TY - JOUR
T1 - Intratumor graph neural network recovers hidden prognostic value of multi-biomarker spatial heterogeneity
AU - Qiu, Lida
AU - Kang, Deyong
AU - Wang, Chuan
AU - Guo, Wenhui
AU - Fu, Fangmeng
AU - Wu, Qingxiang
AU - Xi, Gangqin
AU - He, Jiajia
AU - Zheng, Liqin
AU - Zhang, Qingyuan
AU - Liao, Xiaoxia
AU - Li, Lianhuang
AU - Chen, Jianxin
AU - Tu, Haohua
N1 - We would like to thank Wenjiao Ren, Tingfeng Shen, Wei Wang, Zhong Chen, Xiwen Chen, Ye Fang, Xiahui Han, Na Fang, Xinxing Huang and Zhijun Li for their support in the data acquisition of multiphoton images. This work was supported by the National Natural Science Foundation of China (Grant Nos. 82171991, 82172800, 61972187), Fujian Major Scientific and Technological Special Project for “Social Development” (No. 2020YZ016002), Natural Science Foundation of Fujian Province (Nos. 2019J01269, 2019J01761, 2019J01060044, 2020J011008, 2020J01839), Joint Funds for the Innovation of Science and Technology of Fujian Province (2017Y9038, 2019Y9101), and the special Funds of the Central Government Guiding Local Science and Technology Development (No. 2020L3008). Also, this work was supported, in part, by grants from the National Institutes of Health, U.S. Department of Health and Human Services (R01 CA241618 and R41 GM139528 to H.T.).
PY - 2022/12
Y1 - 2022/12
N2 - 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.
AB - 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.
UR - https://www.scopus.com/pages/publications/85134587053
UR - https://www.scopus.com/pages/publications/85134587053#tab=citedBy
U2 - 10.1038/s41467-022-31771-w
DO - 10.1038/s41467-022-31771-w
M3 - Article
C2 - 35869055
AN - SCOPUS:85134587053
SN - 2041-1723
VL - 13
JO - Nature communications
JF - Nature communications
IS - 1
M1 - 4250
ER -