Combining MALDI-MS with machine learning for metabolomic characterization of lung cancer patient sera

Xiaopin Lai; Kunbin Guo; Wei Huang; Yang Su; Siyu Chen; Qiongdan Li; Kaiqing Liang; Wenhua Gao; Xin Wang; Yuping Chen; Hongbiao Wang; Wen Lin; Xiaolong Wei; Wenxiu Ni; Yan Lin; Dazhi Jiang; Yu-Hong Cheng; Chi-Ming Che; Kwan-Ming Ng

doi:10.1039/D1AY01940F

Combining MALDI-MS with machine learning for metabolomic characterization of lung cancer patient sera†

Xiaopin Lai,‡^a Kunbin Guo,‡^b Wei Huang,

‡^a Yang Su,^a Siyu Chen,^a Qiongdan Li,^a Kaiqing Liang,^a Wenhua Gao,^a Xin Wang,^b Yuping Chen,*^b Hongbiao Wang,^b Wen Lin,*^b Xiaolong Wei,^b Wenxiu Ni,

^c Yan Lin,^d Dazhi Jiang,^e Yu-Hong Cheng,

^f Chi-Ming Che

^f and Kwan-Ming Ng

*^a

Author affiliations

* Corresponding authors

^a Department of Chemistry, Key Laboratory for Preparation and Application of Ordered Structural Materials of Guangdong Province, Shantou University, Guangdong, P. R. China
E-mail: kwanming@stu.edu.cn

^b Cancer Hospital of Shantou University Medical College, Guangdong, P. R. China
E-mail: stchenyp@hotmail.com, 1263811129@qq.com

^c Department of Medical Chemistry, Shantou University Medical College, Shantou, Guangdong, P. R. China

^d The Second Affiliated Hospital of Shantou University Medical College, Guangdong, P. R. China

^e Department of Computer Science, College of Engineering, Shantou University, Guangdong, P. R. China

^f Department of Chemistry and State Key Laboratory of Synthetic Chemistry, The University of Hong Kong, Hong Kong S. A. R., P. R. China

Abstract

An increasing amount of evidence has proven that serum metabolites can instantly reflect disease states. Therefore, sensitive and reproducible detection of serum metabolites in a high-throughput manner is urgently needed for clinical diagnosis. Matrix-assisted laser desorption/ionization mass spectrometry (MALDI-MS) is a high-throughput platform for metabolite detection, but it is hindered by significant signal fluctuations because of the “sweet spot” effect of organic matrices. Here, by screening two transformation methods and four normalization techniques to reduce the significant signal fluctuations of the DHB matrix, an integrated MALDI-MS data processing approach combined with machine learning methods was established to reveal metabolic biomarkers of lung cancer. In our study, 13 distinctive features with statistically significant differences (p < 0.001) between 34 lung cancer patients and 26 healthy controls were selected as significant potential biomarkers of lung cancer. 6 out of the 13 distinctive features were identified as intact metabolites. Our results demonstrate the potential for clinical application of MALDI-MS in serum metabolomics for biomarker screening in lung cancer.

Analytical Methods

Combining MALDI-MS with machine learning for metabolomic characterization of lung cancer patient sera†

Abstract

Supplementary files

Article information

Download Citation

Permissions

Combining MALDI-MS with machine learning for metabolomic characterization of lung cancer patient sera

Social activity

Search articles by author

Spotlight

Advertisements