github"
-      },
-      "original": {
-        "id": "nixpkgs",
-        "type": "indirect"
-      }
-    },
-    "root": {
-      "inputs": {
-        "flake-utils": "flake-utils",
-        "nixpkgs": "nixpkgs"
-      }
-    }
-  },
-  "root": "root",
-  "version": 7
-}

flake.nix

@@ -1,11 +0,0 @@
-{
-  description =
-    "locimend is a tool that corrects DNA sequencing errors using Deep Learning";
-
-  inputs.flake-utils.url = "github:numtide/flake-utils";
-
-  outputs = { self, nixpkgs, flake-utils }:
-    flake-utils.lib.eachDefaultSystem (system:
-      let pkgs = nixpkgs.legacyPackages.${system};
-      in { devShell = import ./shell.nix { inherit pkgs; }; });
-}

locimend/api.py

@@ -1,27 +0,0 @@
-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

@@ -1,24 +0,0 @@
-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

@@ -1,40 +0,0 @@
-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

@@ -1,89 +0,0 @@
-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

nix/sources.json

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

poetry.lock

@@ -1,929 +0,0 @@
-[[package]]
-name = "absl-py"
-version = "0.14.1"
-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 = "1.79"
-description = "Freely available tools for computational molecular biology."
-category = "main"
-optional = false
-python-versions = ">=3.6"
-
-[package.dependencies]
-numpy = "*"
-
-[[package]]
-name = "cachetools"
-version = "4.2.4"
-description = "Extensible memoizing collections and decorators"
-category = "main"
-optional = false
-python-versions = "~=3.5"
-
-[[package]]
-name = "certifi"
-version = "2021.10.8"
-description = "Python package for providing Mozilla's CA Bundle."
-category = "main"
-optional = false
-python-versions = "*"
-
-[[package]]
-name = "charset-normalizer"
-version = "2.0.7"
-description = "The Real First Universal Charset Detector. Open, modern and actively maintained alternative to Chardet."
-category = "main"
-optional = false
-python-versions = ">=3.5.0"
-
-[package.extras]
-unicode_backport = ["unicodedata2"]
-
-[[package]]
-name = "clang"
-version = "5.0"
-description = "libclang python bindings"
-category = "main"
-optional = false
-python-versions = "*"
-
-[[package]]
-name = "click"
-version = "8.0.3"
-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 = "0.66.1"
-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] (>=3.3.0,<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 (>=6.2.4,<7.0.0)", "pytest-cov (>=2.12.0,<3.0.0)", "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 = "0.4.0"
-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 = "2.3.0"
-description = "Google Authentication Library"
-category = "main"
-optional = false
-python-versions = ">= 3.6"
-
-[package.dependencies]
-cachetools = ">=2.0.0,<5.0"
-pyasn1-modules = ">=0.2.1"
-rsa = ">=3.1.4,<5"
-
-[package.extras]
-aiohttp = ["aiohttp (>=3.6.2,<4.0.0dev)", "requests (>=2.20.0,<3.0.0dev)"]
-pyopenssl = ["pyopenssl (>=20.0.0)"]
-reauth = ["pyu2f (>=0.1.5)"]
-
-[[package]]
-name = "google-auth-oauthlib"
-version = "0.4.6"
-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 = "1.41.0"
-description = "HTTP/2-based RPC framework"
-category = "main"
-optional = false
-python-versions = "*"
-
-[package.dependencies]
-six = ">=1.5.2"
-
-[package.extras]
-protobuf = ["grpcio-tools (>=1.41.0)"]
-
-[[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 = "3.1.0"
-description = "Read and write HDF5 files from Python"
-category = "main"
-optional = false
-python-versions = ">=3.6"
-
-[package.dependencies]
-numpy = {version = ">=1.19.3", markers = "python_version >= \"3.9\""}
-
-[[package]]
-name = "idna"
-version = "3.3"
-description = "Internationalized Domain Names in Applications (IDNA)"
-category = "main"
-optional = false
-python-versions = ">=3.5"
-
-[[package]]
-name = "isort"
-version = "5.9.3"
-description = "A Python utility / library to sort Python imports."
-category = "dev"
-optional = false
-python-versions = ">=3.6.1,<4.0"
-
-[package.extras]
-pipfile_deprecated_finder = ["pipreqs", "requirementslib"]
-requirements_deprecated_finder = ["pipreqs", "pip-api"]
-colors = ["colorama (>=0.4.3,<0.5.0)"]
