Artificial Neural Network Prediction of Retention of Amino Acids in Reversed-Phase HPLC under Application of Linear Organic Modifier Gradients and/or pH Gradients.

Angelo Antonio D’Archivio

doi:10.3390/molecules24030632

Abstract

A multi-layer artificial neural network (ANN) was used to model the retention behavior of 16 o-phthalaldehyde derivatives of amino acids in reversed-phase liquid chromatography under application of various gradient elution modes. The retention data, taken from literature, were collected in acetonitrile–water eluents under application of linear organic modifier gradients (φ gradients), pH gradients, or double pH/φ gradients. At first, retention data collected in φ gradients and pH gradients were modeled separately, while these were successively combined in one dataset and fitted simultaneously. Specific ANN-based models were generated by combining the descriptors of the gradient profiles with 16 inputs representing the amino acids and providing the retention time of these solutes as the response. Categorical “bit-string” descriptors were adopted to identify the solutes, which allowed simultaneously modeling the retention times of all 16 target amino acids. The ANN-based models tested on external gradients provided mean errors for the predicted retention times of 1.1% (φ gradients), 1.4% (pH gradients), 2.5% (combined φ and pH gradients), and 2.5% (double pH/φ gradients). The accuracy of ANN prediction was better than that previously obtained by fitting of the same data with retention models based on the solution of the fundamental equation of gradient elution.

Highlights

Reversed-phase high-performance liquid chromatography (RP-HPLC) is an extensively applied technique in the separation and determination of a wide range of multi-class compounds, including biomolecules, pharmaceuticals, and industrial chemicals, in human, environmental, and food samples [1,2,3,4]
Many attempts to describe the retention of solutes in RP-HPLC under the application of mobile-phase gradients are based on the solution of the fundamental equation of gradient elution [12,13,14,15,16], Z tR− t0 dt t0 k where tR is the retention time, t0 is the column hold-up time, and k is the retention factor
artificial neural network (ANN) regression was used to model the RP-HPLC retention of o-phthaladehyde (OPA) derivatives of 16 amino acids collected under the application of φ gradients, pH gradients, or combined pH/φ gradients

Summary

Introduction

Reversed-phase high-performance liquid chromatography (RP-HPLC) is an extensively applied technique in the separation and determination of a wide range of multi-class compounds, including biomolecules, pharmaceuticals, and industrial chemicals, in human, environmental, and food samples [1,2,3,4]. In organic modifier mobile-phase gradients (φ gradients), the concentration of organic solvent in the mobile phase is increased, determining a progressive increase of the elution power of the eluent during the gradient run and a consequent decrease in solute retention. A similar effect occurs in the pH gradient of the mobile phase [7], where an increase or decrease in pH in the case of weak bases or acids, respectively, produces a progressive increase of the ionized form of the analyte and a consequent decrease in its retention time. Many attempts to describe the retention of solutes in RP-HPLC under the application of mobile-phase gradients are based on the solution of the fundamental equation of gradient elution [12,13,14,15,16],

Methods

Results

Conclusion