add init

2023-12-03 23:01:00 +08:00
parent 2aef1c9de6
commit bf03213828
13 changed files with 11691 additions and 0 deletions
--- a/.condarc
+++ b/.condarc
@@ -0,0 +1,18 @@
+show_channel_urls: true
+channels:
+  - conda-forge
+  - r
+  - defaults
+  - bioconda
+  # - https://levinthal:paradox@conda.graylab.jhu.edu
+custom_channels:
+  conda-forge: https://mirrors.bfsu.edu.cn/anaconda/cloud
+  msys2: https://mirrors.bfsu.edu.cn/anaconda/cloud
+  bioconda: https://mirrors.bfsu.edu.cn/anaconda/cloud
+  menpo: https://mirrors.bfsu.edu.cn/anaconda/cloud
+  pytorch: https://mirrors.bfsu.edu.cn/anaconda/cloud
+  simpleitk: https://mirrors.bfsu.edu.cn/anaconda/cloud
+default_channels:
+  - https://mirrors.bfsu.edu.cn/anaconda/pkgs/main
+  - https://mirrors.bfsu.edu.cn/anaconda/pkgs/r
+  - https://mirrors.bfsu.edu.cn/anaconda/pkgs/msys2
--- a/.gitignore
+++ b/.gitignore
@@ -0,0 +1,22 @@
+pyrosetta-2023.31+release.1799523-py311_0.tar.bz2
+*.sif
+test/*
+foldx/*
+*.log
+EvoEF2-master/
+bbDepRotLib.bin
+Agreement.txt
+rotabase.txt
+Scwrl4
+Scwrl4.ini
+yasaraPlugin.zip
+Readme.txt
+QuickStart.txt
+foldx_20231231
+1jpz*.pdb
+abcd_IN.pdb
+*.fxout
+output.pdb
+individual_list.txt
+mutation_clean_mole.py
+4i24*
--- a/57
+++ b/57
@@ -0,0 +1,57 @@
+FROM ubuntu:22.04
+LABEL maintainer="lingyu zeng <pylyzeng@gmail.com>"
+
+WORKDIR /root
+# COPY ../../share_data/opus_mut.zip ./
+COPY 4i24.pdb test.list _foldxLinux64.tar_.gz EvoEF2-master.zip install_scwrl4.0.2_64bit_2020_linux mutation.py pyrosetta-2023.31+release.1799523-py311_0.tar.bz2 noarch/repodata.json ./
+ENV PATH="/root/bin:/root/micromamba/bin:${PATH}"
+ENV CONDA_PREFIX="/root/micromamba/envs/pyrosetta"
+ENV TZ="Asia/Shanghai"
+ENV DEBIAN_FRONTEND="noninteractive"
+
+# Update and install necessary packages
+RUN apt-get update && \
+    ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone && \
+    apt-get install tzdata -y && \
+    apt-get install git zip wget bzip2 libgl1-mesa-glx g++ -y && \
+    unzip EvoEF2-master.zip && \
+    chmod +x EvoEF2-master/build.sh && \
+    cd EvoEF2-master && \
+    ./build.sh && \
+    cd .. && \
+    tar zxvf _foldxLinux64.tar_.gz && \
+    chmod +x install_scwrl4.0.2_64bit_2020_linux && \
+    echo -e "Y\nLicense Holder Name" | ./install_scwrl4.0.2_64bit_2020_linux ./ && \
+    # Install Micromamba
+    wget -qO- https://micromamba.snakepit.net/api/micromamba/linux-64/latest | tar -xvj bin/micromamba && \
+    ./bin/micromamba shell init --shell bash --root-prefix=~/micromamba && \
+    echo -e "show_channel_urls: true\n\
+channels:\n\
+    - conda-forge\n\
+    - r\n\
+    - defaults\n\
+    - bioconda\n\
+    - https://levinthal:paradox@conda.graylab.jhu.edu\n\
+custom_channels:\n\
+    conda-forge: https://mirrors.bfsu.edu.cn/anaconda/cloud\n\
+    msys2: https://mirrors.bfsu.edu.cn/anaconda/cloud\n\
+    bioconda: https://mirrors.bfsu.edu.cn/anaconda/cloud\n\
+    menpo: https://mirrors.bfsu.edu.cn/anaconda/cloud\n\
+    pytorch: https://mirrors.bfsu.edu.cn/anaconda/cloud\n\
+    simpleitk: https://mirrors.bfsu.edu.cn/anaconda/cloud\n\
+default_channels:\n\
+    - https://mirrors.bfsu.edu.cn/anaconda/pkgs/main\n\
+    - https://mirrors.bfsu.edu.cn/anaconda/pkgs/r\n\
+    - https://mirrors.bfsu.edu.cn/anaconda/pkgs/msys2" >> ~/.condarc && \
+    mkdir -p /root/noarch && \
+	mv repodata.json /root/noarch && \
+    mv pyrosetta-2023.31+release.1799523-py311_0.tar.bz2 /root/noarch && \
+    ./bin/micromamba create -n pyrosetta -c conda-forge -c bioconda -c defaults python=3.11 click loguru biopython pymol-open-source pyrosetta-2023.31+release.1799523-py311_0.tar.bz2 -y && \
+    apt-get autoremove -y && \
+    apt-get clean && \
+    rm -rf /var/lib/apt/lists/* EvoEF2-master.zip install_scwrl4.0.2_64bit_2020_linux _foldxLinux64.tar_.gz /root/noarch
+
+WORKDIR /work
+VOLUME ["/work"]
+ENTRYPOINT ["/root/micromamba/envs/pyrosetta/bin/python", "/root/mutation.py"]
+CMD ["--help"]
--- a/57
+++ b/57
@@ -0,0 +1,57 @@
+# Use Ubuntu 22.04 as base image
+FROM ubuntu:22.04
+LABEL maintainer="lingyu zeng <pylyzeng@gmail.com>"
+ENV TZ=Asia/Shanghai
+ENV DEBIAN_FRONTEND=noninteractive
+# $(curl https://ipapi.co/timezone)
+# Configure timezone and install necessary packages  
+RUN sed -i 's/archive.ubuntu.com/mirrors.aliyun.com/g' /etc/apt/sources.list && \
+    sed -i 's/security.ubuntu.com/mirrors.aliyun.com/g' /etc/apt/sources.list && \
+    apt-get update && \
+    ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone && \
+    apt-get install -y tzdata && \
+    apt-get install -y git zip curl wget bzip2 libgl1-mesa-glx g++ sudo software-properties-common && \
+    adduser --disabled-password --gecos "" developer && \
+    echo "developer ALL=(ALL) NOPASSWD: ALL" > /etc/sudoers.d/developer && \
+    sudo apt-get autoremove -y && \
+    apt-get clean && \
