A deep learning framework for identifying essential proteins based on multiple biological information

BMC Bioinformatics

Table 4 The performance of different feature combinations

Method	Accuracy	Precision	Recall	F1 score	Sensitivity	NPV
S + N + G	0.9048	0.7306	0.7885	0.7585	0.9320	0.9496
N	0.8122	0.5094	0.2379	0.3243	0.9464	0.8416
S	0.8639	0.6404	0.6432	0.6418	0.9156	0.9165
G	0.4566	0.2112	0.6828	0.3226	0.4037	0.8448
N + G	0.7888	0.4484	0.4978	0.4718	0.8568	0.8795
N + S	0.8723	0.6713	0.6388	0.6546	0.9269	0.9165
S + G	0.8673	0.6560	0.6300	0.6427	0.9228	0.9143

N network embedding features, G gene expression profile features, N + G network embedding features plus gene expression profile features, N + S network embedding features plus subcellular localization features, S + G subcellular localization features plus gene expression profile features, S + N + G subcellular localization features plus network embedding features and gene expression profile features

ISSN: 1471-2105