Kinase Inhibitor Scaffold Hopping with Deep Learning Approaches

Kinase-Bench: Comprehensive Benchmarking Tools and Guidance for Achieving Selectivity in Kinase Drug Discovery

Developing selective kinase inhibitors remains a formidable challenge in drug discovery because of the highly conserved structural information on adenosine triphosphate (ATP) binding sites across the kinase family. Tailoring docking protocols to identify promising kinase inhibitor candidates for optimization has long been a substantial obstacle to drug discovery. Therefore, we introduced "Kinase-Bench," a pioneering benchmark suite designed for an advanced virtual screen, to improve the selectivity and efficacy of kinase inhibitors. Our comprehensive data set includes 6875 selective ligands and 422,799 decoys for 75 kinases, using extensive bioactivity and structural data from the ChEMBL database and decoys generated by the Directory of Useful Decoys-Enhanced version. Our benchmarking sets and retrospective case studies were designed to provide useful guidance in discovering selective kinase inhibitors. We employed a Glide High-Throughput Virtual Screen and Standard Precision complemented by three scoring functions and customized protein-ligand interaction filters that target specific kinase residue interactions. These innovations were successfully implemented in our virtual screen efforts targeting JAK1 inhibitors, achieving selectivity against its family member, TYK2. Consequently, we identified novel potential hits: Compound 2 (JAK1 IC50: 980.5 nM, TYK2 IC50: 4.5 μM) and the approved pan-AKT inhibitor Capivasertib (JAK1 IC50: 275.9 nM, TYK2 IC50: 10.9 μM). Using the Kinase-Bench protocol, both compounds demonstrated substantial JAK1 selectivity, making them strong candidates for further investigation. Our pharmaceutical results underscore the utility of tailored virtual screen protocols in identifying selective kinase inhibitors with substantial implications for rational drug design. Kinase-Bench offers a robust toolset for selective kinase drug discovery with the potential to effectively guide future therapeutic strategies effectively.

Kinase Drug Discovery: Impact of Open Science and Artificial Intelligence

Given their central role in signal transduction, protein kinases (PKs) were first implicated in cancer development, caused by aberrant intracellular signaling events. Since then, PKs have become major targets in different therapeutic areas. The preferred approach to therapeutic intervention of PK-dependent diseases is the use of small molecules to inhibit their catalytic phosphate group transfer activity. PK inhibitors (PKIs) are among the most intensely pursued drug candidates, with currently 80 approved compounds and several hundred in clinical trials. Following the elucidation of the human kinome and development of robust PK expression systems and high-throughput assays, large volumes of PK/PKI data have been produced in industrial and academic environments, more so than for many other pharmaceutical targets. In addition, hundreds of X-ray structures of PKs and their complexes with PKIs have been reported. Substantial amounts of PK/PKI data have been made publicly available in part as a result of open science initiatives. PK drug discovery is further supported through the incorporation of data science approaches, including the development of various specialized databases and online resources. Compound and activity data wealth compared to other targets has also made PKs a focal point for the application of artificial intelligence (AI) in pharmaceutical research. Herein, we discuss the interplay of open and data science in PK drug discovery and review exemplary studies that have substantially contributed to its development, including kinome profiling or the analysis of PKI promiscuity versus selectivity. We also take a close look at how AI approaches are beginning to impact PK drug discovery in light of their increasing data orientation.

Unlocking comprehensive molecular design across all scenarios with large language model and unordered chemical language

Molecular generation stands at the forefront of AI-driven technologies, playing a crucial role in accelerating the development of small molecule drugs. The intricate nature of practical drug discovery necessitates the development of a versatile molecular generation framework that can tackle diverse drug design challenges. However, existing methodologies often struggle to encompass all aspects of small molecule drug design, particularly those rooted in language models, especially in tasks like linker design, due to the autoregressive nature of large language model-based approaches. To empower a language model for a wider range of molecular design tasks, we introduce an unordered simplified molecular-input line-entry system based on fragments (FU-SMILES). Building upon this foundation, we propose FragGPT, a universal fragment-based molecular generation model. Initially pretrained on extensive molecular datasets, FragGPT utilizes FU-SMILES to facilitate efficient generation across various practical applications, such as de novo molecule design, linker design, R-group exploration, scaffold hopping, and side chain optimization. Furthermore, we integrate conditional generation and reinforcement learning (RL) methodologies to ensure that the generated molecules possess multiple desired biological and physicochemical properties. Experimental results across diverse scenarios validate FragGPT's superiority in generating molecules with enhanced properties and novel structures, outperforming existing state-of-the-art models. Moreover, its robust drug design capability is further corroborated through real-world drug design cases.

ScaffoldGVAE: scaffold generation and hopping of drug molecules via a variational autoencoder based on multi-view graph neural networks

In recent years, drug design has been revolutionized by the application of deep learning techniques, and molecule generation is a crucial aspect of this transformation. However, most of the current deep learning approaches do not explicitly consider and apply scaffold hopping strategy when performing molecular generation. In this work, we propose ScaffoldGVAE, a variational autoencoder based on multi-view graph neural networks, for scaffold generation and scaffold hopping of drug molecules. The model integrates several important components, such as node-central and edge-central message passing, side-chain embedding, and Gaussian mixture distribution of scaffolds. To assess the efficacy of our model, we conduct a comprehensive evaluation and comparison with baseline models based on seven general generative model evaluation metrics and four scaffold hopping generative model evaluation metrics. The results demonstrate that ScaffoldGVAE can explore the unseen chemical space and generate novel molecules distinct from known compounds. Especially, the scaffold hopped molecules generated by our model are validated by the evaluation of GraphDTA, LeDock, and MM/GBSA. The case study of generating inhibitors of LRRK2 for the treatment of PD further demonstrates the effectiveness of ScaffoldGVAE in generating novel compounds through scaffold hopping. This novel approach can also be applied to other protein targets of various diseases, thereby contributing to the future development of new drugs. Source codes and data are available at https://github.com/ecust-hc/ScaffoldGVAE .

