Particle swarm optimization-based protocol for partial least-squares discriminant analysis: Application to 1H nuclear magnetic resonance analysis of lung cancer metabonomics
Particle swarm optimization-based protocol for partial least-squares discriminant analysis: Application to 1H nuclear magnetic resonance analysis of lung cancer metabonomics
复制标题
DOI：
10.1016/j.chemolab.2014.04.014
复制
发表时间：
2014-07-15
影响因子：
3.9
通讯作者：
Cui, Yan-Fang
中科院分区：
文献类型：
--
作者：
Li, Ya-Qiong;Liu, Yi-Fei;Cui, Yan-Fang
代谢谱的复杂性使得多元化学计量学技术对于提取大多数重要信息和提供生物学见解至关重要。偏最小二乘判别分析（PLS-DA）由于其具有良好的应用前景，在代谢组学研究中取得了丰硕的成果。然而，在PLS-DA建模中经常出现次优和过拟合的问题。本研究利用粒子群算法（PSO）对PLS-DA进行改进，同时选取PLS-DA中最优变量子集、关联权值和最优潜变量数，形成一种新的算法PSO- plsda。结合基于H-1核磁共振的代谢组学，将PSO-PLSDA与PLS-DA进行比较，用于识别健康对照的肺癌患者。相对于PLS-DA的训练集和测试集识别率分别为86%和65%，PSO-PLSDA的识别率分别为99%和85%。此外，通过PSO-PLSDA鉴定出几种最具鉴别性的代谢物，包括乳酸、脯氨酸、糖蛋白、谷氨酸、丙氨酸、苏氨酸、牛磺酸、葡萄糖（α -和β -）、三甲胺、谷氨酰胺、甘氨酸和肌醇，有助于肺癌的诊断。(C) 2014 Elsevier B.V.版权所有
The complexity of metabolic profiles makes multivariate chemometric techniques crucial for extracting mostly significant information and offering biological insight. Partial least-squares discriminant analysis (PLS-DA) was proven fruitful in metabonomic community, due to its promising properties. The issues of suboptimum and overfitting, however, often occur in PLS-DA modeling. In the current study, particle swarm optimization (PSO) was invoked to meliorate PLS-DA via simultaneously selecting the optimal variable subset as well as the associated weights and the best number of latent variables in PLS-DA, forming a new algorithm named PSO-PLSDA. Combined with H-1 NMR-based metabonomics, PSO-PLSDA compared with PLS-DA was applied to recognize lung cancer patients from healthy controls. Relatively to the recognition rates of 86% and 65% for the training and test sets yielded by PLS-DA, 99% and 85% were obtained by PSO-PLSDA. Moreover, several most discriminative metabolites were identified by PSO-PLSDA to aid the diagnosis of lung cancer, including lactate, proline, glycoprotein, glutamate, alanine, threonine, taurine, glucose (alpha- and beta-), trimethylamine, glutamine, glycine, and myo-inositol. (C) 2014 Elsevier B.V. All rights reserved.