Sparse bottleneck neural networks for exploratory non-linear visualization of Patch-seq data. (arXiv:2006.10411v3 [cs.LG] UPDATED)

Patch-seq, a recently developed experimental technique, allows
neuroscientists to obtain transcriptomic and electrophysiological information
from the same neurons. Efficiently analyzing and visualizing such paired
multivariate data in order to extract biologically meaningful interpretations
has, however, remained a challenge. Here, we use sparse deep neural networks
with and without a two-dimensional bottleneck to predict electrophysiological
features from the transcriptomic ones using a group lasso penalty, yielding
concise and biologically interpretable two-dimensional visualizations. In two
large example data sets, this visualization reveals …

arxiv data networks neural networks non-linear visualization