Toward universal cell embeddings: integrating single-cell RNA-seq datasets across species with SATURN

Genomic evolution reshapes cell-type diversification in the amniote brain

Over 320 million years of evolution, amniotes have developed complex brains and cognition through largely unexplored genetic and gene expression mechanisms. We created a comprehensive single-cell atlas of over 1.3 million cells from the telencephalon and cerebellum of turtles, zebra finches, pigeons, mice, and macaques, employing single-cell resolution spatial transcriptomics to validate gene expression patterns across species. Our study identifies significant species-specific variations in cell types, highlighting their conservation and diversification in evolution. We found pronounced differences in telencephalon excitatory neurons (EXs) and cerebellar cell types between birds and mammals. Birds predominantly express SLC17A6 in EX, whereas mammals express SLC17A7 in the neocortex and SLC17A6 elsewhere, possibly due to loss of function of SLC17A7 in birds. Additionally, we identified a bird-specific Purkinje cell subtype (SVIL+), implicating the lysine-specific demethylase 11 (LSD1)/KDM1A pathway in learning and circadian rhythms and containing numerous positively selected genes, which suggests an evolutionary optimization of cerebellar functions for ecological and behavioral adaptation. Our findings elucidate the complex interplay between genetic evolution and environmental adaptation, underscoring the role of genetic diversification in the development of specialized cell types across amniotes.

mKmer: an unbiased K-mer embedding of microbiomic single-microbe RNA sequencing data

The advanced single-microbe RNA sequencing (smRNA-seq) technique addresses the pressing need to understand the complexity and diversity of microbial communities, as well as the distinct microbial states defined by different gene expression profiles. Current analyses of smRNA-seq data heavily rely on the integrity of reference genomes within the queried microbiota. However, establishing a comprehensive collection of microbial reference genomes or gene sets remains a significant challenge for most real-world microbial ecosystems. Here, we developed an unbiased embedding algorithm utilizing K-mer signatures, named mKmer, which bypasses gene or genome alignment to enable species identification for individual microbes and downstream functional enrichment analysis. By substituting gene features in the canonical cell-by-gene matrix with highly conserved K-mers, we demonstrate that mKmer outperforms gene-based methods in clustering and motif inference tasks using benchmark datasets from crop soil and human gut microbiomes. Our method provides a reference genome-free analytical framework for advancing smRNA-seq studies.

Integrating Spatially-Resolved Transcriptomics Data Across Tissues and Individuals: Challenges and Opportunities

Advances in spatially-resolved transcriptomics (SRT) technologies have propelled the development of new computational analysis methods to unlock biological insights. The lowering cost of SRT data generation presents an unprecedented opportunity to create large-scale spatial atlases and enable population-level investigation, integrating SRT data across multiple tissues, individuals, species, or phenotypes. Here, unique challenges are described in the SRT data integration, where the analytic impact of varying spatial and biological resolutions is characterized and explored. A succinct review of spatially-aware integration methods and computational strategies is provided. Exciting opportunities to advance computational algorithms amenable to atlas-scale datasets along with standardized preprocessing methods, leading to improved sensitivity and reproducibility in the future are further highlighted.

Advances and applications in single-cell and spatial genomics

The applications of single-cell and spatial technologies in recent times have revolutionized the present understanding of cellular states and the cellular heterogeneity inherent in complex biological systems. These advancements offer unprecedented resolution in the examination of the functional genomics of individual cells and their spatial context within tissues. In this review, we have comprehensively discussed the historical development and recent progress in the field of single-cell and spatial genomics. We have reviewed the breakthroughs in single-cell multi-omics technologies, spatial genomics methods, and the computational strategies employed toward the analyses of single-cell atlas data. Furthermore, we have highlighted the advances made in constructing cellular atlases and their clinical applications, particularly in the context of disease. Finally, we have discussed the emerging trends, challenges, and opportunities in this rapidly evolving field.

