An Improved Algorithm with Gene Selection and Decision Rules for Ovarian Cancer
|
| Title | An Improved Algorithm with Gene Selection and Decision Rules for Ovarian Cancer |
| Authors | |
| Abstract | The microarray data of ovarian cancer consists of tens of thousands of genes on a genomic scale. To avoid higher computational complexity, it needs gene selection to find the gene subsets that are able to classify ovarian cancer. Most of gene selections use traditional statistics or data mining techniques to build the model. However, traditional statistics have no consideration about the variable gene selection and block effect. Data mining techniques may suffer the problem of parameter settings. Therefore, this paper applies scatter search to obtain suitable parameter settings for support vector machine and decision tree. Additionally, it selects a subset of beneficial genes without reducing the classification accuracy, and provides the decision rules for medical experts and biologists to evaluate the block effect of selected genes. In order to evaluate the proposed algorithm, the microarray data of ovarian cancer collected from China Medical University are used as the source datasets. From experimental results, it shows that the proposed algorithm can reduce unnecessary genes, and significantly improve the classification accuracy for ovarian cancer. |
| Publisher | World Science Publisher |
| Date | 2012-01-18 |
| Source | 2166-2924 |
| Rights | Copyright NoticeProposed Creative Commons Copyright Notices1. Proposed Policy for Journals That Offer Open AccessAuthors who publish with this journal agree to the following terms:Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work´s authorship and initial publication in this journal.Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal´s published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).Proposed Policy for Journals That Offer Delayed Open AccessAuthors who publish with this journal agree to the following terms:Authors retain copyright and grant the journal right of first publication, with the work [SPECIFY PERIOD OF TIME] after publication simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work´s authorship and initial publication in this journal.Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal´s published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access). |