Multi-class alignment of LC-MS data using probabilistic-based mixture regression models.
Multi-class alignment of LC-MS data using probabilistic-based mixture regression models.
复制标题
使用基于概率的混合回归模型对 LC-MS 数据进行多类比对。
DOI：
10.1109/iembs.2008.4650109
复制
发表时间：
2008
期刊：
影响因子：
--
通讯作者：
Ressom,HabtomW
中科院分区：
文献类型：
--
作者：
Befekadu,GetachewK;Tadesse,MahletG;Hathout,Yetrib;Ressom,HabtomW
本文提出了一个基于概率的混合回归模型（PMRM）框架，用于液相色谱-质谱（LC-MS）数据的多类比对。所提出的框架在 LC-MS 谱的时间和测量空间上进行对齐。期望最大化（EM）算法用于估计基于样条的混合回归模型和先验变换密度的联合参数。合并后者是为了考虑数据的时间和测量空间的变化。作为概念证明，所提出的方法用于对齐由裂解的大肠杆菌细胞的蛋白质生成的单类复制 LC-MS 光谱。其性能与动态时间规整（DTW）和连续轮廓模型（CPM）方法进行了比较。
In this paper, a framework of probabilistic-based mixture regression models (PMRM) is presented for multi-class alignment of liquid chromatography-mass spectrometry (LC-MS) data. The proposed framework performs the alignment in both time and measurement spaces of the LC-MS spectra. The expectation maximization (EM) algorithm is used to estimate the joint parameters of spline-based mixture regression models and prior transformation densities. The latter are incorporated to account for variability in time and measurement spaces of the data. As a proof of concept, the proposed method is applied to align a single-class replicate LC-MS spectra generated from proteins of lysed E.coli cells. Its performance is compared with the dynamic time warping (DTW) and continuous profile model (CPM) approaches.