Biology subjects

Kluger, Y.

Publications and source records attributed to Kluger, Y..

At least 19 recordsLinked to original sources

bioRxiv2026

The dark transcriptome mouse organogenesis cell atlas

Single-cell atlases have transformed our understanding of mammalian tissue biology, yet the diverse noncoding "dark transcriptome" remains largely uncharted. Here, we present the Dark Transcriptome Mouse Organogenesis Cell Atlas (DT-MOCA), comprising 276,455 cells across embryonic days 11 to 18 and jointly capturing protein-coding transcripts and five major classes of noncoding RNAs through single-nucleus total RNA sequencing, establishing the first comprehensive catalog of noncoding RNAs across major cell types and developmental lineages. We found that long noncoding RNA and microRNA profiles distinguished major cell types and developmental lineages with resolution comparable to messenger RNA, whereas transfer RNA, small nuclear RNA, and small nucleolar RNA programs were less cell type-discriminative and more broadly shared. We further resolve noncoding RNA expression patterns as lineage-specific, temporally modulated, or coordinately regulated by cell identity and developmental stage. We observed that temporally regulated long noncoding RNAs were evolutionarily younger than those associated with cell identity. We further generate a catalog of the change of noncoding RNAs cross all 11 major developmental trajectories. It revealed lineage-specific coordination between transfer RNA supply and codon demand during musculoskeletal organogenesis as well as dynamic microRNA and small nucleolar RNA programs during the central nervous system development. We observed microRNAs converge on regulators of proliferation and gliogenesis and shared induction of Snord116 defining a developmental window relevant to Prader Willi syndrome. Together, this atlas provides a comprehensive catalog of the developmental dark transcriptome and reveals how noncoding RNA programs are organized across cell identity, developmental time, and lineage progression.

developmental biology↗

bioRxiv2026

Cysteine reduction rather than methionine restriction promotes immunometabolic fitness to confer survival benefit in aging

Elevated sulfur-containing amino acids (SAA; methionine and cystine) are linked to human mortality. While methionine restriction (MR) extends lifespan in animals, it is often ignored that traditional longevity-promoting MR diets also lack cystine. When dietary cystine is eliminated, host redirects substrates from methionine cycle and generates cysteine via cystathionine {gamma}-lyase (CTH) in transsulfuration pathway, leaving it unclear which SAA controls aging. Here, we show that selective cysteine restriction in Caenorhabditis elegans enhanced lifespan and stress survival independently of methionine. Notably, cysteine-free diets (methionine-replete or restricted) in Cth-deficient mice induced pro-metabolic effects, whereas MR with normal cysteine was ineffective. Sustained 70% cysteine reduction in aged Cth-/- mice reprogrammed the immunometabolic axis, conferring healthspan benefits. Thus, lowering cysteine while keeping the methionine pool intact enhances healthy lifespan.

physiology↗

bioRxiv2026

Locat: Joint enrichment and depletion testing identifies localized marker genes in single-cell transcriptomics

Several methods identify marker genes that delineate cell populations in single-cell transcriptomic data, yet most emphasize enrichment within candidate populations without testing whether expression is significantly reduced elsewhere. We present Locat, a framework for identifying highly specific localized genes by testing whether expression is concentrated within compact regions of a cellular embedding and depleted outside them. For each gene, Locat fits weighted Gaussian mixture models to gene-specific and background densities, computes concentration and depletion statistics, and integrates them into a unified localization score. Across synthetic benchmarks with controlled ground truth, Locat detects uni-modal, multi-modal, and sparse localized patterns and loses significance when expression becomes indistinguishable from background structure. In developmental, perturbation, and differentiation datasets, Locat identifies compact marker sets that capture lineage organization, condition-specific programs, and temporal dynamics. These sets are often smaller than highly variable gene selections, while embeddings built from them preserve major cell populations and developmental programs in several cases. In murine dermis, interferon-treated PBMCs, and retinoic acid-induced embryonic stem cell differentiation, localized genes recover differentiation trajectories, stimulus-responsive programs, and reproducible stage-specific patterns. Together, these results show that jointly assessing concentration and depletion yields specific, interpretable marker genes.

bioinformatics↗

bioRxiv2026

Human Lymph Node Cellular Senescence Atlas Reveals Age-Dependent Alteration in Germinal Center B Cell Function and Niches

