随机森林方法在致病SNPs检测中的应用

通过全基因组关联研究发现了大量复杂疾病相关变异，近来关注的焦点又集中在了如何利用单核苷酸多态性数据进行深入分析，期待发现更多复杂疾病的易感基因。随机森林是一种新型的集成分类决策器，可以在对样本分类的同时，计算预测变量的重要性值。该文将随机森林方法应用于全基因组数据，实验结果表明该方法可以作为致病SNPs检测的有效参考方法。

Implementation of Random Forests for Causal SNPs Detection

Genome-wide association studies （GWAS） have yielded an unprecedented number of complex diseases-associated variants. Recently, scientists have focused on performing further analysis by utilizing the genome - wide genotyping data to identify more susceptibility genes of complex diseases. Random Forests is a combination of tree predictors, variable importance is measured when the forest grow. We used Random Forests to analysis the GWA dataset, the result shown the validity of the method for causal SNPs detection.