Skip to content

SAnDReS (Statistical Analysis of Docking Results and Scoring functions) is a free and open-source computational environment for the development of machine-learning models for the prediction of ligand-binding affinity. We developed SAnDReS using Python programming language, and SciPy, NumPy, scikit-learn, and Matplotlib libraries as a computational

License

Notifications You must be signed in to change notification settings

azevedolab/sandres

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

SAnDReS 2.0.0

Statistical Analysis of Docking Results and Scoring Functions 2.0.0 (SAnDReS 2.0.0)

 

SAnDReS 2.0.0 (de Azevedo Jr et al., 2024) brings together the most advanced tools for protein-ligand docking simulation and machine-learning modeling. We have the AutoDock Vina 1.2 (Eberhardt et al., 2021) as a docking engine. Also, SAnDReS 2.0.0 uses machine-learning methods available in the Scikit-Learn library (Pedregosa et al., 2011). It has 54 regression methods which allow us to explore the Scoring Function Space (SFS) (Ross et al., 2013). This exploration of the SFS permits us to have an adequate machine-learning (ML) model for a targeted protein system. SAnDReS predicts binding affinity for a specific protein system with superior performance compared against classical scoring functions. In summary, SAnDReS 2.0.0 makes it possible for you to design a scoring function adequate to the protein system of your interest.

You need Python 3 installed on your computer to run SAnDReS 2.0.0. In addition, you need Pandas, Matplotlib, NumPy, Scikit-Learn (Pedregosa et al., 2011), and SciPy. It is also necessary to have ADFRsuite version 1.0 (Ravindranath et al., 2015). You can make the installation of Python packages faster by installing Anaconda.

 

How to Cite SAnDReS 2.0

de Azevedo WF Jr, Quiroga R, Villarreal MA, da Silveira NJF, Bitencourt-Ferreira G, da Silva AD, Veit-Acosta M, Oliveira PR, Tutone M, Biziukova N, Poroikov V, Tarasova O, Baud S. SAnDReS 2.0: Development of machine-learning models to explore the scoring function space. J Comput Chem. 2024; 45(27): 2333–2346. PubMed

 

 

 

 

 

Installing SAnDReS (Linux)

You should type all commands shown here in a Linux terminal. The easiest way to open a Linux terminal is to use the Ctrl+Alt+T key combination.

Step 1. Download Anaconda Installer for Linux (Anaconda3-2021.11-Linux-x86_64.sh).

Do not install newer versions of Anaconda, you may have dependency version issues.

Go to the directory where you have the installer file and type the following commands:

    chmod u+x Anaconda3-2021.11-Linux-x86_64.sh
    ./Anaconda3-2021.11-Linux-x86_64.sh

Follow the instructions of the installer.

Step 2. Download ADFRsuite version 1.0 (ADFRsuite 1.0 Linux 64 installer app).

Type the following commands:

    cd ~
    cp Downloads/ADFRsuite_Linux-x86_64_1.0_install .
    chmod a+x ADFRsuite_Linux-x86_64_1.0_install
    ./ADFRsuite_Linux-x86_64_1.0_install

Follow the instructions of the installer. You need to add the path of ADFRsuite to your .bashrc (e.g.,PATH="/home/walter/ADFRsuite-1.0/bin:$PATH"). You need to change to your user.

Step 3. To run SAnDReS 2.0 properly, you need Scikit-Learn 1.5.2. To be sure you have version 1.5.2, open a terminal and type the following commands:

    python3 -m pip uninstall scikit-learn
    python3 -m pip install scikit-learn==1.5.2

Step 4. Download SAnDReS 2.0.0 here. Copy the sandres2 zipped directory (sandres2.zip) to wherever you want it and unzip the zipped directory.

Type the following command:

    unzip sandres2.zip

cd to sandres2 directory then, type:

python3 sandres2.py

Now you have the GUI window for SAnDReS 2.0.0. That´s it, good SAnDReS session!

About

SAnDReS (Statistical Analysis of Docking Results and Scoring functions) is a free and open-source computational environment for the development of machine-learning models for the prediction of ligand-binding affinity. We developed SAnDReS using Python programming language, and SciPy, NumPy, scikit-learn, and Matplotlib libraries as a computational

Topics

Resources

License

Stars

Watchers

Forks

Languages