TY - GEN
T1 - A Neural network approach to multi-biomarker panel development based on LC/MS/MS proteomics profiles
AU - Zhang, Fan
AU - Chen, Jake Y.
PY - 2009
Y1 - 2009
N2 - Liquid chromatography tandem mass spectrometry (LC/MS/MS) based plasma proteomics profiling technique is a promising technology platform to study candidate protein biomarkers for complex human diseases such as cancer. Factors such as inherent variability, protein detectability limitation, and peptide discovery biases among LC/MS/MS platforms have made the classification and prediction of proteomics profiles challenging. In this paper, we developed a proteomics data analysis method to identify multiprotein biomarker panels for breast cancer diagnosis based on artificial neural networks. Using this method, we first applied standard analysis of variance (ANOVA) to derive a list of single candidate biomarkers that significantly changed from plasma proteomics profiles between breast cancer and controls. Next, we constructed a feed forward neural network (FFNN) for each combination of single marker proteins and trained with plasma proteomics results derived from 40 breast cancer women and 40 control women. We evaluated the results for best fivemarker panel and ten-marker panels on a testing data set of similar cohort of 80 plasma proteomics profiles, of which half are breast cancer women and half are controls, using both statistical methods (receiver operating characteristics curve comparisons) and biological literature validation. We found that fivemarker panel using two-variable FFNN output achieved the best prediction performance in testing data set, with 82.5% in sensitivity and 82.5% in specificity. Our computational method can serve as a general model for multi-biomarker panel discovery applications in other diseases.
AB - Liquid chromatography tandem mass spectrometry (LC/MS/MS) based plasma proteomics profiling technique is a promising technology platform to study candidate protein biomarkers for complex human diseases such as cancer. Factors such as inherent variability, protein detectability limitation, and peptide discovery biases among LC/MS/MS platforms have made the classification and prediction of proteomics profiles challenging. In this paper, we developed a proteomics data analysis method to identify multiprotein biomarker panels for breast cancer diagnosis based on artificial neural networks. Using this method, we first applied standard analysis of variance (ANOVA) to derive a list of single candidate biomarkers that significantly changed from plasma proteomics profiles between breast cancer and controls. Next, we constructed a feed forward neural network (FFNN) for each combination of single marker proteins and trained with plasma proteomics results derived from 40 breast cancer women and 40 control women. We evaluated the results for best fivemarker panel and ten-marker panels on a testing data set of similar cohort of 80 plasma proteomics profiles, of which half are breast cancer women and half are controls, using both statistical methods (receiver operating characteristics curve comparisons) and biological literature validation. We found that fivemarker panel using two-variable FFNN output achieved the best prediction performance in testing data set, with 82.5% in sensitivity and 82.5% in specificity. Our computational method can serve as a general model for multi-biomarker panel discovery applications in other diseases.
UR - http://www.scopus.com/inward/record.url?scp=70449632949&partnerID=8YFLogxK
U2 - 10.1109/CBMS.2009.5255456
DO - 10.1109/CBMS.2009.5255456
M3 - Conference contribution
AN - SCOPUS:70449632949
SN - 9781424448784
T3 - Proceedings - IEEE Symposium on Computer-Based Medical Systems
BT - 2009 22nd IEEE International Symposium on Computer-Based Medical Systems, CBMS 2009
Y2 - 2 August 2009 through 5 August 2009
ER -