{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "e10f92e1-635e-4d01-a1e4-3c73539edec1",
   "metadata": {
    "vscode": {
     "languageId": "raw"
    }
   },
   "source": [
    "# XChrom quick start guide\n",
    "\n",
    "This notebook walks users through a tiny end-to-end run to verify that XChrom is installed and working. We  will load example data, train a small model, and visualize the training history.\n",
    "\n",
    "### Workflow:\n",
    "- Import the XChrom package.\n",
    "- List and access the bundled demo data.\n",
    "- Train XChrom model using the demo data.\n",
    "- Save the model and plot the training curves.\n",
    "\n",
    "### Demo data (model input)\n",
    "- The demo data consists of a small subset (100 cells and 1000 peaks) sampled from the original dataset.\n",
    "- Preprocessed training and test data are provided in `xchrom/data/train_data/` directory.\n",
    "- The raw cell embeddings h5ad file is provided in the `xchrom/data/test_rna.h5ad` directory.\n",
    "\n",
    "### Output\n",
    "- Trained model: `./data/quick_start/E1000best_model.h5`\n",
    "- Training history (pickle): `./data/quick_start/history.pickle`\n",
    "- Training history plot (PDF): `./data/quick_start/train_history_plot.pdf`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "7860b5d7-f60c-44eb-be36-ddccfaa33c79",
   "metadata": {},
   "outputs": [],
   "source": [
    "import xchrom as xc"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "f7e32418-e1ec-4f59-90a6-c960ab05ea4f",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "available files and directories: ['test_rna.h5ad', 'train_data']\n",
      "data directory: /picb/bigdata/project/miaoyuanyuan/train/XChrom_test/XChrom/xchrom/data\n"
     ]
    }
   ],
   "source": [
    "# list all available files and directories in xchrom test data\n",
    "print(\"available files and directories:\", xc.list_items())\n",
    "# get data directory path\n",
    "print(\"data directory:\", xc.get_data_dir())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "c1f2b4e4-783b-4bbd-a293-536d54caff5d",
   "metadata": {},
   "outputs": [],
   "source": [
    "data_path = xc.get_data_dir()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "d1ffa089-3e04-4b39-ba2f-2a6ffe8299d4",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "=== Start training XChrom model ===\n",
      "Input folder: /picb/bigdata/project/miaoyuanyuan/train/XChrom_test/XChrom/xchrom/data/train_data\n",
      "Cell embedding file: /picb/bigdata/project/miaoyuanyuan/train/XChrom_test/XChrom/xchrom/data/test_rna.h5ad\n",
      "Raw cell embedding key: X_pca\n",
      "Output path: /picb/bigdata/project/miaoyuanyuan/train/XChrom_test/XChrom/source/data/quick_start/train_out\n",
      "Model parameters: bottleneck=32, batch_size=128, lr=0.01\n",
      "1. Load raw cell embedding and make z-score normalization...\n",
      "Raw cell embedding saved to: /picb/bigdata/project/miaoyuanyuan/train/XChrom_test/XChrom/xchrom/data/test_rna.h5ad.obsm['X_pca']\n",
      "Initial cell embedding saved to: /picb/bigdata/project/miaoyuanyuan/train/XChrom_test/XChrom/xchrom/data/test_rna.h5ad.obsm['zscore32_perpc']\n",
      "Initial cell embedding shape: (100, 32)\n",
      "2. Load training data...\n",
      "3. Prepare train/val data split...\n",
      "Training peak number: 810, Validation peak number: 91\n",
      "4. Create TensorFlow dataset...\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2025-08-22 15:03:28.083032: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  SSE4.1 SSE4.2 AVX AVX2 AVX512F FMA\n",
      "To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.\n",
      "2025-08-22 15:03:29.667224: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1510] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 20361 MB memory:  -> device: 0, name: NVIDIA GeForce RTX 3090, pci bus id: 0000:31:00.0, compute capability: 8.6\n",
      "2025-08-22 15:03:29.667868: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1510] Created device /job:localhost/replica:0/task:0/device:GPU:1 with 22350 MB memory:  -> device: 1, name: NVIDIA GeForce RTX 3090, pci bus id: 0000:4b:00.0, compute capability: 8.6\n",
      "2025-08-22 15:03:29.668297: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1510] Created device /job:localhost/replica:0/task:0/device:GPU:2 with 22350 MB memory:  -> device: 2, name: NVIDIA GeForce RTX 3090, pci bus id: 0000:98:00.0, compute capability: 8.6\n",