Primer on machine learning applications in brain immunology

Single-cell and spatial technologies have transformed our understanding of brain immunology, providing unprecedented insights into immune cell heterogeneity and spatial organisation within the central nervous system. These methods have uncovered complex cellular interactions, rare cell populations, and the dynamic immune landscape in neurological disorders. This review highlights recent advances in single-cell "omics" data analysis and discusses their applicability for brain immunology. Traditional statistical techniques, adapted for single-cell omics, have been crucial in categorizing cell types and identifying gene signatures, overcoming challenges posed by increasingly complex datasets. We explore how machine learning, particularly deep learning methods like autoencoders and graph neural networks, is addressing these challenges by enhancing dimensionality reduction, data integration, and feature extraction. Newly developed foundation models present exciting opportunities for uncovering gene expression programs and predicting genetic perturbations. Focusing on brain development, we demonstrate how single-cell analyses have resolved immune cell heterogeneity, identified temporal maturation trajectories, and uncovered potential therapeutic links to various pathologies, including brain malignancies and neurodegeneration. The integration of single-cell and spatial omics has elucidated the intricate cellular interplay within the developing brain. This mini-review is intended for wet lab biologists at all career stages, offering a concise overview of the evolving landscape of single-cell omics in the age of widely available artificial intelligence.

New horizons at the interface of artificial intelligence and translational cancer research

Artificial intelligence (AI) is increasingly being utilized in cancer research as a computational strategy for analyzing multiomics datasets. Advances in single-cell and spatial profiling technologies have contributed significantly to our understanding of tumor biology, and AI methodologies are now being applied to accelerate translational efforts, including target discovery, biomarker identification, patient stratification, and therapeutic response prediction. Despite these advancements, the integration of AI into clinical workflows remains limited, presenting both challenges and opportunities. This review discusses AI applications in multiomics analysis and translational oncology, emphasizing their role in advancing biological discoveries and informing clinical decision-making. Key areas of focus include cellular heterogeneity, tumor microenvironment interactions, and AI-aided diagnostics. Challenges such as reproducibility, interpretability of AI models, and clinical integration are explored, with attention to strategies for addressing these hurdles. Together, these developments underscore the potential of AI and multiomics to enhance precision oncology and contribute to advancements in cancer care.

Partially characterized topology guides reliable anchor-free scRNA-integration

Single-cell RNA sequencing (scRNA-seq) is an important technique for obtaining biological insights at cellular resolution, with scRNA-seq batch integration a key step before downstream statistical analysis. Despite the plethora of methods proposed, achieving reliable batch correction while preserving the heterogeneity of biological signals that define cell type continues to pose a challenge. To address this, we propose scCRAFT, an autoencoder model that separates cell-type-related signals from batch effects for reliable multi-batch integration. scCRAFT integrates three key loss components: a reconstruction loss for observation reconstruction, a multi-domain adaptation loss to eliminate batch effects, and an innovative dual-resolution triplet loss to preserve intra-batch, introduced as an effective mechanism to counteract the over-correction effect of domain adaptation loss amid heterogeneous cell distributions across batches. We show that scCRAFT effectively manages unbalanced batches, rare cell types, and batch-specific cell phenotypes in simulations, and surpasses state-of-the-art methods in a diverse set of real datasets.

Investigation of cell development and tissue structure network based on natural Language processing of scRNA-seq data

BACKGROUND

Single-cell multi-omics technologies, particularly single-cell RNA sequencing (scRNA-seq), have revolutionized our understanding of cellular heterogeneity and development by providing insights into gene expression at the single-cell level. Investigating the influence of genes on cellular behavior is crucial for elucidating cell fate determination and differentiation, cell development processes, and disease mechanisms.

METHODS

Inspired by NLP, we present a novel scRNA-seq analysis method that treats genes as analogous to words. Using word2vec to embed gene sequences derived from gene networks, we generate vector representations of genes, which are then used to represent cells by summing gene vectors and subsequently tissues by aggregating cell vectors.

