SFSXplorer is a Python package to explore the concept of Scoring Function Space (SFS). We apply the SFS concept to build a computational model targeted to a specific protein system (targeted-scoring function). SFSXplorer employs binding affinity data and protein-ligand structures (docked or crystallographic) to train machine learning models to predict binding affinity. We base this SFS exploration on a flexible polynomial scoring function. We have the versatility to vary the energy terms in the polynomial equation, which makes available unexplored regions of the SFS.
We describe installation and tutorials running on Linux. For more information see SFSXplorer User Guide 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 here.
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. You may use a newer installer, but be sure to have the right installer in the above command lines.
Step 2. To run SFSXplorer properly, you need Scikit-Learn 1.4.0. To be sure you have version 1.4.0, open a terminal, and type the following commands: python3 -m pip uninstall scikit-learn
python3 -m pip install scikit-learn==1.4.0
Step 3. Download SFSXplorer here. Copy the sfs zipped directory (sfs.zip) to wherever you want it and unzip the zipped directory. Type the following command:
unzip sfs.zip
Now you have SFSXplorer ready to run. Please access SFSXplorer User Guide here for tutorials and details about input files and commands to run it.