Latent space of a small genetic network: Geometry of dynamics and information.

TitleLatent space of a small genetic network: Geometry of dynamics and information.
Publication TypeJournal Article
Year of Publication2022
AuthorsSeyboldt, R, Lavoie, J, Henry, A, Vanaret, J, Petkova, MD, Gregor, T, François, P
JournalProc Natl Acad Sci U S A
Volume119
Issue26
Paginatione2113651119
Date Published2022 06 28
ISSN1091-6490
KeywordsAnimals, Drosophila, Drosophila Proteins, Gene Regulatory Networks, Models, Genetic, Neural Networks, Computer
Abstract

<p>The high-dimensional character of most biological systems presents genuine challenges for modeling and prediction. Here we propose a neural network-based approach for dimensionality reduction and analysis of biological gene expression data, using, as a case study, a well-known genetic network in the early embryo, the gap gene patterning system. We build an autoencoder compressing the dynamics of spatial gap gene expression into a two-dimensional (2D) latent map. The resulting 2D dynamics suggests an almost linear model, with a small bare set of essential interactions. Maternally defined spatial modes control gap genes positioning, without the classically assumed intricate set of repressive gap gene interactions. This, surprisingly, predicts minimal changes of neighboring gap domains when knocking out gap genes, consistent with previous observations. Latent space geometries in maternal mutants are also consistent with the existence of such spatial modes. Finally, we show how positional information is well defined and interpretable as a polar angle in latent space. Our work illustrates how optimization of small neural networks on medium-sized biological datasets is sufficiently informative to capture essential underlying mechanisms of network function.</p>

DOI10.1073/pnas.2113651119
Alternate JournalProc Natl Acad Sci U S A
PubMed ID35737842
PubMed Central IDPMC9245618
Grant ListU01 DK127429 / DK / NIDDK NIH HHS / United States
U01 DA047730 / DA / NIDA NIH HHS / United States
R01 GM097275 / GM / NIGMS NIH HHS / United States