Predicting gene function using hierarchical multi-label decision tree ensembles

BMC Bioinformatics

Table 2 Comparison of between CLUS-HMC-ENS and the MouseFunc systems

Subset	CLUS-HMC-ENS	BSVM⁺	KLR	CSVM	GENE FAS	GENE MANIA	KIM	Funckenstein
BP_3-10	0.120	0.156⊕	0.075⊖	0.075⊖	0.108⊖	0.170⊕	0.108⊖	0.198⊕
BP_11-30	0.110	0.141⊕	0.087⊖	0.085⊖	0.074⊖	0.151⊕	0.107⊖	0.162⊕
BP_31-100	0.139	0.172⊕	0.158⊕	0.140⊕	0.094⊖	0.177⊕	0.116⊖	0.244⊕
BP_101-300	0.171	0.172⊕	0.169⊖	0.173⊕	0.104⊖	0.160⊖	0.056⊖	0.214⊕
CC_3-10	0.319	0.249⊖	0.119⊖	0.083⊖	0.233⊖	0.324⊕	0.271⊖	0.316⊖
CC_11-30	0.260	0.194⊖	0.212⊖	0.151⊖	0.131⊖	0.235⊖	0.178⊖	0.267⊕
CC_31-100	0.217	0.232⊕	0.197⊖	0.161⊖	0.191⊖	0.261⊕	0.144⊖	0.287⊕
CC_101-300	0.244	0.217⊖	0.259⊕	0.221⊖	0.177⊖	0.258⊕	0.118⊖	0.279⊕
MF_3-10	0.320	0.441⊕	0.258⊖	0.228⊖	0.427⊕	0.465⊕	0.304⊖	0.472⊕
MF_11-30	0.356	0.373⊕	0.347⊖	0.393⊕	0.350⊖	0.401⊕	0.302⊖	0.455⊕
MF_31-100	0.269	0.289⊕	0.230⊖	0.278⊕	0.242⊖	0.291⊕	0.255⊖	0.416⊕
MF_101-300	0.322	0.317⊖	0.321⊖	0.374⊕	0.295⊖	0.391⊕	0.172⊖	0.441⊕

For each of the 12 subsets, the of CLUS-HMC-ENS is compared with the MouseFunc systems. A win (⊕) means that the MouseFunc system outperforms CLUS-HMC-ENS, a loss (⊖) means that it is outperformed by CLUS-HMC-ENS.

ISSN: 1471-2105