# Spatially Gene Expression Prediction using Dual-Scale Contrastive Learning

arXiv: https://arxiv.org/abs/2506.23827 · HTML: https://mlsanity.com/paper/2506.23827/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 36 references that are in the map.
- First posted on arXiv 30 Jun 2025.

## Builds on (most cited first, 15 of 15)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [CoCa: Contrastive Captioners are Image-Text Foundation Models](https://mlsanity.com/paper/2205.01917/) (2022)
- [HEST-1k: A Dataset for Spatial Transcriptomics and Histology Image Analysis](https://mlsanity.com/paper/2406.16192/) (2024)
- [Spatially Resolved Gene Expression Prediction from H&E Histology Images via Bi-modal Contrastive Learning](https://mlsanity.com/paper/2306.01859/) (2023)
- [Accurate Spatial Gene Expression Prediction by integrating Multi-resolution features](https://mlsanity.com/paper/2403.07592/) (2024)
- [Exemplar Guided Deep Neural Network for Spatial Transcriptomics Analysis of Gene Expression Prediction](https://mlsanity.com/paper/2210.16721/) (2022)
- [Multimodal contrastive learning for spatial gene expression prediction using histology images](https://mlsanity.com/paper/2407.08216/) (2024)
- [STimage-1K4M: A histopathology image-gene expression dataset for spatial transcriptomics](https://mlsanity.com/paper/2406.06393/) (2024)
- [Prototype-Based Image Prompting for Weakly Supervised Histopathological Image Segmentation](https://mlsanity.com/paper/2503.12068/) (2025)
- [Multimodal Cancer Survival Analysis via Hypergraph Learning with Cross-Modality Rebalance](https://mlsanity.com/paper/2505.11997/) (2025)
- [Approximate Equivariance SO(3) Needlet Convolution](https://mlsanity.com/paper/2206.10385/) (2022)
- [Boundary-Guided Learning for Gene Expression Prediction in Spatial Transcriptomics](https://mlsanity.com/paper/2412.04072/) (2024)
- [The Effect of Batch Size on Contrastive Self-Supervised Speech Representation Learning](https://mlsanity.com/paper/2402.13723/) (2024)

## Built on by (most cited first, 7 of 7)

- [HEXST: Hexagonal Shifted-Window Transformer for Spatial Transcriptomics Gene Expression Prediction](https://mlsanity.com/paper/2605.04682/) (2026)
- [GAOT: Generating Articulated Objects Through Text-Guided Diffusion Models](https://mlsanity.com/paper/2512.03566/) (2025)
- [FEAST: Fully Connected Expressive Attention for Spatial Transcriptomics](https://mlsanity.com/paper/2603.25247/) (2026)
- [Harnessing Hypergraphs in Geometric Deep Learning for 3D RNA Inverse Folding](https://mlsanity.com/paper/2512.03592/) (2025)
- [COAST: Context-Aware Differential Learning for Gene Expression Prediction in Spatial Transcriptomics](https://mlsanity.com/paper/2607.09166/) (2026)
- [Path2ST: Hierarchical Cell-Tissue Grounded Cross-Modal Translation for Spatial Transcriptomics](https://mlsanity.com/paper/2608.14710/) (2026)
- [Hyperbolic Contrastive Learning with Entailment for Spatial Transcriptomics](https://mlsanity.com/paper/2609.16207/) (2026)

## Abstract (arXiv)

Spatial transcriptomics (ST) provides crucial insights into tissue micro-environments, but is limited to its high cost and complexity. As an alternative, predicting gene expression from pathology whole slide images (WSI) is gaining increasing attention. However, existing methods typically rely on single patches or a single pathology modality, neglecting the complex spatial and molecular interactions between target and neighboring information (e.g., gene co-expression). This leads to a failure in establishing connections among adjacent regions and capturing intricate cross-modal relationships. To address these issues, we propose NH2ST, a framework that integrates spatial context and both pathology and gene modalities for gene expression prediction. Our model comprises a query branch and a neighbor branch to process paired target patch and gene data and their neighboring regions, where cross-attention and contrastive learning are employed to capture intrinsic associations and ensure alignments between pathology and gene expression. Extensive experiments on six datasets demonstrate that our model consistently outperforms existing methods, achieving over 20% in PCC metrics. Codes are available at https://github.com/MCPathology/NH2ST