Biology subjects

Lotfollahi, M.

Publications and source records attributed to Lotfollahi, M..

34 records · Page 2Linked to original sources

bioRxiv2023

Predicting cell morphological responses to perturbations using generative modeling

Advancements in high-throughput screening have enabled the exploration of rich phenotypic readouts like high-content microscopy, expediting drug target identification and mode of action studies. However, scaling these experiments to the vast space of drug or genetic manipulations poses challenges, as only a small subset of compounds show activity in screenings. Despite being widely used in various applications, machine learning methods have not shown a reliable ability to extrapolate predictions to scenarios involving unseen phenomena, specifically transforming an unseen control cell image into a desired perturbation. We present a generative model, the IMage Perturbation Autoencoder (IMPA), which predicts cellular morphological effects of chemical and genetic perturbations using untreated cells as input. IMPA learns perturbation-specific styles from generalized embeddings and generates counterfactual treatment response predictions in control cells. We demonstrate IMPA can predict morphological changes caused by small molecule perturbations on breast cancer cells. Additionally, we test IMPA on the unseen drug effect prediction task, showing improved performance over state-of-the-art generative models when compounds are structurally related to the training set. Finally, generalizability and capability to predict more subtle effects are showcased through its application to large microscopy datasets with hundreds of genetic perturbations on U2OS cells. We envision IMPA to become a valuable tool in computational microscopy for aiding phenotypic drug discovery, facilitating navigation of the perturbation space, and rational experimental design.

bioinformatics↗

bioRxiv2022

Population-level integration of single-cell datasets enables multi-scale analysis across samples

The increasing generation of population-level single-cell atlases with hundreds or thousands of samples has the potential to link demographic and technical metadata with high-resolution cellular and tissue data in homeostasis and disease. Constructing such comprehensive references requires large-scale integration of heterogeneous cohorts with varying metadata capturing demographic and technical information. Here, we present single-cell population level integration (scPoli), a semi-supervised conditional deep generative model for data integration, label transfer and query-to-reference mapping. Unlike other models, scPoli learns both sample and cell representations, is aware of cell-type annotations and can integrate and annotate newly generated query datasets while providing an uncertainty mechanism to identify unknown populations. We extensively evaluated the method and showed its advantages over existing approaches. We applied scPoli to two population-level atlases of lung and peripheral blood mononuclear cells (PBMCs), the latter consisting of roughly 8 million cells across 2,375 samples. We demonstrate that scPoli allows atlas-level integration and automatic reference mapping with label transfer. It can explain sample-level biological and technical variations such as disease, anatomical location and assay by means of its novel sample embeddings. We use these embeddings to explore sample-level metadata, enable automatic sample classification and guide a data integration workflow. scPoli also enables simultaneous sample-level and cell-level analysis of gene expression patterns, revealing genes associated with batch effects and the main axes of between-sample variation. We envision scPoli becoming an important tool for population-level single-cell data integration facilitating atlas use but also interpretation by means of multi-scale analyses.

genomics↗

bioRxiv2022

Deep generative modeling of transcriptional dynamics for RNA velocity analysis in single cells

RNA velocity has been rapidly adopted to guide the interpretation of transcriptional dynamics in snapshot single-cell transcriptomics data. Current approaches for estimating and analyzing RNA velocity can empirically reveal complex dynamics but lack effective strategies for quantifying the uncertainty of the estimate and its overall applicability to the system of interest. Here, we present veloVI (velocity variational inference), a deep generative modeling framework for estimating RNA velocity. veloVI learns a gene-specific dynamical model of RNA metabolism and provides a transcriptome-wide quantification of velocity uncertainty. We show in a series of examples that veloVI compares favorably to previous approaches for inferring RNA velocity with improvements in fit to the data, consistency across transcriptionally similar cells, and stability across preprocessing pipelines for quantifying RNA abundance. Further, we demonstrate that properties unique to veloVI, such as posterior velocity uncertainty, can be used to assess the appropriateness of analysis with velocity to the data at hand. Finally, we highlight veloVI as a flexible framework for modeling transcriptional dynamics by adapting the underlying dynamical model to use time-dependent transcription rates.

