Biology subjects

Jordan, M. I.

Publications and source records attributed to Jordan, M. I..

10 recordsLinked to original sources

bioRxiv2026

Mitigating Bias in Spatial Transcriptomic Pipelines via Human Feedback

Biological discovery from experimental data, particularly large-scale assays, requires extensive preprocessing, during which raw outputs (e.g., images, sequences) are processed into structured forms that are more amenable to analysis. While statistical methods for such processed data are at the core of computational biology, the problem of coping with uncertainties introduced during preprocessing is a significant and underexplored issue. We address this issue in the context of differential expression analysis in spatial transcriptomics, which depends on a series of preprocessing steps, including demarcation of cell regions (segmentation), quantification of gene expression in cells, and cell-type annotation. We introduce Corrected Spatial Differential Expression (CSDE), a method that builds on Prediction-Powered Inference to leverage a small set of expert-validated data points (cells) to account for uncertainty due to preprocessing errors. Using two case studies, we demonstrate that CSDE produces more reliable and calibrated estimates of differential expression compared to the prevalent approach that neglects the impact of preprocessing. CSDE incorporates an efficient workflow to generate the required expert-annotated data, and is available as open-source at https://github.com/YosefLab/CSDE.

bioinformatics↗

bioRxiv2022

An Empirical Bayes Method for Differential Expression Analysis of Single Cells with Deep Generative Models

AO_SCPLOWBSTRACTC_SCPLOWDetecting differentially expressed genes is important for characterizing subpopulations of cells. In scRNA-seq data, however, nuisance variation due to technical factors like sequencing depth and RNA capture efficiency obscures the underlying biological signal. Deep generative models have been extensively applied to scRNA-seq data, with a special focus on embedding cells into a low-dimensional latent space and correcting for batch effects. However, little attention has been given to the problem of utilizing the uncertainty from the deep generative model for differential expression. Furthermore, the existing approaches do not allow controlling for the effect size or the false discovery rate. Here, we present lvm-DE, a generic Bayesian approach for performing differential expression from using a fitted deep generative model, while controlling the false discovery rate. We apply the lvm-DE framework to scVI and scSphere, two deep generative models. The resulting approaches outperform the state-of-the-art methods at estimating the log fold change in gene expression levels, as well as detecting differentially expressed genes between subpopulations of cells.

bioinformatics↗

bioRxiv2022

Identifying systematic variation at the single-cell level by leveraging low-resolution population-level data

A major limitation in single-cell genomics is a lack of ability to conduct cost-effective population-level studies. As a result, much of the current research in single-cell genomics focuses on biological processes that are broadly conserved across individuals, such as cellular organization and tissue development. This limitation prevents us from studying the etiology of experimental or clinical conditions that may be inconsistent across individuals owing to molecular variation and a wide range of effects in the population. In order to address this gap, we developed "kernel of integrated single cells" (Keris), a novel model-based framework to inform the analysis of single-cell gene expression data with population-level effects of a condition of interest. By inferring cell-type-specific moments and their variation across conditions using large tissue-level bulk data representing a population, Keris allows us to generate testable hypotheses at the single-cell level that would otherwise require collecting single-cell data from a large number of donors. Within the Keris framework, we show how the combination of low-resolution, large bulk data with small but high-resolution single-cell data enables the identification of changes in cell-subtype compositions and the characterization of subpopulations of cells that are affected by a condition of interest. Using Keris we estimate linear and non-linear age-associated changes in cell-type expression in large bulk peripheral blood mononuclear cells (PBMC) data. Combining with three independent single-cell PBMC datasets, we demonstrate that Keris can identify changes in cell-subtype composition with age and capture cell-type-specific subpopulations of senescent cells. This demonstrates the promise of enhancing single-cell data with population-level information to study compositional changes and to profile condition-affected subpopulations of cells, and provides a potential resource of targets for future clinical interventions.

genomics↗

bioRxiv2021

MultiVI: deep generative model for the integration of multi-modal data

Jointly profiling the transcriptional and chromatin accessibility landscapes of single-cells is a powerful technique to characterize cellular populations. Here we present MultiVI, a probabilistic model to analyze such multiomic data and integrate it with single modality datasets. MultiVI creates a joint representation that accurately reflects both chromatin and transcriptional properties of the cells even when one modality is missing. It also imputes missing data, corrects for batch effects and is available in the scvi-tools framework: https://docs.scvi-tools.org/.

