Metraipolis › archive › dc_ee428a2a2d78
VGL-stGen: Learning a shared multimodal model for lung histology and spatial transcriptomics — arXiv:2610.28266
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.28266
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-21T07:08:22.880Z
- SHA-256 of the archived text
5e242cf00792a0a2d85c0580e18870c75a82ac127f4c29b267e6535efb6695be- Stable URL of this page
https://metraipolis.com/documento/dc_ee428a2a2d78
How to cite
VGL-stGen: Learning a shared multimodal model for lung histology and spatial transcriptomics — arXiv:2610.28266 — arXiv (en), https://arxiv.org/abs/2610.28266 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ee428a2a2d78 (Metraipolis archive dc_ee428a2a2d78, sha256 5e242cf00792a0a2d85c0580e18870c75a82ac127f4c29b267e6535efb6695be)
BibTeX
@misc{dcee428a2a2d78,
title = {VGL-stGen: Learning a shared multimodal model for lung histology and spatial transcriptomics — arXiv:2610.28266},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.28266},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ee428a2a2d78; sha256 5e242cf00792a0a2d85c0580e18870c75a82ac127f4c29b267e6535efb6695be},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.28266. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
VGL-stGen is a multimodal large language model adapted from a pretrained medical vision-language model using paired lung H&E and spatial transcriptomics with single-cell references. Training integrates image-expression and expression-cell-type pairs, and gene-conditioned pseudo-labels transfer transcriptomic cell-type supervision to histology images. One deployed checkpoint supports thirteen evaluated tasks spanning tissue and cell-type classification, gene prediction and conditional expression completion from combinations of histology, cell identity and observed gene expression. Task-specific decoding produces categorical labels, gene lists and structured expression levels. For conditional completion, fixing queried gene identities and predicting their levels autoregressively improves structured prediction. Controlled adaptation shows that restricting supervision to requested expression-level tokens can further improve image-conditioned completion. Image-permutation experiments indicate that correctly paired histology adds information beyond observed expression. External classification relies partly on computational references with shared annotation lineage, and some H&E sources were exposed during cancer training or model development. Within these conditions, VGL-stGen demonstrates how a medical vision-language backbone can learn from spatial transcriptomics and histology to connect tissue morphology and molecular states through shared generative modeling. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Quantitative Methods (q-bio.QM). Pagina del lavoro: https://arxiv.org/abs/2610.28266 — 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 2026-10-21T07:05:43.637Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).