RESULTS

Our NLP-based approach analyzes scRNA-seq data by generating vector representations of genes, cells, and tissues. This multi-scale analysis includes mapping cell states in vector space to reveal developmental trajectories, quantifying cell similarity using Euclidean distance, and constructing inter-tissue relationship networks from aggregated cell vectors.

CONCLUSIONS

This method offers a computationally efficient approach for analyzing scRNA-seq data by constructing embedding representations similar to those used in large language model pre-training, but without requiring high-performance computing clusters. By generating gene embeddings that capture functional relationships, this method facilitates the study of cell development trajectories, the impact of gene perturbations, cell clustering, and the construction and analysis of tissue networks. This provides a valuable tool for single-cell data analysis.

Comprehensive SHAP Values and Single-Cell Sequencing Technology Reveal Key Cell Clusters in Bovine Skeletal Muscle

The skeletal muscle of cattle is the main component of their muscular system, responsible for supporting and movement functions. However, there are still many unknown areas regarding the ranking of the importance of different types of cell populations within it. This study conducted in-depth research and made a series of significant findings. First, we trained 15 bovine skeletal muscle models and selected the best-performing model as the initial model. Based on the SHAP (Shapley Additive exPlanations) analysis of this initial model, we obtained the SHAP values of 476 important genes. Using the contributions of these 476 genes, we reconstructed a 476-gene SHAP value matrix, and relying solely on the interactions among these 476 genes, successfully mapped the single-cell atlas of bovine skeletal muscle. After retraining the model and further interpretation, we found that Myofiber cells are the most representative cell type in bovine skeletal muscle, followed by neutrophils. By determining the key genes of each cell type through SHAP values, we conducted analyses on the correlations among key genes and between cells for Myofiber cells, revealing the critical role these genes play in muscle growth and development. Further, by using protein language models, we performed cross-species comparisons between cattle and pigs, deepening our understanding of Myofiber cells as key cells in skeletal muscle, and exploring the common regulatory mechanisms of muscle development across species.

Cross-species imputation and comparison of single-cell transcriptomic profiles

Cross-species comparison and prediction of gene expression profiles are important to understand regulatory changes during evolution and to transfer knowledge learned from model organisms to humans. Single-cell RNA-seq (scRNA-seq) profiles enable us to capture gene expression profiles with respect to variations among individual cells; however, cross-species comparison of scRNA-seq profiles is challenging because of data sparsity, batch effects, and the lack of one-to-one cell matching across species. Moreover, single-cell profiles are challenging to obtain in certain biological contexts, limiting the scope of hypothesis generation. Here we developed Icebear, a neural network framework that decomposes single-cell measurements into factors representing cell identity, species, and batch factors. Icebear enables accurate prediction of single-cell gene expression profiles across species, thereby providing high-resolution cell type and disease profiles in under-characterized contexts. Icebear also facilitates direct cross-species comparison of single-cell expression profiles for conserved genes that are located on the X chromosome in eutherian mammals but on autosomes in chicken. This comparison, for the first time, revealed evolutionary and diverse adaptations of X-chromosome upregulation in mammals.

Benchmarking cross-species single-cell RNA-seq data integration methods: towards a cell type tree of life

Cross-species single-cell RNA-seq data hold immense potential for unraveling cell type evolution and transferring knowledge between well-explored and less-studied species. However, challenges arise from interspecific genetic variation, batch effects stemming from experimental discrepancies and inherent individual biological differences. Here, we benchmarked nine data-integration methods across 20 species, encompassing 4.7 million cells, spanning eight phyla and the entire animal taxonomic hierarchy. Our evaluation reveals notable differences between the methods in removing batch effects and preserving biological variance across taxonomic distances. Methods that effectively leverage gene sequence information capture underlying biological variances, while generative model-based approaches excel in batch effect removal. SATURN demonstrates robust performance across diverse taxonomic levels, from cross-genus to cross-phylum, emphasizing its versatility. SAMap excels in integrating species beyond the cross-family level, especially for atlas-level cross-species integration, while scGen shines within or below the cross-class hierarchy. As a result, our analysis offers recommendations and guidelines for selecting suitable integration methods, enhancing cross-species single-cell RNA-seq analyses and advancing algorithm development.

