Single cell guided deconvolution of bulk transcriptomics recapitulates differentiation stages of acute myeloid leukemia and predicts drug response

The diagnostic spectrum for AML patients is increasingly based on genetic abnormalities due to their prognostic and predictive value. However, information on the AML blast phenotype regarding their maturational arrest has started to regain importance due to its predictive power on drug responses. Here, we deconvolute 1350 bulk RNA-seq samples from five independent AML cohorts on a single-cell healthy BM reference and demonstrate that the morphological differentiation stage (FAB classification) could be faithfully reconstituted using estimated cell compositions (ECCs). Moreover, we show that the ECCs reliably predict ex-vivo drug resistances as demonstrated for Venetoclax, a BCL-2 inhibitor, resistance specifically in AML with CD14+ monocyte phenotype. We further validate these predictions using in-house proteomics data by showing that BCL-2 protein abundance is split into two distinct clusters for NPM1-mutated AML at the extremes of CD14+ monocyte percentages, which could be crucial for the Venetoclax dosing for these patients. Our results suggest that Venetoclax resistance predictions can also be extended to AML without recurrent genetic abnormalities (NOS), and possibly to MDS-related AML and secondary AML. Collectively, we propose a framework for allowing a joint mutation and maturation stage modeling that could be used as a blueprint for testing sensitivity for new agents across the various subtypes of AML.