id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_77qqyvwmkzehpc4drzvfito2hi	Evangelia I. Zacharaki	Prediction of protein function using a deep convolutional neural network ensemble	2017	17	.pdf	application/pdf	7062	638	58	The automatic prediction of protein function can provide quick annotations on extensive datasets opening the path for relevant applications, such structure-based protein function prediction, but sufficient data may not yet be available Keywords Enzyme classification, Function predition, Deep learning, Convolutional neural How to cite this article Zacharaki (2017), Prediction of protein function using a deep convolutional neural network ensemble. Most methods use features derived from the amino acid sequence author's knowledge, deep CNNs have not been used for prediction of protein function so far. enzymatic function prediction, the method is not based on enzyme-specific properties and multi-channel feature set is introduced to a CNN and results are combined by kNN or SVM classification. of amino acids and their arrangement in space (features XD) predict enzymatic function Using pseudo-amino acid composition and support vector machine to predict protein structural class. Predicting enzyme class from protein structure without convolutional architecture for sequence-based protein structure prediction.	./cache/work_77qqyvwmkzehpc4drzvfito2hi.pdf	./txt/work_77qqyvwmkzehpc4drzvfito2hi.txt