+    rm -rf /var/lib/apt/lists/*
+
+# Set environment variables
+ENV PATH="/home/developer/bin:/home/developer/micromamba/bin:${PATH}"
+ENV CONDA_PREFIX="/home/developer/micromamba/envs/pyrosetta"
+
+# Switch to user developer
+USER developer
+
+# Set working directory
+WORKDIR /home/developer
+
+# Copy necessary files to the working directory
+COPY --chown=developer .condarc mutation.py 4i24.pdb test.list _foldxLinux64.tar_.gz EvoEF2-master.zip install_scwrl4.0.2_64bit_2020_linux pyrosetta-2023.31+release.1799523-py311_0.tar.bz2 noarch/repodata.json .condarc /home/developer/
+
+# Update and install necessary packages
+RUN unzip EvoEF2-master.zip && \
+    chmod +x EvoEF2-master/build.sh && \
+    cd EvoEF2-master && \
+    ./build.sh && \
+    cd .. && \
+    tar zxvf _foldxLinux64.tar_.gz && \
+    chmod +x install_scwrl4.0.2_64bit_2020_linux && \
+    echo -e "Y\nLicense Holder Name" | ./install_scwrl4.0.2_64bit_2020_linux ./ && \
+    # Install Micromamba
+    wget -qO- https://micromamba.snakepit.net/api/micromamba/linux-64/latest | tar -xvj bin/micromamba && \
+    ./bin/micromamba shell init --shell bash --root-prefix=~/micromamba && \
+    mkdir -p ~/noarch && mkdir ~/work && sudo chmod -R 777 ~/work && \
+	mv repodata.json ~/noarch && \
+    mv pyrosetta-2023.31+release.1799523-py311_0.tar.bz2 ~/noarch && \
+    ./bin/micromamba create -n pyrosetta -c conda-forge -c bioconda -c defaults python=3.11 click loguru biopython pymol-open-source pyrosetta-2023.31+release.1799523-py311_0.tar.bz2 -y && \
+    rm -rf EvoEF2-master.zip install_scwrl4.0.2_64bit_2020_linux _foldxLinux64.tar_.gz ~/noarch
+
+WORKDIR /home/developer/work
+VOLUME ["/home/developer/work"]
+ENTRYPOINT ["/home/developer/micromamba/envs/pyrosetta/bin/python", "/home/developer/mutation.py"]
+# 普通用户使用的版本总有奇怪的权限问题（待解决），可以考虑使用Dockerfile构建root用户的镜像（通过测试）
+# PermissionError: [Errno 13] Permission denied: '/home/developer/work/4i24.clean.pdb'
+# docker run --rm -it -v /home/zenglingyu/tools/dockertest:/home/developer/work hotwa/test1:latest rosetta -p /home/developer/work/4i24.pdb -m /home/developer/work/test.list
+# 映射宿主机的目录/home/zenglingyu/tools/dockertest权限要求是777，否则会报错
--- a/EvoEF2-master.zip
+++ b/EvoEF2-master.zip
--- a/base.Dockerfile
+++ b/base.Dockerfile
@@ -0,0 +1,27 @@
+FROM ubuntu:22.04
+LABEL maintainer="lingyu zeng <pylyzeng@gmail.com>"
+ENV TZ=Asia/Shanghai \
+    DEBIAN_FRONTEND=noninteractive \
+    PATH="/home/developer/bin:/home/developer/micromamba/bin:${PATH}" \
+    CONDA_PREFIX="/home/developer/micromamba/envs/pyrosetta"
+
+# Configure timezone and install necessary packages  
+RUN <<EOT
+#!/bin/bash
+sed -i 's/archive.ubuntu.com/mirrors.aliyun.com/g' /etc/apt/sources.list;
+sed -i 's/security.ubuntu.com/mirrors.aliyun.com/g' /etc/apt/sources.list;
+apt-get update;
+ln -snf /usr/share/zoneinfo/\$TZ /etc/localtime; echo \$TZ > /etc/timezone;
+apt-get install -y tzdata git zip curl wget bzip2 sudo;
+adduser --disabled-password --gecos "" developer;
+echo "developer:password" | chpasswd;
+echo "developer ALL=(ALL) NOPASSWD: ALL" > /etc/sudoers.d/developer;
+apt-get clean;
+rm -rf /var/lib/apt/lists/*
+EOT
+
+# Switch to user developer
+USER developer
+
+# Set working directory
+WORKDIR /home/developer
--- a/developer.Dockerfile
+++ b/developer.Dockerfile
@@ -0,0 +1,54 @@
+FROM ubuntu:22.04
+LABEL maintainer="lingyu zeng <pylyzeng@gmail.com>"
+ENV TZ=Asia/Shanghai \
+    DEBIAN_FRONTEND=noninteractive \
+    PATH="/home/developer/bin:/home/developer/micromamba/bin:${PATH}" \
+    CONDA_PREFIX="/home/developer/micromamba/envs/pyrosetta"
+
+# Configure timezone and install necessary packages  
+RUN <<EOT
+#!/bin/bash
+sed -i 's/archive.ubuntu.com/mirrors.aliyun.com/g' /etc/apt/sources.list;
+sed -i 's/security.ubuntu.com/mirrors.aliyun.com/g' /etc/apt/sources.list;
+apt-get update;
+ln -snf /usr/share/zoneinfo/\$TZ /etc/localtime; echo \$TZ > /etc/timezone;
+apt-get install -y tzdata git zip curl wget bzip2 libgl1-mesa-glx g++ sudo software-properties-common build-essential;
+adduser --disabled-password --gecos "" developer;
+echo "developer:password" | chpasswd;
+echo "developer ALL=(ALL) NOPASSWD: ALL" > /etc/sudoers.d/developer;
+apt-get clean;
+rm -rf /var/lib/apt/lists/*
+EOT
+
+# Switch to user developer
+USER developer
+
+# Set working directory
+WORKDIR /home/developer
+
+# Copy files
+COPY --chown=developer .condarc mutation.py 4i24.pdb test.list _foldxLinux64.tar_.gz EvoEF2-master.zip install_scwrl4.0.2_64bit_2020_linux pyrosetta-2023.31+release.1799523-py311_0.tar.bz2 noarch/repodata.json .condarc /home/developer/
+
+# Update and install necessary packages
+RUN <<EOM
+#!/bin/bash
+unzip EvoEF2-master.zip;
+chmod +x EvoEF2-master/build.sh;
+cd EvoEF2-master;
+./build.sh;
+cd ..;
+tar zxvf _foldxLinux64.tar_.gz;
+chmod +x install_scwrl4.0.2_64bit_2020_linux;
