# Single-Cell RNA Sequencing

15 related articles

Subscribe to updates

bioRxiv Oct 14, 2026
CellScribe folds cell identity and state into one generative interface: 0.223 macro-F1 across 309 held-out types, ahead of a frozen-embedding probe
Single-cell annotation has long treated cell identity (lineage) and state (active transcriptional programs) with separate tools, while fixed-output classifiers can only return predefined types. CellScribe feeds frozen single-cell foundation-model embeddings into a pretrained language model through AdaLN adapters, so one shared model generates either an ontology-grounded cell type or a meta-program profile with activity scores under task-specific prompts. On the 309-type, 4.44M-cell study-holdout split of CELLxGENE, the full pipeline reaches 0.223 macro-F1 and 0.484 weighted-F1, above the 0.194 and 0.366 of a supervised probe on frozen scFoundation embeddings; on malignant cells from held-out 3CA studies it reaches 0.344 hallmark accuracy against the probe's 0.227.
Single-cell annotation has long treated cell identity (lineage) and state (active transcriptional programs) with separate tools, while fixed-output classifiers can only return predefined types. CellScribe feeds frozen single-cell foundation-model embeddings into a pretrained language model through AdaLN adapters, so one shared model generates either an ontology-grounded cell type or a meta-program profile with activity scores under task-specific prompts. On the 309-type, 4.44M-cell study-holdout split of CELLxGENE, the full pipeline reaches 0.223 macro-F1 and 0.484 weighted-F1, above the 0.194 and 0.366 of a supervised probe on frozen scFoundation embeddings; on malignant cells from held-out 3CA studies it reaches 0.344 hallmark accuracy against the probe's 0.227.
Université Paris-Saclay
Maxence Gélard（First author, Corresponding author）
CellScribe Cell Type Identification GRPO In-Context Learning Single-Cell RNA Sequencing
bioRxiv Oct 27, 2026
BLOOM turns sparse developmental atlases into a queryable virtual embryo, topping gene and cell correlation on all three mouse atlases
BLOOM frames transcriptomic virtual-embryo modeling as conditional generation: given an observed window of cell populations, a requested developmental stage and cell-state information, it generates the expression distribution at that stage. Pseudo-trajectories link independently sampled populations, while developmental age, cell-identity hierarchy, anatomical context, gene programmes and transcription-factor–target networks condition both a Gaussian base and a flow-matching generator. Across prenatal, visual-cortex and multi-organ endothelial mouse single-cell atlases, BLOOM ranks first for stage-averaged gene and cell correlations against 22 time-series forecasting baselines.
BLOOM frames transcriptomic virtual-embryo modeling as conditional generation: given an observed window of cell populations, a requested developmental stage and cell-state information, it generates the expression distribution at that stage. Pseudo-trajectories link independently sampled populations, while developmental age, cell-identity hierarchy, anatomical context, gene programmes and transcription-factor–target networks condition both a Gaussian base and a flow-matching generator. Across prenatal, visual-cortex and multi-organ endothelial mouse single-cell atlases, BLOOM ranks first for stage-averaged gene and cell correlations against 22 time-series forecasting baselines.
Shenzhen University University of Hong Kong Hong Kong Science and Technology Parks Corporation
Zhuo Liang（First author）Lequan Yu（Corresponding author）
BLOOM Flow Matching Single-Cell RNA Sequencing Virtual Embryo Modeling Optimal Transport
bioRxiv Oct 14, 2026
T-cell clonal organization without TCR sequencing: CloneTrast infers clonal niches from transcriptomes alone
CloneTrast uses clonal identities from paired single-cell RNA and TCR sequencing as training labels, so the model learns T-cell clonal-functional states from gene expression alone and needs no TCR data at inference. Training used 26 datasets across 14 cancer types with more than 1.5 million T cells, and external testing used 11 datasets with more than 1 million T cells, including two cancer types unseen in training. On both training and test sets, patient clonal purity improved significantly over a conventional expression embedding, and one NK-like niche enriched for tumor-blood shared TCRs was associated with poor immunotherapy response across studies.
CloneTrast uses clonal identities from paired single-cell RNA and TCR sequencing as training labels, so the model learns T-cell clonal-functional states from gene expression alone and needs no TCR data at inference. Training used 26 datasets across 14 cancer types with more than 1.5 million T cells, and external testing used 11 datasets with more than 1 million T cells, including two cancer types unseen in training. On both training and test sets, patient clonal purity improved significantly over a conventional expression embedding, and one NK-like niche enriched for tumor-blood shared TCRs was associated with poor immunotherapy response across studies.
Technion – Israel Institute of Technology
Ofir Shorer（First author）Keren Yizhak（Corresponding author）
CloneTrast Supervised Contrastive Learning T-cell clonal niches Single-Cell RNA Sequencing cancer immunotherapy
bioRxiv Nov 5, 2026
Single-cell sequencing only yields snapshots: a latent cell-state model fills in gene expression at unobserved timepoints
Single-cell RNA sequencing destroys each cell as it measures it and samples only discrete timepoints, so one cell's expression profile cannot be followed continuously. The Latent Cell-State Model approximates cell-state transitions as a Markov chain and adds a low-dimensional continuous latent variable to generate expression counts given cell state, time and gene. On the pancreatic development and Waddington-OT reprogramming datasets, maximum mean discrepancy between generated and real samples at held-out timepoints was 0.011 and 0.006 (pancreatic days 3 and 6) and 0.030 and 0.018 (reprogramming days 3.5 and 4), lower than the three compared methods.
