代码改变世界

RoseTTAFold安装

2021-10-21 15:44  丨o聽乄雨o丨  阅读(239)  评论(0编辑  收藏  举报

1. 下载RoseTTAFold

      $ git clone https://github.com/RosettaCommons/RoseTTAFold.git (100M)

      $ cd RoseTTAFold

2. 下载权重、数据库

      $ wget https://files.ipd.uw.edu/pub/RoseTTAFold/weights.tar.gz (0.9G)

      $ tar xfz weights.tar.gz (1.1G)

      $ wget http://wwwuser.gwdg.de/~compbiol/uniclust/2020_06/UniRef30_2020_06_hhsuite.tar.gz (47G)

      $ mkdir -p UniRef30_2020_06

      $ tar xfz UniRef30_2020_06_hhsuite.tar.gz -C ./UniRef30_2020_06 (181G)

      $ wget https://bfd.mmseqs.com/bfd_metaclust_clu_complete_id30_c90_final_seq.sorted_opt.tar.gz (272G)

      $ mkdir -p bfd

      $ tar xfz bfd_metaclust_clu_complete_id30_c90_final_seq.sorted_opt.tar.gz -C ./bfd (1.8T)

      $ wget https://files.ipd.uw.edu/pub/RoseTTAFold/pdb100_2021Mar03.tar.gz (115G)

      $ tar xfz pdb100_2021Mar03.tar.gz (667G)

      # for CASP14 benchmarks, we used this one: https://files.ipd.uw.edu/pub/RoseTTAFold/pdb100_2020Mar11.tar.gz

3. 安装Conda环境

      # create conda environment for RoseTTAFold

      $ conda env create -f RoseTTAFold-linux.yml (cuda11) [RoseTTAFold-linux-cu101.yml (cuda10.1)]

      $ conda env create -f folding-linux.yml (pyrosetta)

      $ ./install_dependencies.sh

      $ conda activate folding

      $ conda config --add channels https://levinthal:paradox@conda.graylab.jhu.edu

      $ conda install pyrosetta=2021.27+release.7ce6488

 4. 环境配置

      (1). 数据库调用

      由于数据库太大(~1.5T),使用公用数据库软链接调用

      IP: 172.16.2.207

      $ ln -s /data0/wangq/Databases/bfd [target dir]

      $ ln -s /data0/wangq/Databases/pdb100 [target dir]

      $ ln -s /data0/wangq/Databases/UniRef30 [target dir]

      (2). Psipred运行报错

      https://www.cnblogs.com/wq242424/p/15037069.html

5. 运行

1 run_[pyrosetta, e2e]_ver.sh input.fa [dir]

      LOG:

      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

 

本文版权归作者和博客园共有,欢迎转载,但未经作者同意必须保留此段声明,且在文章页面明显位置给出原文连接,否则保留追究法律责任的权利。