Immunosenescence, the age-associated decline in immune function, is a key feature of human aging. In human lymphoid organs, however, the specific immune cell populations that acquire senescence-associated phenotypes during aging and how they influence the surrounding tissue microenvironment remain poorly understood. A spatially resolved map of these senescence-associated immune states in human lymphoid tissues could help clarify their relationship with aging and their potential contributions to the progressive decline of immune function. Here, we integrated single-cell and spatial multi-omics to systematically characterize age-related senescence in human lymph nodes (LNs). Single-cell transcriptomics of lymphoid tissues from donors aged 18 to 100 years old identified 34 immune and stromal cell types and revealed age-associated upregulation of senescence signatures in specific populations. Spatial proteomic profiling of 99 LN sections from 51 donors (18-86 years) using high-plex immunofluorescence ([~]20 million cells) mapped senescence markers (p16, p21, HMGB1, -H2AX) at single-cell resolution, revealing diverse senescent-like cell types ("senotypes") and a stepwise shift from extrafollicular to germinal center (GC) localization with age. Notably, we observed focal clonal-like senescence in GC B cells in older donor LNs. Spatial transcriptomics, epigenomics, and metabolic imaging of selected samples further elucidate the multi-omics signatures and underlying mechanisms of functional impairment, metabolic remodeling, and distinct regulatory programs in senescent-like GC B cells. This study presents a comprehensive spatial atlas of senescence-associated immune states in human lymph nodes, revealing cell-type-specific and spatial heterogeneity that may contribute to immunosenescence and the decline of immune function during aging.

immunology↗

bioRxiv2026

Sharp cell type boundaries emerge from coordinated morphogen signaling

Classic models of the French flag problem depict sharp cell-type boundaries emerging from threshold responses to morphogen gradients. How discrete cell-type boundaries arise from morphogen signals that vary continuously across developing tissues is not completely understood. We use hair follicle dermal condensate formation to study a sharp developmental transition in which proliferative progenitors undergo cell-cycle exit concurrent with molecular differentiation. Using genetic and genomic approaches, we show that Wnt and Hedgehog signaling interact to coordinate the timing of these two processes. We identify a division of labor between the pathways: Wnt signaling promotes cell-cycle exit by regulating chromatin binding of the Hedgehog mediator GLI3, while Hedgehog signaling induces differentiation genes in a Wnt-dependent manner and simultaneously elevates Wnt activity. When Wnt and Hedgehog activities are temporally aligned, differentiation and cell-cycle exit occur within the same developmental window, restricting both the duration and abundance of intermediate states and producing a sharp cell-type boundary. When these signals are misaligned, intermediate states persist and expand, producing fuzzy boundaries. These findings reveal a mechanism in which interacting morphogen signals regulate the duration and abundance of intermediate states during a developmental transition, thereby controlling how continuous cell-state progression is translated into discrete tissue patterning.

developmental biology↗

bioRxiv2026

MOSAIC: A Spectral Framework for Integrative Phenotypic Characterization Using Population-Level Single-Cell Multi-Omics

Population-scale single-cell multi-omics offers unprecedented opportunities to link molecular variation to human health and disease. However, existing methods for single-cell multi-omics analysis are either cell-centric, prioritizing batch-corrected cell embeddings that neglect feature relationships, or feature-centric, imposing global feature representations that overlook inter-sample heterogeneity. To address these limitations, we present MOSAIC, a spectral framework that learns a high-resolution feature x sample joint embedding from population-scale single-cell multi-omics data. For each individual, MOSAIC constructs a sample-specific coupling matrix capturing complete intra- and cross-modality feature interactions, then projects these into a shared latent space via spectral decomposition. The joint feature x sample embedding defines each features connectivity profile per sample, enabling three downstream applications. Differential Connectivity analysis identifies features with regulatory network rewiring across conditions even when their abundance remains unchanged, revealing rewiring of proliferation programs in activated T cells from a vaccination cohort. Unsupervised subgroup detection isolates coherent feature modules to discover hidden patient subtypes, uncovering a stress-driven neuronal subtype within an HIV+ cohort. Clinical outcome prediction using connectivity-derived features complements abundance-based analysis, improving COVID-19 severity classification when integrated. MOSAIC provides a general-purpose framework for systems-level phenotypic characterization, bridging network-level discovery with clinical outcome prediction in population-scale single-cell studies.