Single-cell RNA sequencing destroys each cell as it measures it and samples only discrete timepoints, so one cell's expression profile cannot be followed continuously. The Latent Cell-State Model approximates cell-state transitions as a Markov chain and adds a low-dimensional continuous latent variable to generate expression counts given cell state, time and gene. On the pancreatic development and Waddington-OT reprogramming datasets, maximum mean discrepancy between generated and real samples at held-out timepoints was 0.011 and 0.006 (pancreatic days 3 and 6) and 0.030 and 0.018 (reprogramming days 3.5 and 4), lower than the three compared methods.
University of Manchester University College London
Yuhan Wang（First author, Corresponding author）
Latent Cell-State Model Trajectory Reconstruction Single-Cell RNA Sequencing
Nature Communications Nov 2, 2026
Glioblastoma invasion gets a live-brain-slice tracker: thousands of cells followed as standard therapy enriches the fastest branching state
Glioblastoma cells switch among branching, diffuse translocation, locomotion and perivascular invasion modes, but these switches were hard to observe at scale over days in intact brain tissue. GlioTrace links whole-specimen confocal imaging, convolutional-network morphology classification and a covariate hidden Markov model to track thousands of cells across six patient-derived xenograft brain slices. Invasion plasticity proved patient-specific and spatially organized, modulated by vascular proximity and microglial contact; targeted drugs shifted phenotype composition and transition probabilities, while radiation plus temozolomide enriched the fastest, highly connected branching state.
Glioblastoma cells switch among branching, diffuse translocation, locomotion and perivascular invasion modes, but these switches were hard to observe at scale over days in intact brain tissue. GlioTrace links whole-specimen confocal imaging, convolutional-network morphology classification and a covariate hidden Markov model to track thousands of cells across six patient-derived xenograft brain slices. Invasion plasticity proved patient-specific and spatially organized, modulated by vascular proximity and microglial contact; targeted drugs shifted phenotype composition and transition probabilities, while radiation plus temozolomide enriched the fastest, highly connected branching state.
University of Gothenburg Chalmers University of Technology Uppsala University
Hitesh Bhagavanbhai Mangukiya（First author）Sven Nelander（Corresponding author）
GlioTrace Covariate Hidden Markov Model Convolutional Neural Network Glioblastoma Single-Cell RNA Sequencing
researchsquare.com Oct 23, 2026
Tumor clones differ by more than mutations: regulatory networks separate dominant clones across 253 patients and 12 cancers
Whether tumor clones can be told apart by their gene regulatory networks had remained largely unmapped, since clones are usually defined by copy-number profiles and rarely characterized by regulatory activity. Clone-specific networks were inferred from single-cell RNA-seq and compared with a Wasserstein-distance measure of regulatory divergence. Across 253 patients and 12 cancer types, clone-clone networks resembled each other more than clone-normal pairs, and the largest clone diverged from normal cells significantly more than smaller clones.
Whether tumor clones can be told apart by their gene regulatory networks had remained largely unmapped, since clones are usually defined by copy-number profiles and rarely characterized by regulatory activity. Clone-specific networks were inferred from single-cell RNA-seq and compared with a Wasserstein-distance measure of regulatory divergence. Across 253 patients and 12 cancer types, clone-clone networks resembled each other more than clone-normal pairs, and the largest clone diverged from normal cells significantly more than smaller clones.
Rice University Indian Institute of Technology Kanpur
Narein Rao（First author）
Intratumor Heterogeneity Gene Regulatory Network Inference Wasserstein Distance-Based Regulatory Divergence Regulon Analysis Single-Cell RNA Sequencing
researchsquare.com Oct 22, 2026
Neutrophil annotation is not just a detection count: one fixed pipeline, two QC rules, and nine patient pairs that stop agreeing
How many neutrophils a single-cell pipeline labels is not the same as how well it estimates sample composition. Using protein measurements and physical sorting labels from four public cohorts as independent references, a fixed annotation pipeline and two preset QC rules were tested: under frozen QC, SingleR recovered 99.10% of paired whole-blood protein-positive cells and estimated a neutrophil-fraction decrease in all nine patient pairs; under the alternative QC rule the same pipeline estimated a decrease in only three pairs, with a mean paired change of +0.12 percentage points. Most of the shift came from which cells were filtered out, not from the annotator.
How many neutrophils a single-cell pipeline labels is not the same as how well it estimates sample composition. Using protein measurements and physical sorting labels from four public cohorts as independent references, a fixed annotation pipeline and two preset QC rules were tested: under frozen QC, SingleR recovered 99.10% of paired whole-blood protein-positive cells and estimated a neutrophil-fraction decrease in all nine patient pairs; under the alternative QC rule the same pipeline estimated a decrease in only three pairs, with a mean paired change of +0.12 percentage points. Most of the shift came from which cells were filtered out, not from the annotator.
