Project Details
Description
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.
Status | Active |
---|---|
Effective start/end date | 9/22/21 → 8/31/27 |
Funding
- National Human Genome Research Institute: $450,849.00
- National Human Genome Research Institute: $450,034.00
Fingerprint
Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.