Thursday, November 21, 2024
11/21/2024
Project Summary The broad long-term objective of the project concerns the development of novel machine learning methods and computational tools for modeling genomic data, driven by significant biological questions and experiments. Analyzing single-cell RNA-seq (scRNA-seq) data and spatial genomic data poses substantial computational and bioinformatics challenges. The specific aim of the project is to develop novel model-based deep learning methods that incorporate prior biological information to model scRNA-seq data and spatial genomic data. These challenges are motivated by the PI’s close collaborations with biomedical investigators. The proposed approaches are designed to integrate biological information to enhance both analytical performance and biological interpretability. These methods rely on a novel integration of biological insights and statistical techniques with deep learning to analyze the noisy, sparse, and over-dispersed scRNA-seq and spatial genomic data. This integration includes a zero- inflated negative binomial model, autoencoder, variational autoencoder, and deep embedding. The new methods can be applied to various essential analytical tasks for the analysis of scRNA- seq and spatial genomic data, leading to improved interpretability. They will facilitate effective analyses of the increasingly important scRNA-seq datasets and contribute to the ongoing studies with which the PI is currently collaborating, such as Paneth cell regulation, regeneration of human hair follicles, and melanoma. The project will develop practical and feasible computer programs to implement the proposed methods and evaluate their performance through real applications. The work outlined in this proposal will provide deep learning methods for modeling scRNA-seq data and studying complex phenotypes and biological systems, offering insights into each of the biological areas represented by the various datasets. All programs developed under this grant, along with detailed documentation, will be made available free of charge to interested researchers. Undergraduate researchers from diverse backgrounds will be recruited as an integral part of the project to implement the most critical aspects of the proposed aims. This research project aims to stimulate the interests of students, encouraging them to consider a career in the biomedical sciences.
HHS’ Tracking Accountability in Government Grants System (TAGGS) website provides access to detailed descriptions of grants, loans, aggregated direct payments and other types of financial assistance awarded by the HHS Operating Divisions (OPDIVs) and the Office of the Secretary Staff Divisions (STAFFDIVs).
