Molecular Characterization of T-Lineage Acute Lymphoblastic Leukemia by an Optimal-Transport Based Multi-Omics Integration Framework

Abstract

T-lineage acute lymphoblastic leukemia (T-ALL) is an aggressive pediatric malignancy characterized by complex heterogeneity across multiple molecular layers. Accurate subtyping is essential for understanding disease mechanisms, risk stratification, and guiding targeted therapeutic strategies. However, current diagnostic approaches are labor-intensive and time-consuming, and existing computational methods are limited by reliance on single-modality data or simple integration strategies. Effective integration of heterogeneous multi-omics data remains a major computational challenge. We present OTTER (Optimal Transport-based Transcriptomics and gEnomics Representation), a novel multi-modal deep learning framework that jointly models transcriptomic and genomic data for T-ALL molecular characterization. OTTER encodes each omics modality through a modality-specific encoder and aligns the resulting latent representations using Gromov-Wasserstein optimal transport (GW-OT), which preserves the internal geometric structure of each modality without requiring a shared feature space. Benchmarking tests on the Children's Oncology Group (COG) AALL0434 cohort with >1,300 patients across 17 T-ALL subtypes suggested that OTTER significantly outperformed state-of-the-art approaches for T-ALL molecular characterization. In addition, OTTER could identify interpretable subtype-defining and omics-specific features for T-ALL. Furthermore, we have demonstrated the generalizability of OTTER by evaluating on multiple external independent clinical cohorts. In summary, OTTER provides a principled, biologically interpretable, and computationally effective framework for multi-omics driven T-ALL molecular characterization and broader cancer applications.