bioinformatics↗

bioRxiv2021

Reconstructing unobserved cellular states from paired single-cell lineage tracing and transcriptomics data

AO_SCPLOWBSTRACTC_SCPLOWNovel experimental assays now simultaneously measure lineage relationships and transcriptomic states from single cells, thanks to CRISPR/Cas9-based genome engineering. These multimodal measurements allow researchers not only to build comprehensive phylogenetic models relating all cells but also infer transcriptomic determinants of consequential subclonal behavior. The gene expression data, however, is limited to cells that are currently present ("leaves" of the phylogeny). As a consequence, researchers cannot form hypotheses about unobserved, or "ancestral", states that gave rise to the observed population. To address this, we introduce TreeVAE: a probabilistic framework for estimating ancestral transcriptional states. TreeVAE uses a variational autoencoder (VAE) to model the observed transcriptomic data while accounting for the phylogenetic relationships between cells. Using simulations, we demonstrate that TreeVAE outperforms benchmarks in reconstructing ancestral states on several metrics. TreeVAE also provides a measure of uncertainty, which we demonstrate to correlate well with its prediction accuracy. This estimate therefore potentially provides a data-driven way to estimate how far back in the ancestor chain predictions could be made. Finally, using real data from lung cancer metastasis, we show that accounting for phylogenetic relationship between cells improves goodness of fit. Together, TreeVAE provides a principled framework for reconstructing unobserved cellular states from single cell lineage tracing data.

bioinformatics↗

bioRxiv2021

Multi-resolution deconvolution of spatial transcriptomics data reveals continuous patterns of inflammation

The function of mammalian cells is largely influenced by their tissue microenvironment. Advances in spatial transcriptomics open the way for studying these important determinants of cellular function by enabling a transcriptome-wide evaluation of gene expression in situ. A critical limitation of the current technologies, however, is that their resolution is limited to niches (spots) of sizes well beyond that of a single cell, thus providing measurements for cell aggregates which may mask critical interactions between neighboring cells of different types. While joint analysis with single-cell RNA-sequencing (scRNA-seq) can be leveraged to alleviate this problem, current analyses are limited to a discrete view of cell type proportion inside every spot. This limitation becomes critical in the common case where, even within a cell type, there is a continuum of cell states that cannot be clearly demarcated but reflects important differences in the way cells function and interact with their surroundings. To address this, we developed Deconvolution of Spatial Transcriptomics profiles using Variational Inference (DestVI), a probabilistic method for multi-resolution analysis for spatial transcriptomics that explicitly models continuous variation within cell types. Using simulations, we demonstrate that DestVI is capable of providing higher resolution compared to the existing methods and that it can estimate gene expression by every cell type inside every spot. We then introduce an automated pipeline that uses DestVI for analysis of single tissue slices and comparison between tissues. We apply this pipeline to study the immune crosstalk within lymph nodes to infection and explore the spatial organization of a mouse tumor model. In both cases, we demonstrate that DestVI can provide a high resolution and accurate spatial characterization of the cellular organization of these tissues, and that it is capable of identifying important cell-type-specific changes in gene expression - between different tissue regions or between conditions. DestVI is available as an open-source software package in the scvi-tools codebase (https://scvi-tools.org).