      "2025-08-22 15:03:29.668681: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1510] Created device /job:localhost/replica:0/task:0/device:GPU:3 with 22350 MB memory:  -> device: 3, name: NVIDIA GeForce RTX 3090, pci bus id: 0000:b1:00.0, compute capability: 8.6\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "5. Build and compile model...\n",
      "Model: \"model\"\n",
      "__________________________________________________________________________________________________\n",
      "Layer (type)                    Output Shape         Param #     Connected to                     \n",
      "==================================================================================================\n",
      "sequence (InputLayer)           [(None, 1344, 4)]    0                                            \n",
      "__________________________________________________________________________________________________\n",
      "stochastic_reverse_complement ( ((None, 1344, 4), () 0           sequence[0][0]                   \n",
      "__________________________________________________________________________________________________\n",
      "stochastic_shift (StochasticShi (None, 1344, 4)      0           stochastic_reverse_complement[0][\n",
      "__________________________________________________________________________________________________\n",
      "gelu (GELU)                     (None, 1344, 4)      0           stochastic_shift[0][0]           \n",
      "__________________________________________________________________________________________________\n",
      "conv1d (Conv1D)                 (None, 1344, 288)    19584       gelu[0][0]                       \n",
      "__________________________________________________________________________________________________\n",
      "batch_normalization (BatchNorma (None, 1344, 288)    1152        conv1d[0][0]                     \n",
      "__________________________________________________________________________________________________\n",
      "max_pooling1d (MaxPooling1D)    (None, 448, 288)     0           batch_normalization[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "gelu_1 (GELU)                   (None, 448, 288)     0           max_pooling1d[0][0]              \n",
      "__________________________________________________________________________________________________\n",
      "conv1d_1 (Conv1D)               (None, 448, 288)     414720      gelu_1[0][0]                     \n",
      "__________________________________________________________________________________________________\n",
      "batch_normalization_1 (BatchNor (None, 448, 288)     1152        conv1d_1[0][0]                   \n",
      "__________________________________________________________________________________________________\n",
      "max_pooling1d_1 (MaxPooling1D)  (None, 224, 288)     0           batch_normalization_1[0][0]      \n",
      "__________________________________________________________________________________________________\n",
      "gelu_2 (GELU)                   (None, 224, 288)     0           max_pooling1d_1[0][0]            \n",
      "__________________________________________________________________________________________________\n",
      "conv1d_2 (Conv1D)               (None, 224, 323)     465120      gelu_2[0][0]                     \n",
      "__________________________________________________________________________________________________\n",
      "batch_normalization_2 (BatchNor (None, 224, 323)     1292        conv1d_2[0][0]                   \n",
      "__________________________________________________________________________________________________\n",
      "max_pooling1d_2 (MaxPooling1D)  (None, 112, 323)     0           batch_normalization_2[0][0]      \n",
      "__________________________________________________________________________________________________\n",
      "gelu_3 (GELU)                   (None, 112, 323)     0           max_pooling1d_2[0][0]            \n",
      "__________________________________________________________________________________________________\n",
      "conv1d_3 (Conv1D)               (None, 112, 363)     586245      gelu_3[0][0]                     \n",
      "__________________________________________________________________________________________________\n",