+echo -e "Y\nLicense Holder Name" | ./install_scwrl4.0.2_64bit_2020_linux ./;
+wget -qO- https://micromamba.snakepit.net/api/micromamba/linux-64/latest | tar -xvj bin/micromamba;
+./bin/micromamba shell init --shell bash --root-prefix=~/micromamba;
+mkdir -p ~/noarch; mkdir ~/work; sudo chmod -R 777 ~/work;
+mv repodata.json ~/noarch;
+mv pyrosetta-2023.31+release.1799523-py311_0.tar.bz2 ~/noarch;
+./bin/micromamba create -n pyrosetta -c conda-forge -c bioconda -c defaults python=3.11 click loguru biopython pymol-open-source pyrosetta-2023.31+release.1799523-py311_0.tar.bz2 -y;
+rm -rf EvoEF2-master.zip install_scwrl4.0.2_64bit_2020_linux _foldxLinux64.tar_.gz ~/noarch
+EOM
+
+WORKDIR /home/developer/work
+VOLUME ["/home/developer/work"]
+ENTRYPOINT ["/home/developer/micromamba/envs/pyrosetta/bin/python", "/home/developer/mutation.py"]
--- a/install_scwrl4.0.2_64bit_2020_linux
+++ b/install_scwrl4.0.2_64bit_2020_linux
--- a/mutation.def
+++ b/mutation.def
@@ -0,0 +1,48 @@
+Bootstrap: docker
+From: ubuntu:22.04
+
+%files
+	.condarc /root/.condarc
+    4i24.pdb /root/4i24.pdb
+    test.list /root/test.list
+    _foldxLinux64.tar_.gz /root/_foldxLinux64.tar_.gz
+    EvoEF2-master.zip /root/EvoEF2-master.zip
+    install_scwrl4.0.2_64bit_2020_linux /root/install_scwrl4.0.2_64bit_2020_linux
+    mutation.py /root/mutation.py
+	pyrosetta-2023.31+release.1799523-py311_0.tar.bz2 /root/pyrosetta-2023.31+release.1799523-py311_0.tar.bz2
+	noarch/repodata.json /root/repodata.json
+
+%post
+    cd /root && \
+    apt-get update && \
+	apt-get install tzdata -y && \
+	ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone && \
+	apt-get install git zip wget bzip2 libgl1-mesa-glx g++ -y && \
+	unzip EvoEF2-master.zip && \
+	chmod +x EvoEF2-master/build.sh && \
+	cd EvoEF2-master && \
+	./build.sh && \
+	cd .. && \
+	tar zxvf _foldxLinux64.tar_.gz && \
+	chmod +x install_scwrl4.0.2_64bit_2020_linux && \
+	echo -e "Y\nLicense Holder Name" | ./install_scwrl4.0.2_64bit_2020_linux ./ && \
+	wget -qO- https://micromamba.snakepit.net/api/micromamba/linux-64/latest | tar -xvj bin/micromamba && \
+	./bin/micromamba shell init --shell bash --root-prefix=~/micromamba && \
+	mkdir -p /root/noarch && \
+	mv repodata.json /root/noarch && \
+	mv pyrosetta-2023.31+release.1799523-py311_0.tar.bz2 /root/noarch && \
+	./bin/micromamba create -n pyrosetta -c conda-forge -c default -c bioconda python=3.11 click loguru biopython pymol-open-source noarch/pyrosetta-2023.31+release.1799523-py311_0.tar.bz2 -y && \
+	apt-get autoremove -y && \
+	apt-get clean && \
+	rm -rf /var/lib/apt/lists/* EvoEF2-master.zip install_scwrl4.0.2_64bit_2020_linux _foldxLinux64.tar_.gz noarch/*
+
+%environment
+    export author="lingyuzeng"
+    export version="1.0.0"
+    export PATH="/root/bin:/root/micromamba/bin:${PATH}"
+    export CONDA_PREFIX="/root/micromamba/envs/pyrosetta"
+	export DEBIAN_FRONTEND="noninteractive"
+	export TZ="EAsia/Shanghai"
+
+%runscript
+    exec /root/micromamba/envs/pyrosetta/bin/python /root/mutation.py "$@"
--- a/mutation.py
+++ b/mutation.py
@@ -0,0 +1,512 @@
+#!/usr/bin/env python
+# -*- encoding: utf-8 -*-
+'''
+@file               :mutation.py
+@Description:       :利用各种工具（pyrosetta, foldx, scwrl4, evoef2, pymol）的突变脚本,注意不要重复调用，文件覆盖上可能出现问题
+@Date               :2023/9/8 11:26:21
+@Author             :lyzeng
+@mail               :pylyzeng@gmail.com
+@version            :1.0
+'''
+import asyncio
+import click
+from pathlib import Path
+import os
+import subprocess
+from loguru import logger
+from dataclasses import dataclass, field
+import datetime
+import shutil
+from pyrosetta import init, pose_from_pdb, version
+from pyrosetta.toolbox import mutate_residue, cleanATOM
+from multiprocessing import Pool
+from typing import List, Union
+from Bio.SeqUtils import seq3
+from Bio import PDB
+import warnings
+from Bio import BiopythonWarning
+warnings.simplefilter('ignore', BiopythonWarning)
+
+#  ---- config ----
+here = Path(__file__).absolute().parent
+cwd = Path.cwd()
+zfill_number = 4
+CONTEXT_SETTINGS = dict(help_option_names=['-h', '--help'])
+evoef2_binary = here.joinpath("EvoEF2-master/EvoEF2")
+scwrl4_binary = here.joinpath('Scwrl4')
+foldx_binary = here.joinpath('foldx_20231231')
+conda_prefix = os.environ.get('CONDA_PREFIX')
+pymol_binary = Path(conda_prefix).joinpath('bin/pymol') if conda_prefix else Path('/root/micromamba/envs/pyrosetta').joinpath('bin/pymol')
+logger.add(cwd.joinpath('mutation.log'))
+logger.info(f'\n cwd: {cwd}\n here: {here}\n conda_prefix: {conda_prefix}\n pymol_binary: {pymol_binary}\n evoef2_binary: {evoef2_binary}\n scwrl4_binary: {scwrl4_binary}\n foldx_binary: {foldx_binary}')
+# ---- check ----
+if not pymol_binary.exists():
+    raise FileNotFoundError(f'{pymol_binary.as_posix()} not exists!')
