Probing Herbicide Toxicity to Algae (Selenastrum capricornutum) by Lipid Profiling with Machine Learning and Microchip/MALDI-TOF Mass Spectrometry

• Published in: Chemical research in toxicology 2022-04, Vol.35 (4), p.606-615
• Main Authors: Li, Bochao, Stuart, Daniel D, Shanta, Peter V, Pike, Caleb D, Cheng, Quan
• Format: Article
• Language: English
• Subjects: Atrazine; Herbicides - toxicity; Machine Learning; Plants; Spectrometry, Mass, Matrix-Assisted Laser Desorption-Ionization - methods
• ISSN: 0893-228X; 1520-5010
• DOI: 10.1021/acs.chemrestox.1c00397

Matrix-assisted laser desorption ionization mass spectrometry (MALDI-MS)-based lipid profiling is a powerful method to study the cytotoxicity of chemical exposure to microorganisms at the single cell level. We report here a combined approach of machine learning (ML) and microchip-based MALDI-time of flight (TOF) mass spectrometry to investigate the cytotoxic effect of herbicides on algae through single cell lipid profiling. Algal species Selenastrum capricornutum was chosen as the target system, and its exposure to different doses of common chemical herbicides and the resulting cytotoxic behaviors under various stress conditions were characterized. A lipid library for S. capricornutum has been established with 63 identified lipids that include glycosyldiacylglycerols and triacylglycerols. We demonstrated that major alternations occurred for lipids with functional groups of digalactosyldiacylglycerol (DGDG), triacylglycerol (TAG), and monogalactosyldiacylglycerol (MGDG). DGDG was shown to decrease upon exposure to herbicides of norflurazon and atrazine, while some MGDG and TAG lipids would increase for norflurazon. Compared to other algae, S. capricornutum was more strongly impacted by norflurazon than atrazine while the latter was observed to have a greater effect on C. reinhardtii. Machine learning algorithms have been applied to improve the classification of herbicide impact and help identify lipid species affected by the chemical exposure. A total of 69 machine learning models were trained and tested for the identification of ideal algorithms in the classification process, in which flexible discriminant analysis and support vector machine model were found to be the most accurate and consistent. The ML algorithms accurately differentiated herbicide impact and have identified cytotoxic differences that were previously hidden. The results suggest that herbicides express toxicity among different algae likely on the basis of metabolic differences. The ML-assisted method proves to be highly effective and can provide an advanced technological platform for probing cytotoxicity for bacterial species and in metabolic pathway analysis.