      "batch_normalization_3 (BatchNor (None, 112, 363)     1452        conv1d_3[0][0]                   \n",
      "__________________________________________________________________________________________________\n",
      "max_pooling1d_3 (MaxPooling1D)  (None, 56, 363)      0           batch_normalization_3[0][0]      \n",
      "__________________________________________________________________________________________________\n",
      "gelu_4 (GELU)                   (None, 56, 363)      0           max_pooling1d_3[0][0]            \n",
      "__________________________________________________________________________________________________\n",
      "conv1d_4 (Conv1D)               (None, 56, 407)      738705      gelu_4[0][0]                     \n",
      "__________________________________________________________________________________________________\n",
      "batch_normalization_4 (BatchNor (None, 56, 407)      1628        conv1d_4[0][0]                   \n",
      "__________________________________________________________________________________________________\n",
      "max_pooling1d_4 (MaxPooling1D)  (None, 28, 407)      0           batch_normalization_4[0][0]      \n",
      "__________________________________________________________________________________________________\n",
      "gelu_5 (GELU)                   (None, 28, 407)      0           max_pooling1d_4[0][0]            \n",
      "__________________________________________________________________________________________________\n",
      "conv1d_5 (Conv1D)               (None, 28, 456)      927960      gelu_5[0][0]                     \n",
      "__________________________________________________________________________________________________\n",
      "batch_normalization_5 (BatchNor (None, 28, 456)      1824        conv1d_5[0][0]                   \n",
      "__________________________________________________________________________________________________\n",
      "max_pooling1d_5 (MaxPooling1D)  (None, 14, 456)      0           batch_normalization_5[0][0]      \n",
      "__________________________________________________________________________________________________\n",
      "gelu_6 (GELU)                   (None, 14, 456)      0           max_pooling1d_5[0][0]            \n",
      "__________________________________________________________________________________________________\n",
      "conv1d_6 (Conv1D)               (None, 14, 512)      1167360     gelu_6[0][0]                     \n",
      "__________________________________________________________________________________________________\n",
      "batch_normalization_6 (BatchNor (None, 14, 512)      2048        conv1d_6[0][0]                   \n",
      "__________________________________________________________________________________________________\n",
      "max_pooling1d_6 (MaxPooling1D)  (None, 7, 512)       0           batch_normalization_6[0][0]      \n",
      "__________________________________________________________________________________________________\n",
      "gelu_7 (GELU)                   (None, 7, 512)       0           max_pooling1d_6[0][0]            \n",
      "__________________________________________________________________________________________________\n",
      "conv1d_7 (Conv1D)               (None, 7, 256)       131072      gelu_7[0][0]                     \n",
      "__________________________________________________________________________________________________\n",
      "batch_normalization_7 (BatchNor (None, 7, 256)       1024        conv1d_7[0][0]                   \n",
      "__________________________________________________________________________________________________\n",
      "gelu_8 (GELU)                   (None, 7, 256)       0           batch_normalization_7[0][0]      \n",
      "__________________________________________________________________________________________________\n",
      "reshape (Reshape)               (None, 1, 1792)      0           gelu_8[0][0]                     \n",
      "__________________________________________________________________________________________________\n",
      "dense (Dense)                   (None, 1, 32)        57344       reshape[0][0]                    \n",
      "__________________________________________________________________________________________________\n",
