In a groundbreaking study, Mayo Clinic investigators have developed a multiomic molecular method to predict clinical COVID-19 (SARS-CoV-2) outcomes better than traditional cytokines. Using a machine-learning-based prediction model, the team identified 102 biomarkers, which include several novel cytokines and other proteins, lipids, and metabolites. The discovery may help clinicians reliably predict a more severe course of COVID-19 before the patient gets sick enough to be hospitalized. Until now, there have been no biomarkers that can reliably predict which patients are more likely to have severe illness.

In Mayo Clinic’s Advanced Diagnostics Laboratory, there are dozens of projects underway at once to develop new technologies, discover novel findings, validate new tests, and support physicians in providing advanced patient care. For example, researchers are using phage immunoprecipitation sequencing (PhIP-Seq) to discover new serological biomarkers for autoimmune diseases. In a recent study using PhIP-Seq, Mayo Clinic researchers discovered a previously unknown antibody marker for immune-mediated rippling muscle disease (iRMD). This finding will support testing options and accurate diagnosis of iRMD, helping physicians treat patients with iRMD and restore their quality of life.

In a recent study, Mayo Clinic researchers developed the first cellular DNA barcoding with a machine-learning approach to reveal previously unknown metastatic behavior of tumor cells. Researchers barcoded the DNA of millions of human ovarian cancer cells and transplanted them in mice, where rare tumor initiating cells and their progenies could be tracked within the primary tumor as well as in every other organ they were spreading into. The entire community of cells generated by a single barcoded cell had identical barcodes. This enabled the tracking of a large number of benign and metastatic clones by sequencing DNA barcodes in tumors and various organs, including blood and ascites. Using the cellular DNA barcoding approach and a newly developed data analysis system, researchers could track clonal growth dynamics in various metastatic sites and trace it back to its ancestral tumor-initiating cell. They used artificial intelligence to tackle the complex data to identify if the clonal metastatic spread is happening peritoneally or through blood routes.