bioinformatics↗

bioRxiv2021

scvi-tools: a library for deep probabilistic analysis of single-cell omics data

AO_SCPLOWBSTRACTC_SCPLOWProbabilistic models have provided the underpinnings for state-of-the-art performance in many single-cell omics data analysis tasks, including dimensionality reduction, clustering, differential expression, annotation, removal of unwanted variation, and integration across modalities. Many of the models being deployed are amenable to scalable stochastic inference techniques, and accordingly they are able to process single-cell datasets of realistic and growing sizes. However, the community-wide adoption of probabilistic approaches is hindered by a fractured software ecosystem resulting in an array of packages with distinct, and often complex interfaces. To address this issue, we developed scvi-tools (https://scvi-tools.org), a Python package that implements a variety of leading probabilistic methods. These methods, which cover many fundamental analysis tasks, are accessible through a standardized, easy-to-use interface with direct links to Scanpy, Seurat, and Bioconductor workflows. By standardizing the implementations, we were able to develop and reuse novel functionalities across different models, such as support for complex study designs through nonlinear removal of unwanted variation due to multiple covariates and reference-query integration via scArches. The extensible software building blocks that underlie scvi-tools also enable a developer environment in which new probabilistic models for single cell omics can be efficiently developed, benchmarked, and deployed. We demonstrate this through a code-efficient reimplementation of Stereoscope for deconvolution of spatial transcriptomics profiles. By catering to both the end user and developer audiences, we expect scvi-tools to become an essential software dependency and serve to formulate a community standard for probabilistic modeling of single cell omics.

bioinformatics↗

bioRxiv2019

Detecting Zero-Inflated Genes in Single-Cell Transcriptomics Data

In single-cell RNA sequencing data, biological processes or technical factors may induce an overabundance of zero measurements. Existing probabilistic approaches to interpreting these data either model all genes as zero-inflated, or none. But the overabundance of zeros might be gene-specific. Hence, we propose the AutoZI model, which, for each gene, places a spike-and-slab prior on a mixture assignment between a negative binomial (NB) component and a zero-inflated negative binomial (ZINB) component. We approximate the posterior distribution under this model using variational inference, and employ Bayesian decision theory to decide whether each gene is zero-inflated. On simulated data, AutoZI outperforms the alternatives. On negative control data, AutoZI retrieves predictions consistent to a previous study on ERCC spike-ins and recovers similar results on control RNAs. Applied to several datasets and instances of the 10x Chromium protocol, AutoZI allows both biological and technical interpretations of zero-inflation. Finally, AutoZIs decisions on mouse embyronic stem-cells suggest that zero-inflation might be due to transcriptional bursting.

bioinformatics↗

bioRxiv2019

Deep Generative Models for Detecting Differential Expression in Single Cells

Detecting differentially expressed genes is important for characterizing subpopulations of cells. However, in scRNA-seq data, nuisance variation due to technical factors like sequencing depth and RNA capture efficiency obscures the underlying biological signal. First, we show that deep generative models, which combined Bayesian statistics and deep neural networks, better estimate the log-fold-change in gene expression levels between subpopulations of cells. Second, we use Bayesian decision theory to detect differentially expressed genes while controlling the false discovery rate. Our experiments on simulated and real datasets show that our approach out-performs state-of-the-art DE frameworks. Finally, we introduce a technique for improving the posterior approximation, and show that it also improves differential expression performance.

cell biology↗

bioRxiv2019

Harmonization and Annotation of Single-cell Transcriptomics data with Deep Generative Models

As single-cell transcriptomics becomes a mainstream technology, the natural next step is to integrate the accumulating data in order to achieve a common ontology of cell types and states. However, owing to various nuisance factors of variation, it is not straightforward how to compare gene expression levels across data sets and how to automatically assign cell type labels in a new data set based on existing annotations. In this manuscript, we demonstrate that our previously developed method, scVI, provides an effective and fully probabilistic approach for joint representation and analysis of cohorts of single-cell RNA-seq data sets, while accounting for uncertainty caused by biological and measurement noise. We also introduce single-cell ANnotation using Variational Inference (scANVI), a semi-supervised variant of scVI designed to leverage any available cell state annotations -- for instance when only one data set in a cohort is annotated, or when only a few cells in a single data set can be labeled using marker genes. We demonstrate that scVI and scANVI compare favorably to the existing methods for data integration and cell state annotation in terms of accuracy, scalability, and adaptability to challenging settings such as a hierarchical structure of cell state labels. We further show that different from existing methods, scVI and scANVI represent the integrated datasets with a single generative model that can be directly used for any probabilistic decision making task, using differential expression as our case study. scVI and scANVI are available as open source software and can be readily used to facilitate cell state annotation and help ensure consistency and reproducibility across studies.

bioinformatics↗