      "cell_embed (InputLayer)         [(None, 91, 32)]     0                                            \n",
      "__________________________________________________________________________________________________\n",
      "batch_normalization_8 (BatchNor (None, 1, 32)        128         dense[0][0]                      \n",
      "__________________________________________________________________________________________________\n",
      "lambda (Lambda)                 (None, 91, 32)       0           cell_embed[0][0]                 \n",
      "__________________________________________________________________________________________________\n",
      "dropout (Dropout)               (None, 1, 32)        0           batch_normalization_8[0][0]      \n",
      "__________________________________________________________________________________________________\n",
      "layer_normalization (LayerNorma (None, 91, 32)       64          lambda[0][0]                     \n",
      "__________________________________________________________________________________________________\n",
      "gelu_9 (GELU)                   (None, 1, 32)        0           dropout[0][0]                    \n",
      "__________________________________________________________________________________________________\n",
      "dense_1 (Dense)                 (None, 91, 64)       2112        layer_normalization[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "tf.compat.v1.squeeze (TFOpLambd (None, 32)           0           gelu_9[0][0]                     \n",
      "__________________________________________________________________________________________________\n",
      "sequencing_depth (InputLayer)   [(None, 91)]         0                                            \n",
      "__________________________________________________________________________________________________\n",
      "final_cellembed (Dense)         (None, 91, 32)       2080        dense_1[0][0]                    \n",
      "__________________________________________________________________________________________________\n",
      "tf.expand_dims (TFOpLambda)     (None, 32, 1)        0           tf.compat.v1.squeeze[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "tf.expand_dims_1 (TFOpLambda)   (None, 91, 1)        0           sequencing_depth[0][0]           \n",
      "__________________________________________________________________________________________________\n",
      "tf.linalg.matmul (TFOpLambda)   (None, 91, 1)        0           final_cellembed[0][0]            \n",
      "                                                                 tf.expand_dims[0][0]             \n",
      "__________________________________________________________________________________________________\n",
      "dense_2 (Dense)                 (None, 91, 1)        2           tf.expand_dims_1[0][0]           \n",
      "__________________________________________________________________________________________________\n",
      "tf.compat.v1.squeeze_2 (TFOpLam (None, 91)           0           tf.linalg.matmul[0][0]           \n",
      "__________________________________________________________________________________________________\n",
      "tf.compat.v1.squeeze_1 (TFOpLam (None, 91)           0           dense_2[0][0]                    \n",
      "__________________________________________________________________________________________________\n",
      "tf.__operators__.add (TFOpLambd (None, 91)           0           tf.compat.v1.squeeze_2[0][0]     \n",
      "                                                                 tf.compat.v1.squeeze_1[0][0]     \n",
      "__________________________________________________________________________________________________\n",
      "tf.math.sigmoid (TFOpLambda)    (None, 91)           0           tf.__operators__.add[0][0]       \n",
      "==================================================================================================\n",
      "Total params: 4,524,068\n",
      "Trainable params: 4,518,218\n",
      "Non-trainable params: 5,850\n",
      "__________________________________________________________________________________________________\n",
      "6. Set training callbacks...\n",
      "7. Start training...\n",
      "Model will be saved to: data/quick_start/train_out/E1000best_model.h5\n",
