Project Summary We have recently used computational models to identify the protease inhibitor indinavir (used as an antiviral for HIV) as a positive allosteric modulator at the ?7-nicotinic acetylcholine receptor. We now propose to build on this discovery as well as other publications describing compounds that are positive allosteric modulators of the ?7- nicotinic acetylcholine receptor. We propose identifying further compounds that possess activity against this or one of 9 other targets implicated in Alzheimer?s disease using a combination of Bayesian machine learning and in vitro assays. Generating such data will enable us to potentially provide more specific compounds as well as building datasets that can be used to build predictive models to identify additional compounds with activity at these Alzheimer?s targets. These combined efforts should in the first instance provide commercially viable treatments which will be used to experimentally validate our computational models that can be shared with the Alzheimer?s disease scientific community. We are proposing to build and validate models based on public databases, select compounds for testing and use the data generated as a starting point for further optimization.