Research Project
9983443
PROJECT SUMMARY The high rate of failure in CNS drug discovery, in particular of the first-in-class therapeutics with new modes of action, highlights a clear unmet need to improve the success rate in drug discovery for psychiatric disorders. One well-known issue is the poor ability of current bioassays and animal models to predict the efficacy and side-effects of compounds. In response, there is a steady growth in the use of electroencephalogram (EEG) in clinical trials in recent years. Pharmaceutical companies are incorporating EEG more often in their preclinical drug discovery efforts because the high degree of translatability of EEG from rodents to humans makes it ideal to use in de-risking programs in drug discovery. Moreover, quantitative EEG (qEEG) is an objective measurement of brain activity with a high test-retest reliability and considerable predictive, face, and construct validity. Additionally, well-documented literature shows that certain classes of drugs elicit different EEG fingerprints, suggesting that EEG yields pharmaco-dynamic signatures specific to pharmacological action and can be used to enable classification of drugs based on the effects of the EEG. Further, EEG can be used to rapidly screen compounds for potential activity at specific pharmacological targets and provide valuable information for guiding the early stages of drug development. However, to date, no EEG-based tool is broadly available to be used to predict the therapeutic utility of unknown compounds for drug discovery in psychiatric disorders. In order to develop such a tool, PsychoGenics, Inc., is leveraging our existing expertise in performing high-throughput pharmaco-sleep-EEG studies and our established proprietary machine learning approach to develop a novel EEG-based drug discovery platform that can predict therapeutic indications or underlying mechanism of action (MOA; i.e. the neurotransmitter system/receptor targets) of unknown compounds for psychiatric disorders. Our aims are 1) to generate a quantitative electroencephalogram (QEEG) database of compounds with a known mechanism and therapeutic value in mice, and 2) to develop a classifier using supervised machine learning. The success of this Phase I SBIR project will result in a novel EEG-based drug discovery platform that can predict therapeutic indications and MOA of new compounds based on their EEG profiles. In a future Phase II project, we will 1) add in auditory evoked potentials (AEPs) database, 2) test our EEGCube by conducting a phenotypic drug discovery project with our established collaborator (see letters of support), 3) investigate whether integrating the EEGcube database with our SmartCube® database of same compounds helps better understand the circuitry responsible for behavioral responses and/or achieves even greater prediction power in identifying therapeutic indication of novel compounds and 4) explore EEG signatures of transgenic mouse models of disease and investigate use of their signatures to identify potential therapies for the respective diseases based on EEG.
