Single-cell and spatial transcriptomics

scDblFinder in Python with GPU support

The paper presents a Python implementation of scDblFinder with GPU support for faster doublet detection in single-cell RNA sequencing data.

BART-spatial unravels biologically significant transcriptional regulators from spatial omics data

BART-spatial identifies transcriptional regulators from spatial omics data by integrating spatial and pseudotemporal information with TR binding profiles, outperforming existing methods.

scUnify: a unified framework for training and inference across multiple single-cell foundation models

scUnify provides a unified framework for training and inference across multiple single-cell foundation models, enabling comparison and extension of tasks and adaptation strategies.

Spatial microRNA profiling at single-cell resolution by in situ barcoded extension

The paper introduces miR-Space, a method for spatial miRNA profiling at single-cell resolution, revealing new miRNA distributions and cell-type associations in brain tissues.

Genome-wide single-cell perturbation screens with VIPerturb-seq

VIPerturb-seq enables genome-wide CRISPR perturbation screens using probe-based detection, improving throughput and efficiency for single-cell analysis.

RNA velocity in growing cells

This paper investigates the impact of cell growth on RNA velocity methods and shows systematic errors in existing approaches when growth is not accounted for.

PASTRI: Resolving Stage-Specific Cell-State Dynamics from Annotated Cell Lineage Trees

PASTRI infers stage-specific cell-state transition rates from annotated cell lineages, revealing rate-limiting steps and attractor states in development and disease.

A Generative Virtual Tissue Model Enables Computational Design of Therapeutic Perturbation Strategies

This paper introduces CIFM, a generative virtual tissue model that simulates transcriptional dynamics under therapeutic conditions to design immunotherapy strategies for cancer and autoimmune diseases.

bulk2scDiff: A Pseudobulk-Conditioned Diffusion Model for Bulk-to-Single-Cell RNASeq Generation

bulk2scDiff generates single-cell RNA-seq data from bulk profiles using a diffusion model, showing good reconstruction of cell populations in cancer datasets.

Method Choice, Not Biology, Determines In Silico Perturbation Results: A Systematic Evaluation of Eight Methods Across Four Datasets

This paper evaluates eight in silico perturbation methods across four datasets, finding that only two consistently detect TF-to-pathway regulation, highlighting method choice's impact on results.

PerturbLDM: conditional latent diffusion for modelling single-cell perturbation responses

PerturbLDM predicts single-cell transcriptional responses to perturbations using a latent diffusion model, outperforming existing methods in drug-dose-cell line combinations and capturing key biological programs.

STADiffuser: high-fidelity simulation and full-view 3D modeling of spatial transcriptomics

STADiffuser simulates spatial transcriptomic data with high fidelity and enables 3D modeling of large-scale spatial datasets.

Single-cell foundation models benefit from cross-modal training: adding proteomics data beats parameter scaling

The paper shows that adding proteomics data to a single-cell RNA-seq model improves its performance beyond increasing model size.

Phenotype-associated spatial biomarker discovery in spatial transcriptomics with spHOT

spHOT identifies phenotype-associated spatial biomarkers in spatial transcriptomics by localizing disease-relevant niches across multiple diseases.

Benchmarking computational decontamination of ambient RNA

This study benchmarks ambient RNA decontamination methods using simulated and experimental datasets, finding that no single method is optimal across all scenarios, with CellBender, DecontX, and SoupX performing well.

In situ Discovery of Immune Repertoire Reveals Antitumor Immunity and Therapeutic Antibodies

This paper introduces Archimap, a spatial transcriptomic platform that profiles immune repertoires and microbiota in FFPE tissues, revealing antitumor immunity and therapeutic antibodies.

ACCREDIT: A Quality-Aware Agentic Engine for Cell-resolved Cross-modal Image Registration with Dynamic Iterative Tuning

ACCREDIT improves cross-modal image registration by detecting failures and automatically recovering alignments, outperforming existing methods in accuracy and robustness.

Single-Cell Mapping of tRNA Expression Dynamics Across Human Hematopoiesis

This study maps tRNA expression dynamics across human hematopoiesis using sc-STM-seq and identifies tRNAs linked to stemness, differentiation, and cell lineages.

scFair: Geometry-Aware Gene Budgets and Same-Rank Extension for Highly Variable Gene Selection

scFair improves highly variable gene selection by automatically setting list length and adding a tail to reduce bias from fixed cutoffs.

Autonomous Spatial Transcriptomics Analysis (ASTA): Demonstrating Performance Improvements through Clustering, Biological Annotation, and AI-Driven Discovery

ASTA improves spatial transcriptomics analysis through clustering, annotation, and AI-driven hypothesis generation, achieving significant performance gains and biological insights.

dbverse scales spatial omics analysis with embedded analytical databases

dbverse enables efficient analysis of large spatial omics datasets by using embedded databases, outperforming traditional methods in runtime.

Nonparametric kernel-based detection of spatially variable genes with adaptive shrinkage and scalable multi-sample inference

This paper introduces CytoKspace, a nonparametric method for detecting spatially variable genes, showing improved performance and scalability over existing approaches.

PACE, Proximity-Associated Changes in Expression

PACE quantifies how proximity to different cell types affects gene expression in spatial transcriptomics data, revealing tumour-associated reprogramming in breast and melanoma tissues.

Detection of Spatially Aberrant Cells in Spatial Transcriptomics Data by Conformal Prediction

The paper introduces SPADE, a framework that detects spatially aberrant cells in spatial transcriptomics data using variational autoencoders and conformal prediction.

SpatialMOC: Accurate reconstruction of spatial multi-omics landscapes through cross-modality prediction

SpatialMOC reconstructs missing spatial multi-omics data by integrating spatial context and cross-modality learning, outperforming existing methods across multiple tissues and modalities.

Mapping tumor microenvironment heterogeneity of human melanoma metastases across distant organs

This study maps the heterogeneity of human melanoma metastases across brain, liver, and lung using single-nucleus RNA sequencing, revealing organ-specific immune and stromal adaptations.

Longitudinal whole transcriptomic profiling of live cells through domain adaptation

PENNE infers whole-transcriptomic profiles from live-cell images using domain adaptation, capturing temporal gene dynamics and cell-type markers.

scDIVA: semi-supervised integration and fine-grained annotation of tumor-immune single-cell atlases

scDIVA transfers fine-grained immune cell type annotations between tumor-immune scRNA-seq datasets by integrating batch correction and detecting novel cell states.

Robust identification of cell-cell communication heterogeneity in single cells

This paper introduces scRICH, a framework for analyzing cell-cell communication in single-cell and spatial transcriptomics data, showing its ability to capture communication heterogeneity and link it to cell fate decisions.

CellConsensus: An agent-curated atlas for automatic cell typing

CellConsensus provides a consensus cell typing method by aggregating marker genes from curated atlases and literature, improving accuracy and reproducibility across tissues and platforms.