bioinformatics↗

bioRxiv2026

Stack: In-Context Learning of Single-Cell Biology

Foundation models trained on single-cell transcriptomic data offer the promise of identifying and predicting the diversity of cellular phenotypes across species, diseases, and other biological conditions. However, the current models are limited to their supervised training conditions and tasks, which limits their utility for biological discovery. Here, we present SO_SCPLOWTACKC_SCPLOW, a foundation model trained on 149 million uniformly preprocessed human single cells that leverages tabular attention to generate representations for each cell informed by the cells in its context. SO_SCPLOWTACKC_SCPLOW offers substantial improvements for downstream tasks in the zero-shot setting compared to baselines, whether they are zero-shot, fine-tuned, or trained from scratch on the target dataset. SO_SCPLOWTACKC_SCPLOW can perform in-context learning from unlabeled cells representing arbitrary conditions, such as a chemical perturbation or a different donor, and predict the effect of those conditions on a target cell population without requiring data-specific fine-tuning. We apply SO_SCPLOWTACKC_SCPLOW to generate Perturb Sapiens, the first human whole-organism atlas of perturbed cells, spanning 28 tissues, 40 cell types, and 892 drug, cytokine, and genetic perturbations. We validated subsets of Perturb Sapiens using in vitro stimulation profiles. SO_SCPLOWTACKC_SCPLOW uniquely empowers prioritization of donor-specific perturbation effects, a capability we validated in our newly collected DiseasePert-3M data, comprising T cells from 40 donors across 14 diseases, stimulated with 11 cytokines. Overall, SO_SCPLOWTACKC_SCPLOW presents a new modeling framework where cells themselves act as guiding examples at inference time, unlocking general-purpose in-context learning capabilities for single-cell biology.

bioinformatics↗

bioRxiv2025

DiCoLo: Integration-free and cluster-free detection of localized differential gene co-expression in single-cell data

Detecting changes in gene coordination patterns between biological conditions and identifying the cell populations in which these changes occur are key challenges in single-cell analysis. Existing approaches often compare gene co-expression between predefined cell clusters or rely on aligning cells across conditions. These strategies can be suboptimal when changes occur within small subpopulations or when batch effects obscure the underlying biological signal. To address these challenges, we introduce DiCoLo, a framework that identifies genes exhibiting differential co-localization, defined as changes in coordinated expression within localized cell neighborhoods-subsets of highly similar cells in the transcriptomic space. Importantly, DiCoLo does not rely on cell clustering or cross-condition alignment. For each condition, DiCoLo constructs a gene graph using Optimal Transport distances that reflect gene co-localization patterns across the cell manifold. Then, it identifies differential gene programs by detecting changes in connectivity patterns between the gene graphs. We show that DiCoLo robustly identifies differential gene co-localization even under weak signals or complex batch effects, outperforming existing methods across multiple benchmark datasets. When applied to mouse hair follicle development data, DiCoLo reveals coordinated gene programs and emerging cell populations driven by perturbations in morphogen signaling that underlie dermal condensate differentiation. Overall, these results establish DiCoLo as a powerful framework for uncovering localized differential transcriptional coordinated patterns in single-cell data.

bioinformatics↗

bioRxiv2025

Spatial analysis reveals the cellular microenvironments and mechanisms of inflammation and kidney injury in acute interstitial nephritis

Acute interstitial nephritis (AIN) causes 15-20% of all acute kidney injury cases but lacks effective therapies beyond corticosteroids. Using high-resolution imaging mass cytometry and single-cell spatial transcriptomics to analyze human kidney biopsies with AIN, non-immunologic acute tubular injury (ATI), and reference tissue, the CXCL9-CXCR3 axis was identified as the defining immunologic signature of AIN, with 44-fold higher predicted CXCL9-CXCR3 interactions than ATI, creating homotypic inflammatory T cell amplification networks concentrated in lymphoid aggregates. C3AR1+ immune cells were enriched in peritubular neighborhoods of complement 3-expressing injured tubule cells, predominantly VCAM1+ injured proximal tubules, linking tubular injury to immune activation in AIN. Nicotinamide phosphoribosyltransferase (NAMPT) was the strongest predictor of VCAM1+ tubular microenvironments, with expression by both injured tubules and surrounding immune cells coordinating metabolic-inflammatory niches. These findings reveal distinct molecular circuits underlying AIN pathogenesis and identify potential therapeutic targets for improving clinical management and preventing progression to chronic kidney disease.

immunology↗

bioRxiv2025

Interaction of Wnt and SHH gradients synchronizes cell cycle 1 exit and differentiation

