Grant Number:	1R03CA317707-01 Interpret this number
Primary Investigator:	Wan, Shibiao
Organization:	University Of Nebraska Medical Center
Project Title:	Molecular Categorization of T-Cell Acute Lymphoblastic Leukemia Based on Gabriella Miller Kids First Pediatric Research Data
Fiscal Year:	2026

Scientific Abstract Characterized by aberrant proliferation of immature T-cell precursors, T-cell acute lymphoblastic leukemia (T- ALL) is an aggressive hematological malignancy especially for children. While significant progress has been made to improve the overall survival rates of pediatric T-ALL, the prognosis for patients with refractory or relapsed T-ALL is poor. T-ALL has multiple distinct subtypes characterized by morphological, molecular, and genetic alterations. T-ALL molecular categorization is essential for downstream risk stratification and tailored treatment design. While various conventional methods like morphological analysis, cytogenetic analysis, immunophenotyping, or molecular profiling have been used for T-ALL categorization, they are usually costly, time-consuming, labor-intensive, and sometimes inaccurate. Recent progress has witnessed the application of next generation sequencing (NGS) for characterizing T-ALL, but they are limited to bulk NGS data, or single omics data only. With tons of omics data being generated in the Gabriella Miller Kids First (GMKF) Pediatric Research Data and other publicly available databases, we hypothesize that integration of single-cell and bulk multi-omics data including genomics, transcriptomics, and epigenetics data will significantly facilitate subtype- specific biomarker discovery and boost the accuracy of T-ALL molecular categorization. To address these concerns, we propose to develop an integrated artificial intelligence (AI) framework for accurate and cost- effective T-ALL categorization by combining bulk and single-cell multi-omics data from the GMKF database and beyond. To achieve this, we plan to undertake three specific aims. In Aim 1, we will establish a knowledge-transfer machine learning (ML) model that leverages large-scale bulk and single-cell transcriptomics data for categorizing T-ALL. In Aim 2, we will develop a multi-modal AI framework to systematically integrate deep information related with T-ALL subtypes from single-cell and bulk multi-omics data (including genomics, transcriptomics, epigenomics) to further boost T-ALL molecular categorization. In Aim 3, we will identify and evaluate subtype-specific biomarkers from multi-omics data for T-ALL. We will adopt an interpretable ML approach to identify T-ALL subtype-specific biomarkers, and evaluate their clinical significance by correlating them with treatment responses and clinical outcomes. We believe successful completion of this study will have direct impacts on improving downstream childhood T-ALL risk stratification, facilitating diagnosis and prognosis, and optimizing treatment selection. With a strong interdisciplinary team, this project will serve as a foundation for our long-term goals to establish an integrated and unified system for characterizing various types of leukemia, including T-ALL, B-cell ALL (B-ALL), and acute myeloid leukemia (AML). We also expect that our proposed framework in this study can be customized and extensible to molecular categorization of other types of cancers.




Classification of Adolescent Drinking via Behavioral, Biological and Environmental Variables: A Machine Learning Approach With Bias Control.
Authors: Liu R. , Azzam M. , Zabik N.L. , Wan S. , Blackford J.U. , Wang J. .
Source: Addiction Biology, 2026 Sep; 31(9), p. e70188.
PMID: 42725579
Related Citations