No abstract

No abstract

Ovarian cancer is the deadliest gynaecological disease because of the high mortality rate and there is no any symptom in cancer early stage. It was often the terminal cancer period when patients were diagnosed with ovarian cancer and thus delays a good opportunity of treatment. The current common method for detecting ovarian cancer is blood testing for analyzing the tumor marker CA-125 of serum. However, specificity and sensitivity of CA-125 are insufficient for early detection. Therefore, it has become an urgent issue to look for an efficient method which precisely detects the tumor markers for ovarian cancer. This study aims to find the target genes of ovarian cancer by different algorithms of information science. Feature selection and decision tree were applied to analyze 9600 ovarian cancer-related genes. After screening the target genes, candidate genes will be analyzed by Ingenuity Pathway Analysis (IPA) software to create a genetic pathway model and to understand the interactive relationship in the different pathological stages of ovarian cancer. Finally, this research found 9 oncogenes associated with ovarian cancer and some genes had not been discovered in previous studies. This system will assist medical staffs in diagnosis and treatment at cancer early stage and improve the patient's survival.

This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.

Most of GA-based portfolio assets allocation uses normalization method to allocate investment asset's weight. However, the normalization process will cause unease converging and even diverging characteristics, because it changes the gene's relativity of address in chromosome. In this paper, we propose a weighed encoding scheme and crossover algorithm to allocate suitable assets in portfolio. Each gene encoded as a real number in a chromosome is denoted as the weighted number of assets in our approach. Due to no specific relationship assumed in our encoding scheme, the crossover process would not influence overall converging speed. In addition, in order to avoid losing optimal asset allocations through quicker converging, we also introduce the expanding rate to allow enlarging the possible range of asset allocation weight during the evolutionary process. Our experiments also show that higher expanding rate produces higher excess profit of investment.