Classic models of the French flag problem depict sharp cell-type boundaries emerging from threshold responses to morphogen gradients. Yet, how such boundaries arise during dynamic cell-state transitions remains unclear. We use hair follicle dermal condensates to study a sharp cell-type transition in which proliferative progenitors synchronously undergo cell-cycle exit and molecular differentiation. Using genetic and genomic approaches, we show that Wnt and Hedgehog signaling interact to coordinate the timing of these processes. When their activities are temporally aligned, intermediate transitional states are compressed through cell-cycle exit, producing a sharp cell-type boundary; when misaligned, transitional states expand, yielding fuzzy borders. Mechanistically, elevated Wnt activity promotes cell-cycle exit by regulating chromatin binding of the Hedgehog mediator GLI3. Hedgehog signaling induces differentiation genes in a Wnt-dependent manner and simultaneously elevates Wnt activity, aligning arrest and differentiation in time. These findings reveal a mechanism wherein morphogen interactions coordinate transitions to generate precise cell-type boundaries.

developmental biology↗

bioRxiv2025

Hormetic elevation of taurine restrains inflammaging by deactivating the NLRP3 inflammasome.

Taurine, the most abundant sulfonic amino acid in humans is largely obtained from diets rich in animal proteins. However, taurine is dietary non-essential because it can be synthesized from cysteine by activation of transsulfuration pathway (TSP) when food consumption is low or if the diet is predominantly plant based. The decline of taurine was proposed as the driver of aging through an undefined mechanism. Here, we found that mild food restriction in humans for one year that resulted in 14% reduction of calorie intake elevated the hypotaurine and taurine concentration in adipose tissue. Therefore, we investigated whether elevated taurine mimics caloric-restrictions beneficial effects on inflammation, a key mechanism of aging. Interestingly, aging increased the circulating and tissue concentrations of taurine suggesting that elevated taurine may serve as a hormetic stress response metabolite that regulates mechanism of age-related inflammation. The elevated taurine protected mice against mortality from sepsis and inhibited inflammasome-driven inflammation and gasdermin-D (GSDMD) mediated pyroptosis. Mechanistically, danger signals including hypotonicity that activate NLRP3-inflammasome, caused upstream taurine efflux from macrophages, which triggered potassium (K+) release and downstream canonical NLRP3 inflammasome assembly, caspase-1 activation, GSDMD cleavage and IL-1{beta} and IL-18 secretion that was reversed by taurine restoration. Notably, taurine does not efflux from GSDMD pore and inhibited IL-1{beta} from macrophages independently of known transporters SLC6A6 and SLC36A1. Increased taurine in old mice promotes healthspan by inducing anti-inflammatory pathways previously linked to youthfulness. These findings demonstrate that taurine is an upstream metabolic sensor of cellular perturbations that control NLRP3 inflammasome and lowers age-related inflammation.

immunology↗

bioRxiv2025

AMULETY: A Python package to embed adaptive immune receptor sequences

Large language models have been developed to capture relevant features of adaptive immune receptors, each with unique potential applications. However, the diversity in available models presents challenges in accessibility and usability for downstream applications. Here we present AMULETY (Adaptive imMUne receptor Language model Embedding Tool), a Python-based software package to generate language model embeddings for adaptive immune receptor sequences, enabling users to leverage the strengths of different models without the need for complex configuration. AMULETY offers functions for embedding adaptive immune receptor amino acid sequences using pre-trained protein or antibody language models for paired heavy and light chain or single chain sequences. We showcase the variability on the embedding space for several embeddings on a dataset of antibody binders to several SARS-CoV-2 epitopes and showed that different models may be effective at capturing different aspects of the distinctions between epitope groups. AMULETY is available under GPL v3 license from https://github.com/immcantation/amulety or via pip from the Python Package Index (PyPI) from https://pypi.org/project/amulety/. O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=164 SRC="FIGDIR/small/644583v1_ufig1.gif" ALT="Figure 1"> View larger version (33K): org.highwire.dtl.DTLVardef@1c0bafaorg.highwire.dtl.DTLVardef@337816org.highwire.dtl.DTLVardef@111136forg.highwire.dtl.DTLVardef@1300dc_HPS_FORMAT_FIGEXP M_FIG C_FIG

bioinformatics↗

bioRxiv2025

Multi-omic Characterization of HIV Effects at Single Cell Level across Human Brain Regions

