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 tumor-specific 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.

Targeting epigenetic features in clear cell sarcomas based on patient-derived cell lines.

BACKGROUND: Clear cell sarcomas (CCSs) are translocated aggressive malignancies, most commonly affecting young adults with a high incidence of metastases and a poor prognosis. Research into the disease is more feasible when adequate models are available. By establishing CCS cell lines from a primary and metastatic lesion and isolating healthy fibroblasts from the same patient, the in vivo process is accurately reflected and aspects of clinical multistep carcinogenesis recapitulated. METHODS: Isolated tumor cells and normal healthy skin fibroblasts from the same patient were compared in terms of growth behavior and morphological characteristics using light and electron microscopy. Tumorigenicity potential was determined by soft agar colony formation assay and in vivo xenograft applications. While genetic differences between the two lineages were examined by copy number alternation profiles, nuclear magnetic resonance spectroscopy determined arginine methylation as epigenetic features. Potential anti-tumor effects of a protein arginine N-methyltransferase type I (PRMT1) inhibitor were elicited in 2D and 3D cell culture experiments using cell viability and apoptosis assays. Statistical significance was calculated by one-way ANOVA and unpaired t-test. RESULTS: The two established CCS cell lines named MUG Lucifer prim and MUG Lucifer met showed differences in morphology, genetic and epigenetic data, reflecting the respective original tissue. The detailed cell line characterization especially in regards to the epigenetic domain allows investigation of new innovative therapies. Based on the epigenetic data, a PRMT1 inhibitor was used to demonstrate the targeted antitumor effect; normal tissue cells isolated and immortalized from the same patient were not affected with the IC50 used. CONCLUSIONS: MUG Lucifer prim, MUG Lucifer met and isolated and immortalized fibroblasts from the same patient represent an ideal in vitro model to explore the biology of CCS. Based on this cell culture model, novel therapies could be tested in the form of PRMT1 inhibitors, which drive tumor cells into apoptosis, but show no effect on fibroblasts, further supporting their potential as promising treatment options in the combat against CCS. The data substantiate the importance of tailored therapies in the advanced metastatic stage of CCS.