Fast and robust imputation for miRNA expression data using constrained least squares

BMC Bioinformatics

Table 3 Korea data results

Metric	FLI	VIPER	scImpute	Regression	Mean	Zeros
(a) Classification results
AUC	.97	.96	.96	.91	.92	.80
\(F_1\)	.94	.94	.95	.89	.90	.88
ACC	.91	.91	.92	.85	.83	.80
(b) Imputation errors
\(\epsilon _{\mu }\)	.13	.13	.14	.27	.14	.67
\(\epsilon _{\sigma }\)	.01	.01	.01	.17	.01	.02
\(\epsilon _{M}\)	.17	.17	.18	75.3	.19	.72

Time	FLI	VIPER	scImpute	regression	mean	zeros
(c) Imputation time
\(t_\mu\)	.024	18.2	.365	.005	\(\sim\)0	\(\sim\)0
\(t_\sigma\)	.016	5.33	.348	\(\sim 0\)	\(\sim\)0	\(\sim\)0
\(t_{\text {max}}\)	.313	48.0	2.58	.063	\(\sim\)0	\(\sim 0\)

(a) Mean values over curves shown in Fig. 5a–c. b Mean values over curves shown in Fig. 5d–f. c Mean (\(t_\mu\)), standard deviation (\(t_\sigma\)), and maximum (\(t_{\text {max}}\)) imputation times (in seconds) over all test patients. In table (c), \(\sim\)0 indicates that the imputation time is strictly less than .0005 s

ISSN: 1471-2105