Biosignature Discovery for Substance Use Disorders Using Statistical Learning

James W. Baurley, Christopher S. McMahan, Carolyn M. Ervin, Bens Pardamean, Andrew W. Bergen
2018 Trends in Molecular Medicine  
There are limited biomarkers for substance use disorders (SUDs). Traditional statistical approaches are identifying simple biomarkers in large samples, but clinical use cases are still being established. High-throughput clinical, imaging and "omic" technologies are generating data from SUD studies and may lead to more sophisticated and clinically useful models. However, analytic strategies suited for high dimensional data are not regularly used. We review strategies for identifying biomarkers
more » ... d biosignatures from high dimensional data types. Focusing on penalized regression and Bayesian approaches, we address how to leverage evidence from existing studies and knowledge-bases, using as an example, nicotine metabolism. We posit that big data and machine learning approaches will considerably advance SUD biomarker discovery. However, translation to clinical practice, will require integrated scientific efforts. Biosignatures in Substance Use Disorders Biomarkers for substance use disorders (SUD) are available for drug use based on detection of the substance or its metabolites, e.g., ethyl glucuronide for alcohol [1], tetrahydrocannabinol for marijuana [2] , and cotinine for tobacco [3] . They are not, however readily available for the neurobiological modifications that result in the maladaptive behaviors we describe as addiction [4] . Clinical phenotyping has been used to assess the
doi:10.1016/j.molmed.2017.12.008 pmid:29409736 pmcid:PMC5836808 fatcat:ubbbuswxtfbirgnar3vwidlpda