Deep generative modeling of sample-level heterogeneity in single-cell genomics

Boyeau, Pierre; Hong, Justin; Gayoso, Adam; Jordan, Michael I.; Azizi, Elham; Yosef, Nir

doi:10.1101/2022.10.04.510898

Cited by 14 publications

(17 citation statements)

References 110 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Inspired by successful implementations of deep generative models in single-cell omics analysis (scvi-tools 20 , scvi 21 , totalVI 22 , scArches 23 , trVAE 24 , scANVI 25 , MrVI 26 ), Starfysh jointly models ST and histology as data observed from a shared low-dimensional latent representation while incorporating anchors as priors ( Fig. 1c; Supplementary Fig.…”

Section: Resultsmentioning

confidence: 99%

“…Deep generative models parameterized by neural networks have proven effective in analyzing single-cell RNA expression data (scvi-tools 20 , scvi 21 , totalVI 22 , scArches 23 , trVAE 24 , scANVI 25 , MrVI 26 , etc). However, the presence of multiple cell types in each spot in ST data makes it difficult for these models to disentangle the cell-type-specific features.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Starfysh reveals heterogeneous spatial dynamics in the breast tumor microenvironment

Jin

Nazaret

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Spatially-resolved gene expression profiling provides valuable insight into tissue organization and cell-cell crosstalk; however, spatial transcriptomics (ST) lacks single-cell resolution. Current ST analysis methods require single-cell RNA sequencing data as a reference for a rigorous interpretation of cell states and do not utilize associated histology images. Significant sample variation further complicates the integration of ST datasets, which is essential for identifying commonalities across tissues or altered cellular wiring in disease. Here, we present Starfysh, the first comprehensive computational toolbox for joint modeling of ST and histology data, dissection of refined cell states, and systematic integration of multiple ST datasets from complex tissues. Starfysh uses an auxiliary deep generative model that incorporates archetypal analysis and any known cell state markers to avoid the need for a single-cell-resolution reference in characterizing known or novel tissue-specific cell states. Additionally, Starfysh improves the characterization of spatial dynamics in complex tissues by leveraging histology images and enables the comparison of niches as spatial "hubs" across tissues. Integrative analysis of primary estrogen receptor-positive (ER+) breast cancer, triple-negative breast cancer (TNBC), and metaplastic breast cancer (MBC) tumors using Starfysh led to the identification of heterogeneous patient- and disease-specific hubs as well as a shared stromal hub with varying spatial orientation. Our results show the ability to delineate the spatial co-evolution of tumor and immune cell states and their crosstalk underlying intratumoral heterogeneity in TNBC and revealed metabolic reprogramming shaping immunosuppressive hubs in aggressive MBC. Starfysh is publicly available (https://github.com/azizilab/starfysh).

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Starfysh reveals heterogeneous spatial dynamics in the breast tumor microenvironment

Jin

Nazaret

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…These limitations, however, are shared across current tissue-centric tailored methods. In contrast, models based on generative deep learning (De Donno et al , 2022; Boyeau et al , 2022) and the Wasserstein metric (Joodaki et al , 2022; Chen et al , 2020) can take advantage of single-cell measurements to estimate sample-level heterogeneity, but the interpretability of their estimated latent space is limited in comparison to the MOFA models, where features and cell-types can be associated with each factor.…”

Section: Discussionmentioning

confidence: 99%

Multicellular factor analysis of single-cell data for a tissue-centric understanding of disease

Flores

Lanzer

Dimitrov

et al. 2023

Preprint

View full text Add to dashboard Cite

Single-cell atlases across conditions are essential in the characterization of human disease. In these complex experimental designs, patient samples are profiled across distinct cell-types and clinical conditions to describe disease processes at the cellular level. However, most of the current analysis tools are limited to pairwise cross-condition comparisons, disregarding the multicellular nature of disease processes and the effects of other biological and technical factors in the variation of gene expression. Here we propose a computational framework for an unsupervised analysis of samples from cross-condition single-cell atlases and for the identification of multicellular programs associated with disease. Our strategy, that repurposes multi-omics factor analysis, incorporates the variation of patient samples across cell-types and enables the joint analysis of multiple patient cohorts, facilitating integration of atlases. We applied our analysis to a collection of acute and chronic human heart failure single-cell datasets and described multicellular processes of cardiac remodeling that were conserved in independent spatial and bulk transcriptomics datasets. In sum, our framework serves as an exploratory tool for unsupervised analysis of cross-condition single-cell atlas and allows for the integration of the measurements of patient cohorts across distinct data modalities, facilitating the generation of comprehensive tissue-centric understanding of disease.

show abstract

“…While here we applied a naive approach to define sample similarity (suppl. figure 7A), novel methods to model sample-level heterogeneity in scRNA-seq data are being explored (Chen et al ., 2020; Boyeau et al ., 2022; Mitchel et al ., 2022). These could improve the matching of disease samples to optimal controls, and provide new insights into which technical and demographic variables are likely to affect disease-to-healthy comparisons.…”

Section: Discussionmentioning

confidence: 99%

Precise identification of cell states altered in disease with healthy single-cell references

Dann

Teichmann

Marioni

2022

Preprint

View full text Add to dashboard Cite

Single cell genomics is a powerful tool to distinguish altered cell states in disease tissue samples, through joint analysis with healthy reference datasets. Collections of data from healthy individuals are being integrated in cell atlases that provide a comprehensive view of cellular phenotypes in a tissue. However, it remains unclear whether atlas datasets are suitable references for disease-state identification, or whether matched control samples should be employed, to minimise false discoveries driven by biological and technical confounders. Here we quantitatively compare the use of atlas and control datasets as references for identification of disease-associated cell states, on simulations and real disease scRNA-seq datasets. We find that reliance on a single type of reference dataset introduces false positives. Conversely, using an atlas dataset as reference for latent space learning followed by differential analysis against a matched control dataset leads to precise identification of disease-associated cell states. We show that, when an atlas dataset is available, it is possible to reduce the number of control samples without increasing the rate of false discoveries. Using a cell atlas of blood cells from 12 studies to contextualise data from a case-control COVID-19 cohort, we sensitively detect cell states associated with infection, and distinguish heterogeneous pathological cell states associated with distinct clinical severities. Our analysis provides guiding principles for design of disease cohort studies and efficient use of cell atlases within the Human Cell Atlas.

show abstract

Deep generative modeling of sample-level heterogeneity in single-cell genomics

Cited by 14 publications

References 110 publications

Starfysh reveals heterogeneous spatial dynamics in the breast tumor microenvironment

Starfysh reveals heterogeneous spatial dynamics in the breast tumor microenvironment

Multicellular factor analysis of single-cell data for a tissue-centric understanding of disease

Precise identification of cell states altered in disease with healthy single-cell references

Contact Info

Product

Resources

About