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

Graph-AI Model Guided Target and Synthetic Lethality Discovery Among Cell-Death Pathways

Award Number: R01GM162892
ORGANIZATION: NATIONAL INSTITUTE OF GENERAL MEDICAL SCIENCES
OPDIV: NIH
AWARD CLASS: DISCRETIONARY
AWARD ACTIVITY TYPE: SCIENTIFIC/HEALTH RESEARCH (INCLUDES SURVEYS)
PERIOD OF PERFORMANCE START DATE: 09/04/2026
PERIOD OF PERFORMANCE END DATE: 07/31/2030

Group Awards By:

View Award Description

Graph-AI Model Guided Target and Synthetic Lethality Discovery Among Cell-Death Pathways - Summary A gene pair is defined as synthetic lethal (SL) when compromised function of both genes in the pair results in cell death, but the cell survives when the function of only one of the genes is lost. While CRISPR-cas9 and gene combination double knockout (CDKO) experiments are becoming standard approach in SL discovery, it cannot be scaled to handle genome wide gene combinations. A set of pre-selected genes are crucial for CDKO experiment design. Thus, SL discovery from CDKO experiments can be significantly benefited from an effective SL prediction model, and the model has to be cell/patient specific. Multi-omics data-driven studies are at the forefront of precision medicine because they systematically characterize dysfunctional biological processes across multiple levels, providing a comprehensive view of disease pathogenesis. However, there is a lack of effective multi-omics data driven models to prioritize key candidate signaling targets of SLs because of integration and interpretation of complex multi-omics data is challenging. Herein, the goal of this grant proposal is to develop multi-omics graph artificial intelligence (AI) guided CDKO experiments to search for cell/patient specific targets of SLs in a mechanism-explainable and cost-effective manner. In Aim 1, a novel joint text-omics Large Language Model LLM-Graph-AI model is developed to decode cell vulnerability signaling flows as the initial set of candidate targets of SL. This model is designed to identify target with a cold start, i.e. without known SL or non-SL gene pairs in a cell. In aim 2, a graph transfer-learning model is developed for cell-specific SL prediction (GTL-iSL). Complementary to Aim 1, GTL-iSL in Aim 2 is designed to select SLs when there are some SL or non-SL data in the target cell. Aim 3 is designed to discover and validate SLs among targets on cell death pathways. SL prediction models are applicable across a wide range of diseases. For the first time, these models are purposely developed for CDKO experiment design. The optimized SL prediction models select targets and SLs using multi-omics data from either an individual cells or a patient, which demonstrates its clinical and translational impact.


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 = $521,858 )
2026	2026	OHIO STATE UNIVERSITY, THE	1960 KENNY RD	COLUMBUS	OH	43210	FRANKLIN	USA	Biomedical Research and Research Training	000	1	9/4/2026	NEW	$521,858
														Subtotal = $521,858

Grand Total All Awards = $521,858

Top

All Categories

About

Search

Reports

Data Submission

Award Information

Graph-AI Model Guided Target and Synthetic Lethality Discovery Among Cell-Death Pathways

Award Number: R01GM162892

ORGANIZATION: NATIONAL INSTITUTE OF GENERAL MEDICAL SCIENCES

OPDIV: NIH

AWARD CLASS: DISCRETIONARY

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

PERIOD OF PERFORMANCE START DATE: 09/04/2026

PERIOD OF PERFORMANCE END DATE: 07/31/2030

Federal Websites

Department of Health & Human Services

HHS Operating Divisions

HHS Staff Divisions

Download A Document Viewer