Signal Strength Aware Latent Spaces Reveal Molecularly Distinct Substructures within Human Kidney Tissue

As datasets grow increasingly high-dimensional and complex, distinguishing a condensed set of interpretable underlying factors becomes essential. In spatial omics, for example, hundreds to thousands of molecular features per observation promise unprecedented biological insight. However, without meaningful latent representations, that potential remains markedly untapped.

We propose a new approach based on the beta-variational autoencoder and kernel density estimation to dissect data along independent, uncertainty-aware, and interpretable (yet non-linear) latent axes. A comparative-latent-traversal algorithm translates latent findings back into the original measurement context. Applied to imaging mass spectrometry of human kidney, the approach separates signal strength from relative signal content and uncovers previously unrecognized subdivisions within kidney proximal tubules.