HIV infection exerts profound and long-lasting neurodegenerative effects on the central nervous system (CNS) that can persist despite antiretroviral therapy (ART). Here, we used single-nucleus multiome sequencing to map the transcriptomic and epigenetic landscapes of postmortem human brains from 13 healthy individuals and 20 individuals with HIV who have a history of treatment with ART. Our study spanned three distinct regions--the prefrontal cortex, insular cortex, and ventral striatum--enabling a comprehensive exploration of region-specific and cross-regional perturbations. We found widespread and persistent HIV-associated transcriptional and epigenetic alterations across multiple cell types. Detailed analyses of microglia revealed state changes marked by immune activation and metabolic dysregulation, while integrative multiomic profiling of astrocytes identified multiple subpopulations, including a reactive subpopulation unique to HIV-infected brains. These findings suggest that cells from people with HIV exhibit molecular shifts that may underlie ongoing neuroinflammation and CNS dysfunction. Furthermore, cell-cell communication analyses uncovered dysregulated and pro-inflammatory interactions among glial populations, underscoring the multifaceted and enduring impact of HIV on the brain milieu. Collectively, our comprehensive atlas of HIV-associated brain changes reveals distinct glial cell states with signatures of pro-inflammatory signaling and metabolic dysregulation, providing a framework for developing targeted therapies for HIV-associated neurological dysfunction.

bioinformatics↗

bioRxiv2025

Principled PCA separates signal from noise in omics count data

Principal component analysis (PCA) is indispensable for processing high-throughput omics datasets, as it can extract meaningful biological variability while minimizing the influence of noise. However, the suitability of PCA is contingent on appropriate normalization and transformation of count data, and accurate selection of the number of principal components; improper choices can result in the loss of biological information or corruption of the signal due to excessive noise. Typical approaches to these challenges rely on heuristics that lack theoretical foundations. In this work, we present Biwhitened PCA (BiPCA), a theoretically grounded framework for rank estimation and data denoising across a wide range of omics modalities. BiPCA overcomes a fundamental difficulty with handling count noise in omics data by adaptively rescaling the rows and columns - a rigorous procedure that standardizes the noise variances across both dimensions. Through simulations and analysis of over 100 datasets spanning seven omics modalities, we demonstrate that BiPCA reliably recovers the data rank and enhances the biological interpretability of count data. In particular, BiPCA enhances marker gene expression, preserves cell neighborhoods, and mitigates batch effects. Our results establish BiPCA as a robust and versatile framework for high-throughput count data analysis.

bioinformatics↗

bioRxiv2024

Nerve-associated macrophages control adipose homeostasis across lifespan and restrain age-related inflammation

Age-related inflammation or inflammaging is a key mechanism that increases disease burden and may control lifespan. How adipose tissue macrophages (ATMs) control inflammaging is not well understood in part because the molecular identities of niche-specific ATMs are incompletely known. Using intravascular labeling to exclude circulating myeloid cells and subsequent single-cell sequencing with orthogonal validation, we define the diversity and alterations in niche resident ATMs through lifespan. Aging led to depletion of vessel-associated macrophages (VAMs), expansion of lipid-associated macrophages (LAMs), and emergence of a unique subset of CD38+ age-associated macrophages (AAMs) in visceral white adipose tissue (VAT). Interestingly, CD169+CD11c- ATMs are enriched in a subpopulation of nerve-associated macrophages (NAMs) that declines with age. Depletion of CD169+ NAMs in aged mice increases inflammaging and impairs lipolysis suggesting that they are necessary for preventing catecholamine resistance in VAT. These findings reveal specialized ATMs control adipose homeostasis and link inflammation to tissue dysfunction during aging.

immunology↗

bioRxiv2024

IL-4 Licenses B Cell Activation Through Cholesterol Synthesis

Lymphocyte activation involves a transition from quiescence and associated catabolic metabolism to a metabolic state with noted similarities to cancer cells such as heavy reliance on aerobic glycolysis for energy demands and increased nutrient requirements for biomass accumulation and cell division1-3. Following antigen receptor ligation, lymphocytes require spatiotemporally distinct "second signals". These include costimulatory receptor or cytokine signaling, which engage discrete programs that often involve remodeling of organelles and increased nutrient uptake or synthesis to meet changing biochemical demands4-6. One such signaling molecule, IL-4, is a highly pleiotropic cytokine that was first identified as a B cell co-mitogen over 30 years ago7. However, how IL-4 signaling mechanistically supports B cell proliferation is incompletely understood. Here, using single cell RNA sequencing we find that the cholesterol biosynthetic program is transcriptionally upregulated following IL-4 signaling during the early B cell response to influenza virus infection, and is required for B cell activation in vivo. By limiting lipid availability in vitro, we determine cholesterol to be essential for B cells to expand their endoplasmic reticulum, progress through cell cycle, and proliferate. In sum, we demonstrate that the well-known ability of IL-4 to act as a B cell growth factor is through a previously unknown rewiring of specific lipid anabolic programs, relieving sensitivity of cells to environmental nutrient availability.