Texas Tech University
Minhao Liu（First author, Corresponding author）
Cell Type Annotation SingleR CellTypist Single-Cell RNA Sequencing Single-Cell Analysis
researchsquare.com Oct 19, 2026
Fix the label directions before training: single-cell reference mapping lifts query macro-F1 from 0.774 to 0.811
Single-cell reference mapping no longer lets class representatives drift during training. SCLSC built each type representative from a mean expression profile, so its position moved as optimization proceeded; SOLAR assigns every reference label a fixed orthogonal direction before training and lets the encoder learn only where cells land in that space. Across nine held-out batches from human immune, lung and pancreas datasets at 30 dimensions, mean query macro-F1 was 0.811, above 0.774 for matched PCA and below 0.838 for scANVI.
Single-cell reference mapping no longer lets class representatives drift during training. SCLSC built each type representative from a mean expression profile, so its position moved as optimization proceeded; SOLAR assigns every reference label a fixed orthogonal direction before training and lets the encoder learn only where cells land in that space. Across nine held-out batches from human immune, lung and pancreas datasets at 30 dimensions, mean query macro-F1 was 0.811, above 0.774 for matched PCA and below 0.838 for scANVI.
West China Hospital of Sichuan University Kyushu University The University of Tokyo
Guanjie Zou（First author）Minqi Chen（First author）Minrui Chen（First author）Lunxu Liu（Corresponding author）Hiroto Saigo（Corresponding author）Koji Tsuda（Corresponding author）
SOLAR Supervised Contrastive Learning Single-Cell Reference Mapping Label Anchors Single-Cell RNA Sequencing
researchsquare.com Oct 19, 2026
Interferon-stimulated genes were being scored as batch effects: separating condition from batch before ranking genes
In cross-condition single-cell data, an existing gene-level batch-effect score can mistake condition-driven genes for highly batch-sensitive ones. Condition-aware GTE first uses scDisInFact to separate condition effects from batch effects, assigns each gene a condition-driven score, and multiplicatively penalizes the original score by that value. On an interferon-beta-stimulated PBMC dataset of 29,065 cells from eight donors, a penalty exponent of 3 moved 18 known interferon-stimulated genes by an average of 870.2 rank positions while ribosomal control genes stayed within baseline fluctuation.
In cross-condition single-cell data, an existing gene-level batch-effect score can mistake condition-driven genes for highly batch-sensitive ones. Condition-aware GTE first uses scDisInFact to separate condition effects from batch effects, assigns each gene a condition-driven score, and multiplicatively penalizes the original score by that value. On an interferon-beta-stimulated PBMC dataset of 29,065 cells from eight donors, a penalty exponent of 3 moved 18 known interferon-stimulated genes by an average of 870.2 rank positions while ribosomal control genes stayed within baseline fluctuation.
Anhui University of Finance and Economics
Wen Li（First author）
Condition-aware GTE Group Technical Effects scDisInFact Single-Cell RNA Sequencing Lasso
American Journal of Respiratory and Critical Care Medicine Oct 1, 2026
MMP12 identified as a macrophage-intrinsic driver of fibrosis: its inhibition reduces myocardial fibrosis and improves cardiac conduction
Using a myeloid-specific Tsc2 deletion mouse model that recapitulates key features of human cardiac sarcoidosis, and integrating single-cell RNA sequencing, bioinformatic analyses, histopathology, in vitro functional studies in murine and human macrophages, and in vivo pharmacologic inhibition, the study found that constitutive mTORC1 activation induces a fibrogenic macrophage (FibMac) population in the heart characterized by Cd63, Spp1, Gpnmb, and Fabp5 expression and arising through a TGF-β-dependent monocyte-to-FibMac differentiation process, and identified MMP12 as a macrophage-intrinsic inducer and dominant effector of this program: recombinant MMP12 was sufficient to enforce fibrogenic differentiation, clustering, and epithelioid features in mouse and human macrophages, whereas selec
Using a myeloid-specific Tsc2 deletion mouse model that recapitulates key features of human cardiac sarcoidosis, and integrating single-cell RNA sequencing, bioinformatic analyses, histopathology, in vitro functional studies in murine and human macrophages, and in vivo pharmacologic inhibition, the study found that constitutive mTORC1 activation induces a fibrogenic macrophage (FibMac) population in the heart characterized by Cd63, Spp1, Gpnmb, and Fabp5 expression and arising through a TGF-β-dependent monocyte-to-FibMac differentiation process, and identified MMP12 as a macrophage-intrinsic inducer and dominant effector of this program: recombinant MMP12 was sufficient to enforce fibrogenic differentiation, clustering, and epithelioid features in mouse and human macrophages, whereas selec
Centre National de la Recherche Scientifique Medical University of Graz University of Vienna Medical University of Vienna
Mario Mazic（First author）
Matrix Metalloproteinase 12 (MMP12)Fibrogenic Macrophages Cardiac Sarcoidosis Cardiac Fibrosis Single-Cell RNA Sequencing