AI-Assisted Detection and Quantification of Remdesivir Impurities Using RP-HPLC

Abstract

Ensuring the purity of pharmaceutical drugs is essential to maintain their safety, quality, and therapeutic effectiveness. Remdesivir is a nucleotide analogue antiviral drug used for the treatment of severe viral infections. During synthesis, formulation, and storage, several process-related impurities, degradation products, and metabolites may form. Impurities such as GS-441524 and GS-704277 must be carefully monitored because their presence may influence the safety, stability, and efficacy of the drug product. Conventional analytical methods such as reverse-phase high-performance liquid chromatography (RP-HPLC) are widely used for impurity profiling; however, these methods typically rely on manual peak detection and integration, which can be time-consuming and susceptible to human error, particularly at low impurity levels. This work proposes an artificial intelligence (AI)–assisted approach for the detection and quantification of remdesivir impurities using RP-HPLC. In the proposed framework, chromatographic data obtained from impurity and degradation studies are processed using machine learning algorithms capable of automated peak detection, baseline correction, and peak integration. By analysing chromato-graphic features such as retention time, peak area, and spectral characteristics, AI models can estimate impurity concentrations with improved efficiency. This conceptual approach demonstrates the potential of AI to enhance impurity profiling, reduce manual data processing, and support advanced pharmaceutical quality control.