Enhancer-driven cell type comparison reveals similarities between the mammalian and bird pallium

Combinations of transcription factors govern the identity of cell types, which is reflected by genomic enhancer codes. We used deep learning to characterize these enhancer codes and devised three metrics to compare cell types in the telencephalon across amniotes. To this end, we generated single-cell multiome and spatially resolved transcriptomics data of the chicken telencephalon. Enhancer codes of orthologous nonneuronal and γ-aminobutyric acid-mediated (GABAergic) cell types show a high degree of similarity across amniotes, whereas excitatory neurons of the mammalian neocortex and avian pallium exhibit varying degrees of similarity. Enhancer codes of avian mesopallial neurons are most similar to those of mammalian deep-layer neurons. With this study, we present generally applicable deep learning approaches to characterize and compare cell types on the basis of genomic regulatory sequences.

The human and non-human primate developmental GTEx projects

Many human diseases are the result of early developmental defects. As most paediatric diseases and disorders are rare, children are critically underrepresented in research. Functional genomics studies primarily rely on adult tissues and lack critical cell states in specific developmental windows. In parallel, little is known about the conservation of developmental programmes across non-human primate (NHP) species, with implications for human evolution. Here we introduce the developmental Genotype-Tissue Expression (dGTEx) projects, which span humans and NHPs and aim to integrate gene expression, regulation and genetics data across development and species. The dGTEx cohort will consist of 74 tissue sites across 120 human donors from birth to adulthood, and developmentally matched NHP age groups, with additional prenatal and adult animals, with 126 rhesus macaques (Macaca mulatta) and 72 common marmosets (Callithrix jacchus). The data will comprise whole-genome sequencing, extensive bulk, single-cell and spatial gene expression profiles, and chromatin accessibility data across tissues and development. Through community engagement and donor diversity, the human dGTEx study seeks to address disparities in genomic research. Thus, dGTEx will provide a reference human and NHP dataset and tissue bank, enabling research into developmental changes in expression and gene regulation, childhood disorders and the effect of genetic variation on development.

How to build the virtual cell with artificial intelligence: Priorities and opportunities

Cells are essential to understanding health and disease, yet traditional models fall short of modeling and simulating their function and behavior. Advances in AI and omics offer groundbreaking opportunities to create an AI virtual cell (AIVC), a multi-scale, multi-modal large-neural-network-based model that can represent and simulate the behavior of molecules, cells, and tissues across diverse states. This Perspective provides a vision on their design and how collaborative efforts to build AIVCs will transform biological research by allowing high-fidelity simulations, accelerating discoveries, and guiding experimental studies, offering new opportunities for understanding cellular functions and fostering interdisciplinary collaborations in open science.

Deep generative AI models analyzing circulating orphan non-coding RNAs enable detection of early-stage lung cancer

Liquid biopsies have the potential to revolutionize cancer care through non-invasive early detection of tumors. Developing a robust liquid biopsy test requires collecting high-dimensional data from a large number of blood samples across heterogeneous groups of patients. We propose that the generative capability of variational auto-encoders enables learning a robust and generalizable signature of blood-based biomarkers. In this study, we analyze orphan non-coding RNAs (oncRNAs) from serum samples of 1050 individuals diagnosed with non-small cell lung cancer (NSCLC) at various stages, as well as sex-, age-, and BMI-matched controls. We demonstrate that our multi-task generative AI model, Orion, surpasses commonly used methods in both overall performance and generalizability to held-out datasets. Orion achieves an overall sensitivity of 94% (95% CI: 87%-98%) at 87% (95% CI: 81%-93%) specificity for cancer detection across all stages, outperforming the sensitivity of other methods on held-out validation datasets by more than  ~ 30%.

