前提是数据库，权重文件等均已下载！具体教程请参考前面两篇文章

（其实就相当于是把dockerfile文件一步步手动安装）

1.创建AF3环境 

conda create -n alphafold3 python=3.11
conda activate alphafold3
conda install hmmer=3.4

可能遇到报错：PackagesNotFoundError: The following packages are not available from current channels

进入：Hmmer | Anaconda.org

conda install bioconda::hmmer

2.安装其他依赖：

可以分步，我这边都是直接去PYPI：pypi.org 手动下载每个.whl文件，自行安装。

pip install jmp==0.0.4 ml-dtypes==0.5.0 opt-einsum==3.4.0
pip install nvidia-cublas-cu12==12.6.3.3 nvidia-cuda-cupti-cu12==12.6.80 nvidia-cuda-nvcc-cu12==12.6.77 nvidia-cuda-runtime-cu12==12.6.77
pip install nvidia-cufft-cu12==11.3.0.4 nvidia-cusolver-cu12==11.7.1.2 nvidia-cusparse-cu12==12.5.4.2 nvidia-nccl-cu12==2.23.4 nvidia-nvjitlink-cu12==12.6.77
pip install rdkit==2024.3.5 scipy==1.14.1 tabulate==0.9.0 toolz==1.0.0  
pip install typeguard==2.13.3 typing-extensions==4.12.2 zstandard==0.23.0

可能会遇到.whl已经手动下载并上传至服务器但是报错：

python3.11 -m pip install *whl

3.安装所有依赖

pip3 install -r dev-requirements.txt

#下载太慢，换国内镜像源
pip install -r dev-requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple

4.安装alphafold3

pip3 install --no-deps .

5.测试实例

python run_alphafold.py \    --json_path=~/alphafold3/input/fold_input.json \    --model_dir=~/alphafold3/models \    --output_dir=~/alphafold3/output

蛋白质、RNA、DNA按照官方示例进行定义即可~