Advances in artificial intelligence and machine learning in capillary electrophoresis

Area of Science:

• Analytical Chemistry
• Separation Science
• Computational Chemistry

Background:

• Capillary electrophoresis (CE) offers cost-effective and rapid separation but faces challenges in reproducibility and method development.
• Integrating artificial intelligence (AI) and machine learning (ML) presents a promising solution to overcome these inherent limitations.

Purpose of the Study:

• To provide a comprehensive overview of the current status of AI and ML integration within CE.
• To explore various facets of this integration, including software, models, and specific applications.

Main Methods:

• Review and synthesis of existing literature on AI/ML applications in CE.
• Discussion of AI/ML roles in method development, optimization, peak analysis, prediction, data processing, and quality control.
• Exploration of AI/ML integration in nano-CE and comparison with conventional CE.

Main Results:

• AI and ML tools are being utilized for improved peak recognition, deconvolution, retention time forecasting, and data analysis in CE.
• Applications span signal correction, analyte documentation, quality control, and predictive maintenance.
• AI- and ML-integrated CE has demonstrated utility in analyzing real-life samples.

Conclusions:

• The integration of AI and ML significantly enhances CE performance, addressing key drawbacks.
• Further development and recommendations are crucial for maximizing the utility of AI- and ML-based CE across diverse applications.
• Future perspectives indicate a growing role for intelligent CE in analytical science.