Speaker: Graham Heimberg, PhD, Principal Scientist, Genentech

Topic: Scalable cell search of human cell atlases via deep learning reveals commonalities across disease associated macrophages

Date: Monday, June 5, 2023

Time: 3:00 – 4:00 PM Eastern Time (United States and Canada)

Location: Countway Library, Lahey Room 518 (Harvard ID required)

Virtual: Zoom link

Abstract: Single-cell RNA-seq (scRNA-seq) studies have profiled over 100 million human cells across diseases, developmental stages, and perturbations to date. A singular view of this vast and growing expression landscape could help reveal novel associations between cell states and diseases, discover cell states in unexpected tissue contexts, and relate in vivo cells to in vitro models. However, these require a common, scalable representation of expression profiles, a general measure of their similarity, and an efficient way to query these data. Here, we present SCimilarity, a metric learning framework to learn and search a unified and interpretable representation that annotates cell types and instantaneously queries for a cell state across tens of millions of profiles. We demonstrate SCimilarity on a 22.7 million cell corpus assembled across 399 published scRNA-seq studies, showing accurate integration, annotation and querying. We experimentally validated SCimilarity by querying across tissues for a macrophage subset originally identified in interstitial lung disease, and showing that cells with similar profiles are found in other fibrotic diseases, tissues, and a 3D hydrogel system, which we then leveraged to yield this cell state in vitro. SCimilarity enables researchers to query for similar cellular states across the entire human body, providing a powerful tool for generating novel biological insights from the growing Human Cell Atlas.