Novel method to identify group-specific non-catalytic pockets of human kinome for drug design

Prediction of protein-ligand binding affinity via deep learning models

Accurately predicting the binding affinity between proteins and ligands is crucial in drug screening and optimization, but it is still a challenge in computer-aided drug design. The recent success of AlphaFold2 in predicting protein structures has brought new hope for deep learning (DL) models to accurately predict protein-ligand binding affinity. However, the current DL models still face limitations due to the low-quality database, inaccurate input representation and inappropriate model architecture. In this work, we review the computational methods, specifically DL-based models, used to predict protein-ligand binding affinity. We start with a brief introduction to protein-ligand binding affinity and the traditional computational methods used to calculate them. We then introduce the basic principles of DL models for predicting protein-ligand binding affinity. Next, we review the commonly used databases, input representations and DL models in this field. Finally, we discuss the potential challenges and future work in accurately predicting protein-ligand binding affinity via DL models.

Prediction of allosteric druggable pockets of cyclin-dependent kinases

Cyclin-dependent kinase (Cdk) proteins play crucial roles in the cell cycle progression and are thus attractive drug targets for therapy against such aberrant cell cycle processes as cancer. Since most of the available Cdk inhibitors target the highly conserved catalytic ATP pocket and their lack of specificity often lead to side effects, it is imperative to identify and characterize less conserved non-catalytic pockets capable of interfering with the kinase activity allosterically. However, a systematic analysis of these allosteric druggable pockets is still in its infancy. Here, we summarize the existing Cdk pockets and their selectivity. Then, we outline a network-based pocket prediction approach (NetPocket) and illustrate its utility for systematically identifying the allosteric druggable pockets with case studies. Finally, we discuss potential future directions and their challenges.

RPpocket: An RNA–Protein Intuitive Database with RNA Pocket Topology Resources

RNA–protein complexes regulate a variety of biological functions. Thus, it is essential to explore and visualize RNA–protein structural interaction features, especially pocket interactions. In this work, we develop an easy-to-use bioinformatics resource: RPpocket. This database provides RNA–protein complex interactions based on sequence, secondary structure, and pocket topology analysis. We extracted 793 pockets from 74 non-redundant RNA–protein structures. Then, we calculated the binding- and non-binding pocket topological properties and analyzed the binding mechanism of the RNA–protein complex. The results showed that the binding pockets were more extended than the non-binding pockets. We also found that long-range forces were the main interaction for RNA–protein recognition, while short-range forces strengthened and optimized the binding. RPpocket could facilitate RNA–protein engineering for biological or medical applications.

DLSSAffinity: protein-ligand binding affinity prediction via a deep learning model

Evaluating the protein-ligand binding affinity is a substantial part of the computer-aided drug discovery process. Most of the proposed computational methods predict protein-ligand binding affinity using either limited full-length protein 3D structures or simple full-length protein sequences as the input features. Thus, protein-ligand binding affinity prediction remains a fundamental challenge in drug discovery. In this study, we proposed a novel deep learning-based approach, DLSSAffinity, to accurately predict the protein-ligand binding affinity. Unlike the existing methods, DLSSAffinity uses the pocket-ligand structural pairs as the local information to predict short-range direct interactions. Besides, DLSSAffinity also uses the full-length protein sequence and ligand SMILES as the global information to predict long-range indirect interactions. We tested DLSSAffinity on the PDBbind benchmark. The results showed that DLSSAffinity achieves Pearson's R = 0.79, RMSE = 1.40, and SD = 1.35 on the test set. Comparing DLSSAffinity with the existing state-of-the-art deep learning-based binding affinity prediction methods, the DLSSAffinity model outperforms other models. These results demonstrate that combining global sequence and local structure information as the input features of a deep learning model can improve the accuracy of protein-ligand binding affinity prediction.

The TAR binding dynamics and its implication in Tat degradation mechanism

Human immunodeficiency virus (HIV) is a retrovirus that progressively attacks the human immune system. It is known that the HIV viral protein Tat recruits the host elongation factor, positive transcription elongation factor b (P-TEFb), onto the nascent HIV viral transactivation response element (TAR) RNA to overcome the elongation pause for active transcription of the entire viral genome. Interestingly, there exists an amplifying feedback loop between Tat and TAR-a reduction in Tat increases the elongation pause, resulting in more TAR RNA fragments instead of the entire viral genome transcript, and the TAR fragments as a scaffold for PRC2 complex in turn promote Tat ubiquitination and degradation. In this study, the structural ensembles and binding dynamics of various interfaces in the Tat/TAR/P-TEFb complex are probed by all-atom accelerated sampling molecular dynamics simulations. The results show that a protein-binding inhibitor F07#13 targeting the Tat/P-TEFb interface initiates the above feedback loop and shuts down the active transcription. Another RNA binding inhibitor, JB181, targeting the Tat/TAR interface, can prevent TAR from pulling down the Tat from P-TEFb protein and further reducing Tat degradation. The detailed mechanism of the complex dynamics helps elucidate how Tat and TAR coordinate the regulation between HIV genome transcription versus possible HIV latency.

A computational study of Tat-CDK9-Cyclin binding dynamics and its implication in transcription-dependent HIV latency

HIV is a virus that attacks the T cells. HIV may either actively replicate or become latent within host cells for years. Since HIV uses its own protein Tat to hijack the host CDK9-Cyclin complex for transcription, Tat is implicated in transcription-dependent HIV latency. To quantify the impact of Tat binding, we propose a computational framework to probe the dynamics of the CDK9-Cyclin interface and the ATP pocket reorganization upon binding by different Tat mutants. Specifically, we focus on mutations at three Tat residues P10, W11, and N12 that are known to interact directly with CDK9 based on the crystal structure of the Tat-CDK9-Cyclin complex. Our molecular dynamics simulations show that the CDK9-Cyclin interface becomes slightly weaker for P10S and W11R mutants but tighter for the K12N mutant. Furthermore, the side chain orientation of residue K48 in the ATP pocket of CDK9 is similar to the inactive state in P10S and W11R simulations, but similar to the active state in K12N simulations. These are consistent with some existing but puzzling observations of latency for these mutants. This framework may hence help gain a better understanding of the role of Tat in the transcription-dependent HIV latency establishment.