Integration of Parametric, Mechanistic, and AI-Based Modelling in High-Performance Liquid Chromatography: Future Prospect

Abstract

Advanced liquid chromatography remains the most effective method for separating, identifying, and quantifying intricate mixtures in the fields of chemistry, engineering, and life sciences. Modifications have been implemented in chromatographic modeling and optimization due to the demand for enhanced resolution, increased speed, and improved durability. For example, transitioning from single-dimensional separations to dual-dimensional workflows. This review thoroughly examines the methodologies based on parameters and moments that are employed to define mass transfer, dispersion, retention, and reaction kinetics in liquid chromatography systems, emphasizing their significance in the development of methods and enhancement of performance. This article explores the latest advancements in data-centric and AI-driven approaches, focusing on retention forecasting, quantitative structure–retention correlations, and automated parameter fine-tuning. The synergistic integration of mechanistic models and machine-learning techniques is explored as a feasible strategy to tackle issues associated with complex method development, multidimensional data management, and computational costs. Some of the current issues and new trends being looked at are real-time adaptive control, generative method design, and environmentally friendly chromatographic practices. This review aims to guide future progress in HPLC modeling and optimization by synthesizing theoretical, computational, and practical perspectives.