Coupled Mass-Spectrometry-Based Lipidomics Machine Learning Approach for Early Detection of Clear Cell Renal Cell Carcinoma

Manzi, Malena; Palazzo, Martín; Knott, María Elena; Beauseroy, Pierre; Yankilevich, Patricio; Giménez, María Isabel; Monge, Marı́a Eugenia

doi:10.1021/acs.jproteome.0c00663

Cited by 16 publications

(39 citation statements)

References 110 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning and omics data have also been used to identify leukemia in children with 90% accuracy by combining the supervised classification tool, XGBoost, with LC–MS data quantifying amino acids . In another example, lipidomics data were analyzed with LASSO feature selection and an SVM classifier to accurately classify patients with renal cancer . The combination of the latest omics techniques with emerging machine learning methods provides researchers with new opportunities to do a better job at identifying disease states.…”

Section: Introductionmentioning

confidence: 99%

“…More recent supervised classification strategies that leverage the power and speed of modern computing, including Support Vector Machine (SVM) and decision tree-based classifiers, such as XGBoost, show even greater promise for omics researchers over these older methods. In several examples of studies using mass spectrometry data, SVM was the method of choice for performing supervised classification; , this approach outperformed methods such as linear discriminant analysis and partial least-squares discriminant analysis on multiple proteomics data sets. , Decision-tree-based classifiers, including Random Forest, boosted decision trees, and XGBoost, have shown similar promise for accurate classification of omics data. ,, The development of new and better classifiers provides new opportunities to do a better job of supervised classification, which translates into an enhanced ability to discriminate disease and ultimately improve health outcomes.…”

Section: Introductionmentioning

confidence: 99%

“…2 In another example, lipidomics data were analyzed with LASSO feature selection and an SVM classifier to accurately classify patients with renal cancer. 3 The combination of the latest omics techniques with emerging machine learning methods provides researchers with new opportunities to do a better job at identifying disease states.…”

Section: ■ Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Improved Discrimination of Disease States Using Proteomics Data with the Updated Aristotle Classifier

Hua

Desaire

2021

J. Proteome Res.

View full text Add to dashboard Cite

Mass spectrometry data sets from omics studies are an optimal information source for discriminating patients with disease and identifying biomarkers. Thousands of proteins or endogenous metabolites can be queried in each analysis, spanning several orders of magnitude in abundance. Machine learning tools that effectively leverage these data to accurately identify disease states are in high demand. While mass spectrometry data sets are rich with potentially useful information, using the data effectively can be challenging because of missing entries in the data sets and because the number of samples is typically much smaller than the number of features, two challenges that make machine learning difficult. To address this problem, we have modified a new supervised classification tool, the Aristotle Classifier, so that omics data sets can be better leveraged for identifying disease states. The optimized classifier, AC.2021, is benchmarked on multiple data sets against its predecessor and two leading supervised classification tools, Support Vector Machine (SVM) and XGBoost. The new classifier, AC.2021, outperformed existing tools on multiple tests using proteomics data. The underlying code for the classifier, provided herein, would be useful for researchers who desire improved classification accuracy when using their omics data sets to identify disease states.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Improved Discrimination of Disease States Using Proteomics Data with the Updated Aristotle Classifier

Hua

Desaire

2021

J. Proteome Res.

View full text Add to dashboard Cite

show abstract

“…In addition, Falegan et al showed the potential for discriminating between pT1 and pT3 tumor stages using gas chromatography (GC)-MS of serum samples coupled to Partial Least Squares-Discriminant Analysis (PLS-DA) modeling, but did not identify the chemical structure of the metabolites responsible for such clustering [ 14 ]. Furthermore, Monge and co-workers recently reported a 26-lipid panel that discriminates early from late-stage clear cell RCC in human serum samples [ 15 ]. Arendowski et al identified indole-3-acetylglycine, urothion, and myo-inositol 1,4-bisphosphate in urine samples as potential markers to discriminate low stages (pT1 and pT2) from high stages (pT1 and pT2) RCC [ 16 ].…”

Section: Introductionmentioning

confidence: 99%

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

Bifarin

Gaul

Sah

et al. 2021

Cancers

View full text Add to dashboard Cite

Urine metabolomics profiling has potential for non-invasive RCC staging, in addition to providing 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.

show abstract

“…For renal cancer patients treated with the Chinese medicine antitumor formula, an index with high consistency with the mechanism of action should be selected. VEGF is an important indicator that reflects the ability of blood vessel proliferation, and CRP is closely related to the level of inflammation in patients [ 12 – 14 ]. In addition to VEGF, Ang is also closely associated with angiogenesis, and Ang-1 and Ang-2 in this protein family belong to angiogenesis regulators.…”

Section: Introductionmentioning

confidence: 99%

The Diagnostic Value of Serum Ang, VEGF, and CRP Combined with the Chinese Medicine Antitumor Formula in the Treatment of Advanced Renal Carcinoma

Dong

Zhang

et al. 2021

Evidence-Based Complementary and Alternative Medicine

View full text Add to dashboard Cite

Objective. To explore the diagnostic value of serum angiopoietin (Ang), vascular endothelial growth factor (VEGF), and C-reactive protein (CRP) combined with the Chinese medicine antitumor formula in the treatment of advanced renal carcinoma. Methods. Retrospective analysis was performed for the data of 60 patients with advanced renal cancer admitted at Yantaishan Hospital from February 2019 to February 2020. All patients were treated with Chinese medicine antitumor formula. The serum Ang, VEGF, and CRP levels in venous blood samples were detected before and after treatment. Sensitivity, specificity, and AUC of combined serum Ang, VEGF, and CRP were analyzed utilizing the receiver operating characteristic curve (ROC) (95% CI). Results. There were 52 cases of clear-cell carcinoma (86.7%), 7 cases of papillary carcinoma (11.7%), and 1 case of chromophobe renal cell carcinoma (1.7%). The average tumor diameter was (9.67 ± 0.65) cm, and the KPS score was (74.68 ± 1.52). About 75% of the patients had metastasis. After treatment, the level of serum Ang, VEGF, and CRP was immensely lower compared to that before treatment ( P < 0.001). The sensitivity, specificity, and AUC (95%CI) of the combined detection of Ang, VEGF, and CRP before treatment were 86.7%, 90.0%, and 0.883 (0.817–0.950), while the sensitivity, specificity, and AUC (95%CI) of the combined detection of Ang, VEGF, and CRP were 83.3%, 86.7%, and 0.850 (0.776–0.9524), respectively. Conclusion. The combined detection of serum Ang, VEGF, and CRP has high diagnostic value for patients with advanced renal cancer treated with Chinese medicine antitumor formula.

show abstract

Coupled Mass-Spectrometry-Based Lipidomics Machine Learning Approach for Early Detection of Clear Cell Renal Cell Carcinoma

Cited by 16 publications

References 110 publications

Improved Discrimination of Disease States Using Proteomics Data with the Updated Aristotle Classifier

Improved Discrimination of Disease States Using Proteomics Data with the Updated Aristotle Classifier

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

The Diagnostic Value of Serum Ang, VEGF, and CRP Combined with the Chinese Medicine Antitumor Formula in the Treatment of Advanced Renal Carcinoma

Contact Info

Product

Resources

About