Evidence map›Paper›PMID 41647237›Full record

ArticleArXiv2026

SAGE-FM: A lightweight and interpretable spatial transcriptomics foundation model.

Xianghao Zhan, Jingyu Xu, Yuanning Zheng, Zinaida Good, Olivier Gevaert

Abstract readPreprint
PubMed Full text at PMC
In one paragraph

Article in ArXiv, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Not yet cited in PubMed.

0numbers the graph read from it
0cells of the map it votes in
0citing papers in PubMed
–field-weighted citation impact
1 · What the graph read from it

What it found

Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.

The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.

2 · The registry

The trial behind it

Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.

Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.

3 · Its place in the literature

Who cites it

0 citing papers in PubMed.

No citing paper in PubMed yet.

4 · The record

Corrections and comments

PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.

5 · Who and what money

Authors and funding

5 authors.

Xianghao ZhanDepartment of Biomedical Data Science, Stanford University, Stanford, CA 94305, USA.
Jingyu XuDivision of Computational Medicine, Department of Medicine, Stanford University, Stanford, CA 94305, USA.
Yuanning ZhengDepartment of Biomedical Data Science, Stanford University, Stanford, CA 94305, USA.
Zinaida GoodDivision of Computational Medicine, Department of Medicine, Stanford University, Stanford, CA 94305, USA.
Olivier GevaertDepartment of Biomedical Data Science, Stanford University, Stanford, CA 94305, USA.

Funding

TUMOR SPECIFIC CYTOTOXIC T-LYMPHOCYTES IN BONE MARROW TRANSPLANTATIONP01CA049605 · NCI · STANFORD UNIVERSITY · PI David B. Miklos, Robert S Negrin · 1989 to 2026
$73.3M
Multimodal AI modeling of T cell therapies to predict patient response and nominate advanced cell design strategiesOT2OD038101 · OD · STANFORD UNIVERSITY · PI Olivier Gevaert, Crystal Mackall · 2025 to 2026
$4.2M
Multi-scale modeling of glioma for the prediction of treatment response, treatment monitoring and treatment allocationR01CA260271 · NCI · STANFORD UNIVERSITY · PI GEVAERT, OLIVIER · 2021 to 2025
$3.1M
Learning features of optimal CAR T cells for LBCL from patient dataR00CA293149 · NCI · STANFORD UNIVERSITY · PI Zinaida Good · 2025 to 2026
$418k
Harnessing multi-modal and multi-omics data integration to decipher therapeutic response in non-small cell lung cancerK99CA293249 · NCI · STANFORD UNIVERSITY · PI Yuanning Zheng · 2025 to 2026
$236k
Learning features of optimal CAR T cells for LBCL from patient dataK99CA293149 · NCI · STANFORD UNIVERSITY · PI GOOD, ZINAIDA · 2024 to 2024
$171k
NCI NIH HHS K99 CA293149NCI NIH HHS K99 CA293249NCI NIH HHS P01 CA049605NCI NIH HHS R00 CA293149NCI NIH HHS R01 CA260271NIH HHS OT2 OD038101
6 · The paper itself

Abstract

Spatial transcriptomics enables spatial gene expression profiling, motivating computational models that capture spatially conditioned regulatory relationships. We introduce SAGE-FM, a lightweight spatial transcriptomics foundation model based on graph convolutional networks (GCN) trained with a masked-central-spot prediction objective. Trained on 416 human Visium samples spanning 15 organs, SAGE-FM learns spatially coherent embeddings that recover masked genes robustly, with 91% of masked genes showing significant correlations (p < 0.05). The SAGE-FM generated embeddings outperform MOFA and spatial transcriptomics in unsupervised clustering and preservation of biological heterogeneity. SAGE-FM generalizes to downstream tasks, enabling 81% accuracy in pathologist-defined spot annotation in oropharyngeal squamous cell carcinoma and improving glioblastoma subtype prediction relative to MOFA.

Indexed as

foundation modelgraph neural networkrepresentation learningself-supervised learningspatial transcriptomics

Identifiers

PMID41647237
PMCPMC12869381

What OpenQuestion holds

Textmetadata
LicenceCC BY-NC-ND
Read underepoch 390

Registered trials

None linked

Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.