-plugins = ["setuptools"]
-
-[[package]]
-name = "keras"
-version = "2.6.0"
-description = "TensorFlow Keras."
-category = "main"
-optional = false
-python-versions = "*"
-
-[[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 = "3.1.1"
-description = "A generic, spec-compliant, thorough implementation of the OAuth request-signing logic"
-category = "main"
-optional = false
-python-versions = ">=3.6"
-
-[package.extras]
-rsa = ["cryptography (>=3.0.0,<4)"]
-signals = ["blinker (>=1.4.0)"]
-signedtoken = ["cryptography (>=3.0.0,<4)", "pyjwt (>=2.0.0,<3)"]
-
-[[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 = "3.18.1"
-description = "Protocol Buffers"
-category = "main"
-optional = false
-python-versions = ">=3.5"
-
-[[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 = "2.4.0"
-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 = "2.26.0"
-description = "Python HTTP for Humans."
-category = "main"
-optional = false
-python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*, !=3.5.*"
-
-[package.dependencies]
-certifi = ">=2017.4.17"
-charset-normalizer = {version = ">=2.0.0,<2.1.0", markers = "python_version >= \"3\""}
-idna = {version = ">=2.5,<4", markers = "python_version >= \"3\""}
-urllib3 = ">=1.21.1,<1.27"
-
-[package.extras]
-socks = ["PySocks (>=1.5.6,!=1.5.7)", "win-inet-pton"]
-use_chardet_on_py3 = ["chardet (>=3.0.2,<5)"]
-
-[[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 = "2.7.0"
-description = "TensorBoard lets you watch Tensors Flow"
-category = "main"
-optional = false
-python-versions = ">=3.6"
-
-[package.dependencies]
-absl-py = ">=0.4"
-google-auth = ">=1.6.3,<3"
-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 = "2.6.0"
-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"
-clang = ">=5.0,<6.0"
-flatbuffers = ">=1.12.0,<1.13.0"
-gast = "0.4.0"
-google-pasta = ">=0.2,<1.0"
-grpcio = ">=1.37.0,<2.0"
-h5py = ">=3.1.0,<3.2.0"
-keras = ">=2.6,<3.0"
-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 = ">=2.6,<3.0"
-tensorflow-estimator = ">=2.6,<3.0"
-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 = "2.6.0"
-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 = "1.26.7"
-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]
-brotli = ["brotlipy (>=0.6.0)"]
-secure = ["pyOpenSSL (>=0.14)", "cryptography (>=1.3.4)", "idna (>=2.0.0)", "certifi", "ipaddress"]
-socks = ["PySocks (>=1.5.6,!=1.5.7,<2.0)"]
-
-[[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 = "2.0.2"
-description = "The comprehensive WSGI web application library."
-category = "main"
-optional = false
-python-versions = ">=3.6"
-
-[package.extras]
-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 = "3.9.*"
-content-hash = "a87a2e774ea01273c9b218f32a57ea87af82546663f7f977fefe2456f9a1f8c3"
-
-[metadata.files]
-absl-py = [
-    {file = "absl-py-0.14.1.tar.gz", hash = "sha256:eb0383bd431c0d7b2320179904cab00120a10977e3c9671d99efbbed17efb55a"},
-    {file = "absl_py-0.14.1-py3-none-any.whl", hash = "sha256:565a2c1be855e466e697e1be6b9876c2435dda926954d1de4abf0d592561ece8"},
-]
-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-1.79-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:72a1477cf1701964c7224e506a54fd65d1cc5228da200b634a17992230aa1cbd"},
-    {file = "biopython-1.79-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:365569543ea58dd07ef205ec351c23b6c1a3200d5d321eb28ceaecd55eb5955e"},
-    {file = "biopython-1.79-cp36-cp36m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:4be31815226052d86d4c2f6a103c40504e34bba3e25cc1b1d687a3203c42fb6e"},
-    {file = "biopython-1.79-cp36-cp36m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:ceab668be9cbdcddef55ad459f87acd0316ae4a00d32251fea4cf665f5062fda"},
-    {file = "biopython-1.79-cp36-cp36m-win32.whl", hash = "sha256:83bfea8a19f9352c47b13965c4b73853e7aeef3c5aed8489895b0679e32c621b"},
-    {file = "biopython-1.79-cp36-cp36m-win_amd64.whl", hash = "sha256:98deacc30b8654cfcdcf707d93fa4e3c8717bbda07c3f9f828cf84753d4a1e4d"},
-    {file = "biopython-1.79-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:884a2b99ac7820cb84f70089769a512e3238ee60438b8c934ed519613dc570ce"},
