Biologically informed deep learning to infer gene program activity in single cells (preprint)

The increasing availability of large-scale single-cell datasets has enabled the detailed description of cell states across multiple biological conditions and perturbations. In parallel, recent advances in unsupervised machine learning, particularly in transfer learning, have enabled fast and scalable mapping of these new single-cell datasets onto reference atlases. The resulting large-scale machine learning models however often have millions of parameters, rendering interpretation of the newly mapped datasets challenging. Here, we propose expiMap, a deep learning model that enables interpretable reference mapping using biologically understandable entities, such as curated sets of genes and gene programs. The key concept is the substitution of the uninterpretable nodes in an autoencoder’s bottleneck by labeled nodes mapping to interpretable lists of genes, such as gene ontologies, biological pathways, or curated gene sets, for which activities are learned as constraints during reconstruction. This is enabled by the incorporation of predefined gene programs into the reference model, and at the same time allowing the model to learn de novo new programs and refine existing programs during reference mapping. We show that the model retains similar integration performance as existing methods while providing a biologically interpretable framework for understanding cellular behavior. We demonstrate the capabilities of expiMap by applying it to 15 datasets encompassing five different tissues and species. The interpretable nature of the mapping revealed unreported associations between interferon signaling via the RIG-I/MDA5 and GPCRs pathways, with differential behavior in CD8 + T cells and CD14 + monocytes in severe COVID-19, as well as the role of annexins in the cellular communications between lymphoid and myeloid compartments for explaining patient response to the applied drugs. Finally, expiMap enabled the direct comparison of a diverse set of pancreatic beta cells from multiple studies where we observed a strong, previously unreported correlation between the unfolded protein response and asparagine N-linked glycosylation. Altogether, expiMap enables the interpretable mapping of single cell transcriptome data sets across cohorts, disease states and other perturbations.

Hypercapnia limits β-catenin-mediated alveolar type 2 cell progenitor function by altering Wnt production from adjacent fibroblasts (preprint)

ABSTRACT Persistent symptoms and radiographic abnormalities suggestive of failed lung repair are among the most common symptoms in patients with COVID-19 after hospital discharge. In mechanically ventilated patients with ARDS secondary to SARS-CoV-2 pneumonia, low tidal volumes to reduce ventilator-induced lung injury necessarily elevate blood CO 2 levels, often leading to hypercapnia. The role of hypercapnia on lung repair after injury is not completely understood. Here, we show that hypercapnia limits β-catenin signaling in alveolar type 2 (AT2) cells, leading to reduced proliferative capacity. Hypercapnia alters expression of major Wnts in PDGFRa+-fibroblasts from those maintaining AT2 progenitor activity and towards those that antagonize β-catenin signaling and limit progenitor function. Activation of β-catenin signaling in AT2 cells, rescues the inhibition AT2 proliferation induced by hypercapnia. Inhibition of AT2 proliferation in hypercapnic patients may contribute to impaired lung repair after injury, preventing sealing of the epithelial barrier, increasing lung flooding, ventilator dependency and mortality.

Query to reference single-cell integration with transfer learning (preprint)

Large single-cell atlases are now routinely generated with the aim of serving as reference to analyse future smaller-scale studies. Yet, learning from reference data is complicated by batch effects between datasets, limited availability of computational resources, and sharing restrictions on raw data. Leveraging advances in machine learning, we propose a deep learning strategy to map query datasets on top of a reference called single-cell architectural surgery (scArches, https://github.com/theislab/scarches ). It uses transfer learning and parameter optimization to enable efficient, decentralized, iterative reference building, and the contextualization of new datasets with existing references without sharing raw data. Using examples from mouse brain, pancreas, and whole organism atlases, we showcase that scArches preserves nuanced biological state information while removing batch effects in the data, despite using four orders of magnitude fewer parameters compared to de novo integration. To demonstrate mapping disease variation, we show that scArches preserves detailed COVID-19 disease variation upon reference mapping, enabling discovery of new cell identities that are unseen during training. We envision our method to facilitate collaborative projects by enabling the iterative construction, updating, sharing, and efficient use of reference atlases.