基于总体最小二乘方法的基因表达缺失数据估计

在基因芯片实验中，数据缺失客观存在，并在一定程度上影响芯片数据后续分析结果的准确性。在不增加实验次数的情况下，缺失值估计是降低缺失数据对后续分析影响的有效方法。针对基因表达数据含有噪声的特点，提出了基于总体最小二乘估计的基因表达缺失值估计算法。实验结果表明，新的估计算法具有比传统缺失值估计算法更好的稳定性和估计准确度。

Missing Value Estimation for Microarray Expression Data based on Total Least Squares

There is missing value in microarray experiments and it will affect the stability and precision of the expression data analysis.Missing value estimating is a effective method in reducing the influence of missing values on the post-processing and there is no need for increasing experiment number.Consider the additive noise in the expression dataset,a new method based on Total Least Squares(TLS)is presented.Experimental results show that the novel method has better performance than the existing methods that have been employed.