bioinformatics↗

bioRxiv2022

MultiCPA: Multimodal Compositional Perturbation Autoencoder

Single-cell multimodal profiling provides a high-resolution view of cellular information. Recently, multimodal profiling approaches have been coupled with CRISPR technologies to perform pooled screens of single or combinatorial perturbations. This opens the possibility of exploring the massive space of combinatorial perturbations and their regulatory effects computationally from the extrapolation of a few experimentally feasible combinations. Here, we propose MultiCPA, an end-to-end generative architecture to predict multimodal perturbation response at single cell level. Two mixing strategies to integrate multiple modalities are introduced and compared with existing methods. MultiCPA was also shown to accurately predict unseen combinatorial perturbation responses for multiple modalities. The code to reproduce the results is available on GitHub, theislab/multicpa.

systems biology↗

bioRxiv2022

Single-cell reference mapping to construct and extend cell type hierarchies

Single-cell genomics is now producing an ever-increasing amount of datasets that, when integrated, could provide large-scale reference atlases of tissue in health and disease. Such atlases increase the scale and generalizability of analyses and enable combining knowledge generated by individual studies. Specifically, individual studies often differ regarding cell annotation terminology and depth, with different groups often using distinct terminology. Understanding how annotations are related and complement each other would mark a major step towards a consensus-based cell-type annotation reflecting the latest knowledge. Whereas recent computational techniques, referred to as "reference mapping" methods, facilitate the usage and expansion of existing reference atlases by mapping new datasets (i.e., queries) onto an atlas; a systematic approach towards harmonizing dataset-specific cell-type terminology and annotation depth is still lacking. Here, we present "treeArches", a framework to automatically build and extend reference atlases while enriching them with an updatable hierarchy of cell-type annotations across different datasets. We demonstrate various use cases, from automatically resolving relations between reference and query cell types to identifying unseen cell types absent in the reference, such as disease-associated cell states. We envision treeArches enabling data-driven construction of consensus atlas-level cell-type hierarchies and facilitating efficient usage of reference atlases.

bioinformatics↗

bioRxiv2022

Multigrate: single-cell multi-omic data integration

Constructing joint representations from multimodal single-cell datasets is crucial for understanding cellular heterogeneity and function. Traditional methods, such as factor analysis and kNN-based approaches, face computational limitations with scalability across large datasets and multiple modalities. In this work, we demonstrate the product-of-experts VAE-based model, which offers a flexible, scalable solution for integrating multimodal data, allowing for the seamless mapping of both unimodal and multimodal queries onto a reference atlas. We evaluate how different strategies for combining modalities in the VAE framework impact query-to-reference mapping across diverse datasets, including CITE-seq and spatial metabolomics. Our benchmarks assess batch effect correction, biological signal preservation, and imputation of missing modalities. We showcase our approach in a mosaic setting, integrating CITE-seq and multiome data to accurately map unimodal and multimodal queries into the joint latent space. We extend this to spatial data by integrating gene expression and metabolomics from paired Visium and MALDI-MSI slides, achieving a high correlation in metabolite predictions from spatial gene expression. Our results demonstrate that this VAE-based framework is scalable, robust, and easily applicable across multiple modalities, providing a powerful tool for data imputation, querying, and biological discovery.

bioinformatics↗

bioRxiv2022

An integrated cell atlas of the human lung in health and disease

Organ- and body-scale cell atlases have the potential to transform our understanding of human biology. To capture the variability present in the population, these atlases must include diverse demographics such as age and ethnicity from both healthy and diseased individuals. The growth in both size and number of single-cell datasets, combined with recent advances in computational techniques, for the first time makes it possible to generate such comprehensive large-scale atlases through integration of multiple datasets. Here, we present the integrated Human Lung Cell Atlas (HLCA) combining 46 datasets of the human respiratory system into a single atlas spanning over 2.2 million cells from 444 individuals across health and disease. The HLCA contains a consensus re-annotation of published and newly generated datasets, resolving under- or misannotation of 59% of cells in the original datasets. The HLCA enables recovery of rare cell types, provides consensus marker genes for each cell type, and uncovers gene modules associated with demographic covariates and anatomical location within the respiratory system. To facilitate the use of the HLCA as a reference for single-cell lung research and allow rapid analysis of new data, we provide an interactive web portal to project datasets onto the HLCA. Finally, we demonstrate the value of the HLCA reference for interpreting disease-associated changes. Thus, the HLCA outlines a roadmap for the development and use of organ-scale cell atlases within the Human Cell Atlas.

