id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
cord-355351-seqwx9x1	Battey, CJ	Predicting geographic location from genetic variation with deep neural networks	2020-06-08		.txt	text/plain	8728	397	44	At least in the context of windowed analyses, differences in predictions among windows appears to primarily reflect variation in ancestry rather than uncertainty in the inference itself, so we suggest the intervals returned by Locator's kernel density estimation are best interpreted as representing areas from which a given proportion of the genome is likely to have originated. To test whether outlier geographic predictions reflect error in the model fitting procedure versus true variation in ancestry in a given region of the genome, we ran principal component analyses on windows for which a Maya individual (sample HGDP00871) has predicted locations in Europe and Africa. Test error was estimated as the distance in kilometers from the true sampling location to the geographic centroid of the cloud of per-window predictions, and is shown in Figure 8 plotted against local recombination rates from the HapMap genetic map (International HapMap Consortium, 2003) .	./cache/cord-355351-seqwx9x1.txt	./txt/cord-355351-seqwx9x1.txt