-    {file = "biopython-1.79-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:51eb467a60c38820ad1e6c3a7d4cb10535606f559646e824cc65c96091d91ff7"},
-    {file = "biopython-1.79-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:03ee5c72b3cc3f0675a8c22ce1c45fe99a32a60db18df059df479ae6cf619708"},
-    {file = "biopython-1.79-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:9580978803b582e0612b71673cab289e6bf261a865009cfb9501d65bc726a76e"},
-    {file = "biopython-1.79-cp37-cp37m-win32.whl", hash = "sha256:5ae69c5e09769390643aa0f8064517665df6fb99c37433821d6664584d0ecb8c"},
-    {file = "biopython-1.79-cp37-cp37m-win_amd64.whl", hash = "sha256:f0a7e1d94a318f74974345fd0987ec389b16988ec484e67218e900b116b932a8"},
-    {file = "biopython-1.79-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:aa23a83a220486af6193760d079b36543fe00afcfbd18280ca2fd0b2c1c8dd6d"},
-    {file = "biopython-1.79-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4b3d4eec2e348c3d97a7fde80ee0f2b8ebeed849d2bd64a616833a9be03b93c8"},
-    {file = "biopython-1.79-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:947b793e804c59ea45ae46945a57612ad1789ca87af4af0d6a62dcecf3a6246a"},
-    {file = "biopython-1.79-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:d9f6ce961e0c380e2a5435f64c96421dbcebeab6a1b41506bd81251feb733c08"},
-    {file = "biopython-1.79-cp38-cp38-win32.whl", hash = "sha256:155c5b95857bca7ebd607210cb9d8ea459bb0b86b3ca37ea44ec47c26ede7e9a"},
-    {file = "biopython-1.79-cp38-cp38-win_amd64.whl", hash = "sha256:2dbb4388c75b5dfca8ce729e791f465c9c878dbd7ba2ab9a1f9854609d2b5426"},
-    {file = "biopython-1.79-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:76988ed3d7383d566db1d7fc69c9cf136c6275813fb749fc6753c340f81f1a8f"},
-    {file = "biopython-1.79-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e921571b51514a6d35944242d6fef6427c3998acf58940fe1f209ac8a92a6e87"},
-    {file = "biopython-1.79-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:bf634a56f449a4123e48e538d661948e5ac29fb452acd2962b8cb834b472a9d7"},
-    {file = "biopython-1.79-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:ab93d5749b375be3682866b3a606aa2ebd3e6d868079793925bf4fbb0987cf1f"},
-    {file = "biopython-1.79-cp39-cp39-win32.whl", hash = "sha256:8f33dafd3c7254fff5e1684b965e45a7c08d9b8e1bf51562b0a521ff9a6f5ea0"},
-    {file = "biopython-1.79-cp39-cp39-win_amd64.whl", hash = "sha256:b3ab26f26a1956ef26303386510d84e917e31fcbbc94918c336da0163ef628df"},
-    {file = "biopython-1.79.tar.gz", hash = "sha256:edb07eac99d3b8abd7ba56ff4bedec9263f76dfc3c3f450e7d2e2bcdecf8559b"},
-]
-cachetools = [
-    {file = "cachetools-4.2.4-py3-none-any.whl", hash = "sha256:92971d3cb7d2a97efff7c7bb1657f21a8f5fb309a37530537c71b1774189f2d1"},
-    {file = "cachetools-4.2.4.tar.gz", hash = "sha256:89ea6f1b638d5a73a4f9226be57ac5e4f399d22770b92355f92dcb0f7f001693"},
-]
-certifi = [
-    {file = "certifi-2021.10.8-py2.py3-none-any.whl", hash = "sha256:d62a0163eb4c2344ac042ab2bdf75399a71a2d8c7d47eac2e2ee91b9d6339569"},
-    {file = "certifi-2021.10.8.tar.gz", hash = "sha256:78884e7c1d4b00ce3cea67b44566851c4343c120abd683433ce934a68ea58872"},
-]
-charset-normalizer = [
-    {file = "charset-normalizer-2.0.7.tar.gz", hash = "sha256:e019de665e2bcf9c2b64e2e5aa025fa991da8720daa3c1138cadd2fd1856aed0"},
-    {file = "charset_normalizer-2.0.7-py3-none-any.whl", hash = "sha256:f7af805c321bfa1ce6714c51f254e0d5bb5e5834039bc17db7ebe3a4cec9492b"},
-]
-clang = [
-    {file = "clang-5.0-py2-none-any.whl", hash = "sha256:b9301dff507041b5019b30ae710b78b0552c1ca1d4441b8dfa93c2e85078a5f8"},
-    {file = "clang-5.0.tar.gz", hash = "sha256:ceccae97eda0225a5b44d42ffd61102e248325c2865ca53e4407746464a5333a"},
-]
-click = [
-    {file = "click-8.0.3-py3-none-any.whl", hash = "sha256:353f466495adaeb40b6b5f592f9f91cb22372351c84caeb068132442a4518ef3"},
-    {file = "click-8.0.3.tar.gz", hash = "sha256:410e932b050f5eed773c4cda94de75971c89cdb3155a72a0831139a79e5ecb5b"},
-]
-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-0.66.1-py3-none-any.whl", hash = "sha256:958ed7341f97292e2fc3e6401830bbe203a917af93cd10bb6392be170ad3c15f"},
