Select Page


1PsychoGenics, Inc., Paramus, NJ

There is critical need for novel compounds that effectively treat the cognitive and neuropsychiatric symptoms of Alzheimer’s disease. Animal models and functional readouts are essential in this discovery process. Sadly, prevention or reduction of pathology in models of AD has not automatically translated to an improvement in cognitive performance in patients. While many of treatments were able to shift biomarkers in human subjects as they did animal models, they did not improve or stabilize the cognitive performance and functional status of the patients. This translational problem advocates for more refined studies on behavioral effects of drugs and perhaps better Alzheimer’s models. SmartCube® and PhenoCube®, novel, high throughput, high content, mouse behavioral phenotyping platforms offer unique opportunities to reinvigorate the drug discovery process by identifying promising candidate compounds as well as repurposing existing ones. Both systems are automated behavioral platforms that present a sequence of challenges to a mouse through customized hardware, extract thousands of features per session, and, using proprietary machine learning algorithms, can detect the potential therapeutic efficacy of compounds or the phenotype of disease models earlier and more robustly than any standard behavioral tests. Over the years, we generated behavioral profiles of thousands of compounds and several disease models using these platforms. We developed several computational and machine learning methods to successfully identify behavioral patterns or signatures associated with different classes of reference drugs, from which to predict the class of novel compounds (Brunner et al., 2012, Alexandrov et al., 2015), and more recently developed methods to allow us to compare animal models of AD and its progression, and to identify (in silico) novel compounds from our existing database of thousands of novel and reference compounds with the potential to reverse the AD model behavioral profile.