Signal Strength Aware Latent Spaces Reveal Molecularly Distinct Substructures within Human Kidney Tissue
Preprint
Abstract
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. We include a novel comparative-latent-traversal algorithm to translate latent findings back into the original measurement context. Demonstrating on imaging mass spectrometry-based molecular imaging of human kidney, the approach’s disentangling properties are shown to impress a latent space structure that separates signal strength from relative signal content, offering exceptional chemical insight. Our approach uncovers unexpected subdivisions within kidney proximal tubules, confirmed to be biological, and reveals hereto-unknown lipid species differentiating them. This confirms our workflow’s potential as an interpretation-and-hypothesis-generating discovery tool.Keywords
This publication has 29 references indexed in Scilit:
- Peak learning of mass spectrometry imaging data using artificial neural networksNature Communications, 2021
- Phospholipid effects on SGLT1-mediated glucose transport in rabbit ileum brush border membrane vesiclesBiochimica et Biophysica Acta (BBA) - Biomembranes, 2019
- Multivariate Density Estimation2015
- Randomized Approximation Methods for the Efficient Compression and Analysis of Hyperspectral DataAnalytical Chemistry, 2013
- Imaging mass spectrometryMass Spectrometry Reviews, 2007
- Principal Component Analysis for Special Types of Data2006
- Learning the parts of objects by non-negative matrix factorizationNature, 1999
- INTERACTION BETWEEN PROTEIN KINASE C AND SPHINGOMYELIN/CHOLESTEROLCell Biology International, 1999
- Molecular Imaging of Biological Samples: Localization of Peptides and Proteins Using MALDI-TOF MSAnalytical Chemistry, 1997
- Analysis of a complex of statistical variables into principal components.Journal of Educational Psychology, 1933