Machine learning based imputation techniques for estimating phylogenetic trees from incomplete distance matrices

BMC Genomics

Table 3 Average RF rates (± standard error) of different methods on the 201-taxon dataset. The best RF rates for various model conditions are shown in boldface

#Taxa	#Entries	Model	#Missing	Average RF Rate
			Entries	LASSO	MF	AE
			400	0.6 ±0.02	0.36 ±0.04	0.36 ±0.01
			1024	0.61 ±0.02	0.4 ±0.05	0.39 ±0.04
		TN93	2500	0.62 ±0.02	0.41 ±0.03	0.4 ±0.02
			5625	0.63 ±0.03	0.44 ±0.03	0.41 ±0.03
201	20100		10100	N/A	0.59 ±0.02	0.43 ±0.01
			400	0.59 ±0.02	0.38 ±0.02	0.37 ±0.01
			1024	0.62 ±0.01	0.4 ±0.03	0.38 ±0.02
		LogDet	2500	0.61 ±0.02	0.41 ±0.02	0.4 ±0.02
			5625	0.62 ±0.02	0.46 ±0.03	0.43 ±0.02
			10100	N/A	0.58 ±0.03	0.43 ±0.01

ISSN: 1471-2164