Ablation Study Results: Latent Space Metrics for scRNA-seq Models

by AmortizeMay 22nd, 2025

Too Long; Didn't Read

Explore comprehensive latent space metrics from experiments on a simulated single-cell RNA-seq dataset, providing insights into various model modifications.

Coin Mentioned

Table of Links

Abstract and 1. Introduction

2. Background

2.1 Amortized Stochastic Variational Bayesian GPLVM

2.2 Encoding Domain Knowledge through Kernels

3. Our Model and Pre-Processing and Likelihood

3.2 Encoder

4. Results and Discussion and 4.1 Each Component is Crucial to Modifies Model Performance

4.2 Modified Model achieves Significant Improvements over Standard Bayesian GPLVM and is Comparable to SCVI

4.3 Consistency of Latent Space with Biological Factors

4. Conclusion, Acknowledgement, and References

A. Baseline Models

B. Experiment Details

C. Latent Space Metrics

D. Detailed Metrics

D DETAILED METRICS

We report the latent metrics for the first two experiments, taking the mean and standard deviation across trained models from three different seeds. Blue columns correspond to batch metrics and Green columns correspond to cell-type metrics.

D.1 ABLATION STUDY

D.2 BENCHMARKING

This paper is available on arxiv under CC BY-SA 4.0 DEED license.

Authors:

(1) Sarah Zhao, Department of Statistics, Stanford University, (smxzhao@stanford.edu);

(2) Aditya Ravuri, Department of Computer Science, University of Cambridge (ar847@cam.ac.uk);

(3) Vidhi Lalchand, Eric and Wendy Schmidt Center, Broad Institute of MIT and Harvard (vidrl@mit.edu);

(4) Neil D. Lawrence, Department of Computer Science, University of Cambridge (ndl21@cam.ac.uk).

Ablation Study Results: Latent Space Metrics for scRNA-seq Models