Search

Abstract Integrating genomics and histology for cancer prognosis demonstrates promise. Here, we develop a multi-classifier system integrating a lncRNA-based classifier, a deep learning whole-slide-image-based classifier, and a clinicopathological classifier to accurately predict post-surgery localized (stage I–III) papillary renal cell carcinoma (pRCC) recurrence. The multi-classifier system demonstrates significantly higher predictive accuracy for recurrence-free survival (RFS) compared to the three single classifiers alone in the training set and in both validation sets (C-index 0.831-0.858 vs. 0.642-0.777, p

Germline or somatic loss-of-function mutations of fumarate hydratase (FH) predispose patients to an aggressive form of renal cell carcinoma (RCC). Since other than tumor resection there is no effective therapy for metastatic FH-deficient RCC, an accurate method for early diagnosis is needed. Although MRI or CT scans are offered, they cannot differentiate FH-deficient tumors from other RCCs. Therefore, finding noninvasive plasma biomarkers suitable for rapid diagnosis, screening, and surveillance would improve clinical outcomes. Taking advantage of the robust metabolic rewiring that occurs in FH-deficient cells, we performed plasma metabolomics analysis and identified 2 tumor-derived metabolites, succinyl-adenosine and succinic-cysteine, as excellent plasma biomarkers for early diagnosis. These 2 molecules reliably reflected the FH mutation status and tumor mass. We further identified the enzymatic cooperativity by which these biomarkers are produced within the tumor microenvironment. Longitudinal monitoring of patients demonstrated that these circulating biomarkers can be used for reporting on treatment efficacy and identifying recurrent or metastatic tumors.