ASFP (Artificial Intelligence based Scoring Function Platform): a web server for the development of customized scoring functions

Abstract Virtual screening (VS) based on molecular docking has emerged as one of the mainstream technologies drug discovery due to its low cost and high efficiency. However, scoring functions (SFs) implemented in most programs are not always accurate enough how improve their prediction accuracy is still a big challenge. Here, we propose an integrated platform called ASFP, web server for development customized SFs structure-based VS. There three main modules ASFP: (1) descriptor generation module that can generate up 3437 descriptors modelling protein–ligand interactions; (2) AI-based SF construction establish target-specific pre-generated through machine learning (ML) techniques; (3) online provides some well-constructed VS additional generic binding affinity prediction. Our methodology been validated several benchmark datasets. The achieve average ROC AUC 0.973 towards 32 targets Pearson correlation coefficient 0.81 PDBbind version 2016 core set. To sum up, ASFP powerful tool