AI-Enabled Ultra-large Virtual Screening Identifies\nPotential Inhibitors of Choline Acetyltransferase for Theranostic\nPurposes

Alzheimer’s\ndisease (AD) and related dementias are among\nthe primary neurological disorders and call for the urgent need for\nearly-stage diagnosis to gain an upper edge in therapeutic intervention\nand increase the overall success rate. Choline acetyltransferase (ChAT)\nis the key acetylcholine (ACh) biosynthesizing enzyme and a legitimate\ntarget for the development of biomarkers for early-stage diagnosis\nand monitoring of therapeutic responses. It is also a theranostic\ntarget for tackling colon and lung cancers, where overexpression of\nnon-neuronal ChAT leads to the production of acetylcholine, which\nacts as an autocrine growth factor for cancer cells. Theranostics\nis a hybrid of diagnostics and therapeutics that can be used to locate\ncancer cells using radiotracers and kill them without affecting other\nhealthy tissues. Traditional virtual screening protocols have a lot\nof limitations; given the current rate of chemical database expansion\nexceeding billions, much faster screening protocols are required.\nDeep docking (DD) is one such platform that leverages the power of\ndeep neural network (DNN)-based virtual screening, empowering researchers\nto dock billions of molecules in a speedy, yet explicit manner. Here,\nwe have screened 1.3 billion compounds library from the ZINC20 database,\nidentifying the best-performing hits. With each iteration run where\nthe first iteration gave ∼116 million hits, the second iteration\ngave ∼3.7 million hits, and the final third iteration gave\n168,447 hits from which further refinement gave us the top 5 compounds\nas potential ChAT inhibitors. The discovery of novel ChAT inhibitors\nwill enable researchers to develop new probes that can be used as\nnovel theranostic agents against cancer and as early-stage diagnostics\nfor the onset of AD, for timely therapeutic intervention to halt the\nfurther progression of AD.