id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
cord-254592-wa5il5go	Brierley, Liam	Tissue tropism and transmission ecology predict virulence of human RNA viruses	2019-11-26		.txt	text/plain	5887	269	37	To quantify the effects of the most informative risk factors, averaged partial dependence was extracted from the random forests, describing the marginal predicted probabilities of severe virulence associated with each virus trait (Fig 4, S2 Table) . Predicted probability of classifying virulence as 'severe' for each of the most informative risk factors in random forest models applied to all known human RNA viruses and zoonotic viruses only (primary tissue tropism, any known neural tropism, any known renal tropism, level of human-to-human transmissibility, primary transmission route, and any known vector-borne transmission). In both classification tree and random forest models, viruses were more likely to be predicted to cause severe disease if they caused systemic infections, had neural or renal tropism, transmitted via direct contact or respiratory routes, or had limited capability to transmit between humans (0 < R 0 � 1).	./cache/cord-254592-wa5il5go.txt	./txt/cord-254592-wa5il5go.txt