Machine learning approaches to identify sleep genes

Abstract

Genetics impacts sleep, yet, the molecular mechanisms underlying sleep regulation remain elusive. We built machine learning (ML) models to predict genes based on their similarity to known sleep genes. Our predictions fit with prior knowledge of sleep regulation and also identify several key genes/pathways to pursue in follow-up studies. We tested one of our findings, the NF-κB pathway, and showed that its genetic alteration affects sleep duration in mice. Our study highlights the power of ML to integrate prior knowledge and genome-wide data to study genetic regulation of sleep and other complex behaviors.

The NFκBDifis required for behavioral and molecular correlates of sleep homeostasis inDrosophila

“…A connection between sleep and the immune system has long been implicated [1][2][3] , but the nature of this connection is not well understood. Despite its central role in inflammation and illness 4,5 , very few genetic studies in rodent models have investigated a function of specific NFκB genes in daily sleep 6,7 . To address this gap, we have previously explored the role of NFκB in sleep using the Drosophila genetic model 8,9 , where NFκB is also central to innate immune function 5,10,11 .…”