CoCo-ST: Comparing and Contrasting Spatial Transcriptomics data sets using graph contrastive learning.

Traditional feature dimension reduction methods have been widely used to uncover biological patterns or structures within individual spatial transcriptomics data. However, these methods are designed to yield feature representations that emphasize patterns or structures with dominant high variance, such as the normal tissue spatial pattern in a precancer setting. Consequently, they may inadvertently overlook patterns of interest that are potentially masked by these high-variance structures. Herein we present our graph contrastive feature representation method called CoCo-ST (Comparing and Contrasting Spatial Transcriptomics) to overcome this limitation. By incorporating a background data set representing normal tissue, this approach enhances the identification of interesting patterns in a target data set representing precancerous tissue. Simultaneously, it mitigates the influence of dominant common patterns shared by the background and target data sets. This enables discerning biologically relevant features crucial for capturing tissue-specific patterns, a capability we showcased through the analysis of serial mouse precancerous lung tissue samples.

Joint multi-omics discriminant analysis with consistent representation learning using PANDA.

Integrative multi-omics analysis provides deeper insight and enables better and more realistic modeling of the underlying biology and causes of diseases than does single omics analysis. Although several integrative multi-omics analysis methods have been proposed and demonstrated promising results in integrating distinct omics datasets, inconsistent distribution of the different omics data, which is caused by technology variations, poses a challenge for paired integrative multi-omics methods. In addition, the existing discriminant analysis-based integrative methods do not effectively exploit correlation and consistent discriminant structures, necessitating a compromise between correlation and discrimination in using these methods. Herein we present PAN-omics Discriminant Analysis (PANDA), a joint discriminant analysis method that seeks omics-specific discriminant common spaces by jointly learning consistent discriminant latent representations for each omics. PANDA jointly maximizes between-class and minimizes within-class omics variations in a common space and simultaneously models the relationships among omics at the consistency representation and cross-omics correlation levels, overcoming the need for compromise between discrimination and correlation as with the existing integrative multi-omics methods. Because of the consistency representation learning incorporated into the objective function of PANDA, this method seeks a common discriminant space to minimize the differences in distributions among omics, can lead to a more robust latent representations than other methods, and is against the inconsistency of the different omics. We compared PANDA to 10 other state-of-the-art multi-omics data integration methods using both simulated and real-world multi-omics datasets and found that PANDA consistently outperformed them while providing meaningful discriminant latent representations. PANDA is implemented using both R and MATLAB, with codes available at https://github.com/WuLabMDA/PANDA.

Single-cell analysis of human lung epithelia reveals concomitant expression of the SARS-CoV-2 receptor ACE2 with multiple virus receptors and scavengers in alveolar type II cells

The novel coronavirus SARS-CoV-2 was identified as the causative agent of the ongoing pandemic COVID 19. COVID-19-associated deaths are mainly attributed to severe pneumonia and respiratory failure. Recent work demonstrated that SARS-CoV-2 binds to angiotensin converting enzyme 2 (ACE2) in the lung. To better understand ACE2 abundance and expression patterns in the lung we interrogated our in-house single-cell RNA-sequencing dataset containing 70,085 EPCAM+ lung epithelial cells from paired normal and lung adenocarcinoma tissues. Transcriptomic analysis revealed a diverse repertoire of airway lineages that included alveolar type I and II, bronchioalveolar, club/secretory, quiescent and proliferating basal, ciliated and malignant cells as well as rare populations such as ionocytes. While the fraction of lung epithelial cells expressing ACE2 was low (1.7% overall), alveolar type II (AT2, 2.2% ACE2+) cells exhibited highest levels of ACE2 expression among all cell subsets. Further analysis of the AT2 compartment (n = 27,235 cells) revealed a number of genes co-expressed with ACE2 that are important for lung pathobiology including those associated with chronic obstructive pulmonary disease (COPD; HHIP), pneumonia and infection (FGG and C4BPA) as well as malarial/bacterial (CD36) and viral (DMBT1) scavenging which, for the most part, were increased in smoker versus light or non-smoker cells. Notably, DMBT1 was highly expressed in AT2 cells relative to other lung epithelial subsets and its expression positively correlated with ACE2. We describe a population of ACE2-positive AT2 cells that co-express pathogen (including viral) receptors (e.g. DMBT1) with crucial roles in host defense thus comprising plausible phenotypic targets for treatment of COVID-19.