安装环境
CentOS虚拟机(图形界面)7.9
yum install git
安装流程
wget https://repo.anaconda.com/archive/Anaconda3-2024.02-1-Linux-x86_64.sh
bash Anaconda3-2024.02-1-Linux-x86_64.sh
<
enter
yes
/opt/app/anaconda3
no
>
cd
git clone https://github.com/baker-laboratory/RoseTTAFold-All-Atom
cd RoseTTAFold-All-Atom
source /opt/app/anaconda3/bin/activate
vim environment.yaml
<
- tensorflow=2.11.0
- tensorflow-base=2.11.0
- tensorflow-estimator=2.11.0
>
conda env create -f environment.yaml
如果失败,就加载到环境中继续安装软件
conda activate RFAA
conda update -f environment.yaml
如果成功后就继续下一步
从 signalp6 下载许可副本后对其进行配置
signalp-6.0h.fast.tar.gz
signalp-6.0_license.txt
配置
signalp6-register signalp-6.0h.fast.tar.gz
mv /opt/app/anaconda3/envs/RFAA/lib/python3.10/site-packages/signalp/model_weights/distilled_model_signalp6.pt /opt/app/anaconda3/envs/RFAA/lib/python3.10/site-packages/signalp/model_weights/ensemble_model_signalp6.pt
安装输入准备依赖项
bash install_dependencies.sh
下载模型权重
wget http://files.ipd.uw.edu/pub/RF-All-Atom/weights/RFAA_paper_weights.pt
cp RFAA_paper_weights.pt /opt/app/anaconda3/envs/RFAA/lib/python3.10/site-packages/signalp/model_weights/
下载用于 MSA 和模板生成的序列数据库。
# uniref30 [46G]
wget http://wwwuser.gwdg.de/~compbiol/uniclust/2020_06/UniRef30_2020_06_hhsuite.tar.gz
mkdir -p UniRef30_2020_06
tar xfz UniRef30_2020_06_hhsuite.tar.gz -C ./UniRef30_2020_06
# BFD [272G]
wget https://bfd.mmseqs.com/bfd_metaclust_clu_complete_id30_c90_final_seq.sorted_opt.tar.gz
mkdir -p bfd
tar xfz bfd_metaclust_clu_complete_id30_c90_final_seq.sorted_opt.tar.gz -C ./bfd
# structure templates (including *_a3m.ffdata, *_a3m.ffindex)
wget https://files.ipd.uw.edu/pub/RoseTTAFold/pdb100_2021Mar03.tar.gz
tar xfz pdb100_2021Mar03.tar.gz
环境配置
平台安装路径为/opt/app/RoseTTAFold-All-Atom
mkdir -p $HOME/RoseTTAFold-All-Atom
cd /opt/app/RoseTTAFold-All-Atom
cp -r !(dataset|uniclust) $HOME/RoseTTAFold-All-Atom
cd $HOME/RoseTTAFold-All-Atom
ln -s /opt/app/RoseTTAFold-All-Atom/dataset/pdb100_2021Mar03/ pdb100_2021Mar03
vim make_msa.sh
<
# sequence databases 修改数据库路径
DB_UR30="/opt/app/RoseTTAFold-All-Atom/uniclust/UniRef30_2020_06"
DB_BFD="/opt/app/RoseTTAFold-All-Atom/dataset/bfd/bfd_metaclust_clu_complete_id30_c90_final_seq.sorted_opt"
>
source /opt/app/anaconda3/bin/activate
conda activate RFAA
本地安装blast-2.2.26
cd $HOME/RoseTTAFold-All-Atom
wget https://ftp.ncbi.nlm.nih.gov/blast/executables/legacy.NOTSUPPORTED/2.2.26/blast-2.2.26-x64-linux.tar.gz
tar xf blast-2.2.26-x64-linux.tar.gz
vim input_prep/make_ss.sh
<
export BLASHMAT=$HOME/RoseTTAFold-All-Atom/blast-2.2.26/data/ # 加在文件开头第三行
$HOME/RoseTTAFold-All-Atom/blast-2.2.26/bin/makemat -P $ID # 原第18行命令修改为这个
>
运行方法
python -m rf2aa.run_inference --config-name {your inference config}
参考链接
腾讯云
github