Since the QSAR/DNN model showed predominant predictive performance over other conventional methods in the Kaggle QSAR competition, many artificial neural network (ANN) methods have been applied to drug and material discovery. Appearance of artificial intelligence (AI), which is combined various general purpose ANN platforms with large-scale open access chemical databases, has attracting great interest and expectation in a wide range of molecular sciences. In this study, we investigate various DNN settings in order to reach a high-level of predictive performance comparable to the champion team of the competition, even with a general purpose ANN platform, and introduce the Meister setting for constructing a good QSAR/DNNs model. Here, we have used the most commonly available DNN model and constructed many QSAR/DNN models trained with various DNN settings by using the 15 datasets employed in the competition. As a result, it was confirmed that we can constructed the QSAR/DNN model that shows the same level of R2 performance as the champion team. The difference from the DNN setting recommended by the champion team was to reduce the mini-batch size. We have also explained that the R2 performance of each target depends on the molecular activity type, which is related to the complexity of biological mechanisms and chemical processes observed in molecular activity measurements.
We propose a solution method of Time Dependent Schrödinger Equation (TDSE) and the advection equation by quantum walk/quantum cellular automaton with spatially or temporally variable parameters. Using numerical method, we establish the quantitative relation between the quantum walk with the space dependent parameters and the "Time Dependent Schrödinger Equation with a space dependent imaginary diffusion coefficient" or "the advection equation with space dependent velocity fields". Using the 4-point-averaging manipulation in the solution of advection equation by quantum walk, we find that only one component can be extracted out of two components of left-moving and right-moving solutions. In general it is not so easy to solve an advection equation without numerical diffusion, but this method provides perfectly diffusion free solution by virtue of its unitarity. Moreover our findings provide a clue to find more general space dependent formalisms such as solution method of TDSE with space dependent resolution by quantum walk.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.