Back to publications
Scalable Amortized GPLVMs for Single Cell Transcriptomics Data
Paper Details
Published: 2024/05/06
DOI: 10.48550/arXiv.2405.03879
ARXIV ID: 2405.03879v1
Dimensionality reduction is crucial for analyzing large-scale single-cell RNA-seq data. Gaussian Process Latent Variable Models (GPLVMs) offer an interpretable dimensionality reduction method, but current scalable models lack effectiveness in clustering cell types. The authors introduce an improved model, the amortized stochastic variational Bayesian GPLVM (BGPLVM), tailored for single-cell RNA-seq with specialized encoder, kernel, and likelihood designs. This model matches the performance of the leading single-cell variational inference (scVI) approach on synthetic and real-world COVID datasets and effectively incorporates cell-cycle and batch information to reveal more interpretable latent structures as demonstrated on an innate immunity dataset.
