A probabilistic gene expression barcode for annotation of cell types from single-cell RNA-seq data

Baseline immune state and T-cell clonal kinetics are associated with durable response to CAR-T therapy in large B-cell lymphoma

ABSTRACT

Engineered cellular therapy with CD19-targeting chimeric antigen receptor T cells (CAR-Ts) has revolutionized outcomes for patients with relapsed/refractory large B-cell lymphoma (LBCL), but the cellular and molecular features associated with response remain largely unresolved. We analyzed serial peripheral blood samples ranging from the day of apheresis (day -28/baseline) to 28 days after CAR-T infusion from 50 patients with LBCL treated with axicabtagene ciloleucel by integrating single-cell RNA and T-cell receptor sequencing, flow cytometry, and mass cytometry to characterize features associated with response to CAR-T. Pretreatment patient characteristics associated with response included the presence of B cells and increased absolute lymphocyte count to absolute monocyte count ratio (ALC/AMC). Infusion products from responders were enriched for clonally expanded, highly activated CD8+ T cells. We expanded these observations to 99 patients from the ZUMA-1 cohort and identified a subset of patients with elevated baseline B cells, 80% of whom were complete responders. We integrated B-cell proportion ≥0.5% and ALC/AMC ≥1.2 into a 2-factor predictive model and applied this model to the ZUMA-1 cohort. Estimated progression-free survival at 1 year in patients meeting 1 or both criteria was 65% vs 31% for patients meeting neither criterion. Our results suggest that patients' immunologic state at baseline affects the likelihood of response to CAR-T through both modulation of the T-cell apheresis product composition and promoting a more favorable circulating immune compartment before therapy. These baseline immunologic features, measured readily in the clinical setting before CAR-T, can be applied to predict response to therapy.

CellCover Captures Neural Stem Cell Progression in Mammalian Neocortical Development

Definition of cell classes across the tissues of living organisms is central in the analysis of growing atlases of single-cell RNA sequencing (scRNA-seq) data across biomedicine. Marker genes for cell classes are most often defined by differential expression (DE) methods that serially assess individual genes across landscapes of diverse cells. This serial approach has been extremely useful, but is limited because it ignores possible redundancy or complementarity across genes that can only be captured by analyzing multiple genes simultaneously. We aim to identify discriminating panels of genes. To efficiently explore the vast space of possible marker panels, leverage the large number of cells often sequenced, and overcome zero-inflation in scRNA-seq data, we propose viewing gene panel selection as a variation of the "minimal set-covering problem" in combinatorial optimization. We show that this new method, CellCover, captures cell-class-specific signals in the developing mouse neocortex that are distinct from those defined by DE methods. Transfer learning experiments across mouse, primate, and human data demonstrate that CellCover identifies markers of conserved cell classes in neurogenesis, as well as temporal progression in both progenitors and neurons. Exploring markers of human outer radial glia (oRG, or basal RG) across mammals, we show that transcriptomic elements of this key cell type in the expansion of the human cortex appeared in gliogenic precursors of the rodent before the full program emerged in the primate lineage. We have assembled the public datasets we use in this report at NeMO analytics where the expression of individual genes {NeMO Individual Genes} and marker gene panels can be freely explored {NeMO: Telley 3 Sets Covering Panels}, {NeMO: Telley 12 Sets Covering Panels}, and {NeMO: Sorted Brain Cell Covering Panels}. CellCover is available in {CellCover R} and {CellCover Python}.

SIMS: A deep-learning label transfer tool for single-cell RNA sequencing analysis

Cell atlases serve as vital references for automating cell labeling in new samples, yet existing classification algorithms struggle with accuracy. Here we introduce SIMS (scalable, interpretable machine learning for single cell), a low-code data-efficient pipeline for single-cell RNA classification. We benchmark SIMS against datasets from different tissues and species. We demonstrate SIMS's efficacy in classifying cells in the brain, achieving high accuracy even with small training sets (<3,500 cells) and across different samples. SIMS accurately predicts neuronal subtypes in the developing brain, shedding light on genetic changes during neuronal differentiation and postmitotic fate refinement. Finally, we apply SIMS to single-cell RNA datasets of cortical organoids to predict cell identities and uncover genetic variations between cell lines. SIMS identifies cell-line differences and misannotated cell lineages in human cortical organoids derived from different pluripotent stem cell lines. Altogether, we show that SIMS is a versatile and robust tool for cell-type classification from single-cell datasets.

