Commit a95ecc2f authored by yuhai's avatar yuhai
Browse files

Update README.md

parent a81d0061
......@@ -21,7 +21,7 @@ RFDesign基于Rosetta(一个广泛应用于蛋白质结构预测和蛋白质设
## 环境配置
提供[光源](https://www.sourcefind.cn/#/service-details)拉取推理的docker镜像:
```
docker pull image.sourcefind.cn:5000/dcu/admin/base/custom:rfdesign-dtk22.10-patch4-py39-latest
docker pull image.sourcefind.cn:5000/dcu/admin/base/custom:rfdesign-torch2.1.0-dtk24.04-ubuntu20.04-py310
# <Image ID>用上面拉取docker镜像的ID替换
# <Host Path>主机端路径
# <Container Path>容器映射路径
......@@ -29,18 +29,18 @@ docker run -it --name rfdesign --shm-size=32G --device=/dev/kfd --device=/dev/d
```
镜像版本依赖:
* DTK驱动:dtk22.10
* Pytorch: 1.10
* Tensorflow: 2.7
* Jax: 0.2.21
* DTK驱动:dtk24.04.1
* Pytorch: 2.10
* Tensorflow: 2.13.1
* Jax: 0.4.23
* dgl: 0.9.1
* python: python3.9
* python: python3.10
激活镜像环境:
`source /opt/dtk-22.10/env.sh`
`source /opt/dtk-24.04.1/env.sh`
测试目录:
`/opt/RFDesign`
`/RFDesign`
## 数据集
......@@ -48,41 +48,42 @@ docker run -it --name rfdesign --shm-size=32G --device=/dev/kfd --device=/dev/d
## 推理
### 下载权重
cd /opt/RFDesign/hallucination/weights/rf_Nov05
cd /RFDesign/hallucination/weights/rf_Nov05
wget http://files.ipd.uw.edu/pub/rfdesign/weights/BFF_last.pt
cd /opt/RFDesign/inpainting/weights/
cd /RFDesign/inpainting/weights/
wget http://files.ipd.uw.edu/pub/rfdesign/weights/BFF_mix_epoch25.pt
### hallucination
基于hallucination的测试命令:
cd /opt/RFDesign/hallucination/tests/
./run_tests.sh # 结果默认保存在/opt/RFDesign/hallucination/tests/output
cd /RFDesign/hallucination/tests/
./run_tests.sh # 结果默认保存在/RFDesign/hallucination/tests/output
参数说明:--pdb是模板pdb结构,--out是结果保存路径的前缀,--len是hallucination蛋白的长度范围, --contigs是以逗号分隔的pdb范围列表来参考pdb,--steps是逗号分隔的优化步骤数列表,--num是是设计数量
### inpainting
基于inpainting的测试命令:
cd /opt/RFDesign/inpainting/tests/
./run_tests.sh # 结果默认保存在/opt/RFDesign/inpainting/tests/out
cd /RFDesign/inpainting/tests/
./run_tests.sh # 结果默认保存在/RFDesign/inpainting/tests/out
参数说明:--pdb是模板蛋白质结构(序列)的pdb文件,--out 是结果保存路径的前缀,--contigs是指定保留、移除和修复蛋白质的部分,--num_designs是生成的设计数量
### 准备输入和后处理以及hallucination评分结果
运行hallucination或inpainting后,首先生成一个带侧链的松弛模型(.fas、.pdb、.npz、.trb 文件),该步骤需要.pdb和.npz文件,完成后,会生成一个FOLDER/trf_relax文件夹(包含松弛结构的pdb)
cd /opt/RFDesign/scripts
cd /RFDesign/scripts
./trfold_relax.sh FOLDER # FOLDER文件夹包含hallucination或inpainting的结果
#### AlphaFold2
根据hallucination设计模型和模板结构,进行AlphaFold2预测和计算RMSD:
sh /opt/RFDesign/hallucination/models/alphafold/scripts/download_alphafold_params.sh alphafold-data # alphafold-data为下载模型的路径
./af2_metrics.py FOLDER/trf_relax # 修改第241行的data_dir为自己的alphafold2模型路径(即上一行的alphafold-data)
wget https://storage.googleapis.com/alphafold/alphafold_params_2021-07-14.tar
tar -xvf alphafold_params_2021-07-14.tar
./af2_metrics.py FOLDER/trf_relax # 修改第241行的data_dir为自己的alphafold2模型路径(即上两行的下载和解压)
该步骤会将AF2模型输出到FOLDER/trf_relax/af2/,并将指标输出到FOLDER/af2_metrics.csv
......@@ -102,7 +103,7 @@ docker run -it --name rfdesign --shm-size=32G --device=/dev/kfd --device=/dev/d
## result
```
/opt/RFDesign/
/RFDesign/
hallucination/
tests/output/
trf_relax/
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment