MorphVAE: Generating Neural Morphologies from 3D-Walks using a Variational Autoencoder with Spherical Latent Space

Abstract

For the past century, the anatomy of a neuron has been considered one of its defining features: The shape of a neuron`s dendrites and axon fundamentally determines what other neurons it can connect to. These neurites have been described using mathematical tools e.g. in the context of cell type classification, but generative models of these structures have only rarely been proposed and are often computationally inefficient. Here we propose MORPHVAE, a sequence-to-sequence variational autoencoder with spherical latent space as a generative model for neural morphologies. The model operates on walks within the tree structure of a neuron and can incorporate expert annotations on a subset of the data using semi-supervised learning. We develop our model on artificially generated toy data and evaluate its performance on dendrites of excitatory cells and axons of inhibitory cells of mouse motor cortex (M1) and dendrites of retinal ganglion cells. We show that the learned latent feature space allows for better cell type discrimination than other commonly used features. By sampling new walks from the latent space we can easily construct new morphologies with a specified degree of similarity to their reference neuron, providing an efficient generative model for neural morphologies.

Unified classification of mouse retinal ganglion cells using function, morphology, and gene expression

“…Finally, our morphological alignment to the Eyewire dataset was not validated by a classification algorithm. The limited number of cells in both datasets and their methodological differences made such a morphology classifier impractical, but with additional data an RGC morphology classifier is a goal ( Laturnus and Berens, 2021 ). Since our functional classification algorithm produces a posterior probability for each class, functional and morphological information could be incorporated seamlessly into a single prediction.…”

scConfluence : single-cell diagonal integration with regularized Inverse Optimal Transport on weakly connected features

“…At the same time, morphological heterogeneity could be detected in some of these populations. For example, as shown in Figure 6C, excitatory neurons (CT, ET, IT) are organized into three morphological categories: "tufted", "untufted" and "other" based on the visual inspection of their apical dendrites 69 . Most of the CT neurons are untufted and other, ET neurons are mainly tufted, finally, IT neurons result in a continuum progression from tufted to untufted.…”