# Self-supervised pretraining with NuSPIRe unlocks nuclear morphology-driven insights in spatial omics

## TL;DR

NuSPIRe is a deep learning model that uses nuclear shape data to improve understanding of cell biology and spatial omics.

## Contribution

NuSPIRe introduces a self-supervised deep learning approach for analyzing nuclear morphology and integrating it with spatial omics data.

## Key findings

- NuSPIRe performs robust cell type identification and perturbation detection with limited annotations.
- The model reveals correlations between nuclear morphology and gene expression in spatial omics.
- NuSPIRe enhances data efficiency by optimizing region-of-interest identification and field-of-view selection.

## Abstract

Nuclear morphology encodes rich phenotypic information critical for understanding cellular states, yet its full potential remains untapped in biomedical analysis. This study introduces NuSPIRe, a self-supervised deep learning model designed to analyze nuclear morphology using DAPI-stained images. Pretrained on 15.52 million cell nucleus images, NuSPIRe performs robustly in cell type identification and perturbation detection, even with limited annotations. Moreover, NuSPIRe integrates nuclear morphology with spatial omics data, uncovering significant correlations between cellular structure and gene expression. Notably, NuSPIRe further enables AI-driven experimental optimization for region-of-interest identification and field-of-view selection, enhancing data efficiency in spatial omics and molecular cell biology.

The online version contains supplementary material available at 10.1186/s13059-026-03987-2.