116 lines
2.6 KiB
Markdown
116 lines
2.6 KiB
Markdown
# 安装 Vite 创建工具（只需一次）
|
||
```
|
||
npm create vite@latest embryo-frontend -- --template react-ts
|
||
cd embryo-frontend
|
||
npm install
|
||
npm install three @react-three/fiber @react-three/drei
|
||
npm install zustand axios react-router-dom
|
||
npm run dev
|
||
|
||
cd ..
|
||
mkdir embryo-backend
|
||
cd embryo-backend
|
||
```
|
||
# 创建虚拟环境（推荐）
|
||
安装uv：<https://docs.astral.sh/uv/getting-started/installation/>
|
||
```
|
||
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
|
||
```
|
||
|
||
# 运行
|
||
```
|
||
.\start-dev.ps1
|
||
```
|
||
<http://localhost:5000/api/gene/SOX2>
|
||
|
||
|
||
## 脚本功能：
|
||
|
||
1. **同时启动两个服务**：
|
||
- 前端：在 `embryo-frontend` 目录中运行 `npm run dev`
|
||
- 后端：使用 `uv run` 运行 `embryo-backend/app.py`
|
||
|
||
2. **智能检查**：
|
||
- 验证目录和文件是否存在
|
||
- 监控服务状态
|
||
- 提供彩色输出和状态信息
|
||
|
||
3. **优雅的停止机制**：
|
||
- 使用 Ctrl+C 可以同时停止两个服务
|
||
- 自动清理后台作业
|
||
|
||
## 使用方法：
|
||
|
||
在项目根目录中运行：
|
||
|
||
```powershell
|
||
.\start-dev.ps1
|
||
```
|
||
|
||
或者如果需要执行权限：
|
||
|
||
```powershell
|
||
Set-ExecutionPolicy -ExecutionPolicy RemoteSigned -Scope CurrentUser
|
||
.\start-dev.ps1
|
||
```
|
||
|
||
## 预期输出：
|
||
|
||
- 前端开发服务器通常运行在：`http://localhost:5173`
|
||
- 后端API服务器通常运行在：`http://localhost:5000`
|
||
|
||
脚本会显示启动状态，并在两个服务都启动后保持运行状态。按 Ctrl+C 可以同时停止所有服务。
|
||
|
||
现在您可以使用这个脚本来快速启动整个开发环境了！
|
||
|
||
|
||
# 20250721 3D点云可视化
|
||
|
||
```
|
||
npm install three
|
||
```
|
||
|
||
# 20250721生成假的胚胎数据：
|
||
```
|
||
uv run FakeEmbyro.py
|
||
|
||
|
||
cd embryo-frontend
|
||
npm install chart.js react-chartjs-2
|
||
```
|
||
|
||
|
||
|
||
```
|
||
import numpy as np
|
||
import pandas as pd
|
||
import anndata as ad
|
||
import os
|
||
|
||
script_path = os.path.dirname(os.path.realpath(__file__))
|
||
N = 1500
|
||
radius = 10
|
||
np.random.seed(42)
|
||
|
||
phi = np.random.uniform(0, np.pi, N)
|
||
theta = np.random.uniform(0, 2 * np.pi, N)
|
||
|
||
x = radius * np.sin(phi) * np.cos(theta)
|
||
y = radius * np.sin(phi) * np.sin(theta)
|
||
z = radius * 0.7 * np.cos(phi)
|
||
|
||
genes = ["SOX2", "NANOG", "POU5F1", "T", "OTX2", "ZIC2", "FOXA2", "LEFTY1"]
|
||
expression_data = {
|
||
gene: np.exp(-(x**2 + y**2 + z**2) / (2 * radius**2)) + 0.1 * np.random.rand(N)
|
||
for gene in genes
|
||
}
|
||
|
||
obs = pd.DataFrame({"cell_id": [f"cell_{i}" for i in range(N)]}, index=[f"cell_{i}" for i in range(N)])
|
||
var = pd.DataFrame(index=genes)
|
||
obsm = {"spatial": np.vstack([x, y, z]).T}
|
||
X = np.vstack([expression_data[gene] for gene in genes]).T # shape (N, G)
|
||
|
||
adata = ad.AnnData(X=X, obs=obs, var=var, obsm=obsm)
|
||
adata.write(f"{script_path}/CS9.h5ad")
|
||
```
|