A unified solution for different scenarios of predicting drug-target interactions via triple matrix factorization

Shi, Jian-Yu; Zhang, An-Qi; Zhang, Shao-Wu; Mao, Kui-Tao; Yiu, Siu-Ming

doi:10.1186/s12918-018-0663-x

BMC Systems Biology

Table 2 Comparison with state-of-the-art approaches in terms of AUPR

From: A unified solution for different scenarios of predicting drug-target interactions via triple matrix factorization

	NetLapRLS	WNN-GIP	RLScore	KBMF2K	CMF	NRLMF	TMF
S1-CV
EN	0.789 ± 0.005	0.706 ± 0.017	0.828 ± 0.011	0.654 ± 0.008	0.877 ± 0.005	0.892 ± 0.006	0.952 ± 0.002
IC	0.837 ± 0.009	0.717 ± 0.020	0.769 ± 0.015	0.771 ± 0.009	0.923 ± 0.006	0.906 ± 0.008	0.952 ± 0.002
GPCR	0.616 ± 0.015	0.520 ± 0.021	0.625 ± 0.012	0.578 ± 0.018	0.745 ± 0.013	0.749 ± 0.015	0.844 ± 0.006
NR	0.465 ± 0.044	0.589 ± 0.034	0.526 ± 0.045	0.534 ± 0.050	0.584 ± 0.042	0.728 ± 0.041	0.811 ± 0.035
S2-CV
EN	0.123 ± 0.009	0.278 ± 0.037	0.313 ± 0.031	0.263 ± 0.033	0.229 ± 0.020	0.358 ± 0.040	0.438 ± 0.016
IC	0.200 ± 0.026	0.258 ± 0.032	0.300 ± 0.020	0.308 ± 0.038	0.286 ± 0.030	0.344 ± 0.033	0.376 ± 0.017
GPCR	0.229 ± 0.017	0.295 ± 0.025	0.368 ± 0.025	0.366 ± 0.024	0.365 ± 0.022	0.364 ± 0.023	0.428 ± 0.011
NR	0.417 ± 0.048	0.504 ± 0.056	0.500 ± 0.058	0.477 ± 0.049	0.488 ± 0.050	0.545 ± 0.054	0.541 ± 0.033
S3-CV
EN	0.669 ± 0.021	0.566 ± 0.038	0.794 ± 0.021	0.565 ± 0.023	0.698 ± 0.021	0.812 ± 0.018	0.866 ± 0.007
IC	0.737 ± 0.020	0.696 ± 0.035	0.781 ± 0.026	0.677 ± 0.021	0.620 ± 0.027	0.785 ± 0.028	0.853 ± 0.008
GPCR	0.334 ± 0.025	0.550 ± 0.047	0.533 ± 0.051	0.516 ± 0.045	0.433 ± 0.028	0.556 ± 0.038	0.677 ± 0.028
NR	0.449 ± 0.074	0.531 ± 0.073	0.433 ± 0.079	0.324 ± 0.071	0.400 ± 0.077	0.449 ± 0.079	0.675 ± 0.062
S4-CV
EN	–	–	0.238 ± 0.018	0.211 ± 0.020	–	–	0.265 ± 0.023
IC	–	–	0.187 ± 0.020	0.232 ± 0.011	–	–	0.251 ± 0.014
GPCR	–	–	0.208 ± 0.017	0.111 ± 0.034	–	–	0.231 ± 0.021
NR	–	–	0.191 ± 0.051	0.231 ± 0.040	–	–	0.239 ± 0.037

In S1, S2, S3, the results generated by former approaches were reported by [16]. The best results in each benchmark dataset under four kinds of CVs are highlighted in bold face and the second-best results are underlined

Back to article page

ISSN: 1752-0509

Contact us

General enquiries: ORSupport@springernature.com