An end-to-end method for predicting compound-protein interactions based on simplified homogeneous graph convolutional network and pre-trained language model

Table 7 Detailed information and external supporting evidence of top five ranked compounds-protein pairs predicted by SPVec-SGCN model

Rank	Compounds	Target Name	Bioactivity data	References
1	CHEMBL823551	Integrin alpha-4/beta-7	IC50: 211 nM	[69]
2	CHEMBL3286826	ALK tyrosine kinase receptor/Nucleophosmin	Ki: < 0.0800 nM	[70]
3	CHEMBL345144	Integrin alpha-4/beta-7	IC50: 2.10E + 3 nM	[71]
4	CHEMBL116	Protease	Ki: 0.00700 nM	[72]
5	CHEMBL1120718	Histamine H3 receptor	Ki:0.3 nM	[73]

ISSN: 1758-2946