FFLOM: A Flow-Based Autoregressive Model for Fragment-to-Lead Optimization

Recently, deep generative models have been regarded as promising tools in fragment-based drug design (FBDD). Despite the growing interest in these models, they still face challenges in generating molecules with desired properties in low data regimes. In this study, we propose a novel flow-based autoregressive model named FFLOM for linker and R-group design. In a large-scale benchmark evaluation on ZINC, CASF, and PDBbind test sets, FFLOM achieves state-of-the-art performance in terms of validity, uniqueness, novelty, and recovery of the generated molecules and can recover over 92% of the original molecules in the PDBbind test set (with at least five atoms). FFLOM also exhibits excellent potential applicability in several practical scenarios encompassing fragment linking, PROTAC design, R-group growing, and R-group optimization. In all four cases, FFLOM can perfectly reconstruct the ground-truth compounds and generate over 74% of molecules with novel fragments, some of which have higher binding affinity than the ground truth.

CMGC Kinases in Health and Cancer

CMGC kinases, encompassing cyclin-dependent kinases (CDKs), mitogen-activated protein kinases (MAPKs), glycogen synthase kinases (GSKs), and CDC-like kinases (CLKs), play pivotal roles in cellular signaling pathways, including cell cycle regulation, proliferation, differentiation, apoptosis, and gene expression regulation. The dysregulation and aberrant activation of these kinases have been implicated in cancer development and progression, making them attractive therapeutic targets. In recent years, kinase inhibitors targeting CMGC kinases, such as CDK4/6 inhibitors and BRAF/MEK inhibitors, have demonstrated clinical success in treating specific cancer types. However, challenges remain, including resistance to kinase inhibitors, off-target effects, and the need for better patient stratification. This review provides a comprehensive overview of the importance of CMGC kinases in cancer biology, their involvement in cellular signaling pathways, protein-protein interactions, and the current state of kinase inhibitors targeting these kinases. Furthermore, we discuss the challenges and future perspectives in targeting CMGC kinases for cancer therapy, including potential strategies to overcome resistance, the development of more selective inhibitors, and novel therapeutic approaches, such as targeting protein-protein interactions, exploiting synthetic lethality, and the evolution of omics in the study of the human kinome. As our understanding of the molecular mechanisms and protein-protein interactions involving CMGC kinases expands, so too will the opportunities for the development of more selective and effective therapeutic strategies for cancer treatment.

The Importance of the Pyrazole Scaffold in the Design of Protein Kinases Inhibitors as Targeted Anticancer Therapies

The altered activation or overexpression of protein kinases (PKs) is a major subject of research in oncology and their inhibition using small molecules, protein kinases inhibitors (PKI) is the best available option for the cure of cancer. The pyrazole ring is extensively employed in the field of medicinal chemistry and drug development strategies, playing a vital role as a fundamental framework in the structure of various PKIs. This scaffold holds major importance and is considered a privileged structure based on its synthetic accessibility, drug-like properties, and its versatile bioisosteric replacement function. It has proven to play a key role in many PKI, such as the inhibitors of Akt, Aurora kinases, MAPK, B-raf, JAK, Bcr-Abl, c-Met, PDGFR, FGFRT, and RET. Of the 74 small molecule PKI approved by the US FDA, 8 contain a pyrazole ring: Avapritinib, Asciminib, Crizotinib, Encorafenib, Erdafitinib, Pralsetinib, Pirtobrutinib, and Ruxolitinib. The focus of this review is on the importance of the unfused pyrazole ring within the clinically tested PKI and on the additional required elements of their chemical structures. Related important pyrazole fused scaffolds like indazole, pyrrolo[1,2-b]pyrazole, pyrazolo[4,3-b]pyridine, pyrazolo[1,5-a]pyrimidine, or pyrazolo[3,4-d]pyrimidine are beyond the subject of this work.

Application of deep generative model for design of Pyrrolo[2,3-d] pyrimidine derivatives as new selective TANK binding kinase 1 (TBK1) inhibitors

The deep conditional transformer neural network SyntaLinker was applied to identify compounds with pyrrolo[2,3-d]pyrimidine scaffold as potent selective TBK1 inhibitor. Further medicinal chemistry optimization campaign led to the discovery of the most potent compound 7l, which exhibited strong enzymatic inhibitory activity against TBK1 with an IC₅₀ value of 22.4 nM 7l had a superior inhibitory activity in human monocytic THP1-Blue cells reporter gene assay than MRT67307. Furthermore, 7l significantly inhibited TBK1 downstream target genes cxcl10 and ifnβ expression in THP1 and RAW264.7 cells induced by poly (I:C) and lipopolysaccharide, respectively. This study suggested that combination of deep conditional transformer neural network SyntaLinker and transfer learning could be a powerful tool for scaffold hopping in drug discovery.