ARTIFICIAL INTELLIGENCE-ASSISTED COMPARATIVE ANALYSIS OF DNA BARCODING SEQUENCES FOR HERBAL PLANT SPECIES IDENTIFICATION AND ADULTERATION DETECTION

Abstract

DNA barcoding is a widely used molecular technique for identifying species using short, standardized genetic sequences. Traditional analysis relies on manual alignment and comparison of sequences, which becomes inefficient with increasing data complexity. This paper proposes and explores the application of Artificial Intelligence (AI) and machine learning algorithms in automating and enhancing the accuracy of DNA barcoding analysis. Using real-time PCR-generated sequences and COI/ITS2 marker data, AI models are trained to classify and detect adulteration in herbal and biological samples. The results demonstrate improved identification accuracy and adulteration prediction compared to conventional methods.