Unraveling Neuronal Identities Using SIMS: A Deep Learning Label Transfer Tool for Single-Cell RNA Sequencing Analysis

Large single-cell RNA datasets have contributed to unprecedented biological insight. Often, these take the form of cell atlases and serve as a reference for automating cell labeling of newly sequenced samples. Yet, classification algorithms have lacked the capacity to accurately annotate cells, particularly in complex datasets. Here we present SIMS (Scalable, Interpretable Machine Learning for Single-Cell), an end-to-end data-efficient machine learning pipeline for discrete classification of single-cell data that can be applied to new datasets with minimal coding. We benchmarked SIMS against common single-cell label transfer tools and demonstrated that it performs as well or better than state of the art algorithms. We then use SIMS to classify cells in one of the most complex tissues: the brain. We show that SIMS classifies cells of the adult cerebral cortex and hippocampus at a remarkably high accuracy. This accuracy is maintained in trans-sample label transfers of the adult human cerebral cortex. We then apply SIMS to classify cells in the developing brain and demonstrate a high level of accuracy at predicting neuronal subtypes, even in periods of fate refinement, shedding light on genetic changes affecting specific cell types across development. Finally, we apply SIMS to single cell datasets of cortical organoids to predict cell identities and unveil genetic variations between cell lines. SIMS identifies cell-line differences and misannotated cell lineages in human cortical organoids derived from different pluripotent stem cell lines. When cell types are obscured by stress signals, label transfer from primary tissue improves the accuracy of cortical organoid annotations, serving as a reliable ground truth. Altogether, we show that SIMS is a versatile and robust tool for cell-type classification from single-cell datasets.

Immune cell type signature discovery and random forest classification for analysis of single cell gene expression datasets

Background

Robust immune cell gene expression signatures are central to the analysis of single cell studies. Nearly all known sets of immune cell signatures have been derived by making use of only single gene expression datasets. Utilizing the power of multiple integrated datasets could lead to high-quality immune cell signatures which could be used as superior inputs to machine learning-based cell type classification approaches.

Results

We established a novel workflow for the discovery of immune cell type signatures based primarily on gene-versus-gene expression similarity. It leverages multiple datasets, here seven single cell expression datasets from six different cancer types and resulted in eleven immune cell type-specific gene expression signatures. We used these to train random forest classifiers for immune cell type assignment for single-cell RNA-seq datasets. We obtained similar or better prediction results compared to commonly used methods for cell type assignment in independent benchmarking datasets. Our gene signature set yields higher prediction scores than other published immune cell type gene sets in random forest-based cell type classification. We further demonstrate how our approach helps to avoid bias in downstream statistical analyses by re-analysis of a published IFN stimulation experiment.

Discussion and conclusion

We demonstrated the quality of our immune cell signatures and their strong performance in a random forest-based cell typing approach. We argue that classifying cells based on our comparably slim sets of genes accompanied by a random forest-based approach not only matches or outperforms widely used published approaches. It also facilitates unbiased downstream statistical analyses of differential gene expression between cell types for significantly more genes compared to previous cell classification algorithms.

Significance analysis for clustering with single-cell RNA-sequencing data

Unsupervised clustering of single-cell RNA-sequencing data enables the identification of distinct cell populations. However, the most widely used clustering algorithms are heuristic and do not formally account for statistical uncertainty. We find that not addressing known sources of variability in a statistically rigorous manner can lead to overconfidence in the discovery of novel cell types. Here we extend a previous method, significance of hierarchical clustering, to propose a model-based hypothesis testing approach that incorporates significance analysis into the clustering algorithm and permits statistical evaluation of clusters as distinct cell populations. We also adapt this approach to permit statistical assessment on the clusters reported by any algorithm. Finally, we extend these approaches to account for batch structure. We benchmarked our approach against popular clustering workflows, demonstrating improved performance. To show practical utility, we applied our approach to the Human Lung Cell Atlas and an atlas of the mouse cerebellar cortex, identifying several cases of over-clustering and recapitulating experimentally validated cell type definitions.

Predictive and robust gene selection for spatial transcriptomics

A prominent trend in single-cell transcriptomics is providing spatial context alongside a characterization of each cell's molecular state. This typically requires targeting an a priori selection of genes, often covering less than 1% of the genome, and a key question is how to optimally determine the small gene panel. We address this challenge by introducing a flexible deep learning framework, PERSIST, to identify informative gene targets for spatial transcriptomics studies by leveraging reference scRNA-seq data. Using datasets spanning different brain regions, species, and scRNA-seq technologies, we show that PERSIST reliably identifies panels that provide more accurate prediction of the genome-wide expression profile, thereby capturing more information with fewer genes. PERSIST can be adapted to specific biological goals, and we demonstrate that PERSIST's binarization of gene expression levels enables models trained on scRNA-seq data to generalize with to spatial transcriptomics data, despite the complex shift between these technologies.