immunology↗

bioRxiv2024

Supervised fine-tuning of pre-trained antibody language models improves antigen specificity prediction

Antibodies play a crucial role in adaptive immune responses by determining B cell specificity to antigens and focusing immune function on target pathogens. Accurate prediction of antibody-antigen specificity directly from antibody sequencing data would be a great aid in understanding immune responses, guiding vaccine design, and developing antibody-based therapeutics. In this study, we present a method of supervised fine-tuning for antibody language models, which improves on previous results in binding specificity prediction to SARS-CoV-2 spike protein and influenza hemagglutinin. We perform supervised fine-tuning on four pre-trained antibody language models to predict specificity to these antigens and demonstrate that fine-tuned language model classifiers exhibit enhanced predictive accuracy compared to classifiers trained on pretrained model embeddings. The change of model attention activations after supervised fine-tuning suggested that this performance was driven by an increased model focus on the complementarity determining regions (CDRs). Application of the supervised fine-tuned models to BCR repertoire data demonstrated that these models could recognize the specific responses elicited by influenza and SARS-CoV-2 vaccination. Overall, our study highlights the benefits of supervised fine-tuning on pre-trained antibody language models as a mechanism to improve antigen specificity prediction. Author SummaryAntibodies are vigilant sentinels of our adaptive immune system that recognize and bind to targets on foreign pathogens, known as antigens. This interaction between antibody and antigen is highly specific, akin to a fitting lock and key mechanism, to ensure each antibody precisely targets its intended antigen. Recent advancements in language modeling have led to the development of antibody language model to decode specificity information in the sequences of antibodies. We introduce a method based on supervised fine-tuning, which enhances the accuracy of antibody language models in predicting antibody-antigen interactions. By training these models on large datasets of antibody sequences, we can better predict which antibodies will bind to important antigens such as those found on the surface of viruses like SARS-CoV-2 and influenza. Moreover, our study demonstrates the potential of the models to "read" B cell repertoire data and predict ongoing responses, offering new insights into how our bodies respond to vaccination. These findings have significant implications for vaccine design, as accurate prediction of antibody specificity can guide the development of more effective vaccines.

bioinformatics↗

bioRxiv2024

SORBET: Automated cell-neighborhood analysis of spatial transcriptomics or proteomics for interpretable sample classification via GNN

Spatial cellular profiling technologies have revolutionized our understanding of complex biological processes, from development and disease progression to immunity and aging. Despite their promise, integrating spatial information with multiplexed molecular data to accurately predict phenotypes poses significant challenges, especially in clinical settings. Here, we present SORBET, a geometric deep learning framework that directly analyzes complete spatial profiling data, eliminating the need to compress complete cell profiles into a limited set of annotations, such as cell types. SORBET models tissues as graphs of adjacent cells and applies graph convolutional networks to infer emergent phenotypes, such as responses to immunotherapy. The model leverages a novel data augmentation technique to ensure robust predictions, complemented by tailored interpretability analyses to identify the molecular and spatial patterns underlying the models phenotype inferences. We apply our method to a CosMx spatial transcriptomics dataset of pre-treatment metastatic melanoma samples annotated with response to immunotherapy; we show that spatial information significantly improves clinical endpoint, or phenotype, prediction and identifies important biological patterns. To our knowledge, SORBET is the first example of phenotype prediction on spatial transcriptomics data. We further validated our method using two spatial proteomics datasets, Imaging Mass Cytometry (IMC) and Co-detection by indexing (CODEX), obtained from Non-Small Cell Lung Cancer and Colorectal Cancer samples, respectively. SORBET demonstrates superior accuracy in phenotype prediction over leading spatial and non-spatial methods across various datasets of different observed phenotypes and technologies. SORBET sets a new benchmark for predictive analysis in spatial omics, promising to advance personalized medicine through refined patient treatment stratification, grounded in molecular and spatial tissue profiling.

bioinformatics↗