RESUMEN
Data mining has proven to be a reliable method to analyze and discover useful knowledge about various diseases, including cancer research. In particular, data mining and machine learning algorithms to study oral squamous cell carcinoma (OSCC), the most common form of oral cancer, is a new area of research. This malignant neoplasm can be studied using saliva samples. Saliva is an important biofluid that must be used to verify potential biomarkers associated with oral cancer. In this study, first, we provide an overview of OSSC diagnoses based on machine learning and salivary metabolites. To our knowledge, this is the first study to apply advanced data mining techniques to diagnose OSCC. Then, we give new results of classification and feature selection algorithms used to identify potential salivary biomarkers of OSCC. To accomplish this task, we used the filter feature selection random forest importance algorithm and a wrapper methodology to evaluate the importance of metabolites obtained from gas chromatography mass-spectrometry (GC-MS) in the context of differentiation of OSCC and the control group. Salivary samples (n = 68) were collected for the control group, and the OSCC group were from patients matched for gender, age, and smoking habit. The classification process occurred based on Random Forest (RF) classification algorithm along with 10-cross validation. The results showed that glucuronic acid, maleic acid, and batyl alcohol can classify the samples with an area under the curve (AUC) of 0.91 versus an AUC of 0.76 using all 51 metabolites analyzed. The methodology used in this study can assist healthcare professionals and be adopted to discover diagnostic biomarkers for other diseases.
RESUMEN
The urinary volatomic profiling of Indian cohorts composed of 28 lung cancer (LC) patients and 27 healthy subjects (control group, CTRL) was established using headspace solid phase microextraction technique combined with gas chromatography mass spectrometry methodology as a powerful approach to identify urinary volatile organic metabolites (uVOMs) to discriminate among LC patients from CTRL. Overall, 147 VOMs of several chemistries were identified in the intervention groups-including naphthalene derivatives, phenols, and organosulphurs-augmented in the LC group. In contrast, benzene and terpenic derivatives were found to be more prevalent in the CTRL group. The volatomic data obtained were processed using advanced statistical analysis, namely partial least square discriminative analysis (PLS-DA), support vector machine (SVM), random forest (RF), and multilayer perceptron (MLP) methods. This resulted in the identification of nine uVOMs with a higher potential to discriminate LC patients from CTRL subjects. These were furan, o-cymene, furfural, linalool oxide, viridiflorene, 2-bromo-phenol, tricyclazole, 4-methyl-phenol, and 1-(4-hydroxy-3,5-di-tert-butylphenyl)-2-methyl-3-morpholinopropan-1-one. The metabolic pathway analysis of the data obtained identified several altered biochemical pathways in LC mainly affecting glycolysis/gluconeogenesis, pyruvate metabolism, and fatty acid biosynthesis. Moreover, acetate and octanoic, decanoic, and dodecanoic fatty acids were identified as the key metabolites responsible for such deregulation. Furthermore, studies involving larger cohorts of LC patients would allow us to consolidate the data obtained and challenge the potential of the uVOMs as candidate biomarkers for LC.
