开启「云超算」，轻松玩转蛋白质折叠

• 阅读知晓RoseTTAFold及其权重数据的许可要求，并遵守条款中关于商业应用的约定；

• 注册申请PyRoseTTA的许可，通过后可下载对应版本的安装包（建议Python3.7 Linux版本）；

• 注册开通Azure云的全球账号；

• 创建SSHKey并保存Pem私钥；

• 选定Azure的工作区域（建议Southeast Asia区），创建资源组，并新建一个Vnet；

• 提交并完成Azure T4 GPU机型NCas_T4_v3的配额申请，若需更快性能，亦可使用搭载V100的NCs_v3系列；

• 该实验会产生费用，按T4机型一天完成来预估，在Southeast Asia区的计算及存储花费在$50以内，详细定价信息请参考这里，使用过程的账单数据可在控制台的订阅中查询。

sudo parted dev/sdc --script mklabel gpt mkpart xfspart xfs 0% 100%
sudo mkfs.xfs dev/sdc1
sudo partprobe dev/sdc1
sudo mkdir data
sudo mount dev/sdc1 data
sudo chown azureuser:azureuser data/
uuidstr=$(blkid | grep /dev/sdc1 | awk -F " " '{print $2}' | awk -F= '{print $2}' | sed 's/"//g')
cat <<EOF | sudo tee -a etc/fstab
UUID=$uuidstr data xfs defaults, nofail 1 2
EOF
lsblk -o NAME,HCTL,SIZE,MOUNTPOINT | grep -i "sd"

• 安装Anaconda3，安装步骤中阅读License空格翻页，安装路径指定为/opt/anaconda3，询问是否Conda初始化时选Yes；

• 下载RoseTTAFold Github资源；

• 配置Conda env环境；

• 在Folding环境中安装核心的PyRosetta4组件。

## Install anaconda 
wget https://repo.anaconda.com/archive/Anaconda3-2021.05-Linux-x86_64.sh
chmod +x Anaconda3-2021.05-Linux-x86_64.sh
sudo bash ./Anaconda3-2021.05-Linux-x86_64.sh
cat <<EOF | sudo tee -a etc/profile
export PATH=\$PATH:/opt/anaconda3/bin
EOF
source /etc/profile

## Get repo and build 
cd /data
git clone https://github.com/RosettaCommons/RoseTTAFold.git
cd RoseTTAFold
conda env create -f RoseTTAFold-linux.yml
conda env create -f folding-linux.yml
conda env list
./install_dependencies.sh
 
conda init bash
source /home/azureuser/.bashrc
conda activate folding
wget https://asiahpcgbb.blob.core.windows.net/rosettaonazure/PyRosetta4.Release.python37.linux.release-289.tar.bz2
tar -vjxf PyRosetta4.Release.python37.linux.release-289.tar.bz2 
cd PyRosetta4.Release.python37.linux.release-289/setup
python setup.py install
python     #To verify the pyrosetta lib in python commandline
#then input two commands:     <<<import pyrosetta;    <<<pyrosetta.init()
conda deactivate    #back to conda (base)
conda deactivate    #back to VM shell 

(folding) [azureuser@vmRoseTTAFold RoseTTAFold]$ python
Python 3.7.10 (default, Jun  4 2021, 14:48:32) 
[GCC 7.5.0] :: Anaconda, Inc. on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> import pyrosetta;
>>> pyrosetta.init()
PyRosetta-4 2021 [Rosetta PyRosetta4.Release.python37.linux 2021.27+release.7ce64884a77d606b7b667c363527acc846541030 2021-07-09T18:10:05] retrieved from: http://www.pyrosetta.org
(C) Copyright Rosetta Commons Member Institutions. Created in JHU by Sergey Lyskov and PyRosetta Team.
core.init: Checking for fconfig files in pwd and ./rosetta/flags
core.init: Rosetta version: PyRosetta4.Release.python37.linux r289 2021.27+release.7ce6488 7ce64884a77d606b7b667c363527acc846541030 http://www.pyrosetta.org 2021-07-09T18:10:05
core.init: command: PyRosetta -ex1 -ex2aro -database /home/azureuser/.conda/envs/folding/lib/python3.7/site-packages/pyrosetta-2021.27+release.7ce6488-py3.7-linux-x86_64.egg/pyrosetta/database
basic.random.init_random_generator: 'RNG device' seed mode, using '/dev/urandom', seed=-2055557650 seed_offset=0 real_seed=-2055557650
basic.random.init_random_generator: RandomGenerator:init: Normal mode, seed=-2055557650 RG_type=mt19937
>>>

cd /data/RoseTTAFold/
## wget https://files.ipd.uw.edu/pub/RoseTTAFold/weights.tar.gz
wget https://asiahpcgbb.blob.core.windows.net/rosettaonazure/weights.tar.gz
tar -zxvf weights.tar.gz
 
## uniref30 [46G]
## wget http://wwwuser.gwdg.de/~compbiol/uniclust/2020_06/UniRef30_2020_06_hhsuite.tar.gz
wget https://asiahpcgbb.blob.core.windows.net/rosettaonazure/UniRef30_2020_06_hhsuite.tar.gz
mkdir -p UniRef30_2020_06
tar -zxvf 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
wget https://asiahpcgbb.blob.core.windows.net/rosettaonazure/bfd_metaclust_clu_complete_id30_c90_final_seq.sorted_opt.tar.gz
mkdir -p bfd
tar -zxvf bfd_metaclust_clu_complete_id30_c90_final_seq.sorted_opt.tar.gz -C ./bfd
 
## structure templates (including *_a3m.ffdata, *_a3m.ffindex) [over 100G]
## wget https://files.ipd.uw.edu/pub/RoseTTAFold/pdb100_2021Mar03.tar.gz
wget https://asiahpcgbb.blob.core.windows.net/rosettaonazure/pdb100_2021Mar03.tar.gz
tar -zxvf pdb100_2021Mar03.tar.gz

cd example
../run_pyrosetta_ver.sh input.fa .

[azureuser@vmRoseTTAFold example]$ ../run_pyrosetta_ver.sh input.fa .
Running HHblits
Running PSIPRED
Running hhsearch
Predicting distance and orientations
Running parallel RosettaTR.py
Running DeepAccNet-msa
Picking final models
Final models saved in: ./model
Done 

mv t000_.3track.npz t000_.3track.npz.origin
../run_e2e_ver.sh input.fa .