@article{bmc2009alignfree,
	Abstract = {BACKGROUND:In this work we consider barcode DNA analysis problems
	and address them using alternative, alignment-free methods and representations
	which model sequences as collections of short sequence fragments
	(features). The methods use fixed-length representations (spectrum)
	for barcode sequences to measure similarities or dissimilarities
	between sequences coming from the same or different species. The
	spectrum-based representation not only allows for accurate and computationally
	efficient species classification, but also opens possibility for
	accurate clustering analysis of putative species barcodes and identification
	of critical within-barcode loci distinguishing barcodes of different
	sample groups.RESULTS:New alignment-free methods provide highly accurate
	and fast DNA barcode-based identification and classification of species
	with substantial improvements in accuracy and speed over state-of-the-art
	barcode analysis methods. We evaluate our methods on problems of
	species classification and identification using barcodes, important
	and relevant analytical tasks in many practical applications (adverse
	species movement monitoring, sampling surveys for unknown or pathogenic
	species identification, biodiversity assessment, etc.) On several
	benchmark barcode datasets, including ACG, Astraptes, Hesperiidae,
	Fish larvae, and Birds of North America, proposed alignment-free
	methods considerably improve prediction accuracy compared to prior
	results. We also observe significant running time improvements over
	the state-of-the-art methods.CONCLUSION:Our results show that newly
	developed alignment-free methods for DNA barcoding can efficiently
	and with high accuracy identify specimens by examining only few barcode
	features, resulting in increased scalability and interpretability
	of current computational approaches to barcoding.},
	Author = {Kuksa, Pavel and Pavlovic, Vladimir},
	Bib2Html_Pubtype = {Journal},
	Date-Modified = {2020-03-06 13:19:11 -0500},
	Doi = {10.1186/1471-2105-10-S14-S9},
	Issn = {1471-2105},
	Journal = {BMC Bioinformatics},
	Note = {Impact factor: 3.78},
	Number = {Suppl 14},
	Pages = {S9},
	Pubmedid = {19900305},
	Title = {Efficient alignment-free {DNA} barcode analytics},
	Url = {http://www.biomedcentral.com/1471-2105/10/S14/S9},
	Volume = {10},
	Year = {2009},
	Bdsk-Url-1 = {http://www.biomedcentral.com/1471-2105/10/S14/S9},
	Bdsk-Url-2 = {http://dx.doi.org/10.1186/1471-2105-10-S14-S9}}