Novel Strategy to Quantitate Delayed Aging by Caloric Restriction

点击翻译按钮获取中文摘要

PROJECT SUMMARY The parental application proposed to integrate single cell imaging, ATAC-seq, and RNA-seq data from control diet mice and caloric restriction (CR) diet mice. These experiments will provide a large amount of multidimensional and multimodal data that not just suited for AI/ML applications, but in fact, require AI/ML approaches to make sense of the vast datasets. However, these datasets are coming from 3 different type of measurements (microscopic imaging, chromatin accessibility, and gene expression) of which 2 modalities (imaging and sequencing) are very different. At present all three data streams are handled in conventional ways primarily using very large Excel files; this data structure / format is not suitable for AI/ML integration. Hence the need for individual approaches to cleaning, filtering, and quality control (QC) of imaging data, ATAC-seq and RNA-seq data. Next critical step is to structure these diverse datasets in a similar format that streamlines storage and handling and enabling downstream integration and analyses using AI/ML algorithms. To meet these challenges, we will implement the AnnData format, which offers a broad range of computationally efficient features including, among others, sparse data support, Scanpy, and a PyTorch interface. To ensure that AnnData from very different modalities (imaging, ATAC-seq, RNA-seq) could be analyzed together, we will test run already developed computational algorithms that best suited to efficiently assimilate and combine multi- omics data to identify key factors that drive aging. We will combine AnnData objects from imaging, ATAC-seq, and RNA-seq using Bayesian methods for integrating multi-omics data and hyperbolic embedding with principled criteria for choosing the best-fitting curvature and dimension. To further test the utility of the embedded data we will test run CNN with VAEs and GAN on the ensemble of embedded data to ensure the endpoint readiness and to obtain initial feedback from different AI/ML applications. Finally, we will establish an electronic repository for python scripts and AnnData objects and structures for a straightforward dissemination to the broad research community.