cell biology↗

bioRxiv2022

Biologically informed deep learning to infer gene program activity in single cells

The increasing availability of large-scale single-cell datasets has enabled the detailed description of cell states across multiple biological conditions and perturbations. In parallel, recent advances in unsupervised machine learning, particularly in transfer learning, have enabled fast and scalable mapping of these new single-cell datasets onto reference atlases. The resulting large-scale machine learning models however often have millions of parameters, rendering interpretation of the newly mapped datasets challenging. Here, we propose expiMap, a deep learning model that enables interpretable reference mapping using biologically understandable entities, such as curated sets of genes and gene programs. The key concept is the substitution of the uninterpretable nodes in an autoencoders bottleneck by labeled nodes mapping to interpretable lists of genes, such as gene ontologies, biological pathways, or curated gene sets, for which activities are learned as constraints during reconstruction. This is enabled by the incorporation of predefined gene programs into the reference model, and at the same time allowing the model to learn de novo new programs and refine existing programs during reference mapping. We show that the model retains similar integration performance as existing methods while providing a biologically interpretable framework for understanding cellular behavior. We demonstrate the capabilities of expiMap by applying it to 15 datasets encompassing five different tissues and species. The interpretable nature of the mapping revealed unreported associations between interferon signaling via the RIG-I/MDA5 and GPCRs pathways, with differential behavior in CD8+ T cells and CD14+ monocytes in severe COVID-19, as well as the role of annexins in the cellular communications between lymphoid and myeloid compartments for explaining patient response to the applied drugs. Finally, expiMap enabled the direct comparison of a diverse set of pancreatic beta cells from multiple studies where we observed a strong, previously unreported correlation between the unfolded protein response and asparagine N-linked glycosylation. Altogether, expiMap enables the interpretable mapping of single cell transcriptome data sets across cohorts, disease states and other perturbations.

bioinformatics↗

bioRxiv2021

Out-of-distribution prediction with disentangled representations for single-cell RNA sequencing data

Learning robust representations can help uncover underlying biological variation in scRNA-seq data. Disentangled representation learning is one approach to obtain such informative as well as interpretable representations. Here, we learn disentangled representations of scRNA-seq data using {beta} variational autoencoder ({beta}-VAE) and apply the model for out-of-distribution (OOD) prediction. We demonstrate accurate gene expression predictions for cell-types absent from training in a perturbation and a developmental dataset. We further show that {beta}-VAE outperforms a state-of-the-art disentanglement method for scRNA-seq in OOD prediction while achieving better disentanglement performance.

bioinformatics↗

bioRxiv2021

Jointly learning T-cell receptor and transcriptomic information to decipher the immune response

Recent advancements in single-cell immune profiling that enable the measurement of the transcriptome and T-cell receptor (TCR) sequences simultaneously have emerged as a promising approach to study immune responses at cellular resolution. Yet, combining these different types of information from multiple datasets into a joint representation is complicated by the unique characteristics of each modality and the technical effects between datasets. Here, we present mvTCR, a multimodal generative model to learn a unified representation across modalities and datasets for joint analysis of single-cell immune profiling data. We show that mvTCR allows the construction of large-scale and multimodal T-cell atlases by distilling modality-specific properties into a shared view, enabling unique and improved data analysis. Specifically, we demonstrated mvTCRs potential by revealing and separating SARS-CoV-2-specific T-cell clusters from bystanders that would have been missed in individual unimodal data analysis. Finally, mvTCR can enable automated analysis of new datasets when combined with transfer-learning approaches. Overall, mvTCR provides a principled solution for standard analysis tasks such as multimodal integration, clustering, specificity analysis, and batch correction for single-cell immune profiling data.

