Intratumor graph neural network recovers hidden prognostic value of multi-biomarker spatial heterogeneity

Lida Qiu, Deyong Kang, Chuan Wang, Wenhui Guo, Fangmeng Fu, Qingxiang Wu, Gangqin Xi, Jiajia He, Liqin Zheng, Qingyuan Zhang, Xiaoxia Liao, Lianhuang Li (), Jianxin Chen () and Haohua Tu ()
Additional contact information
Lida Qiu: Fujian Normal University
Deyong Kang: Fujian Medical University Union Hospital
Chuan Wang: Fujian Medical University Union Hospital
Wenhui Guo: Fujian Medical University Union Hospital
Fangmeng Fu: Fujian Medical University Union Hospital
Qingxiang Wu: Fujian Normal University
Gangqin Xi: Fujian Normal University
Jiajia He: Fujian Normal University
Liqin Zheng: Fujian Normal University
Qingyuan Zhang: Harbin Medical University Cancer Hospital
Xiaoxia Liao: University of Illinois at Urbana-Champaign
Lianhuang Li: Fujian Normal University
Jianxin Chen: Fujian Normal University
Haohua Tu: University of Illinois at Urbana-Champaign

Nature Communications, 2022, vol. 13, issue 1, 1-12

Abstract: Abstract Biomarkers are indispensable for precision medicine. However, focused single-biomarker development using human tissue has been complicated by sample spatial heterogeneity. To address this challenge, we tested a representation of primary tumor that synergistically integrated multiple in situ biomarkers of extracellular matrix from multiple sampling regions into an intratumor graph neural network. Surprisingly, the differential prognostic value of this computational model over its conventional non-graph counterpart approximated that of combined routine prognostic biomarkers (tumor size, nodal status, histologic grade, molecular subtype, etc.) for 995 breast cancer patients under a retrospective study. This large prognostic value, originated from implicit but interpretable regional interactions among the graphically integrated in situ biomarkers, would otherwise be lost if they were separately developed into single conventional (spatially homogenized) biomarkers. Our study demonstrates an alternative route to cancer prognosis by taping the regional interactions among existing biomarkers rather than developing novel biomarkers.

Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-022-31771-w Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:13:y:2022:i:1:d:10.1038_s41467-022-31771-w

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-022-31771-w

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().