      "Epoch 1/10\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2025-08-22 15:03:32.399414: I tensorflow/compiler/mlir/mlir_graph_optimization_pass.cc:185] None of the MLIR Optimization Passes are enabled (registered 2)\n",
      "2025-08-22 15:03:34.311489: I tensorflow/stream_executor/cuda/cuda_dnn.cc:369] Loaded cuDNN version 8800\n",
      "2025-08-22 15:03:34.384349: I tensorflow/stream_executor/cuda/cuda_blas.cc:1760] TensorFloat-32 will be used for the matrix multiplication. This will only be logged once.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "7/7 [==============================] - 10s 379ms/step - loss: 0.8043 - binary_accuracy: 0.7448 - auc: 0.5669 - pr: 0.1801 - val_loss: 178.2907 - val_binary_accuracy: 0.8591 - val_auc: 0.5000 - val_pr: 0.1409\n",
      "Epoch 2/10\n",
      "7/7 [==============================] - 1s 74ms/step - loss: 0.4698 - binary_accuracy: 0.8192 - auc: 0.6475 - pr: 0.2310 - val_loss: 6.9911 - val_binary_accuracy: 0.8555 - val_auc: 0.5062 - val_pr: 0.1476\n",
      "Epoch 3/10\n",
      "7/7 [==============================] - 1s 73ms/step - loss: 0.4251 - binary_accuracy: 0.8224 - auc: 0.6977 - pr: 0.2798 - val_loss: 1.7770 - val_binary_accuracy: 0.8257 - val_auc: 0.6334 - val_pr: 0.2380\n",
      "Epoch 4/10\n",
      "7/7 [==============================] - 1s 73ms/step - loss: 0.4052 - binary_accuracy: 0.8393 - auc: 0.7175 - pr: 0.3142 - val_loss: 0.7914 - val_binary_accuracy: 0.8022 - val_auc: 0.6343 - val_pr: 0.2196\n",
      "Epoch 5/10\n",
      "7/7 [==============================] - 1s 77ms/step - loss: 0.3960 - binary_accuracy: 0.8454 - auc: 0.7162 - pr: 0.3061 - val_loss: 0.5019 - val_binary_accuracy: 0.8017 - val_auc: 0.6692 - val_pr: 0.2455\n",
      "Epoch 6/10\n",
      "7/7 [==============================] - 1s 71ms/step - loss: 0.3873 - binary_accuracy: 0.8467 - auc: 0.7273 - pr: 0.3299 - val_loss: 0.4448 - val_binary_accuracy: 0.7977 - val_auc: 0.6930 - val_pr: 0.2637\n",
      "Epoch 7/10\n",
      "7/7 [==============================] - 1s 73ms/step - loss: 0.3859 - binary_accuracy: 0.8438 - auc: 0.7382 - pr: 0.3403 - val_loss: 0.4215 - val_binary_accuracy: 0.8044 - val_auc: 0.7035 - val_pr: 0.2759\n",
      "Epoch 8/10\n",
      "7/7 [==============================] - 1s 73ms/step - loss: 0.3791 - binary_accuracy: 0.8476 - auc: 0.7433 - pr: 0.3548 - val_loss: 0.3979 - val_binary_accuracy: 0.8332 - val_auc: 0.7113 - val_pr: 0.2880\n",
      "Epoch 9/10\n",
      "7/7 [==============================] - 1s 71ms/step - loss: 0.3783 - binary_accuracy: 0.8477 - auc: 0.7458 - pr: 0.3519 - val_loss: 0.3838 - val_binary_accuracy: 0.8457 - val_auc: 0.7182 - val_pr: 0.2903\n",
      "Epoch 10/10\n",
      "7/7 [==============================] - 1s 73ms/step - loss: 0.3785 - binary_accuracy: 0.8485 - auc: 0.7446 - pr: 0.3521 - val_loss: 0.3801 - val_binary_accuracy: 0.8504 - val_auc: 0.7290 - val_pr: 0.3060\n",
      "8. Save training results...\n",
      "=== Training completed! ===\n",
      "Best model: /picb/bigdata/project/miaoyuanyuan/train/XChrom_test/XChrom/source/data/quick_start/train_out/E1000best_model.h5\n",
      "Training history: /picb/bigdata/project/miaoyuanyuan/train/XChrom_test/XChrom/source/data/quick_start/train_out/history.pickle\n"
     ]
    }
   ],
   "source": [
    "history = xc.tr.train_XChrom(\n",
    "    input_folder = f'{data_path}/train_data',\n",
    "    cell_embedding_ad = f'{data_path}/test_rna.h5ad',\n",
    "    cellembed_raw='X_pca',\n",
    "    out_path='./data/quick_start/train_out/',\n",
    "    epochs = 10,\n",
    "    verbose = 1\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "79ddb11d-9b66-451f-8176-686911aeec7b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x600 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "xc.pl.plot_train_history(\n",
    "    history = history['history'],\n",
    "    savefig = True,\n",
    "    out_file = './data/quick_start/train_out/train_history_plot.pdf'\n",
    "    )"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a40c1238-d159-4303-b16e-e7871eafa6a6",
   "metadata": {},
   "source": [
    "XChrom has been successfully installed and loaded! You can now use XChrom for analysis."
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "py3.8_tf2.6.0",
   "language": "python",
   "name": "py3.8_tf2.6.0"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.15"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}