NMF-Based Approach for Missing Values Imputation of Mass Spectrometry Metabolomics Data

Molecules

Jingjing Xu¹  Jiyang Dong¹  Yuanshan Wang¹  Kian-Kai Cheng²  Daniel Raftery³  Xiangnan Xu⁴ 

[1] Department of Electronic Science, Xiamen University, Xiamen 361005, China;Innovation Centre in Agritechnology, Universiti Teknologi Malaysia, Johor, Muar 84600, Malaysia;Northwest Metabolomics Research Center, Department of Anesthesiology and Pain Medicine, University of Washington, Seattle, WA 98109, USA;School of Mathematics and Statistics, The University of Sydney, Sydney, NSW 2006, Australia;

关键词: non-negative matrix factorization;    missing values imputation;    mass spectrometry;    metabolomics data;    missing pattern;    outliers;   

DOI  :  10.3390/molecules26195787

来源: DOAJ

【 摘 要 】

In mass spectrometry (MS)-based metabolomics, missing values (NAs) may be due to different causes, including sample heterogeneity, ion suppression, spectral overlap, inappropriate data processing, and instrumental errors. Although a number of methodologies have been applied to handle NAs, NA imputation remains a challenging problem. Here, we propose a non-negative matrix factorization (NMF)-based method for NA imputation in MS-based metabolomics data, which makes use of both global and local information of the data. The proposed method was compared with three commonly used methods: k-nearest neighbors (kNN), random forest (RF), and outlier-robust (ORI) missing values imputation. These methods were evaluated from the perspectives of accuracy of imputation, retrieval of data structures, and rank of imputation superiority. The experimental results showed that the NMF-based method is well-adapted to various cases of data missingness and the presence of outliers in MS-based metabolic profiles. It outperformed kNN and ORI and showed results comparable with the RF method. Furthermore, the NMF method is more robust and less susceptible to outliers as compared with the RF method. The proposed NMF-based scheme may serve as an alternative NA imputation method which may facilitate biological interpretations of metabolomics data.

【 授权许可】

Unknown