e21166 Background: In lung adenocarcinomas (LUADs), lineage plasticity drives neuroendocrine (NE) and squamous cell (LUSC) transdifferentiation in the context of acquired resistance to targeted inhibition of driver mutations, with up to 14% and 9% incidences in EGFR-mutant tumors relapsed on EGFR inhibitors, respectively. Notably, survival of patients with NE- or LUSC-transdifferentiated tumors is remarkably lower than those of LUAD or de novo LUSC patients. The paucity of transforming clinical specimens amenable for molecular analyses has hindered the identification of histological transformation drivers, and to date no specific therapies aimed to prevent or delay transdifferentiation-led therapy relapse are available for patients at high risk of transformation. Methods: We performed multi-omic profiling of LUAD-to-LUSC and LUAD-to-NE transdifferentiating clinical samples, including comprehensive and integrative genomic (whole exome sequencing), epigenomic (bisulfite sequencing), transcriptomic (RNAseq) and protein (antibody arrays) characterization. Clinical findings were validated in preclinical models including cell lines as well as LUSC- and NE-transdifferentiation patient-derived xenograft models. Results: Our data supports that histological transdifferentiation from LUAD to LUSC or NE tumors is driven by epigenetic remodeling rather than by mutational events, and indicate that transdifferentiated tumors retain epigenomic features of their previous LUAD state. Integrative epigenomic, transcriptomic and protein analysis revealed divergent biological pathways dysregulated for each histological outcome, such as downregulation of RTK signaling and Notch-related genes in NE-transformed tumors, and upregulation of genes involved in Hedgehog and Notch signaling and MYC targets in LUSC-transdifferentiated tumors. Most interestingly, these analyses identified commonly dysregulated pathways in both NE- and LUSC-transdifferentiating tumors, including remarkable downregulation of a variety of immune-related pathways and upregulation of genes involved in AKT signaling and in the PRC2 epigenetic remodeling complex. Concurrent activation of AKT and MYC overexpression induced a squamous phenotype in EGFR-mutant LUAD preclinical models, further accentuated by EGFR inhibition. Pharmacological targeting of AKT in combination with osimertinib delayed both squamous and NE transformation in different EGFR-mutant patient-derived xenograft transdifferentiation models. Conclusions: These results identify common and divergent dysregulated pathways in NE and LUSC transdifferentiation, and nominate AKT as a therapeutic target to prevent the acquisition of resistance to EGFR-targeted therapies through histological transdifferentiation.