Ovarian cancer detection from metabolomic liquid chromatography/mass spectrometry data by support vector machines

Abstract

Background: The majority of ovarian cancer biomarker discovery efforts focus on the identification of proteins that can improve the predictive power of presently available diagnostic tests. We here show that metabolomics, the study of metabolic changes in biological systems, can also provide characteristic small molecule fingerprints related to this disease.

Multiple Myeloma Patients Have a Specific Serum Metabolomic Profile That Changes after Achieving Complete Remission

“…High-resolution 1 H-NMR spectroscopy provides quantitative analysis of metabolite concentrations and reproducible information with minimal sample handling. Particularly in the cancer setting, metabolomics has been applied to develop novel early diagnostic biomarkers in renal cancer (3,4), colorectal cancer (5), pancreatic cancer (6), leukemia (7), ovarian cancer (8,9) and oral cancer (10). More recently, this approach has also been used to provide predictive biomarkers associated with prognosis, response to treatment and toxicity (11,12).…”

Preventive Strategies in Epithelial Ovarian Cancer

“…Biomarkers and respective panels identified with proteomics have the potential to influence ovarian cancer prevention; further development and validation, however, are necessary before they may introduced into clinical practice 89 . Evolving technologies, including transcriptomics 84 , epigenomics 85,86 , metabolomics 90 and glycomics 87 , are also under investigation in ovarian cancer. Transcriptomics, or expression profiling, studies the impact of RNA molecules, including mRNA, rRNA, tRNA and noncoding RNAs, in diseases.…”

“…Metabolomics examines the role of small molecules ("metabolites") which are unique to a specific cellular process. Metabolic fingerprints of ovarian cancer can be measured in serum and/or other bodily fluids using mass spectrometry and has the potential to improve detection of early stage and recurrent disease 90 . Lysophosphatidic acid 91 and lipid associated sialic acid 92 are metabolites which are currently under investigation for ovarian cancer detection.…”

Optimal Algorithm for Metabolomics Classification and Feature Selection varies by Dataset

“…Metabolomics has been increasingly applied towards identification of biomarkers for disease diagnosis, prognosis and risk prediction. Applications extend across the health spectrum including Alzheimer's (Han et al, 2011), cancer (Davis et al, 2012;Guan et al, 2009;Nishiumi et al, 2010), diabetes (Bain et al, 2009), and trauma (Determan et al 2014).…”

“…This project seeks to conduct an in depth comparison of algorithm performance on both simulated and real datasets to determine which algorithms perform best given alternate dataset structures. Three simulated datasets were generated to validate algorithm performance and mimic 'real' metabolomics data: (Han et al, 2011) independent null dataset (no correlation, no discriminatory variables), (Davis, Schiller, Eurich, & Sawyer, 2012) correlated null (no discriminating variables), (Guan et al, 2009) correlated discriminatory. This comparison is also applied to 3 open-access datasets including two Nuclear Magnetic Resonance (NMR) and one Mass Spectrometry (MS) dataset.…”