+if not evoef2_binary.exists():
+    raise FileNotFoundError(f'{evoef2_binary.as_posix()} not exists!')
+if not scwrl4_binary.exists():
+    raise FileNotFoundError(f'{scwrl4_binary.as_posix()} not exists!')
+if not foldx_binary.exists():
+    raise FileNotFoundError(f'{foldx_binary.as_posix()} not exists!')
+
+# ---- function ----
+@dataclass()
+class pyrosetta_mutation:
+    pdb: Path
+    mutation_file: Path
+
+    def __post_init__(self):
+        init()
+        cleanATOM(self.pdb.as_posix())
+        self.pose = pose_from_pdb(self.pdb.parent.joinpath(f"{self.pdb.stem}.clean.pdb").as_posix())
+
+    @staticmethod
+    def mutate_task(mutation_file):
+        with open(mutation_file, 'r', encoding='utf-8') as f: # read mutation file
+            mutation_list = f.readlines()
+        parser = lambda x: x.strip().rstrip(';').split(',')
+        mutation_lists = list(map(parser, mutation_list)) # 去除行尾的";"并根据","分割突变
+        return mutation_lists
+    
+    def mutate_from_file(self,file: Path=None)-> List[Path]:
+        if not file: file = self.mutation_file
+        mutation_lists = self.mutate_task(mutation_file = self.mutation_file)
+        # 使用多进程并行处理每行突变
+        with Pool() as pool:
+            all_results = pool.starmap(self.mutation, [(self.pdb, self.pose, i, n + 1, 2.0) for n,i in enumerate(mutation_lists)])
+        logger.info(f'PyRosetta mutation {self.pdb} finished\n results:\n{all_results}')
+        return all_results
+
+    @staticmethod
+    def mutation(pdb: Path, pose, line: List[str], line_number: Union[str, int], pack_radius:float)-> Path: # 每一行的突变操作
+        for mutation in line: # parser site
+            ref_residue = mutation[0]
+            chain = mutation[1]
+            residue_num = int(mutation[2:-1])
+            target_residue = mutation[-1]
+            # 这里可以调用您的突变函数进行实际的突变操作
+            logger.info(f'single site: PyRosetta mutation {pdb.name} {ref_residue}{chain}{residue_num}{target_residue}')
+            pyrosetta_mutation.mutate(pose, chain, residue_num, target_residue, pack_radius)
+        out_file = pdb.parent.joinpath(f'{pdb.stem}_Model_{str(line_number).zfill(zfill_number)}.pdb')
+        return pyrosetta_mutation.save(pose, name=out_file) # 保存单行突变的结果
+
+    @staticmethod
+    def mutate(pose, chain: str, residue_number_in_chain: int, target_residue: str, pack_radius: float=2.0):
+        chain_ids = [pose.pdb_info().chain(i) for i in range(1, pose.total_residue() + 1)]
+        logger.info("Chains:" + str(set(chain_ids)))
+        logger.info("Residues in chain " + chain + ": " + str([pose.pdb_info().number(i) for i in range(1, pose.total_residue() + 1) if pose.pdb_info().chain(i) == chain]))
+
+        pose_residue_number = pose.pdb_info().pdb2pose(res=residue_number_in_chain, chain=chain)
+        logger.info("pose_residue_number: " + str(pose_residue_number))
+        logger.info("Original residue: " + pose.residue(pose_residue_number).name())
+        mutate_residue(pose, pose_residue_number, target_residue, pack_radius=pack_radius) # pack_radius (float): 定义邻近残基的半径。在这个半径范围内的残基可能会被重新打包以适应新的突变残基。
+        logger.info("Mutated residue: " + pose.residue(pose_residue_number).name())
+
+    @staticmethod
+    def save(pose, name:Path) -> Path:
+        # 将突变后的 Pose 保存到新的 PDB 文件
+        pose.dump_pdb(name.as_posix())
+        if name.exists():
+            return name
+        else:
+            raise FileNotFoundError(f'{name.as_posix()} mutation failed!')
+
+@dataclass()
+class pyrosetta_mutate_one: # rosetta 单点突变
+    pdb: Path
+    chain: str
+    residue_number_in_chain: int
+    target_residue: str
+
+    def __post_init__(self):
+        init()
+        cleanATOM(self.pdb.as_posix())
+        pose = pose_from_pdb(self.pdb.absolute().parent.joinpath(f"{self.pdb.stem}.clean.pdb").as_posix())
+        self.mutate(pose)
+
+    def mutate(self, pose):
+        chain_ids = [pose.pdb_info().chain(i) for i in range(1, pose.total_residue() + 1)]
+        logger.info("Chains:" + str(set(chain_ids)))
+        logger.info("Residues in chain " + self.chain + ": " + str([pose.pdb_info().number(i) for i in range(1, pose.total_residue() + 1) if pose.pdb_info().chain(i) == self.chain]))
+
+        pose_residue_number = pose.pdb_info().pdb2pose(res=self.residue_number_in_chain, chain=self.chain)
+        logger.info("pose_residue_number: " + str(pose_residue_number))
+        logger.info("Original residue: " + pose.residue(pose_residue_number).name())
+        mutate_residue(pose, pose_residue_number, self.target_residue, 0.0)
+        logger.info("Mutated residue: " + pose.residue(pose_residue_number).name())
+
+        # 将突变后的 Pose 保存到新的 PDB 文件
+        pose.dump_pdb(self.pdb.stem + "_mutated.pdb")
+        return Path(f"{self.pdb.stem}_mutated.pdb")
+
+@dataclass()
+class evoEF2():
+    pdb: Path
+    mutationfile: Path
+
+    def __post_init__(self):
+        self.file = evoef2_binary
+        if not self.file.exists():
+            raise FileNotFoundError(f'{self.file} not exists!')
