Recent advances in high throughput technologies have led to a substantial increase in multi-omic data characterizing various levels of molecular changes in the progression of disease, including genome, transcriptome, proteome and metabolome. The availability of computational methods that are sufficiently powerful to handle the high dimensionality and heterogeneity of multi-omic data is still very limited. In addition, major findings generated from current -omics studies have been largely restricted to relatively simple patterns, e.g., individual biomarkers, possibly with few functional interactions, which present difficulties for validating these findings and relating them to downstream biology. This project, by coupling the multi-omic data and the systems biology networks, will develop novel computational methods to explore the functional network modules associated with disease quantitative traits. By enabling both strategic and efficient knowledge extraction from the vast biological landscape represented by multi-omic data, this research has may lead to unprecedented discovery of disease mechanisms and suggest surrogate biomarkers for therapeutic trials.
This work will develop new computational methods to enable the integration of large scale heterogeneous multi-omic data with rich domain knowledge for better biomarker and association discovery. Two interrelated tasks will be performed: 1) Develop a novel biological knowledge guided structured sparse learning model together with large-scale optimization methods to integrate -omic data and biological networks from multiple sources and discover -omic modules involving heterogeneous biomarkers for accurately predicting outcomes of interest; and 2) Couple multi-task learning with structured sparse association models to jointly learn the bi-multivariate associations between imaging phenotypes and -omic features with dense functional connections for multiple groups. The project will contribute to a new solution framework spanning the areas of machine learning, data mining and network science, and also provide novel perspectives as to how to effectively integrate the large-scale and heterogeneous -omic data for a systems biology of complex diseases.
This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
