Please login first
Clinical Metabolomics: An Integral Tool Driving Patient Phenotyping in Precision Medicine


Precision medicine is experiencing rapid growth and acceptance in the health-care landscape as a driving force for the future of medicine and is defined by the development of treatment strategies that are tailored to groups of patients based on specific biomarkers. Current precision medicine driven clinical trials assign patients to therapies based on the genetic alterations that are thought to be driving their diseases/cancers. BERG has validated the vision of Interrogative Biology® Platform to understand patients by “phenotype” rather than “genotype” by integrating molecular data directly from a patient with clinical and demographic information to develop artificial intelligence driven clinical trials. BERG is applying Bayesian causal inference to deconvolute unstructured clinical and molecular data and integrate this into models with cause and effect relationships that infers the health status of patients and outcome driven trials. This facilitates the generation of population cohorts for the discovery of biomarkers and drives personalized clinical decision-making. Development of in house Multi-omics platforms facilitates translation of targets and biomarkers in a rapid manner with the focus on cost, throughput, robustness, as well as translational utility into a R&D or CLIA lab setting. At BERG, we have implemented an industrial level high throughput metabolomics platform providing both high quality and depth of information allowing for reliable and broadest capture of the metabolome for the pre-clinical and clinical matrices analyzed. Metabolomics represents one of the most direct quantitative measurment to a patients phenotype to address the precision medicine maxim of treating the right patient, at the right time, with the right dose. Highlights of the BERG’s in-depth patient stratification approach as well as a route of complementary biomarker discovery will be presented.

Keywords: Precision medicine, metabolomics, clinical, AI