Cracking the entangling code of protein-ligand interactions (PLI) is of great importance for structure-based
drug design and target fishing. According to physical and biochemical philosophy, PLI can be characterized by
different representations, such as the energy terms from scoring functions and protein-ligand interaction
fingerprints, which can be used by machine learning (ML) algorithms to capture and learn the mode of PLI. Here,
we propose our ML-based protein-ligand interaction capturer (ML-PLIC) for automatically characterizing PLI and
developing ML-based scoring functions (MLSFs) to identify the potential binders of a specific protein target
through virtual screening.
Pipeline module integrates the individual Docking, Descriptors, Modelling and Screening modules. Users
can submit jobs of ligand docking, descriptor generation, modelling based on one of the three ML algorithms
(eXtreme Gradient Boosting, Support Vector Machine and Random Forest) and virtual screening, and users need to
provide all the required files once and for all.
If you want to know the specific role of each module, please click the button below or go to the
Help page directly.