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.

通过改进的压缩随机变分贝叶斯 GPLVM 模型，我们成功实现了对单细胞 RNA-seq 数据的解释性降维分析，该模型在细胞类型聚类、细胞周期和批次信息的加入等方面表现出相当高的效果，并通过应用于先天免疫数据集验证了更可解释的潜在结构。

可扩展的分摊 GPLVMs 用于单细胞转录组学数据

Scalable Amortized GPLVMs for Single Cell Transcriptomics Data

Advances in high-throughput sequencing technology have led to significant
progress in measuring gene expressions at the single-cell level. The amount of
publicly available single-cell RNA-seq (scRNA-seq) data is already surpassing
50M records for humans with each record measuring 20,000 genes. This highlights
the need for unsupervised representation learning to fully ingest these data,
yet classical transformer architectures are prohibitive to train on such data
in terms of both computation and memory. To address this challenge, we propose
a novel asymmetric encoder-decoder transformer for scRNA-seq data, called
xTrimoGene$^\alpha$ (or xTrimoGene for short), which leverages the sparse
characteristic of the data to scale up the pre-training. This scalable design
of xTrimoGene reduces FLOPs by one to two orders of magnitude compared to
classical transformers while maintaining high accuracy, enabling us to train
the largest transformer models over the largest scRNA-seq dataset today. Our
experiments also show that the performance of xTrimoGene improves as we scale
up the model sizes, and it also leads to SOTA performance over various
downstream tasks, such as cell type annotation, perturb-seq effect prediction,
and drug combination prediction. xTrimoGene model is now available for use as a
service via the following link: this https URL

通过提出一种名为 xTrimoGene 的新型非对称编码器 - 解码器变压器来处理单细胞 RNA 测序数据，该模型利用数据的稀疏特性，在保持高准确性的同时减少了计算量，实现了在当前最大的单细胞 RNA 测序数据集上训练最大的变压器模型。实验证明，xTrimoGene 的性能随着模型规模的增加而提升，并在细胞类型注释、扰动测序效果预测和药物组合预测等多个任务上取得了 SOTA 性能。

xTrimoGene：高效可扩展的单细胞 RNA-Seq 数据表示学习器

xTrimoGene: An Efficient and Scalable Representation Learner for  Single-Cell RNA-Seq Data

The ability to measure the transcriptomes of single cells has only been
feasible for a few years, and is becoming an extremely popular assay. While
many types of analysis and questions can be answered using single cell
RNA-sequencing, a central focus is the ability to survey the diversity of cell
types within a sample. Unbiased and reproducible cataloging of distinct cell
types requires large numbers of cells. Technological developments and protocol
improvements have fuelled a consistent exponential increase in the numbers of
cells studied in single cell RNA-seq analyses. In this perspective, we will
highlight the key technological developments which have enabled this growth in
data.

本文综述了单细胞 RNA 测序技术的发展历程以及相关技术的改进，探讨了大规模单细胞转录组分析在细胞多样性鉴定中的应用与前景。