Bridging biological cfDNA features and machine learning approaches

Liquid biopsies (LBs), particularly using circulating tumor DNA (ctDNA), are expected to revolutionize precision oncology and blood-based cancer screening. Recent technological improvements, in combination with the ever-growing understanding of cell-free DNA (cfDNA) biology, are enabling the detection of tumorspecific changes with extremely high resolution and new analysis concepts beyond genetic alterations, including methylomics, fragmentomics, and nucleosomics. The interrogation of a large number of markers and the high complexity of data render traditional correlation methods insufficient. In this regard, machine learning (ML) algorithms are increasingly being used to decipher disease- and tissue-specific signals from cfDNA. Here, we review recent insights into biological ctDNA features and how these are incorporated into sophisticated ML applications.

Automated summary

Liquid biopsies (LBs), especially using circulating tumor DNA (ctDNA), have the potential to revolutionize precision oncology and blood-based cancer screening. Recent advancements in technology and understanding of cell-free DNA (cfDNA) biology have allowed for the detection of tumor-specific changes with high resolution, including new analysis concepts such as methylomics, fragmentomics, and nucleosomics. Machine learning (ML) algorithms are increasingly being utilized to extract disease- and tissue-specific signals from cfDNA due to the large number of markers and complexity of the data. This review provides insights into the biological features of ctDNA and its incorporation into sophisticated ML applications.