Studies on Computational Analysis Approach to Breast Cancer ...

[Abstract]

Breast cancer is the most frequent female cancer in the world. The approach of prognostic diagnosis of breast cancer has been studied for a long time. Urinary nucleosides were recently presented as potential tumor markers for breast cancer by many groups.Urinary nucleosides were usually analyzed using phenylboronate affinity gel chromatography and HPLC or CE. Several kinds of pattern recognizing technique had been used to study prognostic diagnosis of breast cancer using urinary nucleosides. The result indicated these approaches have some disadvantages and need some improvement.In this thesis, we studied computational analysis approach to breast cancer metabonomics. Some key problems in analysis of urinary nucleosides and diagnosis of breast have been solved.This thesis includes three parts:(1) A novel method to establish calibration model of electrophoretic mobilities in capillary zone electorphresis using support vector regression (SVR) is proposed. Nucleotide was studied as an example and orthogonal design was applied to arrange the experiments. Support vector regression was used to establish calibration models to predict the electrophoretic mobilities of nucleotide from separation conditions of capillary zone electorphresis, i. e. column temperature, voltage, buffer concentration and pH. The results showed that the predictive accuracy of calibration models established by SVR was much better than that of the models by PLSR and ANN.(2) A novel approach of improved repeatablity of CZE using sudden change in electric current has been used with the advantages of needing no markers and easy to be integrated in the software of CE.(3) A new approach for diagnose breast cancer using nucleosides in urine based on metabonomics has been proposed. Four key components wereselected as characteristic pattern with certain feature selection method from the experimental data obtained by high performance liquid chromatography method. These four key components were analyzed with HPLC-MS/MS. BP-ANN has been used as pattern recognition tool to classify the samples form healthy persons and patients. The sensitivity, specificity and accuracy of model are higher than 90%. The results show that the proposed diagnostic method have advantages of low complexity and high diagnoses accuracy in the early diagnosis of breast cancer.

Title: Studies on Computational Analysis Approach to Breast Cancer Metabonomics

Category: Liver Cancer

Filename: Studies on Computational Analysis Approach to Breast Cancer Metabonomics.pdf

Pages: 156

Price: US$70.00

Buy This Paper:

Download:

Donated for this research subject:

FAVORITE: ADD TO FAVORITE

Contact: E-Mail:medpaper@hotmail.com

????????????????TEL:1-888-774-999A

How to get this paper's electronic documents?

1, Click the "Buy Now" button to complete the online payment

2, Download the paper's electronic document from the successful payment return page/Or the system will send this paper's electronic document to your E-Mail within 24 hours

Version:zh-cn

Perhaps You will be interested in these papers

Source: http://www.rescancer.com/liver-cancer/36356.html

new york knicks president day lin j.r. smith espn jeremy lin tyson chandler tyson chandler