A neural network approach to multi-biomarker panel discovery by high-throughput plasma proteomics profiling of breast cancer

BackgroundIn the past several years, there has been increasing interest and enthusiasm in molecular biomarkers as tools for early detection of cancer. Liquid chromatography tandem mass spectrometry (LC/MS/MS) based plasma proteomics profiling technique is a promising technology platform to study candidate protein biomarkers for early detection of 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. Developing proteomics data analysis methods to identify multi-protein biomarker panels for breast cancer diagnosis based on neural networks provides hope for improving both the sensitivity and the specificity of candidate cancer biomarkers for early detection.ResultsIn our previous method, we developed a Feed Forward Neural Network-based method to build the classifier for plasma samples of breast cancer and then applied the classifier to predict blind dataset of breast cancer. However, the optimal combination C* in our previous method was actually determined by applying the trained FFNN on the testing set with the combination. Therefore, in this paper, we applied a three way data split to the Feed Forward Neural Network for training, validation and testing based. We found that the prediction performance of the FFNN model based on the three way data split outperforms our previous method and the prediction performance is improved from (AUC = 0.8706, precision = 82.5%, accuracy = 82.5%, sensitivity = 82.5%, specificity = 82.5% for the testing set) to (AUC = 0.895, precision = 86.84%, accuracy = 85%, sensitivity = 82.5%, specificity = 87.5% for the testing set).ConclusionsFurther pathway analysis showed that the top three five-marker panels are associated with complement and coagulation cascades, signaling, activation, and hemostasis, which are consistent with previous findings. We believe the new approach is a better solution for multi-biomarker panel discovery and it can be applied to other clinical proteomics.

[1]  F. Grus,et al.  Diagnosis of breast cancer by tear proteomic pattern. , 2009, Cancer genomics & proteomics.

[2]  Yan Zhang,et al.  Comparative serum proteome analysis of human lymph node negative/positive invasive ductal carcinoma of the breast and benign breast disease controls via label-free semiquantitative shotgun technology. , 2009, Omics : a journal of integrative biology.

[3]  Kerry G Bemis,et al.  Label-free mass spectrometry-based protein quantification technologies in proteomic analysis. , 2008, Briefings in functional genomics & proteomics.

[4]  Kevin N. Gurney,et al.  An introduction to neural networks , 2018 .

[5]  Chih-Lin Chi,et al.  Application of Artificial Neural Network-Based Survival Analysis on Two Breast Cancer Datasets , 2007, AMIA.

[6]  Fan Zhang,et al.  IPAD: the Integrated Pathway Analysis Database for Systematic Enrichment Analysis , 2012, BMC Bioinformatics.

[7]  Heaton T. Jeff,et al.  Introduction to Neural Networks with Java , 2005 .

[8]  Ilias Maglogiannis,et al.  Neural network-based diagnostic and prognostic estimations in breast cancer microscopic instances , 2006, Medical and Biological Engineering and Computing.

[9]  Christian W Klampfl,et al.  Review coupling of capillary electrochromatography to mass spectrometry. , 2004, Journal of chromatography. A.

[10]  Terence P. Speed,et al.  A comparison of normalization methods for high density oligonucleotide array data based on variance and bias , 2003, Bioinform..

[11]  Akbar Fotouhi,et al.  Assessment of gastric cancer survival: using an artificial hierarchical neural network. , 2008, Pakistan journal of biological sciences : PJBS.

[12]  Fazel Amiri.  The effect of type of marginal land use on the production of biomass and plant diversity. , 2008, Pakistan journal of biological sciences : PJBS.

[13]  Charles Darwin,et al.  Experiments , 1800, The Medical and physical journal.

[14]  Fan Zhang,et al.  A neural network approach to multi-biomarker panel development based on LC/MS/MS proteomics profiles: A case study in breast cancer , 2009, 2009 22nd IEEE International Symposium on Computer-Based Medical Systems.

[15]  E. Birney,et al.  The International Protein Index: An integrated database for proteomics experiments , 2004, Proteomics.

[16]  Fuu-Jen Tsai,et al.  Artificial neural network-based study can predict gastric cancer staging. , 2008, Hepato-gastroenterology.

[17]  Jeff Heaton,et al.  Introduction to Neural Networks for C#, 2nd Edition , 2008 .

[18]  Richard E Higgs,et al.  Comprehensive label-free method for the relative quantification of proteins from biological samples. , 2005, Journal of proteome research.

[19]  Fan Zhang,et al.  Discovery of pathway biomarkers from coupled proteomics and systems biology methods , 2010, BMC Genomics.

[20]  Kornelia Polyak,et al.  Breast cancer: origins and evolution. , 2007, The Journal of clinical investigation.

[21]  Nick Murray,et al.  Proteomic analysis of archival breast cancer serum. , 2009, Cancer genomics & proteomics.

[22]  Hau-San Wong,et al.  A neural network-based biomarker association information extraction approach for cancer classification , 2009, J. Biomed. Informatics.