Unlocking the Potential of Kinase Targets in Cancer: Insights from CancerOmicsNet, an AI-Driven Approach to Drug Response Prediction in Cancer.

Deregulated protein kinases are crucial in promoting cancer cell proliferation and driving malignant cell signaling. Although these kinases are essential targets for cancer therapy due to their involvement in cell development and proliferation, only a small part of the human kinome has been targeted by drugs. A comprehensive scoring system is needed to evaluate and prioritize clinically relevant kinases. We recently developed CancerOmicsNet, an artificial intelligence model employing graph-based algorithms to predict the cancer cell response to treatment with kinase inhibitors. The performance of this approach has been evaluated in large-scale benchmarking calculations, followed by the experimental validation of selected predictions against several cancer types. To shed light on the decision-making process of CancerOmicsNet and to better understand the role of each kinase in the model, we employed a customized saliency map with adjustable channel weights. The saliency map, functioning as an explainable AI tool, allows for the analysis of input contributions to the output of a trained deep-learning model and facilitates the identification of essential kinases involved in tumor progression. The comprehensive survey of biomedical literature for essential kinases selected by CancerOmicsNet demonstrated that it could help pinpoint potential druggable targets for further investigation in diverse cancer types.

Artificial intelligence to guide precision anticancer therapy with multitargeted kinase inhibitors.

BACKGROUND: Vast amounts of rapidly accumulating biological data related to cancer and a remarkable progress in the field of artificial intelligence (AI) have paved the way for precision oncology. Our recent contribution to this area of research is CancerOmicsNet, an AI-based system to predict the therapeutic effects of multitargeted kinase inhibitors across various cancers. This approach was previously demonstrated to outperform other deep learning methods, graph kernel models, molecular docking, and drug binding pocket matching. METHODS: CancerOmicsNet integrates multiple heterogeneous data by utilizing a deep graph learning model with sophisticated attention propagation mechanisms to extract highly predictive features from cancer-specific networks. The AI-based system was devised to provide more accurate and robust predictions than data-driven therapeutic discovery using gene signature reversion. RESULTS: Selected CancerOmicsNet predictions obtained for "unseen" data are positively validated against the biomedical literature and by live-cell time course inhibition assays performed against breast, pancreatic, and prostate cancer cell lines. Encouragingly, six molecules exhibited dose-dependent antiproliferative activities, with pan-CDK inhibitor JNJ-7706621 and Src inhibitor PP1 being the most potent against the pancreatic cancer cell line Panc 04.03. CONCLUSIONS: CancerOmicsNet is a promising AI-based platform to help guide the development of new approaches in precision oncology involving a variety of tumor types and therapeutics.

In utero tobacco smoke exposure alters lung inflammation, viral clearance, and CD8+ T-cell responses in neonatal mice infected with respiratory syncytial virus.

Maternal smoking during pregnancy and exposure of infants to cigarette smoke are strongly associated with adverse health effects in childhood including higher susceptibility to respiratory viral infections. Human respiratory syncytial virus (HRSV) is the most important cause of lower respiratory tract infection among young infants. Exacerbation of respiratory disease, including HRSV bronchiolitis and higher susceptibility to HRSV infection, is well correlated with previous smoke exposure. The mechanisms of recurrence and susceptibility to viral pathogens after passive smoke exposure are multifactorial and include alteration of the structural and immunologic host defenses. In this work, we used a well-established mouse model of in utero smoke exposure to investigate the effect of in utero smoke exposure in HRSV-induced pathogenesis. Sample analysis indicated that in utero exposure led to increased lung inflammation characterized by an increased influx of neutrophils to the airways of the infected mice and a delayed viral clearance. On the other hand, decreased HRSV-specific CD8+ T-cell response was observed. These findings indicate that cigarette smoke exposure during pregnancy alters HRSV-induced disease as well as several aspects of the neonatal immune responses.

Distinguishing Lipid Subtypes by Amplifying Contrast from J-Coupling.

Previous work has highlighted the complicated and distinctive dynamics that set signal evolution during a train of spin echoes, especially with nonuniform echo spacing applied to complex molecules like fats. The work presented here regards those signal patterns as codes that can be used as a contrast mechanism, capable of distinguishing mixtures of molecules with an imaging sequence, sidestepping many challenges of spectroscopy. For particular arrays of echo spacings, non-monotonic and distinctive signal evolution can be enhanced to improve contrast between target species. This work presents simulations that show how contrast between two molecules: (a) depends on the specific sequence of echo spacing, (b) is directly linked to the presence of J-coupling, and (c) can be relatively insensitive to variations in B0, T2 and B1. Imaging studies with oils demonstrate this phenomenon experimentally and also show that spin echo codes can be used for quantification. Finally, preliminary experiments apply the method to human liver in vivo, verifying that the presence of fat can lead to nonmonotonic codes like those seen in vitro. In summary, nonuniformly spaced echo trains introduce a new approach to molecular imaging of J-coupled species, such as lipids, which may have implications diagnosing metabolic diseases.

Anti-viral immunity in the tumor microenvironment: implications for the rational design of herpes simplex virus type 1 oncolytic virotherapy.

PURPOSE OF REVIEW: The design of novel herpes simplex type I (HSV-1)-derived oncolytic virotherapies is a balancing act between safety, immunogenicity and replicative potential. We have undertaken this review to better understand how these considerations can be incorporated into rational approaches to the design of novel herpesvirus oncolytic virotherapies. RECENT FINDINGS: Several recent papers have demonstrated that enhancing the potential of HSV-1 oncolytic viruses to combat anti-viral mechanisms present in the tumor microenvironment leads to greater efficacy than their parental viruses. SUMMARY: It is not entirely clear how the immunosuppressive tumor microenvironment affects oncolytic viral replication and spread within tumors. Recent work has shown that the manipulation of specific cellular and molecular mechanisms of immunosuppression operating within the tumor microenvironment can enhance the efficacy of oncolytic virotherapy. We anticipate that future work will integrate greater knowledge of immunosuppression in tumor microenvironments with design of oncolytic virotherapies.

Interferon-Mediated Response to Human Metapneumovirus Infection.

Human metapneumovirus (HMPV) is one of the leading causes of respiratory diseases in infants and children worldwide. Although this pathogen infects mainly young children, elderly and immunocompromised people can be also seriously affected. To date, there is no commercial vaccine available against it. Upon HMPV infection, the host innate arm of defense produces interferons (IFNs), which are critical for limiting HMPV replication. In this review, we offer an updated landscape of the HMPV mediated-IFN response in different models as well as some of the defense tactics employed by the virus to circumvent IFN response.