A PERTURBATION CELL ATLAS OF HUMAN INDUCED PLURIPOTENT STEM CELLS

Towards comprehensively investigating the genotype-phenotype relationships governing the human pluripotent stem cell state, we generated an expressed genome-scale CRISPRi Perturbation Cell Atlas in KOLF2.1J human induced pluripotent stem cells (hiPSCs) mapping transcriptional and fitness phenotypes associated with 11,739 targeted genes. Using the transcriptional phenotypes, we created a minimum distortion embedding map of the pluripotent state, demonstrating rich recapitulation of protein complexes, such as strong co-clustering of MRPL, BAF, SAGA, and Ragulator family members. Additionally, we uncovered transcriptional regulators that are uncoupled from cell fitness, discovering potential novel pluripotency (JOSD1, RNF7) and metabolic factors (ZBTB41). We validated these findings via phenotypic, protein-interaction, and metabolic tracing assays. Finally, we propose a contrastive human-cell engineering framework (CHEF), a machine learning architecture that learns from perturbation cell atlases to predict perturbation recipes that achieve desired transcriptional states. Taken together, our study presents a comprehensive resource for interrogating the regulatory networks governing pluripotency.

Differentiating visceral sensory ganglion organoids from induced pluripotent stem cells

The ability to generate visceral sensory neurons (VSN) from induced pluripotent stem (iPS) cells may help to gain insights into how the gut-nerve-brain axis is involved in neurological disorders. We established a protocol to differentiate human iPS-cell-derived visceral sensory ganglion organoids (VSGOs). VSGOs exhibit canonical VSN markers, and single-cell RNA sequencing revealed heterogenous molecular signatures and developmental trajectories of VSGOs aligned with native VSN. We integrated VSGOs with human colon organoids on a microfluidic device and applied this axis-on-a-chip model to Alzheimer's disease. Our results suggest that VSN could be a potential mediator for propagating gut-derived amyloid and tau to the brain in an APOE4- and LRP1-dependent manner. Furthermore, our approach was extended to include patient-derived iPS cells, which demonstrated a strong correlation with clinical data.

Astrocyte regional specialization is shaped by postnatal development

Astrocytes are an abundant class of glial cells with critical roles in neural circuit assembly and function. Though many studies have uncovered significant molecular distinctions between astrocytes from different brain regions, how this regionalization unfolds over development is not fully understood. We used single-nucleus RNA sequencing to characterize the molecular diversity of brain cells across six developmental stages and four brain regions in the mouse and marmoset brain. Our analysis of over 170,000 single astrocyte nuclei revealed striking regional heterogeneity among astrocytes, particularly between telencephalic and diencephalic regions, at all developmental time points surveyed in both species. At the stages sampled, most of the region patterning was private to astrocytes and not shared with neurons or other glial types. Though astrocytes were already regionally patterned in late embryonic stages, this region-specific astrocyte gene expression signature changed dramatically over postnatal development, and its composition suggests that regional astrocytes further specialize postnatally to support their local neuronal circuits. Comparing across species, we found divergence in the expression of astrocytic region- and age-differentially expressed genes and the timing of astrocyte maturation relative to birth between mouse and marmoset, as well as hundreds of species differentially expressed genes. Finally, we used expansion microscopy to show that astrocyte morphology is largely conserved across gray matter regions of prefrontal cortex, striatum, and thalamus in the mouse, despite substantial molecular divergence.

