美国匹兹堡大学Jishnu Das、Robert A. Lafyatis、Alok V. Joglekar和Amanda C. Poholek课题组合作的一项最新研究建立了跨生物领域重要潜在交互因素发现与探索（SLIDE）的技术。该项研究成果发表在2024年2月19日出版的《自然-方法学》上。

研究人员建立了重要潜在因素交互发现与探索技术，这是一种卓越的可解释的机器学习技术，用于从高维omic数据集中识别潜在的重要交互因素。SLIDE对数据生成机制不做任何假设，为潜在因素/相应推论的可识别性提供理论保证，并严格控制错误的发现率。

利用SLIDE分析单细胞和空间omic数据集，研究发现了一系列重要的潜在分子、细胞和生物体表型交互因素。SLIDE的表现至少优于/胜过其他潜在因子发现的各种最先进的方法。更重要的是，它提供了其他方法无法提供的预测外生物推断。因此，SLIDE是利用现代多组学数据集进行生物发现的多功能引擎。

研究人员表示，现代多组学技术可以生成深度多尺度剖面图。然而，数据模式的差异、数据的多重共线性以及大量不相关的特征，使得高维omic数据集的分析和整合具有一定挑战性。

附：英文原文

Title: SLIDE: Significant Latent Factor Interaction Discovery and Exploration across biological domains

Author: Rahimikollu, Javad, Xiao, Hanxi, Rosengart, AnnaElaine, Rosen, Aaron B. I., Tabib, Tracy, Zdinak, Paul M., He, Kun, Bing, Xin, Bunea, Florentina, Wegkamp, Marten, Poholek, Amanda C., Joglekar, Alok V., Lafyatis, Robert A., Das, Jishnu

Issue&Volume: 2024-02-19

Abstract: Modern multiomic technologies can generate deep multiscale profiles. However, differences in data modalities, multicollinearity of the data, and large numbers of irrelevant features make analyses and integration of high-dimensional omic datasets challenging. Here we present Significant Latent Factor Interaction Discovery and Exploration (SLIDE), a first-in-class interpretable machine learning technique for identifying significant interacting latent factors underlying outcomes of interest from high-dimensional omic datasets. SLIDE makes no assumptions regarding data-generating mechanisms, comes with theoretical guarantees regarding identifiability of the latent factors/corresponding inference, and has rigorous false discovery rate control. Using SLIDE on single-cell and spatial omic datasets, we uncovered significant interacting latent factors underlying a range of molecular, cellular and organismal phenotypes. SLIDE outperforms/performs at least as well as a wide range of state-of-the-art approaches, including other latent factor approaches. More importantly, it provides biological inference beyond prediction that other methods do not afford. Thus, SLIDE is a versatile engine for biological discovery from modern multiomic datasets.

DOI: 10.1038/s41592-024-02175-z

Source: https://www.nature.com/articles/s41592-024-02175-z