AI-driven 3D Spatial Transcriptomics

2025-02-25

AI Summary

Current spatial transcriptomics (ST) technologies are constrained by reliance on 2D tissue sections, labor-intensive protocols, poor scalability, and incompatibility with non-destructive 3D imaging. To address these limitations, we propose VORTEX—the first deep learning–based cross-modal framework for 3D transcriptome prediction. Integrating U-Net and Transformer architectures, VORTEX leverages multi-scale morphology–transcriptome registration, self-supervised pretraining, and target-region fine-tuning to reconstruct whole-tissue, subcellular-resolution 3D gene expression maps from minimal 2D ST data and standard 3D morphological images (e.g., light-sheet microscopy). The method is compatible with mainstream 3D imaging platforms, achieves >100× computational speedup, reduces experimental cost by 90%, and enables large-scale modeling and interactive visualization. VORTEX significantly accelerates morphology–molecular correlation analysis and biomarker discovery.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data

Abstract

A comprehensive three-dimensional (3D) map of tissue architecture and gene expression is crucial for illuminating the complexity and heterogeneity of tissues across diverse biomedical applications. However, most spatial transcriptomics (ST) approaches remain limited to two-dimensional (2D) sections of tissue. Although current 3D ST methods hold promise, they typically require extensive tissue sectioning, are complex, are not compatible with non-destructive 3D tissue imaging technologies, and often lack scalability. Here, we present VOlumetrically Resolved Transcriptomics EXpression (VORTEX), an AI framework that leverages 3D tissue morphology and minimal 2D ST to predict volumetric 3D ST. By pretraining on diverse 3D morphology-transcriptomic pairs from heterogeneous tissue samples and then fine-tuning on minimal 2D ST data from a specific volume of interest, VORTEX learns both generic tissue-related and sample-specific morphological correlates of gene expression. This approach enables dense, high-throughput, and fast 3D ST, scaling seamlessly to large tissue volumes far beyond the reach of existing 3D ST techniques. By offering a cost-effective and minimally destructive route to obtaining volumetric molecular insights, we anticipate that VORTEX will accelerate biomarker discovery and our understanding of morphomolecular associations and cell states in complex tissues. Interactive 3D ST volumes can be viewed at https://vortex-demo.github.io/

Problem

• AI predicts 3D gene expression
• Minimizes tissue destruction in 3D imaging
• Scales to large tissue volumes

Innovation

• AI predicts 3D transcriptomics from 2D data
• Pretrains on 3D morphology-transcriptomic pairs
• Enables high-throughput, scalable 3D spatial transcriptomics