Applying machine learning algorithms to protein–ligand scoring functions has aroused widespread attention in recent years due to the high predictive accuracy and affordable computational cost. Nevertheless, most machine learning-based scoring functions are only applicable to a specific task, e.g., binding affinity prediction, binding pose prediction or virtual screening, suggesting that the development of a scoring function with balanced performance in all critical tasks remains a grand challenge. To this end, we propose a novel parameterization strategy by introducing an adjustable binding affinity term that represents the correlation between the predicted outcomes and experimental data into the training of mixture density network. The resulting residue-atom distance likelihood potential not only retains the superior docking and screening power over all the other state-of-the-art approaches, but also achieves a remarkable improvement in scoring and ranking performance. We emphatically explore the impacts of several key elements on prediction accuracy as well as the task preference, and demonstrate that the performance of scoring/ranking and docking/screening tasks of a certain model could be well balanced through an appropriate manner. Overall, our study highlights the potential utility of our innovative parameterization strategy as well as the resulting scoring framework in future structure-based drug design.

Androgen receptor (AR) is a ligand-activated transcription factor that plays a pivotal role in the development and progression of many severe diseases such as prostate cancer, muscle atrophy, and osteoporosis. Binding of ligands to AR triggers the conformational changes in AR that may affect the recruitment of coactivators and downstream response of AR signaling pathway. Therefore, AR ligands have great potential to treat these diseases. In this study, we searched for novel AR ligands by performing a docking-based virtual screening (VS) on the basis of the crystal structure of the AR ligand binding domain (LBD) in complex with its agonist. A total of 58 structurally diverse compounds were selected and subjected to LBD affinity assay, with five of them (HBP1-3, HBP1-17, HBP1-38, HBP1-51, and HBP1-58) exhibiting strong binding to AR-LBD. The IC50 values of HBP1-51 and HBP1-58 are 3.96 µM and 4.92 µM, respectively, which are even lower than that of enzalutamide (Enz, IC50 = 13.87 µM), a marketed second-generation AR antagonist. Further bioactivity assays suggest that HBP1-51 is an AR agonist, whereas HBP1-58 is an AR antagonist. In addition, molecular dynamics (MD) simulations and principal components analysis (PCA) were carried out to reveal the binding principle of the newly-identified AR ligands toward AR. Our modeling results indicate that the conformational changes of helix 12 induced by the bindings of antagonist and agonist are visibly different. In summary, the current study provides a highly efficient way to discover novel AR ligands, which could serve as the starting point for development of new therapeutics for AR-related diseases.

The G protein-coupled chemokine receptor CXCR4 is implicated in a variety of physiological responses that also share several downstream effectors involved in multiple pathological processes. The interaction between CXCR4 and its natural ligand CXCL12/stromal-derived factor-1 (SDF-1) plays important roles in cancer metastasis, HIV-1 infection, and inflammatory diseases. Therefore, investigating the CXCR4–CXCL12 interaction is critical for understanding the molecular mechanisms of the modulation of chemokine-receptor functions and designing new pharmaceutical agents to target the CXCR4–CXCL12 pathway. Based on known experimental data, the interaction between CXCR4 and CXCL12 was predicted by an integrated protocol, which combines protein–protein docking, molecular dynamics (MD) simulations, Molecular Mechanics/Generalized Born Surface Area (MM/GBSA) binding free energy calculations, and MM/GBSA binding free energy decomposition analysis. The predicted CXCR4–CXCL12 binding pattern is in good agreement with the experimental data. Analysis of the binding structure reveals an obvious electrostatic complementarity between CXCR4 and CXCL12. Moreover, significant conformational rearrangements were observed during the 50 ns MD simulations. In particular, the basic Lys1 at the CXCL12 N-terminus, an essential residue in receptor activation, forms a strong polar interaction with the Glu32 in the CXCR4 extracellular region. It facilitates the significant movement of TM5 and TM6 in the conformational transition, which is coupled to the association with the intracellular signal transduction pathways via heterotrimer G-protein. Based on the dynamic and energetic analyses, a two-site binding model was proposed. We believe that our study provides useful information for understanding the mechanisms of CXCR4 ligand binding and structure-based drug design of CXCR4.