Systematic Investigation of Docking Failures in Large-Scale Structure-Based Virtual Screening

Min, Xu; Shen, Cheng; Yang, Jincai; Wang, Qing; Huang, Niu

doi:10.1021/acsomega.2c05826

Cited by 10 publications

(6 citation statements)

References 77 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, AiKPro demonstrated superior scoring performance when compared to AutoDock Vina, a widely used traditional docking tool. AutoDock Vina mainly scores poses using pairwise interatomic distances and includes a repulsive parabolic function, making it sensitive to bumps and strains 48 . In contrast, AiKPro uses 3D structure information from svMSA and 3CED, allowing approximate binding affinity predictions with significantly reduced computational demands.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

AiKPro: deep learning model for kinome-wide bioactivity profiling using structure-based sequence alignments and molecular 3D conformer ensemble descriptors

Park¹,

Hong²,

Lee³

et al. 2023

Sci Rep

View full text Add to dashboard Cite

The discovery of selective and potent kinase inhibitors is crucial for the treatment of various diseases, but the process is challenging due to the high structural similarity among kinases. Efficient kinome-wide bioactivity profiling is essential for understanding kinase function and identifying selective inhibitors. In this study, we propose AiKPro, a deep learning model that combines structure-validated multiple sequence alignments and molecular 3D conformer ensemble descriptors to predict kinase-ligand binding affinities. Our deep learning model uses an attention-based mechanism to capture complex patterns in the interactions between the kinase and the ligand. To assess the performance of AiKPro, we evaluated the impact of descriptors, the predictability for untrained kinases and compounds, and kinase activity profiling based on odd ratios. Our model, AiKPro, shows good Pearson’s correlation coefficients of 0.88 and 0.87 for the test set and for the untrained sets of compounds, respectively, which also shows the robustness of the model. AiKPro shows good kinase-activity profiles across the kinome, potentially facilitating the discovery of novel interactions and selective inhibitors. Our approach holds potential implications for the discovery of novel, selective kinase inhibitors and guiding rational drug design.

show abstract

Section: Discussionmentioning

confidence: 99%

“…The parameters used in the docking study are listed in Table S3 . All target and ligand structures were prepared as flexible, following the protocol outlined in the literature reference for AutoDock Vina 48 , 49 . The results of the two scoring functions using AutoDock Vina docking were compared with the predictions by AiKPro.…”

Section: Methodsmentioning

confidence: 99%

AiKPro: deep learning model for kinome-wide bioactivity profiling using structure-based sequence alignments and molecular 3D conformer ensemble descriptors

Park¹,

Hong²,

Lee³

et al. 2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…While scoring functions provide a numerical estimate of binding affinity, they can sometimes be misleading due to their inherent limitations, such as the inability to accurately model solvent effects or protein flexibility. Visual inspection helps to confirm that the top-scoring poses are chemically and physically reasonable [55][56][57].…”

Section: Analysis Of Docking Posesmentioning

confidence: 99%

Molecular Docking in Drug Discovery: Techniques, Applications, and Advancements

Aguiar,

Camps

2024

Preprint

View full text Add to dashboard Cite

Objective: The primary objective of this study is to conduct a comprehensive review of the significance of molecular docking in the field of drug discovery. This includes an examination of the various approaches and methods used in molecular docking, as well as an exploration of the techniques used for interpreting and validating docking results. Methods: To gather relevant data, a systematic search was conducted using Web of Science, PubMed, and Google Scholar. The search focused on articles related to molecular docking methodologies and their applications in drug discovery. Additionally, alternative techniques that can be used for more precise simulations of ligand-protein interactions were also considered. Results: Molecular docking has proven to be an incredibly rich and valuable process in the field of drug discovery. Its flexibility allows for the incorporation of advanced computational techniques, thereby enhancing the reliability and efficiency of drug discovery processes. The results of the study highlight the significant strides made in the field of molecular docking, demonstrating its potential to revolutionize drug discovery. Conclusions: Molecular docking continues to evolve, with new advancements being made regularly. Despite the challenges faced, these advancements have significantly contributed to the enhancement of molecular docking, solidifying its position as a crucial tool in the field of drug discovery.

show abstract

“…Approaches relying on docking are often used to identify novel scaffolds; however, they present a low success rate [22]. The low rate of success may be associated with the onerous step of identifying hits within an extensive library, which can be time-consuming and often depends on visual analysis.…”

Section: The Native Ros1 Kinase Domainmentioning

confidence: 99%

Structural Aspects of the ROS1 Kinase Domain and Oncogenic Mutations

Vilachã,

Wassenaar,

Marrink

2024

Crystals

View full text Add to dashboard Cite

Protein kinases function as pivotal regulators in biological events, governing essential cellular processes through the transfer of phosphate groups from ATP molecules to substrates. Dysregulation of kinase activity is frequently associated with cancer, ocasionally arising from chromosomal translocation events that relocate genes encoding kinases. Fusion proteins resulting from such events, particularly those involving the proto-oncogene tyrosine-protein kinase ROS (ROS1), manifest as constitutively active kinases, emphasizing their role in oncogenesis. Notably, the chromosomal reallocation of the ros1 gene leads to fusion of proteins with the ROS1 kinase domain, implicated in various cancer types. Despite their prevalence, targeted inhibition of these fusion proteins relies on repurposed kinase inhibitors. This review comprehensively surveys experimentally determined ROS1 structures, emphasizing the pivotal role of X-ray crystallography in providing high-quality insights. We delve into the intricate interactions between ROS1 and kinase inhibitors, shedding light on the structural basis for inhibition. Additionally, we explore point mutations identified in patients, employing molecular modeling to elucidate their structural impact on the ROS1 kinase domain. By integrating structural insights with in vitro and in silico data, this review advances our understanding of ROS1 kinase in cancer, offering potential avenues for targeted therapeutic strategies.

show abstract

Systematic Investigation of Docking Failures in Large-Scale Structure-Based Virtual Screening

Cited by 10 publications

References 77 publications

AiKPro: deep learning model for kinome-wide bioactivity profiling using structure-based sequence alignments and molecular 3D conformer ensemble descriptors

AiKPro: deep learning model for kinome-wide bioactivity profiling using structure-based sequence alignments and molecular 3D conformer ensemble descriptors

Molecular Docking in Drug Discovery: Techniques, Applications, and Advancements

Structural Aspects of the ROS1 Kinase Domain and Oncogenic Mutations

Contact Info

Product

Resources

About