-    {file = "fastapi-0.66.1.tar.gz", hash = "sha256:1ac66c0635301bbd99785fb825300064d54adb774e8a5562661901de14ce6560"},
-]
-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-0.4.0-py3-none-any.whl", hash = "sha256:b7adcdd5adbebf1adf17378da5ba3f543684dbec47b1cda1f3997e573cd542c4"},
-    {file = "gast-0.4.0.tar.gz", hash = "sha256:40feb7b8b8434785585ab224d1568b857edb18297e5a3047f1ba012bc83b42c1"},
-]
-google-auth = [
-    {file = "google-auth-2.3.0.tar.gz", hash = "sha256:2800f6dfad29c6ced5faf9ca0c38ea8ba1ebe2559b10c029bd021e3de3301627"},
-    {file = "google_auth-2.3.0-py2.py3-none-any.whl", hash = "sha256:91892727c09cf5d090c391936a8e67ef5b9a9794c2f426b3d0ceedddbcc0ef50"},
-]
-google-auth-oauthlib = [
-    {file = "google-auth-oauthlib-0.4.6.tar.gz", hash = "sha256:a90a072f6993f2c327067bf65270046384cda5a8ecb20b94ea9a687f1f233a7a"},
-    {file = "google_auth_oauthlib-0.4.6-py2.py3-none-any.whl", hash = "sha256:3f2a6e802eebbb6fb736a370fbf3b055edcb6b52878bf2f26330b5e041316c73"},
-]
-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-1.41.0-cp310-cp310-linux_armv7l.whl", hash = "sha256:9ecd0fc34aa46eeac24f4d20e67bafaf72ca914f99690bf2898674905eaddaf9"},
-    {file = "grpcio-1.41.0-cp310-cp310-macosx_10_10_universal2.whl", hash = "sha256:d539ebd05a2bbfbf897d41738d37d162d5c3d9f2b1f8ddf2c4f75e2c9cf59907"},
-    {file = "grpcio-1.41.0-cp310-cp310-manylinux_2_17_aarch64.whl", hash = "sha256:2410000eb57cf76b05b37d2aee270b686f0a7876710850a2bba92b4ed133e026"},
-    {file = "grpcio-1.41.0-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:be3c6ac822edb509aeef41361ca9c8c5ee52cb9e4973e1977d2bb7d6a460fd97"},
-    {file = "grpcio-1.41.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a0c4bdd1d646365d10ba1468bcf234ea5ad46e8ce2b115983e8563248614910a"},
-    {file = "grpcio-1.41.0-cp310-cp310-win32.whl", hash = "sha256:7033199706526e7ee06a362e38476dfdf2ddbad625c19b67ed30411d1bb25a18"},
-    {file = "grpcio-1.41.0-cp310-cp310-win_amd64.whl", hash = "sha256:fb64abf0d92134cb0ba4496a3b7ab918588eee42de20e5b3507fe6ee16db97ee"},
-    {file = "grpcio-1.41.0-cp36-cp36m-linux_armv7l.whl", hash = "sha256:b6b68c444abbaf4a2b944a61cf35726ab9645f45d416bcc7cf4addc4b2f2d53d"},
-    {file = "grpcio-1.41.0-cp36-cp36m-macosx_10_10_x86_64.whl", hash = "sha256:5292a627b44b6d3065de4a364ead23bab3c9d7a7c05416a9de0c0624d0fe03f4"},
-    {file = "grpcio-1.41.0-cp36-cp36m-manylinux2010_i686.whl", hash = "sha256:1820845e7e6410240eff97742e9f76cd5bf10ca01d36a322e86c0bd5340ac25b"},
-    {file = "grpcio-1.41.0-cp36-cp36m-manylinux2010_x86_64.whl", hash = "sha256:462178987f0e5c60d6d1b79e4e95803a4cd789db961d6b3f087245906bb5ae04"},
-    {file = "grpcio-1.41.0-cp36-cp36m-manylinux_2_17_aarch64.whl", hash = "sha256:7b07cbbd4eea56738e995fcbba3b60e41fd9aa9dac937fb7985c5dcbc7626260"},
-    {file = "grpcio-1.41.0-cp36-cp36m-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:3a92e4df5330cd384984e04804104ae34f521345917813aa86fc0930101a3697"},
-    {file = "grpcio-1.41.0-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ccd2f1cf11768d1f6fbe4e13e8b8fb0ccfe9914ceeff55a367d5571e82eeb543"},
-    {file = "grpcio-1.41.0-cp36-cp36m-win32.whl", hash = "sha256:59645b2d9f19b5ff30cb46ddbcaa09c398f9cd81e4e476b21c7c55ae1e942807"},
-    {file = "grpcio-1.41.0-cp36-cp36m-win_amd64.whl", hash = "sha256:0abd56d90dff3ed566807520de1385126dded21e62d3490a34c180a91f94c1f4"},
-    {file = "grpcio-1.41.0-cp37-cp37m-linux_armv7l.whl", hash = "sha256:9674a9d3f23702e35a89e22504f41b467893cf704f627cc9cdd118cf1dcc8e26"},
-    {file = "grpcio-1.41.0-cp37-cp37m-macosx_10_10_x86_64.whl", hash = "sha256:c95dd6e60e059ff770a2ac9f5a202b75dd64d76b0cd0c48f27d58907e43ed6a6"},
-    {file = "grpcio-1.41.0-cp37-cp37m-manylinux2010_i686.whl", hash = "sha256:a3cd7f945d3e3b82ebd2a4c9862eb9891a5ac87f84a7db336acbeafd86e6c402"},
-    {file = "grpcio-1.41.0-cp37-cp37m-manylinux2010_x86_64.whl", hash = "sha256:c07acd49541f5f6f9984fe0adf162d77bf70e0f58e77f9960c6f571314ff63a4"},
-    {file = "grpcio-1.41.0-cp37-cp37m-manylinux_2_17_aarch64.whl", hash = "sha256:7da3f6f6b857399c9ad85bcbffc83189e547a0a1a777ab68f5385154f8bc1ed4"},
-    {file = "grpcio-1.41.0-cp37-cp37m-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:39ce785f0cbd07966a9019386b7a054615b2da63da3c7727f371304d000a1890"},
