Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
ModelZoo
FastFold_pytorch
Commits
bddfe331
Commit
bddfe331
authored
Sep 24, 2024
by
yuhai
Browse files
Update README.md
parent
1617b154
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
19 additions
and
17 deletions
+19
-17
README.md
README.md
+19
-17
No files found.
README.md
View file @
bddfe331
...
@@ -21,22 +21,24 @@ FastFold通过搜索同源序列和模板进行特征构造,基于蛋白质结
...
@@ -21,22 +21,24 @@ FastFold通过搜索同源序列和模板进行特征构造,基于蛋白质结
## 环境配置
## 环境配置
提供
[
光源
](
https://www.sourcefind.cn/#/service-details
)
拉取推理的docker镜像:
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:fastfold-
0.2.0-dtk23.10-v2
docker pull image.sourcefind.cn:5000/dcu/admin/base/custom:fastfold-
torch2.1.0-dtk24.04-centos7.6
# <Image ID>用上面拉取docker镜像的ID替换
# <Image ID>用上面拉取docker镜像的ID替换
# <Host Path>主机端路径
# <Host Path>主机端路径
# <Container Path>容器映射路径
# <Container Path>容器映射路径
docker run -it --name fastfold --
privileged --shm-size=32G --device=/dev/kfd
--device=/dev/dri
/
--cap-add=SYS_PTRACE --security-opt seccomp=unconfined -
-ulimit memlock=-1:-1 --ipc=host --network host
--group-add video -v <Host Path>:<Container Path> <Image ID>
/bin/bash
docker run -it
-d
--name fastfold --
device=/dev/kfd --privileged --network=host
--device=/dev/dri --cap-add=SYS_PTRACE --security-opt seccomp=unconfined -
v /opt/hyhal:/opt/hyhal:ro -v /usr/local/hyhal:/usr/local/hyhal:ro
--group-add video
--shm-size 32G
-v <Host Path>:<Container Path> <Image ID>
```
```
镜像版本依赖:
镜像版本依赖:
*
DTK驱动:dtk2
3.10
*
DTK驱动:dtk2
4.04
*
Pytorch:
1.13
*
Pytorch:
2.1.0
*
fastfold: 0.2.
0
*
fastfold: 0.2.
1
*
python: python3.
8
*
python: python3.
10
激活镜像环境:
`source /home/env.sh`
测试目录:
测试目录:
`/
opt/docker/tests
`
`/
home/fastfold_pytorch
`
## 数据集
## 数据集
推荐使用AlphaFold2中的开源数据集,包括BFD、MGnify、PDB70、Uniclust、Uniref90等,数据集大小约3TB。数据集格式如下:
推荐使用AlphaFold2中的开源数据集,包括BFD、MGnify、PDB70、Uniclust、Uniref90等,数据集大小约3TB。数据集格式如下:
...
@@ -93,16 +95,16 @@ $DOWNLOAD_DIR/
...
@@ -93,16 +95,16 @@ $DOWNLOAD_DIR/
### 单体
### 单体
python inference.py T1024.fasta data/pdb_mmcif/mmcif_files/ \
python inference.py T1024.fasta
/
data/pdb_mmcif/mmcif_files/ \
--output_dir ./ \
--output_dir ./
output
\
--gpus
1
\
--gpus
4
\
--use_precomputed_alignments alignments/ \
--use_precomputed_alignments
data/
alignments/ \
--param_path /data/params/params_model_1.npz \
--param_path /data/params/params_model_1.npz \
--uniref90_database_path data/uniref90/uniref90.fasta \
--uniref90_database_path
/
data/uniref90/uniref90.fasta \
--mgnify_database_path data/mgnify/mgy_clusters_2018_12.fa \
--mgnify_database_path
/
data/mgnify/mgy_clusters_2018_12.fa \
--pdb70_database_path data/pdb70/pdb70 \
--pdb70_database_path
/
data/pdb70/pdb70 \
--uniclust30_database_path data/uniclust30/uniclust30_2018_08/uniclust30_2018_08 \
--uniclust30_database_path
/
data/uniclust30/uniclust30_2018_08/uniclust30_2018_08 \
--bfd_database_path data/bfd/bfd_metaclust_clu_complete_id30_c90_final_seq.sorted_opt \
--bfd_database_path
/
data/bfd/bfd_metaclust_clu_complete_id30_c90_final_seq.sorted_opt \
--jackhmmer_binary_path `which jackhmmer` \
--jackhmmer_binary_path `which jackhmmer` \
--hhblits_binary_path `which hhblits` \
--hhblits_binary_path `which hhblits` \
--hhsearch_binary_path `which hhsearch` \
--hhsearch_binary_path `which hhsearch` \
...
@@ -110,7 +112,7 @@ $DOWNLOAD_DIR/
...
@@ -110,7 +112,7 @@ $DOWNLOAD_DIR/
--chunk_size 4 \
--chunk_size 4 \
--inplace
--inplace
或者使用
`
./
inference.sh`
或者使用
`
sh
inference.sh`
#### 单体推理参数说明
#### 单体推理参数说明
T1024.fasta为推理的单体序列;data修改为数据集下载目录;
T1024.fasta为推理的单体序列;data修改为数据集下载目录;
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment