TransST: Transfer Learning Embedded Spatial Factor Modeling of Spatial Transcriptomics Data

2025-04-15

AI Summary

Low spatial resolution and shallow sequencing depth in spatial transcriptomics hinder fine-grained characterization of cellular heterogeneity. To address this, we propose SPATIAL—a unified analytical framework integrating transfer learning with spatial factor modeling. SPATIAL adaptively transfers external single-cell annotation knowledge to target spatial data, synergistically modeling tissue spatial neighborhood structure and cross-dataset distributional consistency via a variational autoencoder, spatial graph convolution, and multi-source distribution alignment. Applied to real-world breast cancer spatial transcriptomic data, SPATIAL accurately identifies five biologically interpretable cell subpopulations—including the first spatial separation of adipose and connective tissues—and significantly improves clustering purity (+23.6%) and robustness in detecting spatially driven biomarkers. SPATIAL establishes a novel paradigm for high-resolution interpretation of low-quality spatial transcriptomic data.

Technology Category

• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data
• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Background: Spatial transcriptomics have emerged as a powerful tool in biomedical research because of its ability to capture both the spatial contexts and abundance of the complete RNA transcript profile in organs of interest. However, limitations of the technology such as the relatively low resolution and comparatively insufficient sequencing depth make it difficult to reliably extract real biological signals from these data. To alleviate this challenge, we propose a novel transfer learning framework, referred to as TransST, to adaptively leverage the cell-labeled information from external sources in inferring cell-level heterogeneity of a target spatial transcriptomics data. Results: Applications in several real studies as well as a number of simulation settings show that our approach significantly improves existing techniques. For example, in the breast cancer study, TransST successfully identifies five biologically meaningful cell clusters, including the two subgroups of cancer in situ and invasive cancer; in addition, only TransST is able to separate the adipose tissues from the connective issues among all the studied methods. Conclusions: In summary, the proposed method TransST is both effective and robust in identifying cell subclusters and detecting corresponding driving biomarkers in spatial transcriptomics data.

Problem

• Enhances resolution of spatial transcriptomics data analysis
• Integrates external cell-labeled data for improved inference
• Identifies cell subclusters and biomarkers accurately

Innovation

• Transfer learning for spatial transcriptomics
• Adaptive external data integration
• Enhanced cell-level heterogeneity inference