Evaluation of points of improvement in NGS data analysis

Abstract

[EN]DNA sequencing is a fundamental technique in molecular biology that allows the exact sequence of nucleotides in a DNA sample to be read. Over the past decades, DNA sequencing has seen significant advances, evolving from manual and laborious techniques to modern high-throughput techniques. Despite these advances, interpretation and analysis of sequencing data continue to present challenges. Artificial Intelligence (AI), and in particular machine learning, has emerged as an essential tool to address these challenges. The application of AI in the sequencing pipeline refers to the use of algorithms and models to automate, optimize and improve the precision of the sequencing process and its subsequent analysis. The Sanger sequencing method, introduced in the 1970s, was one of the first to be widely used. Although effective, this method is slow and is not suitable for sequencing large amounts of DNA, such as entire genomes. With the arrival of next generation sequencing (NGS) in the 21st century, greater speed and efficiency in obtaining genomic data has been achieved. However, the exponential increase in the amount of data produced has created a bottleneck in its analysis and interpretation.