The wealth of gene expression values being generated by high throughput microarray technologies leads to complex high dimensional datasets. Moreover, many cohorts have the problem of imbalanced classes where the number of patients belonging to each class is not the same. With this kind of dataset, biologists need to identify a small number of informative genes that can be used as biomarkers for a disease.
The identification of a subset of genes having the ability to capture the necessary information to distinguish classes of patients is crucial in bioinformatics applications. Ensemble and bagging methods have been shown to work effectively in the process of gene selection and classification. Testament to that is random forest which combines random decision trees with bagging to improve overall feature selection and classification accuracy. Surprisingly, the adoption of these methods in support vector machines has only recently received attention but mostly on classification not gene selection. This paper introduces an ensemble SVM-Recursive Feature Elimination (ESVM-RFE) for gene selection that follows the concepts of ensemble and bagging used in random forest but adopts the backward elimination strategy which is the rationale of RFE algorithm. The rationale behind this is, building ensemble SVM models using randomly drawn bootstrap samples from the training set, will produce different feature rankings which will be subsequently aggregated as one feature ranking. As a result, the decision for elimination of features is based upon the ranking of multiple SVM models instead of choosing one particular model. Moreover, this approach will address the problem of imbalanced datasets by constructing a nearly balanced bootstrap sample. Our experiments show that ESVM-RFE for gene selection substantially increased the classification performance on five microarray datasets compared to state-of-the-art methods. Experiments on the childhood leukaemia dataset show that an average 9% better accuracy is achieved by ESVM-RFE over SVM-RFE, and 5% over random forest based approach. The selected genes by the ESVM-RFE algorithm were further explored with Singular Value Decomposition (SVD) which reveals significant clusters with the selected data.
Software as a Service (SaaS) is an online software delivery model which permits a third party provider offering software services to be used on-demand by tenants over the internet, instead of installing and maintaining them in their premises. Nowadays, more and more companies are offering their web-base business application by adopting this model. Multi-tenancy is the primary characteristic of SaaS, it allows SaaS vendors to run a single instance application which supports multiple tenants on the same hardware and software infrastructure. This application should be highly customizable to meet tenants' expectations and business requirements. In this paper, we propose a novel customizable database design for multi-tenant applications. Our design introduces an Elastic Extension Tables (EET) which consists of Common Tenant Tables (CTT) and Virtual Extension Tables (VET). This design enables tenants to create their own elastic database schema during multi-tenant application run-time execution to satisfy their business needs.
Gene expression data is a very complex data set characterised by abundant numbers of features but with a low number of observations. However, only a small number of these features are relevant to an outcome of interest. With this kind of data set, feature selection becomes a real prerequisite. This paper proposes a methodology for feature selection for an imbalanced leukaemia gene expression data based on random forest algorithm. It presents the importance of feature selection in terms of reducing the number of features, enhancing the quality of machine learning and providing better understanding for biologists in diagnosis and prediction. Algorithms are presented to show the methodology and strategy for feature selection taking care to avoid over fitting. Moreover, experiments are done using imbalanced Leukaemia gene expression data and special measurement is used to evaluate the quality of feature selection and performance of classification.