Generative modeling of single-cell gene expression for dose-dependent chemical perturbations

CoupleVAE: coupled variational autoencoders for predicting perturbational single-cell RNA sequencing data

With the rapid advances in single-cell sequencing technology, it is now feasible to conduct in-depth genetic analysis in individual cells. Study on the dynamics of single cells in response to perturbations is of great significance for understanding the functions and behaviors of living organisms. However, the acquisition of post-perturbation cellular states via biological experiments is frequently cost-prohibitive. Predicting the single-cell perturbation responses poses a critical challenge in the field of computational biology. In this work, we propose a novel deep learning method called coupled variational autoencoders (CoupleVAE), devised to predict the postperturbation single-cell RNA-Seq data. CoupleVAE is composed of two coupled VAEs connected by a coupler, initially extracting latent features for controlled and perturbed cells via two encoders, subsequently engaging in mutual translation within the latent space through two nonlinear mappings via a coupler, and ultimately generating controlled and perturbed data by two separate decoders to process the encoded and translated features. CoupleVAE facilitates a more intricate state transformation of single cells within the latent space. Experiments in three real datasets on infection, stimulation and cross-species prediction show that CoupleVAE surpasses the existing comparative models in effectively predicting single-cell RNA-seq data for perturbed cells, achieving superior accuracy.

Machine learning to dissect perturbations in complex cellular systems

Understanding the responses of biological systems to various perturbations, such as genetic, chemical, or environmental challenges, is essential for reconstructing causal network models. Emerging single-cell technologies have become instrumental in elucidating cell states and phenotypes and they have been used in combination with genetic screening. Recent advances in machine learning and artificial intelligence architectures have stimulated the development of computational tools for modeling perturbations and the response to compounds. This study outlined core principles underpinning perturbation analysis and discussed the methodologies and analytical frameworks used to decode drug and genetic perturbation responses, complex multicellular interactions, and network dynamics. The current tools used for various applications were overviewed. These developments hold great promise for improving drug development and personalized medicine. Foundation models and perturbation cell and tissue atlases offer immense potential for advancing our understanding of cellular behavior and disease mechanisms.

A mini-review on perturbation modelling across single-cell omic modalities

Recent advances in single-cell omics technology have transformed the landscape of cellular and molecular research, enriching the scope and intricacy of cellular characterisation. Perturbation modelling seeks to comprehensively grasp the effects of external influences like disease onset or molecular knock-outs or external stimulants on cellular physiology, specifically on transcription factors, signal transducers, biological pathways, and dynamic cell states. Machine and deep learning tools transform complex perturbational phenomena in algorithmically tractable tasks to formulate predictions based on various types of single-cell datasets. However, the recent surge in tools and datasets makes it challenging for experimental biologists and computational scientists to keep track of the recent advances in this rapidly expanding filed of single-cell modelling. Here, we recapitulate the main objectives of perturbation modelling and summarise novel single-cell perturbation technologies based on genetic manipulation like CRISPR or compounds, spanning across omic modalities. We then concisely review a burgeoning group of computational methods extending from classical statistical inference methodologies to various machine and deep learning architectures like shallow models or autoencoders, to biologically informed approaches based on gene regulatory networks, and to combinatorial efforts reminiscent of ensemble learning. We also discuss the rising trend of large foundational models in single-cell perturbation modelling inspired by large language models. Lastly, we critically assess the challenges that underline single-cell perturbation modelling while pointing towards relevant future perspectives like perturbation atlases, multi-omics and spatial datasets, causal machine learning for interpretability, multi-task learning for performance and explainability as well as prospects for solving interoperability and benchmarking pitfalls.

Predicting transcriptional responses to novel chemical perturbations using deep generative model for drug discovery

Understanding transcriptional responses to chemical perturbations is central to drug discovery, but exhaustive experimental screening of disease-compound combinations is unfeasible. To overcome this limitation, here we introduce PRnet, a perturbation-conditioned deep generative model that predicts transcriptional responses to novel chemical perturbations that have never experimentally perturbed at bulk and single-cell levels. Evaluations indicate that PRnet outperforms alternative methods in predicting responses across novel compounds, pathways, and cell lines. PRnet enables gene-level response interpretation and in-silico drug screening for diseases based on gene signatures. PRnet further identifies and experimentally validates novel compound candidates against small cell lung cancer and colorectal cancer. Lastly, PRnet generates a large-scale integration atlas of perturbation profiles, covering 88 cell lines, 52 tissues, and various compound libraries. PRnet provides a robust and scalable candidate recommendation workflow and successfully recommends drug candidates for 233 diseases. Overall, PRnet is an effective and valuable tool for gene-based therapeutics screening.

Toward subtask-decomposition-based learning and benchmarking for predicting genetic perturbation outcomes and beyond

Deciphering cellular responses to genetic perturbations is fundamental for a wide array of biomedical applications. However, there are three main challenges: predicting single-genetic-perturbation outcomes, predicting multiple-genetic-perturbation outcomes and predicting genetic outcomes across cell lines. Here we introduce Subtask Decomposition Modeling for Genetic Perturbation Prediction (STAMP), a flexible artificial intelligence strategy for genetic perturbation outcome prediction and downstream applications. STAMP formulates genetic perturbation prediction as a subtask decomposition problem by resolving three progressive subtasks in a problem decomposition manner, that is, identifying postperturbation differentially expressed genes, determining the expression change directions of differentially expressed genes and finally estimating the magnitudes of gene expression changes. STAMP exhibits a substantial improvement over the existing approaches on three subtasks and beyond, including the ability to identify key regulatory genes and pathways on small samples and to reveal precise genetic interactions of diverse types.

