TY - JOUR
T1 - AI-driven multimodal algorithm predicts immunotherapy and targeted therapy outcomes in clear cell renal cell carcinoma
AU - Stupichev, Danil
AU - Miheecheva, Natalia
AU - Postovalova, Ekaterina
AU - Lyu, Yang
AU - Ramachandran, Akshaya
AU - Galkin, Ilya
AU - Khegai, Gleb
AU - Perevoshchikova, Kristina
AU - Love, Anna
AU - Menshikova, Sofia
AU - Tarasov, Artem
AU - Svekolkin, Viktor
AU - Bruttan, Maria
AU - Varlamova, Arina
AU - Kriukov, Kirill
AU - Ataullakhanov, Ravshan
AU - Fowler, Nathan
AU - Cheng, Emily
AU - Bagaev, Alexander
AU - Hsieh, James J.
N1 - Publisher Copyright:
© 2025 The Authors
PY - 2025/8/19
Y1 - 2025/8/19
N2 - Treatment for metastatic clear cell renal cell carcinoma (ccRCC) has dramatically advanced with tyrosine kinase inhibitor (TKI) and immune checkpoint inhibitor (ICI) administration. However, most patients eventually succumb to their disease, and toxicities associated with individual treatment modalities are significant. Multiple single-modality transcriptomic signatures have been developed to predict treatment response, yielding insightful yet inconsistent results when applied to independent cohorts. By unifying transcriptomic data from 14 cohorts (total n = 3,621), we present harmonized immune tumor microenvironment (HiTME) ccRCC subtypes validated with spatial proteomics. This AI-based multimodal approach integrates genomic, transcriptomic, and tumor microenvironment (TME) features for ICI and TKI therapy response prediction.
AB - Treatment for metastatic clear cell renal cell carcinoma (ccRCC) has dramatically advanced with tyrosine kinase inhibitor (TKI) and immune checkpoint inhibitor (ICI) administration. However, most patients eventually succumb to their disease, and toxicities associated with individual treatment modalities are significant. Multiple single-modality transcriptomic signatures have been developed to predict treatment response, yielding insightful yet inconsistent results when applied to independent cohorts. By unifying transcriptomic data from 14 cohorts (total n = 3,621), we present harmonized immune tumor microenvironment (HiTME) ccRCC subtypes validated with spatial proteomics. This AI-based multimodal approach integrates genomic, transcriptomic, and tumor microenvironment (TME) features for ICI and TKI therapy response prediction.
KW - artificial intelligence-based predictive modeling
KW - clear cell renal cell carcinoma
KW - immune checkpoint inhibitors
KW - multiplex immunofluorescence
KW - predictive biomarkers
KW - single-cell proteogenomics
KW - spatial heterogeneity
KW - tumor heterogeneity
KW - tumor microenvironment
KW - tyrosine kinase inhibitors
UR - https://www.scopus.com/pages/publications/105013592878
U2 - 10.1016/j.xcrm.2025.102299
DO - 10.1016/j.xcrm.2025.102299
M3 - Article
C2 - 40834854
AN - SCOPUS:105013592878
SN - 2666-3791
VL - 6
JO - Cell Reports Medicine
JF - Cell Reports Medicine
IS - 8
M1 - 102299
ER -