+
+    def evoEF2base(self):
+        CMD_ = f"{self.file.absolute().as_posix()} --command=BuildMutant --pdb={self.pdb.absolute().as_posix()} " \
+               f"--mutant_file={self.mutationfile.absolute().as_posix()}"
+        p = subprocess.Popen(CMD_, shell=True, stdout=subprocess.PIPE, cwd=self.pdb.absolute().parent.as_posix())
+        while p.poll() is None:  # progress still running
+            subprocess_read_res = p.stdout.read().decode('utf-8')
+            logger.info(f'''Task record : {datetime.datetime.now()}:\n {subprocess_read_res}''')
+        with open(self.mutationfile.as_posix(), 'r', encoding='utf-8') as f: # read mutation file
+            mutation_list = f.readlines()
+        mf_list = []
+        for j,i in enumerate(mutation_list): # check mutation file
+            mf = self.pdb.parent.joinpath(f'{self.pdb.stem}_Model_{str(j + 1).zfill(zfill_number)}.pdb')
+            if not mf.exists():
+                logger.error(f'{mf.as_posix()} mutation failed! mutation line: {i}')
+            else:
+                mf_list.append(mf)
+        return mf_list
+
+@dataclass()
+class Scwrl4(): 
+    '''
+    Scwrl4的主要功能是优化蛋白质侧链的构象，以达到最低的能量状态。这是通过使用旋转异构体库（rotamer library）来实现的，该库包含了各种氨基酸侧链可能的构象。Scwrl4通过在这个库中寻找最低能量的侧链构象，来优化蛋白质的侧链。
+    如果你想使用Scwrl4来构建蛋白质突变体，你可能需要先使用其他工具或方法来创建一个包含突变的蛋白质结构，然后再使用Scwrl4来优化这个突变蛋白质的侧链构象。例如，你可以使用Biopython或其他蛋白质处理库来创建突变蛋白质，然后使用Scwrl4来优化侧链。
+    Scwrl4是一个用于预测蛋白质侧链构象的程序，它在给定固定的蛋白质主链后，可以预测蛋白质侧链的构象。
+    scwrl4接受一个骨架的PDB，然后修复侧链构象。这里使用任何一个工具(rosetta,pymol等)突变氨基酸并使用opus_mut/mk_mut_backbone.py生成蛋白质骨架（仅改变了希望突变蛋白质的缩写），然后使用scwrl4进行残基突变。
+    '''
+    input_pdb: Path
+    mutationfile: Path
+
+    def __post_init__(self):
+        self.file = scwrl4_binary
+        if not self.file.exists():
+            raise FileNotFoundError(f'{self.file} not exists!')
+        
+    def prepare_backbone(self)->List[Path]: # 准备骨架文件
+        out_file = pyrosetta_mutation(pdb=Path(self.input_pdb), mutation_file=Path(self.mutationfile)).mutate_from_file() # pyrosetta mutate file for change residue name
+        out_file_list = []
+        for i in out_file:
+            r = self.prepare_backone_base(i)
+            out_file_list.append(r)
+        # delete pyrosetta mutate file
+        for i in out_file:
+            i.unlink()
+        return out_file_list
+
+    async def async_scwrl4(self):
+        backbone_files = self.prepare_backbone()
+        tasks = []
+        output_files = []  # 存储输出文件名
+
+        for n, input_pdb in enumerate(backbone_files):
+            output_pdb = input_pdb.parent / f"{self.input_pdb.stem}_Model_{str(n + 1).zfill(4)}.pdb"
+            output_files.append(output_pdb)  # 将输出文件名添加到列表
+            cmd = [
+                scwrl4_binary.absolute().as_posix(),
+                '-i', input_pdb.as_posix(),
+                '-o', output_pdb.as_posix()
+            ]
+            tasks.append(self.run_command(cmd))
+
+        await asyncio.gather(*tasks)
+
+        # remove backbone files
+        for file in backbone_files:
+            file.unlink()
+
+        return output_files  # 返回输出文件名列表
+
+    async def run_command(self, cmd):
+        process = await asyncio.create_subprocess_exec(
+            *cmd,
+            stdout=asyncio.subprocess.PIPE,
+            stderr=asyncio.subprocess.PIPE
+        )
+
+        stdout, stderr = await process.communicate()
+
+        print(f"[stdout]\n{stdout.decode()}")
+        print(f"[stderr]\n{stderr.decode()}")
+        print(f"Return Code: {process.returncode}")
+
+    @staticmethod
+    def prepare_backone_base(file: Path)-> Path: # 使用biopython删除侧链, 静态方法
+        parser = PDB.PDBParser()
+        structure = parser.get_structure(file.stem, file.as_posix())
+        io = PDB.PDBIO()
+        for model in structure:
+            for chain in model:
+                for residue in chain:
+                    for atom in list(residue):
+                        if atom.id not in ["N", "CA", "C", "O"]:
+                            residue.detach_child(atom.id)
+        io.set_structure(structure) # 保存新的PDB文件，没有侧链
+        out_file = file.parent.joinpath(f"{file.stem}_backbone.pdb")
+        io.save(out_file.as_posix())
+        return out_file
+
+@dataclass()
+class foldX():
+    '''
+    This class is for using FoldX to predict the changes in the Gibbs free energy of a protein upon mutation.
+    ./foldx_20231231 --command=BuildModel --pdb=4i24.pdb --mutant-file=individual_list.txt --pdb-dir=/home/zenglingyu/tools
+    '''
+    pdb: Path
+    mutationfile: Path
+
+    def __post_init__(self):
+        self.file = foldx_binary
+        if not self.file.exists():
+            raise FileNotFoundError(f'{self.file} not exists!')
