Research Approach With Machine Learning Underpinned

This chapter describes several methodologies and proposed models used to examine the accuracy and efficiency of high-performance colon-cancer feature selection and classification algorithms to solve the problems identified in Chapter 2. An elaboration of the diverse methods of gene/feature selection algorithms and the related classification algorithms implemented throughout this study are presented. A prototypical methodology blueprint for each experiment is developed to answer the research questions in Chapter 1. Each system model is also presented, and the measures used to validate the performance of the model's outcome are discussed.

Findings for the Conducted Investigations

This chapter focuses on the results produced from each case study experiment. For case one, the experiments were conducted in three phases. Phase one implemented GA, PSO, and IG as the gene/feature selection algorithms over the entire dataset. Phase =two2 utilised the original dataset to implement only the cancer classification algorithms without involving any gene/feature selection algorithms. Four recognised classification algorithms are employed: SVM, NB, GP, and DT. The third phase implemented the combined approach of gene selection and cancer classification algorithms. The results of these phases are presented in the next subsections. For case two, these experiments were implemented in two phases. Phase one implemented the classification algorithms over the features selected by the hybridised selection algorithms (GA+IG), whereas Phase two classified the features using the proposed two-stage multifilter selection system. In this section, the results are presented as follows

Gene Selection for the Discrimination of Colorectal Cancer

Background: Colorectal cancer (CRC) is the third most common cancer worldwide. Cancer discrimination is a typical application of gene expression analysis using a microarray technique. However, microarray data suffer from the curse of dimensionality and usual imbalanced class distribution between the majority (tumor samples) and minority (normal samples) classes. Feature gene selection is necessary and important for cancer discrimination. Objectives: To select feature genes for the discrimination of CRC. Methods: We select out 16 single-gene feature sets for colorectal cancer discrimination and 19 single-gene feature sets only for colon cancer discrimination. Results: In summary, we find a series of high potential candidate biomarkers or signatures, which can discriminate either or both of colon cancer and rectal cancer with high sensitivity and specificity.

Integrating ensemble systems biology feature selection and bimodal deep neural network for breast cancer prognosis prediction

MotivationBreast cancer is a heterogeneous disease. In order to guide proper treatment decisions for each individual patient, there is an urgent need for robust prognostic biomarkers that allow reliable prognosis prediction. Gene feature selection on microarray data is an approach to systematically discover potential biomarkers. However, common pure-statistical feature selection approaches often fail to incorporate prior biological knowledge and thus tend to select genes that lack biological insights. In addition, due to the high dimensionality and low sample size properties of microarray data, selecting robust gene features is an intrinsically challenging problem. We therefore combined systems biology feature selection with ensemble learning in this study, aiming to address the above challenges and select genes with biological insights, as well as robust prognostic predictive power. Moreover, in order to capture the complex molecular processes of breast cancer, where multiple disease-contributing genes may exist and interact, we adopted a multi-gene approach to predict the prognosis status using machine learning classifiers.ResultsWe systematically evaluated three different ensemble approaches that all improved the original systems biology feature selector. We found that compared to the most popular data-perturbation approach, function perturbation can produce significant improvement with just a few ensembles. Among all, the hybrid ensemble approach led to the most robust feature selection result, and the identified genes were shown to be highly involved in pathways, such as ubiquitination and cell cycle. Final prognosis prediction models were constructed using the identified genes and clinical information as input features. Among all models, bimodal deep neural network (DNN) achieved the highest AUC (area under receiver operating characteristic curve) in test performance evaluation, where subsequent survival analysis also verified its ability to differentiate patients with different prognosis statuses. In summary, the study demonstrated the potential of ensemble learning to improve gene feature selection robustness, as well as the potential of bimodal DNN in providing reliable prognosis prediction and guiding precision medicine.