Ouroboros: cross-linking protein expression perturbations and cancer histology imaging with generative-predictive modeling

SUMMARY

Imagine if we could simultaneously predict spatial protein expression in tissues from their routine Hematoxylin and Eosin (H&E) stained images, and create tissue images given protein expression profiles thus enabling virtual simulations of how protein expression alterations impact histology in complex diseases like cancer. Such an approach could lead to more informed diagnostic and therapeutic decisions for precision medicine at lower costs and shorter turnaround times, more detailed insights into underlying disease pathology as well as improvement in predictive and generative performance. In this study, we investigate the intricate correlation between protein expressions obtained from Hyperion mass cytometry and histopathological microstructures in conventional H&E stained glioblastoma (GBM) samples, unveiling morphological patterns and cellular-level spatial alterations associated with protein expression changes. To model these complex relationships, we propose a novel generative-predictive framework called Ouroboros for producing H&E images from protein expressions and simultaneously predicting protein expressions from H&E images. Our comprehensive sample-independent validation over 9920 tissue spots from 4 GBM samples encompassing visual image analysis, quantitative analysis, subspace alignment and perturbation experiments shows that the proposed generative-predictive approach offers significant improvements in predicting protein expression from images in comparison to baseline methods as well as accurate generation of virtual GBM sample images. This proof of concept study can contribute to advancing our understanding of histological responses to protein expression perturbations and lays the foundations for further developments in this area.

AVAILABILITY AND IMPLEMENTATION

Implementation and associated data for the proposed approach are available at the URL: https://github.com/Srijay/Ouroboros.

scRank infers drug-responsive cell types from untreated scRNA-seq data using a target-perturbed gene regulatory network

Cells respond divergently to drugs due to the heterogeneity among cell populations. Thus, it is crucial to identify drug-responsive cell populations in order to accurately elucidate the mechanism of drug action, which is still a great challenge. Here, we address this problem with scRank, which employs a target-perturbed gene regulatory network to rank drug-responsive cell populations via in silico drug perturbations using untreated single-cell transcriptomic data. We benchmark scRank on simulated and real datasets, which shows the superior performance of scRank over existing methods. When applied to medulloblastoma and major depressive disorder datasets, scRank identifies drug-responsive cell types that are consistent with the literature. Moreover, scRank accurately uncovers the macrophage subpopulation responsive to tanshinone IIA and its potential targets in myocardial infarction, with experimental validation. In conclusion, scRank enables the inference of drug-responsive cell types using untreated single-cell data, thus providing insights into the cellular-level impacts of therapeutic interventions.

Unique challenges and best practices for single cell transcriptomic analysis in toxicology

The application and analysis of single-cell transcriptomics in toxicology presents unique challenges. These include identifying cell sub-populations sensitive to perturbation; interpreting dynamic shifts in cell type proportions in response to chemical exposures; and performing differential expression analysis in dose-response studies spanning multiple treatment conditions. This review examines these challenges while presenting best practices for critical single cell analysis tasks. This covers areas such as cell type identification; analysis of differential cell type abundance; differential gene expression; and cellular trajectories. Towards enhancing the use of single-cell transcriptomics in toxicology, this review aims to address key challenges in this field and offer practical analytical solutions. Overall, applying appropriate bioinformatic techniques to single-cell transcriptomic data can yield valuable insights into cellular responses to toxic exposures.

scPRAM accurately predicts single-cell gene expression perturbation response based on attention mechanism

MOTIVATION

With the rapid advancement of single-cell sequencing technology, it becomes gradually possible to delve into the cellular responses to various external perturbations at the gene expression level. However, obtaining perturbed samples in certain scenarios may be considerably challenging, and the substantial costs associated with sequencing also curtail the feasibility of large-scale experimentation. A repertoire of methodologies has been employed for forecasting perturbative responses in single-cell gene expression. However, existing methods primarily focus on the average response of a specific cell type to perturbation, overlooking the single-cell specificity of perturbation responses and a more comprehensive prediction of the entire perturbation response distribution.

RESULTS

Here, we present scPRAM, a method for predicting perturbation responses in single-cell gene expression based on attention mechanisms. Leveraging variational autoencoders and optimal transport, scPRAM aligns cell states before and after perturbation, followed by accurate prediction of gene expression responses to perturbations for unseen cell types through attention mechanisms. Experiments on multiple real perturbation datasets involving drug treatments and bacterial infections demonstrate that scPRAM attains heightened accuracy in perturbation prediction across cell types, species, and individuals, surpassing existing methodologies. Furthermore, scPRAM demonstrates outstanding capability in identifying differentially expressed genes under perturbation, capturing heterogeneity in perturbation responses across species, and maintaining stability in the presence of data noise and sample size variations.

AVAILABILITY AND IMPLEMENTATION

https://github.com/jiang-q19/scPRAM and https://doi.org/10.5281/zenodo.10935038.