EUVIMEDEUVIMED entdecken
Open Access

AI-predicted spatial transcriptomics unlocks breast cancer biomarkers from pathology

Eldad D Shulman, Emma M Campagnolo, Roshan Lodha, Youngmin Chung, Amos Stemmer, Thomas Cantore, Beibei Ru, Tian-Gen Chang, Sumona Biswas, Saugato Rahman Dhruba, Sumeet Patiyal, Sushant Patkar und 22 weitere

Cell · 2026-07 · 189 (14) · 4225-4240.e25

DOI: 10.1016/j.cell.2026.04.023 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Cell, 2026-07. Verfasst von Eldad D Shulman und 33 weiteren Autor:innen. Beteiligte Einrichtung: Cancer Data Science Laboratory, Center for Cancer Research, National Cancer Institute, Bethesda, MD 20892, USA. Electronic address: eldad.shulman@nih…. Hauptthemen laut MEDLINE: Breast Neoplasms, Biomarkers, Tumor, Artificial Intelligence. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 77 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Intramural NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Spatial transcriptomics (ST) assays are transforming our understanding of tumor heterogeneity, but their high cost limits their application in large-scale biomarker discovery. Here, we present "Path2Space," a deep-learning model that predicts spatial gene expression directly from histopathology slides. Trained on extensive breast cancer ST data, Path2Space robustly predicts the spatial expression of thousands of genes, outperforming 21 established methods. Charting the tumor microenvironment (TME) of 976 breast cancer TCGA (The Cancer Genome Atlas) tumors, it accurately infers cell-type abundances and identifies three spatially defined breast cancer subgroups with distinct survival outcomes. Notably, the derived low-cost spatial TME landscapes enable more accurate predictions of patient response to chemotherapy and trastuzumab compared with costly conventional bulk-sequencing-based biomarkers. Path2Space thus offers a scalable, fast, and cost-effective alternative to molecular assays. It opens avenues for large cohort treatment biomarker discovery and translationally relevant insights into tumor biology, with potential applicability across many cancer indications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Breast NeoplasmsBiomarkers, TumorArtificial IntelligenceHumansFemaleSpatial TranscriptomicsTumor MicroenvironmentGene Expression Regulation, NeoplasticDeep LearningTranscriptomeErb-b2 Receptor Tyrosine KinasesTrastuzumab

Stichwörter der Autor:innen

HER2artificial intelligencebreast cancerdeep learningdigital pathologyhistopathologyspatial biomarkersspatial transcriptomicstreatment response predictiontumor microenvironment

Substanzen

Biomarkers, TumorErb-b2 Receptor Tyrosine KinasesTrastuzumab

Autor:innen und Institutionen

  • Cancer Data Science Laboratory, Center for Cancer Research, National Cancer Institute, Bethesda, MD 20892, USA. Electronic address: eldad.shulman@nih.gov.
  • Cancer Data Science Laboratory, Center for Cancer Research, National Cancer Institute, Bethesda, MD 20892, USA; Center for Bioinformatics and Computational Biology, University of Maryland, College Park, College Park, MD…
  • Cancer Data Science Laboratory, Center for Cancer Research, National Cancer Institute, Bethesda, MD 20892, USA.
  • Department of Artificial Intelligence, Sungkyunkwan University, Suwon 16419, South Korea.
  • Cancer Data Science Laboratory, Center for Cancer Research, National Cancer Institute, Bethesda, MD 20892, USA; Faculty of Medical and Health Sciences, Tel Aviv University, Tel Aviv 6997801, Israel.
  • Artificial Intelligence Resource, Molecular Imaging Branch, Center for Cancer Research, National Cancer Institute, Bethesda, MD 20892, USA.

Förderung

  • Intramural NIH HHS

Zitieren

APA

Shulman, E. D., Campagnolo, E. M., Lodha, R., Chung, Y., Stemmer, A., Cantore, T., Ru, B., Chang, T. G., Biswas, S., Dhruba, S. R., Patiyal, S., Patkar, S., Wang, A., Barman, R. K., Wang, C., Paul, R., Kalisetty, S. C., Hu, T., Nasrallah, M. P., …, & Ruppin, E. (2026). AI-predicted spatial transcriptomics unlocks breast cancer biomarkers from pathology. Cell, 189(14), 4225-4240.e25. https://doi.org/10.1016/j.cell.2026.04.023

Vancouver

Shulman ED, Campagnolo EM, Lodha R, Chung Y, Stemmer A, Cantore T, et al. AI-predicted spatial transcriptomics unlocks breast cancer biomarkers from pathology. Cell. 2026;189(14):4225-4240.e25. doi:10.1016/j.cell.2026.04.023

BibTeX
@article{Shulman2026,
  author = {Shulman, Eldad D and Campagnolo, Emma M and Lodha, Roshan and Chung, Youngmin and Stemmer, Amos and Cantore, Thomas and Ru, Beibei and Chang, Tian-Gen and Biswas, Sumona and Dhruba, Saugato Rahman and Patiyal, Sumeet and Patkar, Sushant and Wang, Andrew and Barman, Ranjan K and Wang, Chuhan and Paul, Rohit and Kalisetty, Sarath Chandra and Hu, Tom and Nasrallah, MacLean P and Patrick, Ellis and Yang, Jean and Yuan, Yuan and Sargsyan, Karine and Plotkin, Amy and Rajagopal, Padma Sheila and Sammut, Stephen-John and Lipkowitz, Stanley and Jiang, Peng and Caldas, Carlos and Knott, Simon R V and Aldape, Kenneth and Lee, Joo Sang and Hoang, Danh-Tai and Ruppin, Eytan},
  title = {AI-predicted spatial transcriptomics unlocks breast cancer biomarkers from pathology},
  journal = {Cell},
  year = {2026},
  volume = {189},
  number = {14},
  pages = {4225--4240.e25},
  doi = {10.1016/j.cell.2026.04.023}
}
Kostenlos starten →