-    {file = "grpcio-1.41.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:07594e585a5ba25cf331ddb63095ca51010c34e328a822cb772ffbd5daa62cb5"},
-    {file = "grpcio-1.41.0-cp37-cp37m-win32.whl", hash = "sha256:3bbeee115b05b22f6a9fa9bc78f9ab8d9d6bb8c16fdfc60401fc8658beae1099"},
-    {file = "grpcio-1.41.0-cp37-cp37m-win_amd64.whl", hash = "sha256:dcb5f324712a104aca4a459e524e535f205f36deb8005feb4f9d3ff0a22b5177"},
-    {file = "grpcio-1.41.0-cp38-cp38-linux_armv7l.whl", hash = "sha256:83c1e731c2b76f26689ad88534cafefe105dcf385567bead08f5857cb308246b"},
-    {file = "grpcio-1.41.0-cp38-cp38-macosx_10_10_x86_64.whl", hash = "sha256:5d4b30d068b022e412adcf9b14c0d9bcbc872e9745b91467edc0a4c700a8bba6"},
-    {file = "grpcio-1.41.0-cp38-cp38-manylinux2010_i686.whl", hash = "sha256:d71aa430b2ac40e18e388504ac34cc91d49d811855ca507c463a21059bf364f0"},
-    {file = "grpcio-1.41.0-cp38-cp38-manylinux2010_x86_64.whl", hash = "sha256:c8c5bc498f6506b6041c30afb7a55c57a9fd535d1a0ac7cdba9b5fd791a85633"},
-    {file = "grpcio-1.41.0-cp38-cp38-manylinux_2_17_aarch64.whl", hash = "sha256:a144f6cecbb61aace12e5920840338a3d246123a41d795e316e2792e9775ad15"},
-    {file = "grpcio-1.41.0-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e516124010ef60d5fc2e0de0f1f987599249dc55fd529001f17f776a4145767f"},
-    {file = "grpcio-1.41.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c1e0a4c86d4cbd93059d5eeceed6e1c2e3e1494e1bf40be9b8ab14302c576162"},
-    {file = "grpcio-1.41.0-cp38-cp38-win32.whl", hash = "sha256:a614224719579044bd7950554d3b4c1793bb5715cbf0f0399b1f21d283c40ef6"},
-    {file = "grpcio-1.41.0-cp38-cp38-win_amd64.whl", hash = "sha256:b2de4e7b5a930be04a4d05c9f5fce7e9191217ccdc174b026c2a7928770dca9f"},
-    {file = "grpcio-1.41.0-cp39-cp39-linux_armv7l.whl", hash = "sha256:056806e83eaa09d0af0e452dd353db8f7c90aa2dedcce1112a2d21592550f6b1"},
-    {file = "grpcio-1.41.0-cp39-cp39-macosx_10_10_x86_64.whl", hash = "sha256:5502832b7cec670a880764f51a335a19b10ff5ab2e940e1ded67f39b88aa02b1"},
-    {file = "grpcio-1.41.0-cp39-cp39-manylinux2010_i686.whl", hash = "sha256:585847ed190ea9cb4d632eb0ebf58f1d299bbca5e03284bc3d0fa08bab6ea365"},
-    {file = "grpcio-1.41.0-cp39-cp39-manylinux2010_x86_64.whl", hash = "sha256:d0cc0393744ce3ce1b237ae773635cc928470ff46fb0d3f677e337a38e5ed4f6"},
-    {file = "grpcio-1.41.0-cp39-cp39-manylinux_2_17_aarch64.whl", hash = "sha256:2882b62f74de8c8a4f7b2be066f6230ecc46f4edc8f42db1fb7358200abe3b25"},
-    {file = "grpcio-1.41.0-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:297ee755d3c6cd7e7d3770f298f4d4d4b000665943ae6d2888f7407418a9a510"},
-    {file = "grpcio-1.41.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ace080a9c3c673c42adfd2116875a63fec9613797be01a6105acf7721ed0c693"},
-    {file = "grpcio-1.41.0-cp39-cp39-win32.whl", hash = "sha256:1bcbeac764bbae329bc2cc9e95d0f4d3b0fb456b92cf12e7e06e3e860a4b31cf"},
-    {file = "grpcio-1.41.0-cp39-cp39-win_amd64.whl", hash = "sha256:4537bb9e35af62c5189493792a8c34d127275a6d175c8ad48b6314cacba4021e"},
-    {file = "grpcio-1.41.0.tar.gz", hash = "sha256:15c04d695833c739dbb25c88eaf6abd9a461ec0dbd32f44bc8769335a495cf5a"},
-]
-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-3.1.0-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:1cd367f89a5441236bdbb795e9fb9a9e3424929c00b4a54254ca760437f83d69"},
-    {file = "h5py-3.1.0-cp36-cp36m-manylinux1_x86_64.whl", hash = "sha256:fea05349f63625a8fb808e57e42bb4c76930cf5d50ac58b678c52f913a48a89b"},
-    {file = "h5py-3.1.0-cp36-cp36m-win_amd64.whl", hash = "sha256:2e37352ddfcf9d77a2a47f7c8f7e125c6d20cc06c2995edeb7be222d4e152636"},
-    {file = "h5py-3.1.0-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:e33f61d3eb862614c0f273a1f993a64dc2f093e1a3094932c50ada9d2db2170f"},
-    {file = "h5py-3.1.0-cp37-cp37m-manylinux1_x86_64.whl", hash = "sha256:236ac8d943be30b617ab615c3d4a4bf4a438add2be87e54af3687ab721a18fac"},
-    {file = "h5py-3.1.0-cp37-cp37m-win_amd64.whl", hash = "sha256:02c391fdb980762a1cc03a4bcaecd03dc463994a9a63a02264830114a96e111f"},
-    {file = "h5py-3.1.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:f89a3dae38843ffa49d17a31a3509a8129e9b46ece602a0138e1ed79e685c361"},