+        self.mutationfile = self.mutationfile.rename('individual_list.txt') # 改名，foldx要求固定名称为individual_list.txt
+
+    def foldXbase(self): # foldx 使用的是单进程
+        CMD_ = f"{self.file.absolute().as_posix()} --command=BuildModel" \
+               f" --pdb={self.pdb.name} --mutant-file={self.mutationfile.absolute().as_posix()} --pdb-dir={self.pdb.absolute().parent.as_posix()} --output-dir={self.pdb.absolute().parent.as_posix()}"
+        p = subprocess.Popen(CMD_, shell=True, stdout=subprocess.PIPE, cwd=self.file.parent.as_posix())
+        while p.poll() is None:  # progress still runing
+            subprocess_read_res = p.stdout.read().decode('utf-8')
+            logger.info(f'''Task record : {datetime.datetime.now()}:\n {subprocess_read_res}''')
+        with open(self.mutationfile.as_posix(), 'r', encoding='utf-8') as f: # read mutation file
+            mutation_list = f.readlines()
+        for j,i in enumerate(mutation_list): # check mutation file
+            mf = self.pdb.parent.joinpath(f'{self.pdb.stem}_{str(j + 1)}.pdb')
+            out = f'{self.pdb.stem}_Model_{str(j + 1).zfill(zfill_number)}.pdb'
+            if not mf.exists():
+                logger.error(f'{out} mutation failed! mutation line: {j + 1} content: {i}')
+            else:
+                mf.rename(out)
+                logger.info(f'foldX mutaion {out} success')
+            
+@dataclass()
+class pymol_mutation(pyrosetta_mutation):
+    pdb: Path
+    mutation_file: Path
+
+    def __post_init__(self):
+        ...
+        
+    def mutate_from_file(self, file: Path=None, cleanATOM:bool=False)-> List[Path]:
+        if not file: file = self.mutation_file
+        if cleanATOM:
+            cleanATOM(self.pdb.as_posix())
+            cleanfilename = self.pdb.parent / f'{self.pdb.stem}.clean.pdb'
+            if not cleanfilename.exists(): raise FileNotFoundError(f'{cleanfilename.as_posix()} not exists! use pyrosetta cleanATOM faild.')
+            self.pdb = cleanfilename
+        mutation_lists = self.mutate_task(mutation_file = self.mutation_file)
+        # 使用多进程并行处理每行突变
+        with Pool() as pool:
+            all_results = pool.starmap(self.mutation, [(self.pdb, i, n+1) for n,i in enumerate(mutation_lists)])
+        logger.info(f'Pymol mutation {self.pdb} finished\n results:\n{all_results}')
+        return all_results
+
+    @staticmethod
+    def mutation(pdb_file:Path, mutate_list:List, mutate_number:int):
+        """
+        mutate_string: list, like: [CA797G,CB797G,MA793G,MB793G] one line in .list file
+        突变前应该完全删除无关信息，如头部等信息可以保留ATOM和HETATM列
+        """
+        from pymol import cmd
+        cmd.load(pdb_file.as_posix())
+        cmd.remove('solvent')
+        for mutate_string in mutate_list:
+            ref_residue = mutate_string[0]
+            chain = mutate_string[1]
+            site = mutate_string[2:-1]
+            mutation_type = seq3(mutate_string[-1]).upper()
+            logger.info(f'pymol mutation reference: {seq3(ref_residue).upper()} to {mutation_type} [chain {chain} site {site}]')
+            # Implement the pymol mutation here
+            # Rest of the code from the Mutagenesis_site function...
+            PDBs = cmd.get_names()
+            if len(PDBs) == 1:
+                PDB = PDBs[0]
+            else:
+                raise ValueError(f'this pdb have more than one object! PDBs:{PDBs}')
+            CAindex = cmd.identify(f"{PDB} and name CA") # get CA index
+            pdbstrList = [cmd.get_pdbstr("%s and id %s" % (PDB, CAid)).splitlines() for CAid in CAindex]
+            # Function to filter each sublist
+            filter_sublist = lambda sublist: list(filter(lambda x: x.startswith(('ATOM', 'HETATM')), sublist)) # 保留ATOM和HETATM列
+            # Use map to apply the function to each sublist
+            filtered_pdbstrList = list(map(filter_sublist, pdbstrList))
+            ProtChainResiList = [[i[0][21], i[0][22:26].strip()] for i in filtered_pdbstrList] # get pdb chain line string
+            for item in ProtChainResiList:
+                if item[0] == str(chain) and item[1] == str(site):
+                    cmd.wizard("mutagenesis")
+                    cmd.refresh_wizard()
+                    cmd.get_wizard().set_mode(mutation_type)
+                    selection = f"/{PDB}//{item[0]}/{item[1]}"
+                    cmd.get_wizard().do_select(selection)
+                    cmd.get_wizard().apply()        
+                    cmd.set_wizard("done")
+        # save pdb
+        pid = PDB.split('.')[0] if '.' in PDB else PDB # split name pid.clean.pdb
+        outfile = Path(f'{pid}_Model_{str(mutate_number).zfill(zfill_number)}.pdb')
+        cmd.save(outfile.as_posix(), f"{PDB}")
+        cmd.reinitialize('everything')
+        if outfile.exists():
+            return outfile.name
+
+def print_version(ctx, param, value):
+    if not value or ctx.resilient_parsing:
+        return
+
+    # The command to run
+    cmd = {
+        'evoef2': [evoef2_binary.as_posix(), "--version"],
+        'foldx': [foldx_binary.as_posix(), "--help"],
+        'scwrl4': [scwrl4_binary.as_posix(), "--help"],
+        'pymol': [pymol_binary.as_posix(), "--version"]
+    }
+
+    # Run the command and capture the output
+    if value in cmd.keys():
+        result = subprocess.run(cmd[value], capture_output=True, text=True)
+        # Check if the command was successful
+        if result.returncode == 0:
+            print(result.stdout)
+        else:
+            print(result.stderr)
+    elif value == 'rosetta':
+        print(version())
+    else:
+        print('Not match, please input a correct software name!')
+
+    ctx.exit()
+
+
+@click.group(context_settings=CONTEXT_SETTINGS)
+def cli():
+    """
+author: zenglingyu
+
+email: pylyzeng@gmail.com
+
+data: 2023/8/17
+
+version: 1.0
+
+description: \n
+This is a tool for protein mutation using various methods.\n
+Here, the 'test.list' file shows the mutants that you want to build. It has the following format: \n
+CA171A,DB180E; \n
+Each mutant is written in one line ending with “;”, and multiple mutations in a mutant are divided by “,”. Note that there is no gap or space character between single mutations. For each single mutation, the first letter is the reference amino acid, the second letter is the chain identifier of the amino acid followed by its position in the chain, and the last letter is the amino acid after mutation.
