GPLVM for Single-Cell RNA-seq Dimensionality Reduction
本文提出了一种改进的贝叶斯高斯过程潜在变量模型（BGPLVM），通过引入变分推断和核编码方法整合领域知识，提升单细胞数据分析的性能。实验表明该模型在性能上显著优于标准BGPLVM，并与SCVI相当。 2025-5-20 02:0:3 Author: hackernoon.com(查看原文) 阅读量:3 收藏

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

2 BACKGROUND

This section provides a concise introduction to existing BGPLVM models from the literature.

2.1 AMORTIZED STOCHASTIC VARIATIONAL BAYESIAN GPLVM

where the variational distributions are:

Authors:

(1) Sarah Zhao, Department of Statistics, Stanford University, ([email protected]);

(2) Aditya Ravuri, Department of Computer Science, University of Cambridge ([email protected]);

(3) Vidhi Lalchand, Eric and Wendy Schmidt Center, Broad Institute of MIT and Harvard ([email protected]);

(4) Neil D. Lawrence, Department of Computer Science, University of Cambridge ([email protected]).


文章来源: https://hackernoon.com/gplvm-for-single-cell-rna-seq-dimensionality-reduction?source=rss
如有侵权请联系:admin#unsafe.sh