The gene signatures of Alzheimer's Disease (AD) brains reflect an output of a complex interplay of genetic, epigenetic, epi-transcriptomic, and post-transcriptional regulations. To identify the most significant factor that shapes the AD brain signature, we developed a machine learning model (DEcode-tree) to integrate cellular and molecular factors explaining differential gene expression in AD. Our model indicates that YTHDF proteins, the canonical readers of N6-methyladenosine RNA modification (m6A), are the most influential predictors of the AD brain signature. We then show that protein modules containing YTHDFs are downregulated in human AD brains, and knocking out YTHDFs in iPSC-derived neural cells recapitulates the AD brain gene signature in vitro . Furthermore, eCLIP-seq analysis revealed that YTHDF proteins influence AD signatures through both m6A-dependent and independent pathways. These results indicate the central role of YTHDF proteins in shaping the gene signature of AD brains.