id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
cord-136540-2h2braww	Buehler, Markus J.	Liquified protein vibrations, classification and cross-paradigm de novo image generation using deep neural networks	2020-04-16		.txt	text/plain	3684	209	51	Here we present a method to transform these molecular vibrations into materialized vibrations of thin water films using acoustic actuators, leading to complex patterns of surface waves, and using the resulting macroscopic images in further processing using deep convolutional neural networks. Specifically, the patterns of water surface waves for each protein structure is used to build training sets for neural networks, aimed to classify and further process the patterns. Once trained, the neural network model is capable of discerning different proteins solely by analyzing the macroscopic surface wave patterns in the water film. This article focuses on a different perspective and reports a distinct, complementary and translational approach, in which we transform these molecular vibrations into vibrations of thin water films using acoustic actuators, leading to visual images of complex materialized patterns of surface waves. We use DeepDream [39] to generate novel images by activating select layers in the deep neural network, based on the model trained against the water surface images.	./cache/cord-136540-2h2braww.txt	./txt/cord-136540-2h2braww.txt