GenNet framework
interpretable deep learning for predicting phenotypes from genetic data
Arno van Hilten (Erasmus MC)
Steven A. Kushner (Erasmus MC)
Manfred Kayser (Erasmus MC)
M. Arfan Ikram (Erasmus MC)
Hieab H.H. Adams (Erasmus MC)
Caroline C.W. Klaver (Erasmus MC)
Wiro J. Niessen (Erasmus MC, TU Delft - ImPhys/Computational Imaging, TU Delft - ImPhys/Medical Imaging)
Gennady V. Roshchupkin (Erasmus MC)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
Applying deep learning in population genomics is challenging because of computational issues and lack of interpretable models. Here, we propose GenNet, a novel open-source deep learning framework for predicting phenotypes from genetic variants. In this framework, interpretable and memory-efficient neural network architectures are constructed by embedding biologically knowledge from public databases, resulting in neural networks that contain only biologically plausible connections. We applied the framework to seventeen phenotypes and found well-replicated genes such as HERC2 and OCA2 for hair and eye color, and novel genes such as ZNF773 and PCNT for schizophrenia. Additionally, the framework identified ubiquitin mediated proteolysis, endocrine system and viral infectious diseases as most predictive biological pathways for schizophrenia. GenNet is a freely available, end-to-end deep learning framework that allows researchers to develop and use interpretable neural networks to obtain novel insights into the genetic architecture of complex traits and diseases.
help_outline