Association rule mining based study for identification of clinical parameters akin to occurrence of brain tumor

Healthcare sector is generating a large amount of information corresponding to diagnosis, disease identification and treatment of an individual. Mining knowledge and providing scientific decision-making for the diagnosis & treatment of disease from the clinical dataset is therefore increasingly becoming necessary. Aim of this study was to assess the applicability of knowledge discovery in brain tumor data warehouse, applying data mining techniques for investigation of clinical parameters that can be associated with occurrence of brain tumor. In this study, a brain tumor warehouse was developed comprising of clinical data for 550 patients. Apriori association rule algorithm was applied to discover associative rules among the clinical parameters. The rules discovered in the study suggests - high values of Creatinine, Blood Urea Nitrogen (BUN), SGOT & SGPT to be directly associated with tumor occurrence for patients in the primary stage with atleast 85% confidence and more than 50% support. A normalized regression model is proposed based on these parameters along with Haemoglobin content, Alkaline Phosphatase and Serum Bilirubin for prediction of occurrence of STATE (brain tumor) as 0 (absent) or 1 (present). The results indicate that the methodology followed will be of good value for the diagnostic procedure of brain tumor, especially when large data volumes are involved and screening based on discovered parameters would allow clinicians to detect tumors at an early stage of development.     

基于基因突变频率识别低级别脑胶质瘤驱动基因

癌症通常由基因变异的累积所驱动,有效地识别癌症的驱动突变是一个巨大的挑战。目前已有方法更多是通过将基因组区域中观察到的突变率与背景突变率(BMR)预期的突变率进行比较或功能影响测试来识别驱动基因,该驱动基因本质上是存在统计异常的基因。而且并未对已有明确分类的癌症的子类之间驱动基因进行研究。本文引入关联规则算法,探寻发生该基因突变诱使病人患该子类低级别脑胶质瘤的有效规则,将突变数据与患癌结果通过算法建立关系,再通过支持度、置信度和提升度这三个指标对产生的规则进行筛选和评估,来预测候选驱动基因以及类间驱动基因差异。最后利用491例低级别脑胶质瘤体细胞突变数据,得到22个与结果存在关联的驱动基因及其所属的子类,敏感性和假阳性结果优于目前已有的单一算法,且22个基因均具有重要的生物学功能。同时建立了基于22个基因的低级别脑胶质瘤子类识别方法,模型总体准确率达98.99%,方法可有效区分三子类。     

基于云计算的农作物种质资源数据挖掘平台研究

针对作物种质数据量大、多维带来的挖掘效率偏低的问题,通过探讨云计算技术及其解决方案,提出了一种基于Hadoop的农作物种质资源数据挖掘平台,详述了平台的各功能模块并给出了具体的开发方案。通过改进经典的Apriori算法并在平台上对其进行效率测试,验证了平台的有效性、可行性。