Zhe Wang

Protein degradation and synthesis are essential for regulating various biological activities within the body. As a member of deubiquitinating enzymes (DUBs), ubiquitin-specific protease 14 (USP14) plays a critical role in regulating protein degradation and maintaining cellular protein homeostasis. However, abnormal expression of USP14 has been associated with a variety of malignant tumors and other diseases. In this study, we conducted hierarchical virtual screening against the palm–thumb pocket of USP14, which resulted in the identification of two promising hits with novel scaffolds. We systematically evaluated the potential of these two hits in terms of their binding affinity and selectivity at the computational level. The results indicated that they had stronger binding affinities than previously reported molecules, as evidenced by lower docking scores and binding free energies. The binding stability analysis and hotspot residue prediction based on the MD simulations further revealed that they were capable of stably binding to the palm–thumb pocket of USP14 via crucial interactions with the residues GLN197, TYR476, ASP199, PHE331, TYR436 and HIS426. More importantly, both candidates exhibit higher selectivity for USP14 over several other USP family members (USP5, USP7 and USP15). Our findings are hoped to be a good starting point for the development of selective USP14 inhibitors.

Machine-learning-basedscoring functions (MLSFs) have gained attentionfor their potential to improve accuracy in binding affinity predictionand structure-based virtual screening (SBVS) compared to classicalSFs. Developing accurate MLSFs for SBVS requires a large and unbiaseddataset that includes structurally diverse actives and decoys. Unfortunately,most datasets suffer from hidden biases and data insufficiency. Here,we developed topology-based and conformation-based decoys database(ToCoDDB). The biological targets and active ligands in ToCoDDB werecollected from scientific literature and established datasets. Thedecoys were generated and debiased by using conditional recurrentneural networks and molecular docking. ToCoDDB is presently the largestunbiased database with 2.4 million decoys encompassing 155 targets.The detailed information and performance benchmark for each targetare provided, which are beneficial for training and evaluating MLSFs.Moreover, the online decoys generation function of ToCoDDB furtherexpands its application range to any target. ToCoDDB is freely availableat http://cadd.zju.edu.cn/tocodecoy/.

Binding affinity prediction largely determines the discovery efficiency of lead compounds in drug discovery. Recently, machine learning (ML)-based approaches have attracted much attention in hopes of enhancing the predictive performance of traditional physics-based approaches. In this study, we evaluated the impact of structural dynamic information on the binding affinity prediction by comparing the models trained on different dimensional descriptors, using three targets (i.e. JAK1, TAF1-BD2 and DDR1) and their corresponding ligands as the examples. Here, 2D descriptors are traditional ECFP4 fingerprints, 3D descriptors are the energy terms of the Smina and NNscore scoring functions and 4D descriptors contain the structural dynamic information derived from the trajectories based on molecular dynamics (MD) simulations. We systematically investigate the MD-refined binding affinity prediction performance of three classical ML algorithms (i.e. RF, SVR and XGB) as well as two common virtual screening methods, namely Glide docking and MM/PBSA. The outcomes of the ML models built using various dimensional descriptors and their combinations reveal that the MD refinement with the optimized protocol can improve the predictive performance on the TAF1-BD2 target with considerable structural flexibility, but not for the less flexible JAK1 and DDR1 targets, when taking docking poses as the initial structure instead of the crystal structures. The results highlight the importance of the initial structures to the final performance of the model through conformational analysis on the three targets with different flexibility.

The structural dynamics of the target-recognition-domain loop and its role in regulating DNMT3A activity are investigated through MD simulations, which would arouse more interest in the rational design of novel DNMT3A inhibitors targeting the region.

Virtual screening (VS) based on molecular docking has emerged as one of the mainstream technologies of drug discovery due to its low cost and high efficiency. However, the scoring functions (SFs) implemented in most docking programs are not always accurate enough and how to improve their prediction accuracy is still a big challenge. Here, we propose an integrated platform called ASFP, a web server for the development of customized SFs for structure-based VS. There are three main modules in ASFP: 1) the descriptor generation module that can generate up to 3437 descriptors for the modelling of protein-ligand interactions; 2) the AI-based SF construction module that can establish target-specific SFs based on the pre-generated descriptors through three machine learning (ML) techniques; 3) the online prediction module that provides some well-constructed target-specific SFs for VS and a generic SF for binding affinity prediction. Our methodology has been validated on several benchmark datasets. The target-specific SFs can achieve an average ROC AUC of 0.841 towards 32 targets and the generic SF can achieve the Pearson correlation coefficient of 0.81 on the PDBbind version 2016 core set. To sum up, the ASFP server is a powerful tool for structure-based VS and binding affinity prediction. Availability and Implementation: ASFP web server is freely available at http://cadd.zju.edu.cn/asfp/.

Graph neural networks (GNN) has been considered as an attractive modelling method for molecular property prediction, and numerous studies have shown that GNN could yield more promising results than traditional descriptor-based methods. In this study, based on 11 public datasets covering various property endpoints, the predictive capacity and computational efficiency of the prediction models developed by eight machine learning (ML) algorithms, including four descriptor-based models (SVM, XGBoost, RF and DNN) and four graph-based models (GCN, GAT, MPNN and Attentive FP), were extensively tested and compared. The results demonstrate that on average the descriptor-based models outperform the graph-based models in terms of prediction accuracy and computational efficiency. SVM generally achieves the best predictions for the regression tasks. Both RF and XGBoost can achieve reliable predictions for the classification tasks, and some of the graph-based models, such as Attentive FP and GCN, can yield outstanding performance for a fraction of larger or multi-task datasets. In terms of computational cost, XGBoost and RF are the two most efficient algorithms and only need a few seconds to train a model even for a large dataset. The model interpretations by the SHAP method can effectively explore the established domain knowledge for the descriptor-based models. Finally, we explored use of these models for virtual screening (VS) towards HIV and demonstrated that different ML algorithms offer diverse VS profiles. All in all, we believe that the off-the-shelf descriptor-based models still can be directly employed to accurately predict various chemical endpoints with excellent computability and interpretability.

Graph neural networks (GNN) has been considered as an attractive modelling method for molecular property prediction, and numerous studies have shown that GNN could yield more promising results than traditional descriptor-based methods. In this study, based on 11 public datasets covering various property endpoints, the predictive capacity and computational efficiency of the prediction models developed by eight machine learning (ML) algorithms, including four descriptor-based models (SVM, XGBoost, RF and DNN) and four graph-based models (GCN, GAT, MPNN and Attentive FP), were extensively tested and compared. The results demonstrate that on average the descriptor-based models outperform the graph-based models in terms of prediction accuracy and computational efficiency. SVM generally achieves the best predictions for the regression tasks. Both RF and XGBoost can achieve reliable predictions for the classification tasks, and some of the graph-based models, such as Attentive FP and GCN, can yield outstanding performance for a fraction of larger or multi-task datasets. In terms of computational cost, XGBoost and RF are the two most efficient algorithms and only need a few seconds to train a model even for a large dataset. The model interpretations by the SHAP method can effectively explore the established domain knowledge for the descriptor-based models. Finally, we explored use of these models for virtual screening (VS) towards HIV and demonstrated that different ML algorithms offer diverse VS profiles. All in all, we believe that the off-the-shelf descriptor-based models still can be directly employed to accurately predict various chemical endpoints with excellent computability and interpretability.