spatial transcriptomics
PulseAugur coverage of spatial transcriptomics — every cluster mentioning spatial transcriptomics across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New AI models predict gene expression from histology images
Researchers have developed new methods for predicting gene expression from histology images, offering a more cost-effective alternative to traditional spatial transcriptomics. One approach, GATE-ST, integrates text desc…
-
New model HyCLoST improves gene expression prediction using hyperbolic geometry
Researchers have developed a new model called HyCLoST, which utilizes hyperbolic geometry and an entailment loss to improve the prediction of gene expression from histopathology images. This approach aims to address iss…
-
New flow matching methods enhance generative models for design and imaging · 6 sources tracked
Researchers are exploring advanced flow matching techniques to enhance generative models for inverse design problems and image generation. Conditional Flow Matching (CFM) shows promise in engineering inverse design, out…
-
New AI models translate histology images to spatial transcriptomics data
Two new research papers, Path2ST and PaSTel, introduce advanced methods for translating histological images into spatial transcriptomic data. Path2ST utilizes a hierarchical approach, grounding cross-modal translation i…
-
Disentangled representations boost morpho-transcriptomic integration
Researchers have explored methods to improve the integration of spatial transcriptomics and Hematoxylin & Eosin (H&E) imaging data by disentangling shared and modality-specific variations. They compared variational auto…
-
New Diffusion Model Predicts Gene Expression from Histology Images
Researchers have developed a novel method for predicting gene expression from histology images by reformulating the task as a conditional generation problem within the transcriptional program space. This approach utiliz…
-
CellWorld foundation model advances spatial transcriptomics prediction
Researchers have introduced CellWorld, a novel foundation model for spatial transcriptomics that shifts its prediction target from gene expression to latent cell representations. This approach aims to improve the transf…
-
New AI model predicts gene expression from histology images
Researchers have developed HierarchicalDAEW, a novel dual-graph architecture designed to predict gene expression from H&E histology images. This method addresses the limitations of current spatial transcriptomics assays…
-
New COAST framework enhances gene expression prediction in spatial transcriptomics
Researchers have developed COAST, a novel framework for predicting gene expression in spatial transcriptomics using histology images. This context-aware differential learning approach leverages both local and global con…
-
DriftST framework infers gene expression from histology images
Researchers have developed DriftST, a novel framework for inferring spatially resolved gene expression from H&E stained histology images. This method addresses limitations of existing approaches by enabling efficient on…
-
New SN-VI Framework Enhances Latent Variable Modeling in AI
Researchers have developed Structured Nonparametric Variational Inference (SN-VI), a new framework that models complex dependencies among latent variables in posterior approximation using multivariate spline techniques.…
-
New augmentation method improves spatial transcriptomics imputation
Researchers have developed SNR-ST-Mix, a novel data augmentation framework for spatial transcriptomics imputation using deep neural networks. This method addresses limitations in current augmentation strategies by ensur…
-
Foundation models enable cross-modal transfer for single-cell biology
Researchers have developed a novel method for transferring information between different types of single-cell biological data. By using adversarial fine-tuning on foundation models, their approach can translate spatial …
-
New method treats spatial transcriptomics as images for AI pretraining
Researchers have developed a novel method to represent spatial transcriptomics data as images for large-scale pretraining. This approach treats tissue sections as croppable image patches, allowing for a significant incr…
-
New AI models integrate spatial omics data for biological insights
Researchers have developed HEIST, a hierarchical graph transformer model designed to analyze spatial transcriptomics and proteomics data. This model represents tissues as hierarchical graphs, capturing both spatial cell…
-
New RankByGene method aligns gene expression with histology images
Researchers have developed a new framework called RankByGene to improve the alignment between spatial transcriptomics (ST) data and histology images. This method uses a novel ranking-based alignment loss to preserve rel…
-
New GEARS Framework Reconstructs Spatial Data for Single-Cell RNA Sequencing
Researchers have developed GEARS, a novel geometry-first framework designed to reconstruct spatial information for single-cell RNA sequencing (scRNA-seq) data. Unlike previous methods that rely on fixed grids or cell-to…
-
QueST method identifies cellular niches in spatial transcriptomics data
Researchers have developed QueST, a novel computational method designed to identify similar cellular niches across different spatial transcriptomics samples. This method models niches as subgraphs and utilizes contrasti…
-
New benchmark SpaPath-Bench evaluates spatial understanding in pathology AI models
Researchers have introduced SpaPath-Bench, a new benchmark designed to evaluate the spatial representation capabilities of pathology foundation models (PFMs). This benchmark assesses how well PFM embeddings can distingu…
-
HEXST Transformer predicts spatial gene expression from histology slides
Researchers have developed HEXST, a novel Transformer model designed to predict gene expression from histology slides. This model addresses limitations in existing methods by accounting for the hexagonal sampling patter…