Towards Scalable Context-Aware Single-Cell Spatial Transcriptomics Prediction from Histology Images
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
The Flow has not summarised this story yet — read it at arXiv Computer Vision.
arXiv:2606. 02424v1 Announce Type: cross Abstract: Histology-based single-cell spatial transcriptomics (ST) estimation aims to predict gene expression for individual cells from histopathological images and cell locations, reducing the need for costly single-cell ST measurements.
The paper introduces BCARP, a Biology‑Guided Context‑Aware Residual Propagation framework that predicts spatial gene expression from H&E‑stained histology images. Rather than directly decoding expression from visual features, BCARP treats histology embeddings as morphological priors and iteratively refines spot representations in a transcriptomics‑oriented latent space, integrating nuclei‑guided local context and prototype‑guided global propagation. Evaluations on three spatial transcriptomics datasets and ten HEST‑1k cohorts show that BCARP outperforms existing baselines in mean correlation‑based metrics, demonstrating the effectiveness of biology‑guided local‑global residual propagation for histology‑to‑transcriptomics prediction.
The paper presents a method for predicting single‑cell spatial gene expression from hematoxylin and eosin (H&E) images by adapting pathology foundation models with domain‑informed, task‑specific strategies. Using paired H&E and Xenium 5K data, the approach improves mean gene‑wise Pearson correlation by 2.67× over a zero‑shot baseline and achieves state‑of‑the‑art performance, with an AUROC of 0.800 across the full gene panel. The study shows that predictive performance varies across biological contexts, achieving the highest correlation for spatially variable genes (r = 0.643), and demonstrates that H&E‑derived representations can recover biologically meaningful spatial expression patterns despite sparse single‑cell measurements.
MIST is a Multi‑context Spatial Transformer that predicts spatial gene expression from H&E images by adding two context pathways to a standard Transformer: a coordinate‑invariant local pathway that attends to spatial k‑nearest‑neighbor spots, and a slide pathway that broadcasts a whole‑slide summary to every spot. In intra‑cohort evaluation across six human organ cohorts, MIST improves mean Pearson correlation by 9.7%–11.6% over the strongest baseline for 10‑, 50‑, and 100‑gene panels, and achieves lower MSE and MAE. It also outperforms baselines in leave‑one‑organ‑out transfer, domain recovery, and reproduces spatial expression patterns of cancer‑marker genes.
arXiv:2607. 14163v1 Announce Type: cross Abstract: Most single-cell foundation models are adapted from language models, representing each cell as a sequence of gene tokens.
arXiv:2608. 14924v1 Announce Type: cross Abstract: Spatial transcriptomics (ST) links tissue morphology with molecular programs, motivating multimodal pretraining methods that align histology images with gene expression.