+    """
+    pass
+
+def mutate_line(line, protein_path):
+    # 去除行尾的";"并根据","分割突变
+    mutations = line.strip().rstrip(';').split(',')
+    results = []
+    # 对于该行中的每个突变，都进行相应的处理
+    for mutation in mutations:
+        ref_residue = mutation[0]
+        chain = mutation[1]
+        residue_num = int(mutation[2:-1])
+        target_residue = mutation[-1]
+        # 这里可以调用您的突变函数进行实际的突变操作
+        ins = pyrosetta_mutation(Path(protein_path), chain, int(residue_num), target_residue)
+        logger.info(f'PyRosetta mutation {protein_path} {ref_residue}{chain}{residue_num}{target_residue}')
+        results.append(f"Processed mutation: {mutation}")
+    return results
+
+# 修饰器统一移动文件的代码，用于将结果文件移动到/work工作目录下，在docker执行的时候可以将/work目录挂载映射
+def handle_file_path(here):
+    def decorator(func):
+        def wrapper(protein, mutation, *args, **kwargs):
+            current_working_directory = Path(protein).parent
+            if here.resolve() != current_working_directory.resolve():
+                shutil.copy(protein, here.as_posix())
+            result = func(protein=Path(protein), mutation=Path(mutation), *args, **kwargs)
+            if here.resolve() != current_working_directory.resolve():
+                for file_path in here.glob('*_Model_*.pdb'):
+                    dest_path = current_working_directory.joinpath(file_path.name)
+                    if dest_path.exists():
+                        dest_path.unlink()
+                    shutil.move(file_path.as_posix(), dest_path.as_posix())
+                for file_path in here.glob('*.log'):
+                    dest_path = current_working_directory.joinpath(file_path.name)
+                    if dest_path.exists():
+                        dest_path.unlink()
+                    shutil.move(file_path.as_posix(), dest_path.as_posix())
+            return result
+        return wrapper
+    return decorator
+
+@click.command(help='This tool is designed for mutating proteins using PyRosetta and analyzing the results. Version:\n PyRosetta-4 2023 [Rosetta PyRosetta4.conda.linux.cxx11thread.serialization.CentOS.python311.Release 2023.31+release.1799523c1e5ce7129824215cddea0f15d3f087dd 2023-08-01T12:24:20] retrieved from: http://www.pyrosetta.org(C) Copyright Rosetta Commons Member Institutions. Created in JHU by Sergey Lyskov and PyRosetta Team.', context_settings=CONTEXT_SETTINGS)
+@click.option('-p', '--protein', type=click.Path(exists=True), help='Path to the input protein file in PDB format.(.pdb)')
+@click.option('-m', '--mutation', type=click.Path(exists=True), 
+              help="Path to the mutation list file. ")
+@click.option('-v', '--version', is_flag=True, flag_value='rosetta', callback=print_version, expose_value=False, is_eager=True, help='Print version information.')
+def rosetta(protein, mutation):
+    @handle_file_path(here)
+    def execute_rosetta(protein, mutation):  # 参数名与wrapper中的相同
+        pyrosetta_mutation(pdb=protein, mutation_file=mutation).mutate_from_file()
+        
+    execute_rosetta(protein, mutation)
+
+
+@click.command(help="This tool is designed for mutating proteins using EvoEF2 and analyzing the results.", context_settings=CONTEXT_SETTINGS)
+@click.option('-p', '--protein', type=click.Path(exists=True), help='Path to the input protein file in PDB format.(.pdb)')
+@click.option('-m', '--mutation', type=click.Path(exists=True), 
+              help="Path to the mutation list file. ")
+@click.option('-v', '--version', is_flag=True, flag_value='evoef2', callback=print_version, expose_value=False, is_eager=True, help='Print version information.')
+def evoef2(protein, mutation):
+    @handle_file_path(here)
+    def execute_evoef2(protein, mutation):
+        # EvoEF2 specific code here
+        ins = evoEF2(Path(protein), Path(mutation)).evoEF2base()
+        logger.info(f'EvoEF2 mutation {protein} finished\n results:\n{ins}')
+    execute_evoef2(protein, mutation)
+    
+
+
+@click.command(help="This tool is designed for mutating proteins using FoldX and analyzing the results. Version: foldx_20231231", context_settings=CONTEXT_SETTINGS)
+@click.option('-p', '--protein', type=click.Path(exists=True), help='Path to the input protein file in PDB format.(.pdb)')
+@click.option('-m', '--mutation', type=click.Path(exists=True), 
+              help="Path to the mutation list file. ")
+@click.option('-v', '--version', is_flag=True, flag_value='foldx', callback=print_version, expose_value=False, is_eager=True, help='Print version information.')
+def foldx(protein, mutation):
+    @handle_file_path(here)
+    def execute_foldx(protein, mutation):
+        # FoldX specific code here
+        ins = foldX(Path(protein), Path(mutation))
+        ins.foldXbase()
+    execute_foldx(protein, mutation)
+    
+
+@click.command(help="This tool is designed for mutating proteins using PyMOL and analyzing the results. Version: PyMOL 2.5.0 Open-Source (04df6f86a0), 2023-05-23", context_settings=CONTEXT_SETTINGS)
+@click.option('-p', '--protein', type=click.Path(exists=True), help='Path to the input protein file in PDB format.(.pdb)')
+@click.option('-m', '--mutation', type=click.Path(exists=True), 
+              help="Path to the mutation list file. ")
+@click.option('-v', '--version', is_flag=True, flag_value='pymol', callback=print_version, expose_value=False, is_eager=True, help='Print version information.')