-    {file = "h5py-3.1.0-cp38-cp38-manylinux1_x86_64.whl", hash = "sha256:ba71f6229d2013fbb606476ecc29c6223fc16b244d35fcd8566ad9dbaf910857"},
-    {file = "h5py-3.1.0-cp38-cp38-win_amd64.whl", hash = "sha256:dccb89358bc84abcd711363c3e138f9f4eccfdf866f2139a8e72308328765b2c"},
-    {file = "h5py-3.1.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:cb74df83709d6d03d11e60b9480812f58da34f194beafa8c8314dbbeeedfe0a6"},
-    {file = "h5py-3.1.0-cp39-cp39-manylinux1_x86_64.whl", hash = "sha256:80c623be10479e81b64fa713b7ed4c0bbe9f02e8e7d2a2e5382336087b615ce4"},
-    {file = "h5py-3.1.0-cp39-cp39-win_amd64.whl", hash = "sha256:1cdfd1c5449ca1329d152f0b66830e93226ebce4f5e07dd8dc16bfc2b1a49d7b"},
-    {file = "h5py-3.1.0.tar.gz", hash = "sha256:1e2516f190652beedcb8c7acfa1c6fa92d99b42331cbef5e5c7ec2d65b0fc3c2"},
-]
-idna = [
-    {file = "idna-3.3-py3-none-any.whl", hash = "sha256:84d9dd047ffa80596e0f246e2eab0b391788b0503584e8945f2368256d2735ff"},
-    {file = "idna-3.3.tar.gz", hash = "sha256:9d643ff0a55b762d5cdb124b8eaa99c66322e2157b69160bc32796e824360e6d"},
-]
-isort = [
-    {file = "isort-5.9.3-py3-none-any.whl", hash = "sha256:e17d6e2b81095c9db0a03a8025a957f334d6ea30b26f9ec70805411e5c7c81f2"},
-    {file = "isort-5.9.3.tar.gz", hash = "sha256:9c2ea1e62d871267b78307fe511c0838ba0da28698c5732d54e2790bf3ba9899"},
-]
-keras = [
-    {file = "keras-2.6.0-py2.py3-none-any.whl", hash = "sha256:504af5656a9829fe803ce48a8580ef16916e89906aceddad9e098614269437e7"},
-]
-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-3.1.1-py2.py3-none-any.whl", hash = "sha256:42bf6354c2ed8c6acb54d971fce6f88193d97297e18602a3a886603f9d7730cc"},
-    {file = "oauthlib-3.1.1.tar.gz", hash = "sha256:8f0215fcc533dd8dd1bee6f4c412d4f0cd7297307d43ac61666389e3bc3198a3"},
-]
-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-3.18.1-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:fa6d1049d5315566f55c04d0b50c0033415144f96a9d25c820dc542fe2bb7f45"},
-    {file = "protobuf-3.18.1-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c0e2790c580070cff2921b93d562539ae027064340151c50db6aaf94c33048cd"},
-    {file = "protobuf-3.18.1-cp36-cp36m-win32.whl", hash = "sha256:7e2f0677d68ecdd1cfda2abea65873f5bc7c3f5aae199404a3f5c1d1198c1a63"},
-    {file = "protobuf-3.18.1-cp36-cp36m-win_amd64.whl", hash = "sha256:6f714f5de9d40b3bec90ede4a688cce52f637ccdc5403afcda1f67598f4fdcd7"},
-    {file = "protobuf-3.18.1-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:7a7be937c319146cc9f2626f0181e6809062c353e1fe449ecd0df374ba1036b2"},
-    {file = "protobuf-3.18.1-cp37-cp37m-manylinux2014_aarch64.whl", hash = "sha256:10544fc7ace885a882623083c24da5b14148c77563acddc3c58d66f6153c09cd"},
-    {file = "protobuf-3.18.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e2ee8b11e3eb2ed38f12137c3c132270a0b1dd509e317228ac47b67f21a583f1"},
-    {file = "protobuf-3.18.1-cp37-cp37m-win32.whl", hash = "sha256:c492c217d3f69f4d2d5619571e52ab98538edbf53caf67e53ea92bd0a3b5670f"},
-    {file = "protobuf-3.18.1-cp37-cp37m-win_amd64.whl", hash = "sha256:3c1644f8a7f19b45c7a4c32278e2a55ae9e7e2f9e5f02d960a61f04a4890d3e6"},
-    {file = "protobuf-3.18.1-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:e9ac691f7b24e4371dcd3980e4f5d6c840a2010da37986203053fee995786ec5"},
-    {file = "protobuf-3.18.1-cp38-cp38-manylinux2014_aarch64.whl", hash = "sha256:93bad12895d8b0ebc66b605c2ef1802311595f881aef032d9f13282b7550e6b2"},
-    {file = "protobuf-3.18.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0851b5b89191e1976d34fa2e8eb8659829dfb45252053224cf9df857fb5f6a45"},
-    {file = "protobuf-3.18.1-cp38-cp38-win32.whl", hash = "sha256:09d9268f6f9da81b7657adcf2fb397524c82f20cdf9e0db3ff4e7567977abd67"},
-    {file = "protobuf-3.18.1-cp38-cp38-win_amd64.whl", hash = "sha256:d6d927774c0ec746fed15a4faff5f44aad0b7a3421fadb6f3ae5ca1f2f8ae26e"},
-    {file = "protobuf-3.18.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:4d19c9cb805fd2be1d59eee39e152367ee92a30167e77bd06c8819f8f0009a4c"},
-    {file = "protobuf-3.18.1-cp39-cp39-manylinux2014_aarch64.whl", hash = "sha256:387f621bf7295a331f8c8a6962d097ceddeb85356792888cfa6a5c6bfc6886a4"},
