改进的稳健Lowess标准化算法在基因芯片中的应用

Improved Robust Lowess Normalization Method in Analysis of Gene Chip

标准化是基因芯片预处理的一个重要的步骤。通过对基因芯片的标准化方法的研究,本文提出了一种算法与稳健Lowess标准化法的效果相当、效率有较大提高的算法。本算法首先利用局部加权线性回归对数据点进行平滑估计,然后再对得到的误差项运用核估计法进一步减小误差,最后对每个格子里的数据点进行缩放处理。实验证明了本算法的高效性。

Normalization is an important step in the pre-processing of gene chip. By studying normalization methods for gene chip, an improved algorithm is proposed, which can achieve comparable performance with that of the robust Lowess normalization method. However, the method can be implemented much more effectively. In the algorithm, the data are firstly smoothed with the locally weighted linear regression method, then the error is further reduced by estimating the residue in the smoothing estimation in a framework of kernel estimation. Fi- nally, scaling operation is performed with respect to each data point on the grid. Experimental results show both effectiveness and efficiency of the algorithm.