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↗

bioRxiv2021

Compositional perturbation autoencoder for single-cell response modeling

Recent advances in multiplexed single-cell transcriptomics experiments are facilitating the high-throughput study of drug and genetic perturbations. However, an exhaustive exploration of the combinatorial perturbation space is experimentally unfeasible, so computational methods are needed to predict, interpret, and prioritize perturbations. Here, we present the compositional perturbation autoencoder (CPA), which combines the interpretability of linear models with the flexibility of deep-learning approaches for single-cell response modeling. CPA encodes and learns transcriptional drug responses across different cell type, dose, and drug combinations. The model produces easy-to-interpret embeddings for drugs and cell types, which enables drug similarity analysis and predictions for unseen dosage and drug combinations. We show that CPA accurately models single-cell perturbations across compounds, doses, species, and time. We further demonstrate that CPA predicts combinatorial genetic interactions of several types, implying that it captures features that distinguish different interaction programs. Finally, we demonstrate that CPA can generate in-silico 5,329 missing genetic combination perturbations (97.6% of all possibilities) with diverse genetic interactions. We envision our model will facilitate efficient experimental design and hypothesis generation by enabling in-silico response prediction at the single-cell level, and thus accelerate therapeutic applications using single-cell technologies.

bioinformatics↗

bioRxiv2021

Squidpy: a scalable framework for spatial single cell analysis

Spatial omics data are advancing the study of tissue organization and cellular communication at an unprecedented scale. Here, we present Squidpy, a Python framework that brings together tools from omics and image analysis to enable scalable description of spatial molecular data, such as transcriptome or multivariate proteins. Squidpy provides both infrastructure and numerous analysis methods that allow to efficiently store, manipulate and interactively visualize spatial omics data.

bioinformatics↗

bioRxiv2020

Learning interpretable latent autoencoder representations with annotations of feature sets

Existing methods for learning latent representations for single-cell RNA-seq data are based on autoencoders and factor models. However, representations learned by autoencoders are hard to interpret and representations learned by factor models have limited flexibility. Here, we introduce a framework for learning interpretable autoencoders based on regularized linear decoders. It decomposes variation into interpretable components using prior knowledge in the form of annotated feature sets obtained from public databases. Through this, it provides an alternative to enrichment techniques and factor models for the task of explaining observed variation with biological knowledge. Benchmarking our model on two single-cell RNA-seq datasets, we demonstrate how our model outperforms an existing factor model regarding scalability while maintaining interpretability.

bioinformatics↗

bioRxiv2020

Query to reference single-cell integration with transfer learning

Large single-cell atlases are now routinely generated with the aim of serving as reference to analyse future smaller-scale studies. Yet, learning from reference data is complicated by batch effects between datasets, limited availability of computational resources, and sharing restrictions on raw data. Leveraging advances in machine learning, we propose a deep learning strategy to map query datasets on top of a reference called single-cell architectural surgery (scArches, https://github.com/theislab/scarches). It uses transfer learning and parameter optimization to enable efficient, decentralized, iterative reference building, and the contextualization of new datasets with existing references without sharing raw data. Using examples from mouse brain, pancreas, and whole organism atlases, we showcase that scArches preserves nuanced biological state information while removing batch effects in the data, despite using four orders of magnitude fewer parameters compared to de novo integration. To demonstrate mapping disease variation, we show that scArches preserves detailed COVID-19 disease variation upon reference mapping, enabling discovery of new cell identities that are unseen during training. We envision our method to facilitate collaborative projects by enabling the iterative construction, updating, sharing, and efficient use of reference atlases.

bioinformatics↗

bioRxiv2018

Generative modeling and latent space arithmetics predict single-cell perturbation response across cell types, studies and species

Accurately modeling cellular response to perturbations is a central goal of computational biology. While such modeling has been proposed based on statistical, mechanistic and machine learning models in specific settings, no generalization of predictions to phenomena absent from training data ( out-of-sample) has yet been demonstrated. Here, we present scGen, a model combining variational autoencoders and latent space vector arithmetics for high-dimensional single-cell gene expression data. In benchmarks across a broad range of examples, we show that scGen accurately models dose and infection response of cells across cell types, studies and species. In particular, we demonstrate that scGen learns cell type and species specific response implying that it captures features that distinguish responding from non-responding genes and cells. With the upcoming availability of large-scale atlases of organs in healthy state, we envision scGen to become a tool for experimental design through in silico screening of perturbation response in the context of disease and drug treatment.

bioinformatics↗