Analysis of machine learning algorithms on bioinformatics data of varying quality.

摘要

One of the main applications of machine learning in bioinformatics is the construction of classification models which can accurately classify new instances using information gained from previous instances. With the help of machine learning algorithms (such as supervised classification and gene selection) new meaningful knowledge can be extracted from bioinformatics datasets that can help in disease diagnosis and prognosis as well as in prescribing the right treatment for a disease. One particular challenge encountered when analyzing bioinformatics datasets is data noise, which refers to incorrect or missing values in datasets. Noise can be introduced as a result of experimental errors (e.g. faulty microarray chips, insufficient resolution, image corruption, and incorrect laboratory procedures), as well as other errors (errors during data processing, transfer, and/or mining). A special type of data noise called class noise, which occurs when an instance/example is mislabeled. Previous research showed that class noise has a detrimental impact on machine learning algorithms (e.g. worsened classification performance and unstable feature selection). In addition to data noise, gene expression datasets can suffer from the problems of high dimensionality (a very large feature space) and class imbalance (unequal distribution of instances between classes). As a result of these inherent problems, constructing accurate classification models becomes more challenging.;To provide guidance to researchers and practitioners in deciding which machine learning algorithms to apply for their analysis, this dissertation performs thorough empirical investigations of machine learning algorithms on bioinformatics data of varying data quality. Comprehensive experiments are performed to assess the robustness of machine learning techniques to class noise. First, we provide a detailed experimental analysis of feature selection techniques as well as classification algorithms in the context of data quality. We then investigate the effectiveness of three forms of ensemble classification techniques when learning from balanced bioinformatics datasets in the context of data quality. We also investigate the importance of alleviating class imbalance for classification problems on bioinformatics datasets. Finally, we address the combined problem of high dimensionality and class imbalance in the context of data quality. vi.