id	author	title	date	pages	extension	mime	words	sentence	flesch	summary	cache	txt
admet-852	Falcón-Cano, Gabriela; Molina, Christophe; Cabrera-Pérez, Miguel Angel	ADME prediction with KNIME: In silico aqueous solubility consensus model based on supervised recursive random forest approaches	2020	23	.pdf	application/pdf	11406	584	62	In order to find a way to improve the predictive accuracy of aqueous solubility models in silico, a new protocol was developed based on the combination of regression and classification models. Recently, some machine learning (ML) algorithms such as random forests (RF), support vector machines (SVM), k-nearest neighbors (k-NN), and convolutional and recurrent networks have been applied for aqueous solubility prediction, and their performance matches or outperforms the previous results obtained [11–15].	cache/admet-852.pdf	txt/admet-852.txt