id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
cord-286303-wo6356vq	Khanna, Varun	Prediction of novel mouse TLR9 agonists using a random forest approach	2019-12-20		.txt	text/plain	6153	320	55	In the current study, we present a machine learning based method for predicting novel mouse TLR9 (mTLR9) agonists based on features including count and position of motifs, the distance between the motifs and graphically derived features such as the radius of gyration and moment of Inertia. We therefore selected RF with the 20-fold cross-validation scheme, having maximum mean balanced accuracy and MCC and minimum standard deviation on both measures, to perform the Fig. 2 The effect of top 20 motifs in the high (a) and low (b) mTLR9 activity group of ODNs in the dataset. Our RF model predicted 545 of these 6000 random ODNs to be of high activity and we selected the top 100 for chemical synthesis, and then experimental tested them for mTLR9 activity using the RAW-Blue reporter cell line that expresses mTLR. The test dataset used to evaluate the performance of a model was composed of 46 ODNs (23 each from the two groups of high and low mTLR9 activity).	./cache/cord-286303-wo6356vq.txt	./txt/cord-286303-wo6356vq.txt