 In this paper, the authors present an approach called PrismEXP for improving gene annotation predictions based on RNA-seq gene-gene co-expression data. They demonstrate its utility in multiple use cases and show how it can be used to enhance unsupervised machine learning methods to better understand the roles of understudied genes and proteins. PrismEXP is available as a web-based application, a Python package, and in a PyTor notebook. This article was authored by Alexander Lachman, Kaley A. Rizzo, Alon Bartow, and others.