Feature extraction with spectral clustering for gene function prediction using hierarchical multi-label classification

Applied Network Science

Table 1 Resulting sub-hierarchies \(H'\) of biological processes for maize

Root	Description	Functions	Genes	Functions per level
GO:0050896	Response to stimulus	13	1733	5/5/2
GO:0051179	Localization	25	1497	3/5/9/6/1
GO:0065007	Biological regulation	37	2647	2/5/11/10/4/2/2
GO:0008152	Metabolic process	92	6596	8/18/38/12/7/6/2
GO:0009987	Cellular process	92	8005	13/19/19/17/13/8/2

The identifier and description of each root function r is presented in the first and second columns, respectively. The third column shows the number of functions \(A'\) within each sub-hierarchy and the fourth column shows the number maize genes in the GCN subgraph \(G'\) associated to \(H'\). The last column shows the number of functions per level, e.g., the first sub-hierarchy has 3 levels and there are 5, 5, and 2 functions on each level