Loading...

The Pattern Recognition Methods in Combination with Nuclear Magnetic Resonance (NMR)Spectroscopy in Order to Develop a Metabolomic Approach to Breast Cancer Prognosis

Esmaeili, Pedram | 2020

510 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 53599 (03)
  4. University: Sharif University of Technology
  5. Department: Chemistry
  6. Advisor(s): Parastar Shahri, Hadi
  7. Abstract:
  8. The emerging field of “metabolomics” focuses on investigating into the changes of low-molecular-weight – less than 1500 Daltons – molecules, or metabolites, and it has significantly developed in the field of detecting diseases, particularly cancer in recent years. Regarding the importance of breast cancer (BC), especially among women, developing simple, trusted metabolic approaches are crucial. In the present work, utilizing multivariate class-modelling techniques combined to nuclear magnetic resonance (NMR) in order to predict breast cancer based on analyzing the blood serum of healthy and BC patients is presented. To do so, using 42 blood samples, 18 BC patients and 24 healthy individuals, optimizing the process of metabolite extraction is primarily focused on thanks to Box-Behnken experimental design, and based on the design software, the optimized, selected parameters are as follow: blood serum volume of 174 µL, solvent volume of 595 µL, methanol to chloroform ratio of 2:1, and vortex time of 1.5 min. The output NMR data are then preprocessed by baseline and smoothing filtrations, and to correspond our peaks with the literature, ico-shift was implemented on the data. The output of the last step is eventually normalized in order to be comparable with the other data. In the virtue of DD-SIMCA chemometric method, we were able to model the healthy class and distinguish it from the alien class, hence both the sensitivity and specificity of the model are 100%. In the following, in order to interpret the results, we opted for PLS-DA and observed that this model discriminates between the two classes as well and puts every sample in their specified class with sensitivity and specificity of 100%. Thanks to the VIP plot of this technique, variables with the VIP score of 3 or above were chosen as influential variables, among which 13 metabolites such as lactic acid, tartaric acid, and tagatose were detected as the effective factors for this discrimination, and by using the aforementioned metabolites, involved metabolic pathways were also detected
  9. Keywords:
  10. Chemometrics Method ; Classification ; Breast Cancer ; Nuclear Magnetic Resonance Spectroscopy ; Discriminative Model ; Metabolomics

 Digital Object List

 Bookmark

No TOC