Title: Detecting memory-related gene modules and causal regulations in snRNA-seq data by deep-learning

Abstract

To understand the detailed molecular mechanisms of memory formation in engram cellsis one of the most fundamental questions in neuroscience and computational system biology. Recent single-nucleus RNA-seq (snRNA-seq) techniques have allowed us to explore the sparsely activated engram ensembles, enabling access to the molecular mechanisms that underlie experience-dependent memory formation and consolidation. However, the absence of specific and powerful computational methods to detect memory-related genes (modules) and their regulatory relationships in the snRNA-seq datasets has strictly limited the analysis of underlying mechanisms and memory coding principles in mammalian brains. We have designed a deep-learning method to detect memory-related gene modules in snRNA-seq datasets, anddesigned a deep-learning method to infer causal regulatory relationships within gene modules. We applied them on snRNA-seq datasets of TRAP; Ai14 mice brains with fear memory and detected not only known memory-related genes, but also the modules and potential causal regulations. Our results provided novel regulations within an interesting module including Arc, Bdnf, Creb, Dusp1, Rgs4 and Btg2. Overall, our methodsprovide a series ofcomputational tools for processing snRNA-seq data and delineate the regulation mechanisms underlying remote memory formation. The detected gene modules may provide potential targets and strategies for treatment of memory loss in neuron degenerative diseases. The methods can also be used to process general scRNA-seq datasets that are generated from case versus control studies.