NMF-Based Approach for Missing Values Imputation of Mass Spectrometry Metabolomics Data
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 imputat...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-09-01
|
| Series: | Molecules |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1420-3049/26/19/5787 |
| _version_ | 1797516014129250304 |
|---|---|
| author | Jingjing Xu Yuanshan Wang Xiangnan Xu Kian-Kai Cheng Daniel Raftery Jiyang Dong |
| author_facet | Jingjing Xu Yuanshan Wang Xiangnan Xu Kian-Kai Cheng Daniel Raftery Jiyang Dong |
| author_sort | Jingjing Xu |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-10T06:55:20Z |
| format | Article |
| id | doaj.art-bb026e9f709d43dc9dbf781b597b5388 |
| institution | Directory Open Access Journal |
| issn | 1420-3049 |
| language | English |
| last_indexed | 2024-03-10T06:55:20Z |
| publishDate | 2021-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Molecules |
| spelling | doaj.art-bb026e9f709d43dc9dbf781b597b53882023-11-22T16:32:37ZengMDPI AGMolecules1420-30492021-09-012619578710.3390/molecules26195787NMF-Based Approach for Missing Values Imputation of Mass Spectrometry Metabolomics DataJingjing Xu0Yuanshan Wang1Xiangnan Xu2Kian-Kai Cheng3Daniel Raftery4Jiyang Dong5Department of Electronic Science, Xiamen University, Xiamen 361005, ChinaDepartment of Electronic Science, Xiamen University, Xiamen 361005, ChinaSchool of Mathematics and Statistics, The University of Sydney, Sydney, NSW 2006, AustraliaInnovation Centre in Agritechnology, Universiti Teknologi Malaysia, Johor, Muar 84600, MalaysiaNorthwest Metabolomics Research Center, Department of Anesthesiology and Pain Medicine, University of Washington, Seattle, WA 98109, USADepartment of Electronic Science, Xiamen University, Xiamen 361005, ChinaIn 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.https://www.mdpi.com/1420-3049/26/19/5787non-negative matrix factorizationmissing values imputationmass spectrometrymetabolomics datamissing patternoutliers |
| spellingShingle | Jingjing Xu Yuanshan Wang Xiangnan Xu Kian-Kai Cheng Daniel Raftery Jiyang Dong NMF-Based Approach for Missing Values Imputation of Mass Spectrometry Metabolomics Data Molecules non-negative matrix factorization missing values imputation mass spectrometry metabolomics data missing pattern outliers |
| title | NMF-Based Approach for Missing Values Imputation of Mass Spectrometry Metabolomics Data |
| title_full | NMF-Based Approach for Missing Values Imputation of Mass Spectrometry Metabolomics Data |
| title_fullStr | NMF-Based Approach for Missing Values Imputation of Mass Spectrometry Metabolomics Data |
| title_full_unstemmed | NMF-Based Approach for Missing Values Imputation of Mass Spectrometry Metabolomics Data |
| title_short | NMF-Based Approach for Missing Values Imputation of Mass Spectrometry Metabolomics Data |
| title_sort | nmf based approach for missing values imputation of mass spectrometry metabolomics data |
| topic | non-negative matrix factorization missing values imputation mass spectrometry metabolomics data missing pattern outliers |
| url | https://www.mdpi.com/1420-3049/26/19/5787 |
| work_keys_str_mv | AT jingjingxu nmfbasedapproachformissingvaluesimputationofmassspectrometrymetabolomicsdata AT yuanshanwang nmfbasedapproachformissingvaluesimputationofmassspectrometrymetabolomicsdata AT xiangnanxu nmfbasedapproachformissingvaluesimputationofmassspectrometrymetabolomicsdata AT kiankaicheng nmfbasedapproachformissingvaluesimputationofmassspectrometrymetabolomicsdata AT danielraftery nmfbasedapproachformissingvaluesimputationofmassspectrometrymetabolomicsdata AT jiyangdong nmfbasedapproachformissingvaluesimputationofmassspectrometrymetabolomicsdata |