Computational drug discovery provides an efficient tool for helping large-scale lead molecule screening. One of the major tasks of lead discovery is identifying molecules with promising binding affinities toward a target, a protein in general. The accuracies of current scoring functions that are used to predict the binding affinity are not satisfactory enough. Thus, machine learning or deep learning based methods have been developed recently to improve the scoring functions. In this study, a deep convolutional neural network model (called OnionNet) is introduced; its features are based on rotation-free element-pair-specific contacts between ligands and protein atoms, and the contacts are further grouped into different distance ranges to cover both the local and nonlocal interaction information between the ligand and the protein. The prediction power of the model is evaluated and compared with other scoring functions using the comparative assessment of scoring functions (CASF-2013) benchmark and the v2016 core set of the PDBbind database. The robustness of the model is further explored by predicting the binding affinities of the complexes generated from docking simulations instead of experimentally determined PDB structures.

“Virtual Screening” is a common step of in silico drug design, where researchers screen a large library of small molecules (ligands) for interesting hits, in a process known as “Docking”. However, docking is a computationally intensive and time-consuming process, usually restricted to small size binding sites (pockets) and small number of interacting residues. When the target site is not known (blind docking), researchers split the docking box into multiple boxes, or repeat the search several times using different seeds, and then merge the results manually. Otherwise, the search time becomes impractically long. In this research, we studied the relation between the search progression and Average Sum of Proximity relative Frequencies (ASoF) of searching threads, which is closely related to the search speed and accuracy. A new inter-process spatio-temporal integration method is employed in Quick Vina 2, resulting in a new docking tool, QuickVina-W, a suitable tool for “blind docking”, (not limited in search space size or number of residues). QuickVina-W is faster than Quick Vina 2, yet better than AutoDock Vina. It should allow researchers to screen huge ligand libraries virtually, in practically short time and with high accuracy without the need to define a target pocket beforehand.

One key task in virtual screening is to accurately predict the binding affinity (△G) of protein-ligand complexes. Recently, deep learning (DL) has significantly increased the predicting accuracy of scoring functions due to the extraordinary ability of DL to extract useful features from raw data. Nevertheless, more efforts still need to be paid in many aspects, for the aim of increasing prediction accuracy and decreasing computational cost. In this study, we proposed a simple scoring function (called OnionNet-2) based on convolutional neural network to predict △G. The protein-ligand interactions are characterized by the number of contacts between protein residues and ligand atoms in multiple distance shells. Compared to published models, the efficacy of OnionNet-2 is demonstrated to be the best for two widely used datasets CASF-2016 and CASF-2013 benchmarks. The OnionNet-2 model was further verified by non-experimental decoy structures from docking program and the CSAR NRC-HiQ data set (a high-quality data set provided by CSAR), which showed great success. Thus, our study provides a simple but efficient scoring function for predicting protein-ligand binding free energy.