Official websites use .gov

A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS

A lock ( 🔒 ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Need Help

Knowledge-Guided Multi-Omics Integration and Transfer Learning for Emerging Infections

Award Number: R21AI203026
ORGANIZATION: NATIONAL INSTITUTE OF ALLERGY & INFECTIOUS DISEASES
OPDIV: NIH
AWARD CLASS: DISCRETIONARY
AWARD ACTIVITY TYPE: SCIENTIFIC/HEALTH RESEARCH (INCLUDES SURVEYS)
PERIOD OF PERFORMANCE START DATE: 09/17/2026
PERIOD OF PERFORMANCE END DATE: 08/31/2028

Group Awards By:

View Award Description

Knowledge-Guided Multi-Omics Integration and Transfer Learning for Emerging Infections - Project Summary The broad objective of this project is to develop knowledge-guided machine learning methods that enhance interpretability and predictive power for small-sample multi-omics studies in emerging infectious diseases. This project is motivated by the omics-related research on melioidosis, a severe bacterial infection caused by Burkholderia pseudomallei that leads to high mortality but remains neglected due to limited diagnostic and prognostic tools. Recent high-throughput technologies have enabled multi-omics profiling of infected patients, but these datasets are high-dimensional, noisy and of limited sample size, making traditional analytical methods prone to overfitting and inadequate for identifying reproducible biological mechanisms or building reliable prognostic models. The proposed project pursues two specific aims. Aim 1 will develop a pathway- guided penalized neural network that integrates multi-omics and curated pathway information, using group lasso penalties to select biologically meaningful pathways while maintaining network sparsity and interpretability. This approach directly links molecular features to diagnosis through known pathways in a highly nonparametric model, providing a principled and interpretable framework for pathway analysis. Aim 2 will develop a transfer learning framework that leverages larger clinical-only datasets to improve prognostic accuracy in a smaller cohort with multi-omics and clinical data. The proposed method will align the latent representations of shared clinical features across cohorts using domain adaptation principles, enabling effective information transfer when feature availability differs across cohorts. This project is innovative in combining biological prior knowledge, neural network regularization, and transfer learning to address the challenges of high-dimensional, small-sample multi-omics data in emerging infectious diseases. The resulting methods will yield interpretable models that uncover perturbed pathways underlying melioidosis, improve prediction of patient outcomes, and facilitate translation of molecular findings to clinical practice. All methods will be implemented in open-source software, ensuring accessibility and reproducibility. Successful completion of this R21 project will advance machine learning methodology for multi-omics data integration and provide generalizable analytical tools to study melioidosis and other emerging infectious diseases.


Issue Date FY	Funding FY	Legal Entity Name	Legal Entity Address	Legal Entity City	Legal Entity State	Legal Entity Zip Code	Legal Entity COUNTY	Legal Entity COUNTRY	Assistance Listing	Award Code	Budget Year	Action Date	Action Type	Action Amount

Issue Date FY: 2026 ( Subtotal = $239,917 )
2026	2026	MICHIGAN STATE UNIVERSITY	426 AUDITORIUM RD RM 360	EAST LANSING	MI	48824	INGHAM	USA	Allergy and Infectious Diseases Research	000	1	9/17/2026	NEW	$239,917
														Subtotal = $239,917

Grand Total All Awards = $239,917

Top

All Categories

About

Search

Reports

Data Submission

Award Information

Knowledge-Guided Multi-Omics Integration and Transfer Learning for Emerging Infections

Award Number: R21AI203026

ORGANIZATION: NATIONAL INSTITUTE OF ALLERGY & INFECTIOUS DISEASES

OPDIV: NIH

AWARD CLASS: DISCRETIONARY

AWARD ACTIVITY TYPE: SCIENTIFIC/HEALTH RESEARCH (INCLUDES SURVEYS)

PERIOD OF PERFORMANCE START DATE: 09/17/2026

PERIOD OF PERFORMANCE END DATE: 08/31/2028

Federal Websites

Department of Health & Human Services

HHS Operating Divisions

HHS Staff Divisions

Download A Document Viewer