National Institute of General Medical Sciences 5R35GM133657-08

Advanced machine learning models to integrate multi-modal biomedical datasets for gene regulation and precision medicine

The award supports the development of advanced machine learning and deep learning tools to integrate diverse biomedical datasets for improved gene regulation understanding and precision medicine applications. It aims to create interpretable models to predict clinical outcomes and identify drug repurposing opportunities.

Description

This project aims to develop machine learning and deep learning architectures for integrating multi-modal biomedical datasets, with applications in gene regulation and precision medicine. The research program focuses on developing open-source integrative computational tools to analyze high-dimensional multi-modal biomedical datasets such as multi-omics and electronic health records data. The goal is to create generalizable, biologically inspired, and interpretable machine learning solutions to address challenges in biomedical datasets, including data irregularities, dependencies between data modalities, and missing and noisy data. Novel computational methods based on machine learning, deep learning, and graph representation learning will be developed to integrate multi-modal biomedical datasets for various prediction tasks such as predicting clinical outcomes, inferring regulatory networks, and identifying drugs for repurposing. The vision is to advance precision medicine by enhancing understanding of gene regulatory interactions and disease mechanisms.

View original record