-    {file = "protobuf-3.18.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8c1c5d3966c856f60a9d8d62f4455d70c31026422acdd5c228edf22b65b16c38"},
-    {file = "protobuf-3.18.1-cp39-cp39-win32.whl", hash = "sha256:f20f803892f2135e8b96dc58c9a0c6a7ad8436794bf8784af229498d939b4c77"},
-    {file = "protobuf-3.18.1-cp39-cp39-win_amd64.whl", hash = "sha256:d76201380f41a2d83fb613a4683059d1fcafbe969518b3e409e279a8788fde2f"},
-    {file = "protobuf-3.18.1-py2.py3-none-any.whl", hash = "sha256:61ca58e14033ca0dfa484a31d57237c1be3b6013454c7f53876a20fc88dd69b1"},
-    {file = "protobuf-3.18.1.tar.gz", hash = "sha256:1c9bb40503751087300dd12ce2e90899d68628977905c76effc48e66d089391e"},
-]
-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-2.4.0-py2.py3-none-any.whl", hash = "sha256:3bb3a3f256f4b7968c9c788781e4ff07dce46bdf12339dcda61053375426ee2e"},
-    {file = "pyflakes-2.4.0.tar.gz", hash = "sha256:05a85c2872edf37a4ed30b0cce2f6093e1d0581f8c19d7393122da7e25b2b24c"},
-]
-requests = [
-    {file = "requests-2.26.0-py2.py3-none-any.whl", hash = "sha256:6c1246513ecd5ecd4528a0906f910e8f0f9c6b8ec72030dc9fd154dc1a6efd24"},
-    {file = "requests-2.26.0.tar.gz", hash = "sha256:b8aa58f8cf793ffd8782d3d8cb19e66ef36f7aba4353eec859e74678b01b07a7"},
-]
-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-2.7.0-py3-none-any.whl", hash = "sha256:239f78a4a8dff200ce585a030c787773a8c1184d5c159252f5f85bac4e3c3b38"},
-]
-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-2.6.0-cp36-cp36m-macosx_10_11_x86_64.whl", hash = "sha256:c67fad296a3a2133b7a14da5f06c9937e7911b02c5d7a3ff6ba52a1d79b6bc9e"},
-    {file = "tensorflow-2.6.0-cp36-cp36m-manylinux2010_x86_64.whl", hash = "sha256:8b5ce09ede0fe45ef100f4dc65cf3f46722194e75139f85d524058315e2ce9fa"},
-    {file = "tensorflow-2.6.0-cp36-cp36m-win_amd64.whl", hash = "sha256:dea97f664246e185d79cbe40a86309527affd4232f06afa8a6500c4fc4b64a03"},
-    {file = "tensorflow-2.6.0-cp37-cp37m-macosx_10_11_x86_64.whl", hash = "sha256:4716c9b25a61a2c79b1f253d1e114f1f8679241559c13ad18c657c626a7d5924"},
-    {file = "tensorflow-2.6.0-cp37-cp37m-manylinux2010_x86_64.whl", hash = "sha256:e45e026a9d08c89cecc1160d8248135e2fb79bdc3267328399e1fb25ce583bd6"},
-    {file = "tensorflow-2.6.0-cp37-cp37m-win_amd64.whl", hash = "sha256:6e38b6969414d16afc560c58ca34e1328cc0a5dbd644b64e060f5be8a6653274"},
-    {file = "tensorflow-2.6.0-cp38-cp38-macosx_10_11_x86_64.whl", hash = "sha256:2a067d22a356c2cd4753bdd16ee492c55a610f5ebc52713e2954c642f070321c"},
-    {file = "tensorflow-2.6.0-cp38-cp38-manylinux2010_x86_64.whl", hash = "sha256:2c9b8c6adc060acfcf805a2ea501db0124b679d95b522fd5983a4c110e8e0264"},
-    {file = "tensorflow-2.6.0-cp38-cp38-win_amd64.whl", hash = "sha256:d6468e05552720100e8f94097feb770de320e4c8c244323a8746bd84e5ba4052"},
-    {file = "tensorflow-2.6.0-cp39-cp39-macosx_10_11_x86_64.whl", hash = "sha256:00b1af0a0c5c102db19caceffac4bd4e6c536e6d7512144c241a4ace4428e7c6"},
-    {file = "tensorflow-2.6.0-cp39-cp39-manylinux2010_x86_64.whl", hash = "sha256:bc73ebdd30c48cfc27ba307271117e6dbb795b37396ed817b2fec9393380b115"},
-    {file = "tensorflow-2.6.0-cp39-cp39-win_amd64.whl", hash = "sha256:bfb255c2b0400bc5b4060dda098d46cd7ddeb53b7cbac1dfa29435612cba828c"},
-]
-tensorflow-estimator = [
-    {file = "tensorflow_estimator-2.6.0-py2.py3-none-any.whl", hash = "sha256:cf78528998efdb637ac0abaf525c929bf192767544eb24ae20d9266effcf5afd"},
-]
-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 = "urllib3-1.26.7-py2.py3-none-any.whl", hash = "sha256:c4fdf4019605b6e5423637e01bc9fe4daef873709a7973e195ceba0a62bbc844"},
-    {file = "urllib3-1.26.7.tar.gz", hash = "sha256:4987c65554f7a2dbf30c18fd48778ef124af6fab771a377103da0585e2336ece"},
-]
-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-2.0.2-py3-none-any.whl", hash = "sha256:63d3dc1cf60e7b7e35e97fa9861f7397283b75d765afcaefd993d6046899de8f"},
-    {file = "Werkzeug-2.0.2.tar.gz", hash = "sha256:aa2bb6fc8dee8d6c504c0ac1e7f5f7dc5810a9903e793b6f715a9f015bdadb9a"},
-]
-wrapt = [
-    {file = "wrapt-1.12.1.tar.gz", hash = "sha256:b62ffa81fb85f4332a4f609cab4ac40709470da05643a082ec1eb88e6d9b97d7"},
-]

