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

Rabea Seyboldt (1) , Juliette Lavoie (1) , Adrien Henry (1) , Jules Vanaret (1, 2) , Mariela Petkova (3) , Thomas Gregor (4, 5) , Paul François (1)

1 McGill University = Université McGill [Montréal, Canada]
2 Phys-ENS - Laboratoire de Physique de l'ENS Lyon
3 Harvard University
4 Princeton University
5 Physique des fonctions biologiques / Physics of Biological Functions

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 Drosophila 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.

Mots clés: systems biology; developmental biology; machine learning; dimensionality reduction; Drosophila gap genes

Domaines: Biophysique; Biologie du développement; Génétique animale

Rabea Seyboldt, Juliette Lavoie, Adrien Henry, Jules Vanaret, Mariela Petkova, et al.. Latent space of a small genetic network: Geometry of dynamics and information. Proceedings of the National Academy of Sciences of the United States of America, 2022, 119 (26), pp.e2113651119. ⟨10.1073/pnas.2113651119⟩. ⟨pasteur-03896725⟩