How to Build the Virtual Cell with Artificial Intelligence: Priorities and Opportunities

The cell is arguably the most fundamental unit of life and is central to understanding biology. Accurate modeling of cells is important for this understanding as well as for determining the root causes of disease. Recent advances in artificial intelligence (AI), combined with the ability to generate large-scale experimental data, present novel opportunities to model cells. Here we propose a vision of leveraging advances in AI to construct virtual cells, high-fidelity simulations of cells and cellular systems under different conditions that are directly learned from biological data across measurements and scales. We discuss desired capabilities of such AI Virtual Cells, including generating universal representations of biological entities across scales, and facilitating interpretable in silico experiments to predict and understand their behavior using Virtual Instruments. We further address the challenges, opportunities and requirements to realize this vision including data needs, evaluation strategies, and community standards and engagement to ensure biological accuracy and broad utility. We envision a future where AI Virtual Cells help identify new drug targets, predict cellular responses to perturbations, as well as scale hypothesis exploration. With open science collaborations across the biomedical ecosystem that includes academia, philanthropy, and the biopharma and AI industries, a comprehensive predictive understanding of cell mechanisms and interactions has come into reach.

Artificial intelligence and machine learning applications for cultured meat

Cultured meat has the potential to provide a complementary meat industry with reduced environmental, ethical, and health impacts. However, major technological challenges remain which require time-and resource-intensive research and development efforts. Machine learning has the potential to accelerate cultured meat technology by streamlining experiments, predicting optimal results, and reducing experimentation time and resources. However, the use of machine learning in cultured meat is in its infancy. This review covers the work available to date on the use of machine learning in cultured meat and explores future possibilities. We address four major areas of cultured meat research and development: establishing cell lines, cell culture media design, microscopy and image analysis, and bioprocessing and food processing optimization. In addition, we have included a survey of datasets relevant to CM research. This review aims to provide the foundation necessary for both cultured meat and machine learning scientists to identify research opportunities at the intersection between cultured meat and machine learning.

Computational strategies for cross-species knowledge transfer and translational biomedicine

Research organisms provide invaluable insights into human biology and diseases, serving as essential tools for functional experiments, disease modeling, and drug testing. However, evolutionary divergence between humans and research organisms hinders effective knowledge transfer across species. Here, we review state-of-the-art methods for computationally transferring knowledge across species, primarily focusing on methods that utilize transcriptome data and/or molecular networks. We introduce the term "agnology" to describe the functional equivalence of molecular components regardless of evolutionary origin, as this concept is becoming pervasive in integrative data-driven models where the role of evolutionary origin can become unclear. Our review addresses four key areas of information and knowledge transfer across species: (1) transferring disease and gene annotation knowledge, (2) identifying agnologous molecular components, (3) inferring equivalent perturbed genes or gene sets, and (4) identifying agnologous cell types. We conclude with an outlook on future directions and several key challenges that remain in cross-species knowledge transfer.

Integrating spatially-resolved transcriptomics data across tissues and individuals: challenges and opportunities

Advances in spatially-resolved transcriptomics (SRT) technologies have propelled the development of new computational analysis methods to unlock biological insights. As the cost of generating these data decreases, these technologies provide an exciting opportunity to create large-scale atlases that integrate SRT data across multiple tissues, individuals, species, or phenotypes to perform population-level analyses. Here, we describe unique challenges of varying spatial resolutions in SRT data, as well as highlight the opportunities for standardized preprocessing methods along with computational algorithms amenable to atlas-scale datasets leading to improved sensitivity and reproducibility in the future.

Revisiting Cardiac Biology in the Era of Single Cell and Spatial Omics

Throughout our lifetime, each beat of the heart requires the coordinated action of multiple cardiac cell types. Understanding cardiac cell biology, its intricate microenvironments, and the mechanisms that govern their function in health and disease are crucial to designing novel therapeutical and behavioral interventions. Recent advances in single-cell and spatial omics technologies have significantly propelled this understanding, offering novel insights into the cellular diversity and function and the complex interactions of cardiac tissue. This review provides a comprehensive overview of the cellular landscape of the heart, bridging the gap between suspension-based and emerging in situ approaches, focusing on the experimental and computational challenges, comparative analyses of mouse and human cardiac systems, and the rising contextualization of cardiac cells within their niches. As we explore the heart at this unprecedented resolution, integrating insights from both mouse and human studies will pave the way for novel diagnostic tools and therapeutic interventions, ultimately improving outcomes for patients with cardiovascular diseases.