Prioritising Drug Targets in non-canonical pathways from multi-omic data

目前有大量且快速增长的公开数据集，这些数据集来自于使用大量和单细胞转录组学、LS-MS/MS蛋白质组学和磷蛋白质组学、代谢组学和表观遗传学等方法监测细胞对扰动的反应的研究。虽然单个研究本身是有用的，但对研究数据的大规模荟萃分析有望带来更重大的突破，比如发现有价值的新药物靶点线索。该项目的目的是开发和应用人工智能方法，从大量汇总的组学数据中识别潜在的药物靶点。具体来说，您将探索使用监督机器学习方法来学习已证实的药物靶标所表现出的行为模式，并使用这项工作的结果来构建能够根据其药物靶标潜力对其他分子进行排名的预测器。最终，目标将是将您新开发的人工智能方法应用于MSD持有的内部数据。该项目在使用的人工智能方法和研究的数据集方面提供了广泛的自由，因此提供了一个获得最新机器学习算法实践经验的绝佳机会，并评估不同类型的组学数据的价值。

There exists a large and rapidly growing body of publicly available datasets from studies that monitor cellular response to perturbation using methods such as bulk and single cell transcriptomics, LS-MS/MS proteomics and phosphoproteomics, metabolomics and epigenetics. While individual studies are useful in their own right, large scale meta-analysis of data across studies promises more significant breakthroughs, such as the discovery of valuable new drug target leads. The aim of this project is to develop and apply AI methodologies to identify potential drug targets from large collections of aggregated omics data. Specifically, you will explore the use of supervised machine learning approaches to learn patterns of behaviour exhibited by proven drug targets and use the results of this work to build predictors capable of ranking other molecules according to their drug target potential. Ultimately, the aim will be to apply your newly developed AI approach to in-house data held by MSD. The project offers extensive freedom in terms of the AI methods used and the data sets studied, so provides an excellent opportunity to gain hands-on experience of the latest machine learning algorithms, and to evaluate the value of different types of omics data.