Optimising the quality-of-results (QoR) of circuits during logic synthesis is a formidable challenge necessitating the exploration of exponentially sized search spaces. While expert-designed operations aid in uncovering effective sequences, the increase in complexity of logic circuits favours automated procedures. To enable efficient and scalable solvers, we propose BOiLS, the first algorithm adapting Bayesian optimisation to navigate the space of synthesis operations. BOiLS requires no human intervention and trades-off exploration versus exploitation through novel Gaussian process kernels and trust-region constrained acquisitions. In a set of experiments on EPFL benchmarks, we demonstrate BOiLS's superior performance compared to state-of-the-art in terms of both sample efficiency and QoR values.
In the last few decades, Alzheimer’s disease (AD) has emerged as a serious global problem, and it has been considered as the most common type of dementia. PPARγ and beta-secretase 1 (BACE1) are considered as potential targets for Alzheimer’s disease management. In the same time, sulfonylureas and sulfonamides have been confirmed to have PPARγ agonistic activity. Aiming to obtain new anti-AD agents, thirty-five compounds of sulfonamide and sulfonylurea derivatives having the same essential pharmacophoric features of the reported PPARγ agonists have been subjected to virtual screening. Docking studies revealed that five compounds (1, 2, 3, 4, and 5) have promising affinities to PPARγ. They were also docked into the binding site of BACE1. In addition, ADMET and physicochemical properties of these compounds were considered. Additionally, these compounds were further evaluated against BACE1 and PPARγ. Compound 2 showed IC50 value of 1.64 μM against BACE1 and EC50 value of 0.289 μM against PPARγ.