AI-Enabled Ultra-large Virtual Screening Identifies Potential Inhibitors of Choline Acetyltransferase for Theranostic Purposes

Abstract

Alzheimer’s disease (AD) and related dementias are among the primary neurological disorders and call for the urgent need for early-stage diagnosis to gain an upper edge in therapeutic intervention and increase the overall success rate. Choline acetyltransferase (ChAT) is the key acetylcholine (ACh) biosynthesizing enzyme and a legitimate target for the development of biomarkers for early-stage diagnosis and monitoring of therapeutic responses. It is also a theranostic target for tackling colon and lung cancers, where overexpression of non-neuronal ChAT leads to the production of acetylcholine, which acts as an autocrine growth factor for cancer cells. Theranostics is a hybrid of diagnostics and therapeutics that can be used to locate cancer cells using radiotracers and kill them without affecting other healthy tissues. Traditional virtual screening protocols have a lot of limitations; given the current rate of chemical database expansion exceeding billions, much faster screening protocols are required. Deep docking (DD) is one such platform that leverages the power of deep neural network (DNN)-based virtual screening, empowering researchers to dock billions of molecules in a speedy, yet explicit manner. Here, we have screened 1.3 billion compounds library from the ZINC20 database, identifying the best-performing hits. With each iteration run where the first iteration gave ∼116 million hits, the second iteration gave ∼3.7 million hits, and the final third iteration gave 168,447 hits from which further refinement gave us the top 5 compounds as potential ChAT inhibitors. The discovery of novel ChAT inhibitors will enable researchers to develop new probes that can be used as novel theranostic agents against cancer and as early-stage diagnostics for the onset of AD, for timely therapeutic intervention to halt the further progression of AD.