Mechanistic modelling of multitargeted therapeutics

胰腺癌仍然难以治愈，导致高死亡率。因此，迫切需要创新的方法来应对这种疾病。异常的表观遗传学是癌细胞用来推动正常细胞去分化为胚胎鳞状状态的一个关键的“癌症标志”，这种状态有利于不受控制的增殖。我们最近确定了定义这些表型变化的表观遗传学机制，并发现生物靶向药物(二甲双胍和维生素C)的组合可以恢复表观遗传控制，并使胰腺鳞状细胞癌细胞恢复到更受调控的分化状态[1]。尽管我们观察到了向正常细胞表观遗传学的转变，但这种药物组合并没有完全优化来驱动表型转变。因此，我们的目标是使用由Epicombi.ai开发的创新的数据驱动的人工智能(AI)方法，基于现有的算法[2]，描述能够证明表观遗传状态和胰腺分化的改善和强大的重新正常化的新分子，以便为这种迄今难以治愈的癌症提供新的治疗方法。我们的目标是开发针对胰腺癌的AI衍生分子的机制数学模型。拟议的项目将探索AI/机器学习平台(Epicombi.ai)预测的分子改变细胞表型的作用机制。该项目将集中于机制模型的开发[3，4]，以更好地了解这些新型制剂如何通过相关细胞信令网络的扰动实现表型变化。这些分子可能有多个细胞靶点，扰乱了许多信号通路，这些通路可能结合在一起，实现细胞的表型正常化。因此，要理解这种“多重干预”分子如何发挥作用来改变细胞信号网络，就需要建立机制模型。然后，这些模型将被用来进一步改进平台发现和优化引擎，并提供Epicombi.ai数据驱动的药物发现平台的机械基础，以识别针对这一治疗适应症的优化药物。

Pancreatic cancers remain intractable, resulting in high mortality. Thus, there is an urgent need for innovative ways to tackle this disease. Aberrant epigenetics is a key "Hallmark of cancer" that cancer cells use to drive de-differentiation of normal cells into an embryonic squamous-like state which favours uncontrolled proliferation. We recently identified the epigenetic mechanism defining these phenotypic changes and found that a combination of biologically-targeted agents (Metformin and Vitamin C) could restore epigenetic control and revert squamous pancreatic cancer cells to a more regulated differentiated state [1]. Although we observe a shift towards normal cell epigenetics, this drug combination is not fully optimised to drive the phenotypic shift. Therefore, we aim to use an innovative data-driven artificial intelligence (AI) approach developed by Epicombi.ai, based on existing algorithms[2], to delineate novel molecules that can demonstrate improved and robust re-normalisation of epigenetic status and pancreatic differentiation, in order to offer new treatments for this hitherto intractable cancer. Our aim is to develop mechanistic mathematical models for AI-derived molecules targeting pancreatic cancer.The proposed project will explore the mechanism of action of molecules predicted by a AI/Machine Learning platform (Epicombi.ai) to modify cellular phenotype. This project will centre on the development of mechanistic models [3,4] to better understand how these novel agents achieve phenotypic changes through the perturbation of relevant cellular signalling networks. These molecules are likely to have multiple cellular targets, perturbing a number of signalling pathways, which may all combine to achieving phenotypic normalisation of the cell. Thus, mechanistic modelling is required to understand how such a 'multi-intervention' molecule functions to alter cell signalling networks. The models will then be employed to further refine the platform discovery and optimisation engine, and provide a mechanistic underpinning of Epicombi.ai data-driven drug-discovery platform to identify optimised drugs for this therapeutic indication.