Abstract 219: Uncovering synergistic and antagonistic interactions in epigenetic therapeutics using perturb-seq

Abstract Acute myeloid leukemia (AML) is a heterogeneous malignancy characterized by genetic and epigenetic dysregulation, including aberrant activity of chromatin modifiers. The complex interactions among these modifiers and regulators in AML pathogenesis remain poorly understood, posing significant challenges to developing effective combination therapies. To address this, we used Perturb-seq, a CRISPR-based single-cell transcriptomics approach, to profile 16 key genes from the Menin-MLL, Polycomb, and histone acetyltransferase (HAT) complexes in the MOLM-13 AML cell line. We developed a machine learning framework called Composer, which predicts the combinatorial effects of perturbations by analyzing their impact on the transcriptome. We identified cooperative regulation of oncogenic pathways by Menin-MLL and KAT6A, while PRC1 components, such as PCGF1, were found to antagonize DOT1L activity. These predictions were validated using bulk RNA-seq and experiments combining perturbations through small molecule inhibitors and gene knockouts, demonstrating that dual inhibition of Menin-MLL and KAT6A, or DOT1L and KAT6A, significantly reduced AML cell viability. This study underscores the power of combining AI with single-cell Perturb-seq to provide novel insight into the epigenetic landscape of AML and identify promising therapeutic targets to overcome treatment resistance. Citation Format: Changde Cheng, Rui Lu, Sajesan Aryal, Doug A. Welsch. Uncovering synergistic and antagonistic interactions in epigenetic therapeutics using perturb-seq [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2025; Part 1 (Regular Abstracts); 2025 Apr 25-30; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2025;85(8_Suppl_1):Abstract nr 219.