aiqbench analysis
PaSTel advances spatial transcriptomics by integrating multiscale biological priors—ranging from gene reweighting to pathway anchoring—to overcome limitations in current multimodal alignment methods. This hierarchical framework successfully captures critical spatial dependencies, yielding superior representations for downstream tasks compared to standard vision and omics encoders. The work demonstrates a significant step forward in leveraging structured domain knowledge within AI models for complex bio-medical data analysis.
PaSTel: Anchoring Histology in Spatial Transcriptomics via Multi-Scale Hierarchical Bio-Prior Contrastive Pretraining
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. However, existing approaches suffer from two key limitations: spatially informative gene selection is often dominated by ubiquitous housekeeping genes, leading to weakly discriminative representations, and independent spot-patch alignment fails to capture spatial dependencies that are critical for tissue organization. To address these challenges, we introduce PaSTel, a hierarchical multimodal pretraining framework that integrates biological priors at three levels. At the spot level, TF-IDF reweighting is used to identify spatially informative genes; at the functional level, curated KEGG pathways serve as anchors for encoding global biological semantics; and at the regional level, spatial clustering aggregates neighboring spots to model meso-scale tissue structure. Across multiple downstream tasks, PaSTel consistently outperforms existing vision and vision-omics encoders, demonstrating that incorporating multiscale biological priors yields more informative and transferable representations for spatial transcriptomics.
Abstract:Spatial transcriptomics (ST) links tissue morphology with molecular programs, motivating multimodal pretraining methods that align histology images with gene expression. However, existing approaches suffer from two key limitations: spatially informative gene selection is often dominated by ubiquitous housekeeping genes, leading to weakly discriminative representations, and independent spot-patch alignment fails to capture spatial dependencies that are critical for tissue organization. To address these challenges, we introduce PaSTel, a hierarchical multimodal pretraining framework that integrates biological priors at three levels. At the spot level, TF-IDF reweighting is used to identify spatially informative genes; at the functional level, curated KEGG pathways serve as anchors for encoding global biological semantics; and at the regional level, spatial clustering aggregates neighboring spots to model meso-scale tissue structure. Across multiple downstream tasks, PaSTel consistently outperforms existing vision and vision-omics encoders, demonstrating that incorporating multiscale biological priors yields more informative and transferable representations for spatial transcriptomics.
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
68T07, cs.LG, q-bio.GN
arXiv:2608.14924 [cs.CV]
(or arXiv:2608.14924v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2608.14924 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 251 words
Related coverage
HierarchicalDAEW: Domain-Aware Edge-Weighted Graph Convolution with Evidential Uncertainty for Multi-Section Spatial Gene Expression Prediction from H&E Histology
arXiv · Jul 24, 2026
Imaging-anchored Multiomics in Cardiovascular Disease: Integrating Cardiac Imaging, Bulk, Single-cell, and Spatial Transcriptomics
arXiv · Oct 15, 2026
BioKERN: Biological Kernel Regularization for Histology-to-Transcriptomics Neighborhood Retrieval
arXiv · Aug 26, 2026
Samples, Sources, Space: Decomposing Data Scale in Spatially Structured Representation Learning of Human Brain Microarchitecture
arXiv · Sep 28, 2026