Metraipolis › archive › dc_dcb1bf281db3

PaSTel: Anchoring Histology in Spatial Transcriptomics via Multi-Scale Hierarchical Bio-Prior Contrastive Pretraining — arXiv:2608.14924

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.14924
License (as archived): CC0-1.0
Archived: 2026-10-18T17:55:07.923Z
SHA-256 of the archived text: 549d10159385b8891f58f6c41a04b4a06c5b751838f3db0054d9b032cc2e47b6
Stable URL of this page: https://metraipolis.com/documento/dc_dcb1bf281db3

How to cite

PaSTel: Anchoring Histology in Spatial Transcriptomics via Multi-Scale Hierarchical Bio-Prior Contrastive Pretraining — arXiv:2608.14924 — arXiv (en), https://arxiv.org/abs/2608.14924 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dcb1bf281db3 (Metraipolis archive dc_dcb1bf281db3, sha256 549d10159385b8891f58f6c41a04b4a06c5b751838f3db0054d9b032cc2e47b6)

BibTeX

@misc{dcdcb1bf281db3,
  title = {PaSTel: Anchoring Histology in Spatial Transcriptomics via Multi-Scale Hierarchical Bio-Prior Contrastive Pretraining — arXiv:2608.14924},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.14924},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dcb1bf281db3; sha256 549d10159385b8891f58f6c41a04b4a06c5b751838f3db0054d9b032cc2e47b6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14924. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.14924 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T16:29:13.967Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).