Bio
John is an internationally recognized expert in genetic epidemiology who integrates genomic, clinical, and environmental data with machine learning to understand and predict factors underlying cancer and other complex traits. His lab and collaborators develop novel methods for risk estimation and prediction using large-scale data from biobanks and cohorts. This includes recent advances that genetically adjust biomarkers to improve screening and outcome prediction (e.g., adjusted prostate specific antigen for prostate cancer). His research program has been continuously supported by the National Cancer Institute, where he served on the Board of Scientific Counselors. A committed educator and mentor, John has guided more than 50 trainees, including pre- and postdoctoral fellows, and co-directs an NIH T32 predoctoral training program focused on the genetic and environmental basis of cancer risk. Prior to Stanford, he was Professor and Vice Chair of Epidemiology and Biostatistics at UCSF.