+def pymol(protein, mutation):
+    @handle_file_path(here)
+    def execute_pymol(protein, mutation):
+        # PyMol specific code here
+        ins = pymol_mutation(Path(protein), mutation).mutate_from_file()
+        logger.info(f'PyMOL mutation {protein} finished\n results:\n{ins}')
+    execute_pymol(protein, mutation)
+    
+
+@click.command(help="This tool is designed for mutating proteins using scwrl4 and analyzing the results. Version: 4.0 Copyright (c) 2009-2020 Georgii Krivov, Maxim Shapovalov and Roland Dunbrack Fox Chase Cancer Center, Philadelphia PA 19111, USA", context_settings=CONTEXT_SETTINGS)
+@click.option('-p', '--protein', type=click.Path(exists=True), help='Path to the input protein file in PDB format.(.pdb)')
+@click.option('-m', '--mutation', type=click.Path(exists=True), 
+              help="Path to the mutation list file. ")
+@click.option('-v', '--version', is_flag=True, flag_value='scwrl4', callback=print_version, expose_value=False, is_eager=True, help='Print version information.')
+def scwrl4(protein, mutation):
+    @handle_file_path(here)
+    def execute_scwrl4(protein, mutation):
+        ins = Scwrl4(Path(protein), mutation)
+        output_files = asyncio.run(ins.async_scwrl4())  # 获取输出文件名
+        logger.info(f'Scwrl4 mutation {protein} finished\nOutput files:\n{output_files}\n')
+    execute_scwrl4(protein, mutation)
+
+cli.add_command(rosetta)
+cli.add_command(evoef2)
+cli.add_command(foldx)
+cli.add_command(pymol)
+cli.add_command(scwrl4)
+
+if __name__ == '__main__':
+    cli()
--- a/noarch/repodata.json
+++ b/noarch/repodata.json
--- a/sifbuild.md
+++ b/sifbuild.md
@@ -0,0 +1,99 @@
+构建Singularity（现在称为Apptainer）的SIF（Singularity Image Format）文件有几种不同的方法。以下是一些常见的构建方法：
+
+1. **使用定义文件**：使用定义文件（例如您之前提供的内容）是最常见的构建方法。您可以通过定义文件详细描述镜像的内容和构建过程。
+
+   ```
+   sudo singularity build output.sif definition.def
+   ```
+
+2. **从现有的Docker容器构建**：您可以直接从Docker镜像构建SIF文件。
+
+   ```
+   sudo singularity build output.sif docker-daemon://ubuntu:22.04
+   ```
+
+3. **从现有的Singularity容器构建**：如果您有现有的Singularity容器，您可以从那个容器构建新的SIF文件。
+
+   ```
+   sudo singularity build new_output.sif old_output.sif
+   ```
+
+4. **使用沙盒（sandbox）模式**：沙盒模式允许您在一个可写的目录结构中构建和修改容器。这在迭代开发和测试中很有用。
+
+   ```
+   sudo singularity build --sandbox sandbox/ definition.def
+   ```
+
+   您可以随后将沙盒目录转换为SIF文件：
+
+   ```
+   sudo singularity build final_output.sif sandbox/
+   ```
+
+5. **使用远程构建服务**：如果您不希望在本地机器上构建容器，您可以使用Singularity的远程构建服务。
+
+以上方法可以根据您的需求和限制进行混合和匹配。例如，您可以先使用定义文件在沙盒模式下构建容器，然后手动修改容器，最后将其转换为SIF文件。
+
+
+
+## 使用使用沙盒（sandbox）模式构建sif文件
+
+使用沙盒（sandbox）模式构建SIF文件允许您以更灵活的方式工作。沙盒是一个可写的目录结构，您可以在其中修改和测试容器的内容。以下是使用沙盒模式构建SIF文件的步骤：
+
+1. **创建沙盒目录**：首先，您可以使用定义文件或从现有的Docker或Singularity镜像创建沙盒目录。
+
+   使用定义文件创建沙盒：
+
+   ```
+   sudo singularity build --sandbox sandbox/ definition.def
+   ```
+
+   或从Docker镜像创建沙盒：
+
+   ```
+   sudo singularity build --sandbox sandbox/ docker://ubuntu:22.04
+   ```
+
+   这里，“sandbox/”是沙盒目录的名称，您可以更改为所需的任何路径。
+
+2. **修改沙盒内容**：一旦沙盒被创建，您可以直接在该目录结构中进行更改。您可以使用`singularity shell`命令进入沙盒，并进行所需的修改：
+
+   ```
+   sudo singularity shell --writable sandbox/
+   ```
+
+   您也可以直接在文件系统中编辑沙盒目录的内容。
+
+3. **构建SIF文件**：一旦您对沙盒的内容满意，可以将其转换为SIF文件：
+
+   ```
+   sudo singularity build final_output.sif sandbox/
+   ```
+
+   这里，“final_output.sif”是最终SIF文件的名称。
+
+4. **清理**：如果您不再需要沙盒，可以删除沙盒目录：
+
+   ```
+   sudo rm -r sandbox/
+   ```
+
+沙盒模式特别适合需要迭代开发和测试的情况。通过直接在可写的目录结构中工作，您可以更容易地尝试不同的配置和设置。
+
+## wsl2 沙盒模式
+
+如果你想在WSL2的子系统中进入沙盒模式，首先确保你的镜像文件（如 `mutation.sif`）已经存在。然后，你可以使用以下命令进入沙盒模式：
+
+```
+singularity shell --writable-tmpfs mutation.sif
+```
+
+这个命令将允许你在容器内部进行更改，但更改不会保存到原始SIF文件中。如果你想保存更改，你可能需要使用可写的沙盒目录。你可以通过以下命令创建沙盒目录并启动容器：
+
+```
+singularity shell --writable mutation/
+```
+
+在沙盒模式中，你可以对容器进行更改，并且更改将会保存。当你完成时，可以使用 `exit` 命令退出沙盒模式。
+
+在wsl2使用apptainer会在当前目录解压目录mutation_sandbox一个目录，里面包括了一整个linux系统的文件。但是交互环境还是在windows的wsl2的子系统中，可能原因在于windows的wsl2的子系统本来就在沙盒中运行，所以无法在沙盒中在创建一个沙盒于是就解压出来。可能需要在真正是Linux系统的物理机中才能正常进入沙盒模式。
--- a/test.list
+++ b/test.list
@@ -0,0 +1,6 @@
+CA797G,CB797G,MA793G,MB793G;
+CA797A,CB797A,MA793G,MB793G;
+CA797M,CB797M,MA793A,MB793A;
+CA797G,CB797G,MA793C,MB793C;
+CA797A,CB797A,MA793A,MB793A;
+CA797M,CB797M,MA793A,MB793A;