pyproject.toml

@@ -6,19 +6,14 @@ authors = ["coolneng <akasroua@gmail.com>"]
 license = "GPL-3.0-or-later"
 
 [tool.poetry.dependencies]
-python = "3.9.*"
+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"

shell.nix

@@ -1,9 +1,9 @@
-{ pkgs ? import <nixpkgs> { } }:
+{ sources ? import ./nix/sources.nix, pkgs ? import sources.nixpkgs { } }:
 
 with pkgs;
 
 mkShell {
-  buildInputs = [ python39 poetry ];
+  buildInputs = [ python38 poetry ];
   shellHook = ''
     export LD_LIBRARY_PATH=${pkgs.stdenv.cc.cc.lib}/lib:$LD_LIBRARY_PATH
     unset SOURCE_DATE_EPOCH

src/constants.py

@@ -0,0 +1,9 @@
+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

@@ -0,0 +1,95 @@
+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")

src/preprocessing.py

@@ -3,13 +3,14 @@ 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, one_hot
+from tensorflow import Tensor, int64
+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
 
-BASES = "ACGT-"
+from constants import *
 
 
 def align_sequences(sequence, label) -> Tuple[str, str]:
@@ -22,6 +23,19 @@ 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
@@ -30,59 +44,29 @@ def encode_sequence(sequence) -> List[int]:
     return encoded_sequence
 
 
-def decode_sequence(sequence) -> str:
+def read_fastq(data_file, label_file) -> List[bytes]:
-    """
-    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(hyperparams.data_file) as data, open(hyperparams.label_file) as labels:
+    with open(data_file) as data, open(label_file) as labels:
         for element, label in zip(parse(data, "fastq"), parse(labels, "fastq")):
-            example = generate_example(sequence=str(element.seq), label=str(label.seq))
+            example = generate_example(
+                sequence=str(element.seq),
+                label=str(label.seq),
+            )
             examples.append(example)
     return examples
 
 
-def create_dataset(hyperparams, dataset_split=[0.8, 0.1, 0.1]) -> None:
+def create_dataset(data_file, label_file, 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(hyperparams)
+    data = read_fastq(data_file, label_file)
-    with TFRecordWriter(hyperparams.train_dataset) as training, TFRecordWriter(
+    with TFRecordWriter(TRAIN_DATASET) as training, TFRecordWriter(
-        hyperparams.test_dataset
+        TEST_DATASET
-    ) as test, TFRecordWriter(hyperparams.eval_dataset) as evaluation:
+    ) as test, TFRecordWriter(EVAL_DATASET) as evaluation:
         for element in data:
             if random() < dataset_split[0]:
                 training.write(element)
@@ -94,13 +78,12 @@ def create_dataset(hyperparams, 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 one hot encoded Tensors
+    Transform the parsed features of an Example into a list of dense 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
 
 
@@ -117,32 +100,25 @@ def process_input(byte_string) -> Tuple[Tensor, Tensor]:
     return features["sequence"], features["label"]
 
 
-def read_dataset(filepath, hyperparams) -> TFRecordDataset:
+def read_dataset(filepath) -> 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.padded_batch(
+    dataset = data_input.map(map_func=process_input, num_parallel_calls=AUTOTUNE)
-        batch_size=hyperparams.batch_size,
+    batched_dataset = shuffled_dataset.batch(batch_size=BATCH_SIZE).repeat(count=EPOCHS)
-        padded_shapes=(
-            [hyperparams.max_length, len(BASES)],
-            [hyperparams.max_length, len(BASES)],
-        ),
-        padding_values=-1.0,
-    )
     return batched_dataset
 
 
 def dataset_creation(
-    hyperparams,
+    data_file, label_file
 ) -> Tuple[TFRecordDataset, TFRecordDataset, TFRecordDataset]:
     """
     Generate the TFRecord files and split them into training, validation and test data
     """
-    create_dataset(hyperparams)
+    create_dataset(data_file, label_file)
-    train_data = read_dataset(hyperparams.train_dataset, hyperparams)
+    train_data = read_dataset(TRAIN_DATASET)
-    eval_data = read_dataset(hyperparams.eval_dataset, hyperparams)
+    eval_data = read_dataset(EVAL_DATASET)
-    test_data = read_dataset(hyperparams.test_dataset, hyperparams)
+    test_data = read_dataset(TEST_DATASET)
     return train_data, eval_data, test_data