id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
cord-007259-vj9tv3or	Guo, Feng-Biao	Accurate prediction of human essential genes using only nucleotide composition and association information	2017-06-15		.txt	text/plain	5656	315	52	RESULTS: Our model accurately predicted human gene essentiality with an AUC higher than 0.88 both for 5-fold cross-validation and jackknife tests. reported a machine learningbased method that integrated various intrinsic and predicted features to identify essential genes in yeast S.cerevisiae genomes (Seringhaus et al., 2006) . The data from these three groups provided a rare opportunity to theoretically study the function, sequence composition, evolution and network topology of human essential genes. Based on the k-interval Z curve, we obtained excellent performance in human essential gene identification. For human essential gene identification, we only used the sequence composition and interval association information in the present study and still obtained an AUC of 0.8854. Considering that this result is better than the results obtained in previous studies using integrated features, the gene essentiality of the human genome can be accurately reflected based on only the sequence information.	./cache/cord-007259-vj9tv3or.txt	./txt/cord-007259-vj9tv3or.txt