Urine-Based Metabolomics and Machine Learning Reveals Metabolites Associated with Renal Cell Carcinoma Stage

• Type of Material: Article
• Authors: Olatomiwa O Bifarin, University of Georgia; David A Gaul, Georgia Institute of Technology; Samyukta Sah, Georgia Institute of Technology; Rebecca Arnold, Emory University; Kenneth Ogan, Emory University; Viraj Master, Emory University; David Roberts, Emory University; Sharon Bergquist, Emory University; John Petros, Emory University; Arthur S Edison, University of Georgia; Facundo M Fernandez, Georgia Institute of Technology
• Language: English
• Date: 2021-12-01
• Publisher: MDPI
• Publication Version: Final Published Version
• Copyright Statement: © 2021 by the authors.
• License: Creative Commons Attribution 4.0 International
• Final Published Version (URL): http://dx.doi.org/10.3390/cancers13246253
• Title of Journal or Parent Work: CANCERS
• Volume: 13
• Issue: 24
• Grant/Funding Information: F.M.F and A.S.E. acknowledge support by NIH 1U2CES030167-01. F.M.F. was also supported by 1R01CA218664-01, NSF MRI CHE-1726528 and GT discretionary funds.
• Keywords: renal cell carcinoma; tumor metabolism; GRADE; ACID; CANCER; TRANSFER-RNAS; GLYCINE; DIAGNOSIS; BIOMARKERS; Oncology; biomarker; Science & Technology; Life Sciences & Biomedicine; EXPRESSION; metabolomics; QUEUINE; liquid chromatography-mass spectrometry; MASS-SPECTROMETRY; nuclear magnetic resonance spectroscopy; machine learning
• Research Categories: Health Sciences, Medicine and Surgery; Chemistry, Biochemistry; Biology, Molecular

Abstract

Urine metabolomics profiling has potential for non-invasive RCC staging, in addition to pro-viding metabolic insights into disease progression. In this study, we utilized liquid chromatography-mass spectrometry (LC-MS), nuclear magnetic resonance (NMR), and machine learning (ML) for the discovery of urine metabolites associated with RCC progression. Two machine learning questions were posed in the study: Binary classification into early RCC (stage I and II) and advanced RCC stages (stage III and IV), and RCC tumor size estimation through regression analysis. A total of 82 RCC patients with known tumor size and metabolomic measurements were used for the regression task, and 70 RCC patients with complete tumor-nodes-metastasis (TNM) staging information were used for the classification tasks under ten-fold cross-validation conditions. A voting ensemble regression model consisting of elastic net, ridge, and support vector regressor predicted RCC tumor size with a R2 value of 0.58. A voting classifier model consisting of random forest, support vector machines, logistic regression, and adaptive boosting yielded an AUC of 0.96 and an accuracy of 87%. Some identified metabolites associated with renal cell carcinoma progression included 4-guanidinobutanoic acid, 7-aminomethyl-7-carbaguanine, 3-hydroxyanthranilic acid, lysyl-glycine, glycine, citrate, and pyruvate. Overall, we identified a urine metabolic phenotype associated with renal cell carcinoma stage, exploring the promise of a urine-based metabolomic assay for staging this disease.