Scalable Amortized GPLVMs for Single Cell Transcriptomics Data

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhao, Sarah, Ravuri, Aditya, Lalchand, Vidhi, Lawrence, Neil D.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916237700759552
author Zhao, Sarah
Ravuri, Aditya
Lalchand, Vidhi
Lawrence, Neil D.
author_facet Zhao, Sarah
Ravuri, Aditya
Lalchand, Vidhi
Lawrence, Neil D.
contents 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. We 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 we demonstrate on an innate immunity dataset.
format Preprint
id arxiv_https___arxiv_org_abs_2405_03879
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Scalable Amortized GPLVMs for Single Cell Transcriptomics Data
Zhao, Sarah
Ravuri, Aditya
Lalchand, Vidhi
Lawrence, Neil D.
Machine Learning
Genomics
Applications
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. We 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 we demonstrate on an innate immunity dataset.
title Scalable Amortized GPLVMs for Single Cell Transcriptomics Data
topic Machine Learning
Genomics
Applications
url https://arxiv.org/abs/2405.03879