Unveiling functional relationships between various molecular cell phenotypes from data using machine learning models is a key promise of multiomics. Existing methods either use flexible but hard-to-interpret models or simpler, misspecified models. VI-VS (Variational Inference for Variable Selection) balances flexibility and interpretability to identify relevant feature relationships in multiomic data. It uses deep generative models to identify conditionally dependent features, with false discovery rate control. VI-VS is available as an open-source Python package, providing a robust solution to identify features more likely representing genuine causal relationships.

The development of CD4+ T cells and CD8+ T cells in the thymus is critical to adaptive immunity and is widely studied as a model of lineage commitment. Recognition of self-peptide major histocompatibility complex (MHC) class I or II by the T cell antigen receptor (TCR) determines the CD8+ or CD4+ T cell lineage choice, respectively, but how distinct TCR signals drive transcriptional programs of lineage commitment remains largely unknown. Here we applied CITE-seq to measure RNA and surface proteins in thymocytes from wild-type and T cell lineage-restricted mice to generate a comprehensive timeline of cell states for each T cell lineage. These analyses identified a sequential process whereby all thymocytes initiate CD4+ T cell lineage differentiation during a first wave of TCR signaling, followed by a second TCR signaling wave that coincides with CD8+ T cell lineage specification. CITE-seq and pharmaceutical inhibition experiments implicated a TCR-calcineurin-NFAT-GATA3 axis in driving the CD4+ T cell fate. Our data provide a resource for understanding cell fate decisions and implicate a sequential selection process in guiding lineage choice.

Most spatial transcriptomics technologies are limited by their resolution, with spot sizes larger than that of a single cell. Although joint analysis with single-cell RNA sequencing can alleviate this problem, current methods are limited to assessing discrete cell types, revealing the proportion of cell types inside each spot. To identify continuous variation of the transcriptome within cells of the same type, we developed Deconvolution of Spatial Transcriptomics profiles using Variational Inference (DestVI). Using simulations, we demonstrate that DestVI outperforms existing methods for estimating gene expression for every cell type inside every spot. Applied to a study of infected lymph nodes and of a mouse tumor model, DestVI provides high-resolution, accurate spatial characterization of the cellular organization of these tissues and identifies cell-type-specific changes in gene expression between different tissue regions or between conditions. DestVI is available as part of the open-source software package scvi-tools ( https://scvi-tools.org ).