{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "00a96048",
   "metadata": {},
   "source": [
    "# DNN Model Training\n",
    "\n",
    "This notebook is used to train DNN models.\n",
    "\n",
    "\n",
    "### Introduction\n",
    "\n",
    "##### Model architecture\n",
    "\n",
    "- Recognizing the distinct transcriptomic profiles between cortical and subcortical regions and the higher functional differentiation in human cortical regions, we trained a detached deep neural network model.\n",
    "- **Cortical model** took separately normalized data of the cortex as input, with an input layer dimension of 4,542 and an output layer of 105 cortical region labels (for BN atlas).\n",
    "- **Subcortical model** took separately normalized data of the subcortex as input, with an input layer dimension of 5,063 and an output layer of 22 subcortical region labels.\n",
    "\n",
    "\n",
    "##### Region-specific embeddings\n",
    "\n",
    "- We fed the regional average expression matrices into the model and extracted the outputs from the final hidden layer, which served as the foundation for constructing the homologous mapping relationships.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "130922d9-4d60-4bb4-ac01-4ba258fa527b",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "ae1b1ddf-c3a4-4b69-9756-cd12d89bb848",
   "metadata": {},
   "outputs": [],
   "source": [
    "homo_mouse_region_cortex=['PL','PL','ACAd','ACAv','ACAd','ACAv','ACAd','ACAv','ACAd','ACAv','RSPd','RSPd','RSPv','RSPv','ORBl','ORBl','ORBl','ORBl','ORBm','ORBm','ORBm','ORBm','ORBvl','ORBvl','ORBvl','ORBvl','MOp','MOp','MOp','MOp','SSp-ul',\n",
    "                   'SSp-m','SSp-ll','SSp-tr','VISp','VISp','VISp','VISp','AId','AIv','AUDp']\n",
    "homo_human_region_cortex=['A32p','A32sg','A32p','A32p','A32sg','A32sg','A24rv','A24rv','A24cd','A24cd','A23d','A23v','A23d','A23v','A11l','A11m','A12/47o','A12/47l','A11l','A11m','A12/47o','A12/47l','A11l','A11m','A12/47o','A12/47l','A4hf','A4t','A4ul','A4ll','A1/2/3ulhf',\n",
    "                   'A1/2/3tonIa','A1/2/3ll','A1/2/3tru','cCunG','rCunG','cLinG','rLinG','dIa','vIa','TE1.0 and TE1.2']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "ea8897a1-20b1-4081-a950-47f8ced1b5e5",
   "metadata": {},
   "outputs": [],
   "source": [
    "homo_mouse_region_subcortex = ['DG','CP','PAL','CA1','SUB','CA2','CA3','ACB','MED']\n",
    "homo_human_region_subcortex = ['CA4DG','body of caudate','external segment of globus pallidus','CA1','subiculum','CA2CA3','CA2CA3','nucleus accumbens','mPFtha']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "9bbf819f-f067-4444-9ffe-bec348759950",
   "metadata": {},
   "outputs": [],
   "source": [
    "homo_cortex = pd.DataFrame()\n",
    "homo_cortex['human_region'] = homo_human_region_cortex\n",
    "homo_cortex['mouse_region'] = homo_mouse_region_cortex\n",
    "homo_cortex.to_csv('./files/homo_cortex.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "db0fe449-dba3-4cba-ba74-6ea43a08bfe7",
   "metadata": {},
   "outputs": [],
   "source": [
    "homo_subcortex = pd.DataFrame()\n",
    "homo_subcortex['human_region'] = homo_human_region_subcortex\n",
    "homo_subcortex['mouse_region'] = homo_mouse_region_subcortex\n",
    "homo_subcortex.to_csv('./files/homo_subcortex.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "593a15a2-4359-4e8e-af07-83cad360a1e9",
   "metadata": {},
   "outputs": [],
   "source": [
    "homo_all = pd.DataFrame()\n",
    "homo_all['human_region'] = homo_human_region_cortex+homo_human_region_subcortex\n",
    "homo_all['mouse_region'] = homo_mouse_region_cortex+homo_mouse_region_subcortex\n",
    "homo_all.to_csv('./files/homo_all.csv')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "00b47d65-3d1e-4ac0-9d96-581cffa280e4",
   "metadata": {},
   "source": [
    "## cortical train"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "c53965cc",
   "metadata": {},
   "outputs": [],
   "source": [
    "# ! python ../code/dnn/main.py -n 10 -iu 4542 -ou 105 -g_path ./files/common_stable_genes_cortex.csv -d_path ../datasets/integrated_dataset/cortical_integrated/Integrated_dataset_0.h5ad -s_path ./dnn_result/detached_model/cortical_model -m_trans_path ../datasets/processeddata/mouse_st/Mouse_trans_data_cortex.h5ad -h_trans_path ../datasets/processeddata/human_ahba/Human_trans_data_cortex.h5ad -hm_path ./files/homo_cortex.csv"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "52139976-a876-4883-bc87-67c7076eb483",
   "metadata": {},
   "source": [
    "## subcortical train"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "6e37ddd0",
   "metadata": {},
   "outputs": [],
   "source": [
    "# ! python ../code/dnn/main.py -n 10 -iu 5063 -ou 22 -g_path ./files/common_stable_genes_subcortex.csv -d_path ../datasets/integrated_dataset/subcortical_integrated/Integrated_dataset_0.h5ad -s_path ./dnn_result/detached_model/subcortical_model -m_trans_path ../datasets/processeddata/mouse_st/Mouse_trans_data_subcortex.h5ad -h_trans_path ../datasets/processeddata/human_ahba/Human_trans_data_subcortex.h5ad -hm_path ./files/homo_subcortex.csv"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "transbrain_test",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}