Gene expression profiling of breast cancer survivability by pooled cDNA microarray analysis using logistic regression, artificial neural networks and decision trees.

BACKGROUND: Microarray technology can acquire information about thousands of genes simultaneously. We analyzed published breast cancer microarray databases to predict five-year recurrence and compared the performance of three data mining algorithms of artificial neural networks (ANN), decision trees (DT) and logistic regression (LR) and two composite models of DT-ANN and DT-LR. The collection of microarray datasets from the Gene Expression Omnibus, four breast cancer datasets were pooled for predicting five-year breast cancer relapse. After data compilation, 757 subjects, 5 clinical variables and 13,452 genetic variables were aggregated. The bootstrap method, Mann-Whitney U test and 20-fold cross-validation were performed to investigate candidate genes with 100 most-significant p-values. The predictive powers of DT, LR and ANN models were assessed using accuracy and the area under ROC curve. The associated genes were evaluated using Cox regression. RESULTS: The DT models exhibited the lowest predictive power and the poorest extrapolation when applied to the test samples. The ANN models displayed the best predictive power and showed the best extrapolation. The 21 most-associated genes, as determined by integration of each model, were analyzed using Cox regression with a 3.53-fold (95% CI: 2.24-5.58) increased risk of breast cancer five-year recurrence. CONCLUSIONS: The 21 selected genes can predict breast cancer recurrence. Among these genes, CCNB1, PLK1 and TOP2A are in the cell cycle G2/M DNA damage checkpoint pathway. Oncologists can offer the genetic information for patients when understanding the gene expression profiles on breast cancer recurrence.

Gene expression profiling of colorectal tumors and normal mucosa by microarrays meta-analysis using prediction analysis of microarray, artificial neural network, classification, and regression trees.

BACKGROUND: Microarray technology shows great potential but previous studies were limited by small number of samples in the colorectal cancer (CRC) research. The aims of this study are to investigate gene expression profile of CRCs by pooling cDNA microarrays using PAM, ANN, and decision trees (CART and C5.0). METHODS: Pooled 16 datasets contained 88 normal mucosal tissues and 1186 CRCs. PAM was performed to identify significant expressed genes in CRCs and models of PAM, ANN, CART, and C5.0 were constructed for screening candidate genes via ranking gene order of significances. RESULTS: The first screening identified 55 genes. The test accuracy of each model was over 0.97 averagely. Less than eight genes achieve excellent classification accuracy. Combining the results of four models, we found the top eight differential genes in CRCs; suppressor genes, CA7, SPIB, GUCA2B, AQP8, IL6R and CWH43; oncogenes, SPP1 and TCN1. Genes of higher significances showed lower variation in rank ordering by different methods. CONCLUSION: We adopted a two-tier genetic screen, which not only reduced the number of candidate genes but also yielded good accuracy (nearly 100%). This method can be applied to future studies. Among the top eight genes, CA7, TCN1, and CWH43 have not been reported to be related to CRC.