This work proposes the use of IN-A(l/v:identity matrix; A:adjacency matrix),instead of l/v + A,the normalized form of which has intensively been used for the construction of graph convolutional networks(GCNs),in deep-learning chemistry.The performance of the GCN model with D~(-1/2)(IN-A)D~(-1)~(-1/2)in its convolution step is at least on a par with the vanilla GCN that uses D~(-1/2)(IN + A)D~(-1/2)(D:degree matrix of IN + A)in various chemistry datasets,such as FreeSolv,ESOL,lipophilicity,and blood-brain barrier penetration datasets.It could be seen that the use of IN-A might be more chemically intuitive than the use of l/v + A,potentially embracing the information on bond properties,such as dipole moment,and functional groups in a molecule.This work suggests unavoidable necessity of tackling molecular-representation problems in deep-learning chemistry from unprecedented angles of view for advanced development and construction of chemically intuitive deep-learning models.
展开▼
