[论文解读] Conditionally Invariant Representation Learning for Disentangling Cellular Heterogeneity

Hananeh Aliee, Ferdinand Kapl+2 more|arXiv (Cornell University)|Jul 2, 2023

Cell Image Analysis Techniques被引用 8

一句话总结

本文提出了一种条件不变的深度生成模型，它将不变的生物信号与域特异性噪声解耦，以提高多域单细胞数据整合与解读。

ABSTRACT

This paper presents a novel approach that leverages domain variability to learn representations that are conditionally invariant to unwanted variability or distractors. Our approach identifies both spurious and invariant latent features necessary for achieving accurate reconstruction by placing distinct conditional priors on latent features. The invariant signals are disentangled from noise by enforcing independence which facilitates the construction of an interpretable model with a causal semantic. By exploiting the interplay between data domains and labels, our method simultaneously identifies invariant features and builds invariant predictors. We apply our method to grand biological challenges, such as data integration in single-cell genomics with the aim of capturing biological variations across datasets with many samples, obtained from different conditions or multiple laboratories. Our approach allows for the incorporation of specific biological mechanisms, including gene programs, disease states, or treatment conditions into the data integration process, bridging the gap between the theoretical assumptions and real biological applications. Specifically, the proposed approach helps to disentangle biological signals from data biases that are unrelated to the target task or the causal explanation of interest. Through extensive benchmarking using large-scale human hematopoiesis and human lung cancer data, we validate the superiority of our approach over existing methods and demonstrate that it can empower deeper insights into cellular heterogeneity and the identification of disease cell states.

研究动机与目标

• 推动学习表示，使其在多域单细胞数据集中将不变的生物信号与域特定噪声分离开来。
• 提出一种条件可识别的生成模型，能够识别伪相关因素和不变量潜在因素。
• 提供可识别性保证，并在大规模的造血过程与肺癌scRNA-seq数据上进行验证。

提出的方法

• 使用带有条件分解先验的变分自编码器，以实现潜在变量的可识别性。
• 将潜在空间分成不变（Z_I）和伪相关（Z_S）分量，以捕捉稳定信息与域可变信息。
• 强加Z_I与Z_S之间的独立性，以实现重建的同时分离不变量特征。
• 加入辅助样本信息（d）和环境（e），以建模依赖关系并引导解耦。
• 目标是一个不变预测器，利用Z_I来预测标签Y，并在各环境中具有良好表现。
• 与NF-iVAE及其他不变量学习方法进行对比，以基准化可识别性和数据整合能力。

Figure 1: Data integration using different methods. Shown are the UMAP representations of single cells colored by samples and cell types (bottom right). inVAE preserves biological variations between donors while mixing similar cells with technical noise (s1d1 and s2d1), whereas other methods either

实验结果

研究问题

• RQ1 如何在多域单细胞数据中将潜在表示划分为不变量和非不变量成分？
• RQ2 在保留跨环境预测性能的同时，条件可识别的VAE是否能够将生物信号与技术或域驱动的噪声分离？
• RQ3 哪些先验和假设能够实现可识别性并在跨数据集的单细胞基因组学中具有实际适用性？

主要发现

• 所提出的方法在条件VAE框架中同时识别不变量和伪相关的潜在变量。
• 该模型在简单变换和潜在变量置换的情况下具有可识别性。
• 在大规模的人类造血过程和人类肺癌scRNA-seq数据（49个样本，覆盖两种癌症类型）上的评估显示，数据整合和细胞状态分析得到改进（文本所述）。
• 该方法能够将生物机制如基因程序、疾病状态或治疗条件等纳入数据整合过程。
• 该方法在单细胞数据整合和细胞类型注释方面，优于现有的不变量与可识别深度生成模型。

Figure 2: The data generating process.