DC Field | Value | Language |
---|---|---|
dc.contributor.author | Jeong, Yoonho | ko |
dc.contributor.author | Kim, Jihoo | ko |
dc.contributor.author | Kim, Yeji | ko |
dc.contributor.author | Choi, Insung S. | ko |
dc.date.accessioned | 2022-07-31T00:00:33Z | - |
dc.date.available | 2022-07-31T00:00:33Z | - |
dc.date.created | 2022-05-06 | - |
dc.date.created | 2022-05-06 | - |
dc.date.issued | 2022-07 | - |
dc.identifier.citation | BULLETIN OF THE KOREAN CHEMICAL SOCIETY, v.43, no.7, pp.934 - 936 | - |
dc.identifier.issn | 0253-2964 | - |
dc.identifier.uri | http://hdl.handle.net/10203/297639 | - |
dc.description.abstract | This work proposes the use of I-N - A (I-N: identity matrix; A: adjacency matrix), instead of I-N + 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(I-N - A)D-1/2 in its convolution step is at least on a par with the vanilla GCN that uses (D) over tilde (-1/2)(I-N + A)(D) over tilde (-1/2) ((D) over tilde: degree matrix of I-N + A) in various chemistry datasets, such as FreeSolv, ESOL, lipophilicity, and blood-brain barrier penetration datasets. It could be seen that the use of I-N - A might be more chemically intuitive than the use of I-N + 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. | - |
dc.language | English | - |
dc.publisher | WILEY-V C H VERLAG GMBH | - |
dc.title | Development of a chemically intuitive filter for chemical graph convolutional network | - |
dc.type | Article | - |
dc.identifier.wosid | 000787104100001 | - |
dc.identifier.scopusid | 2-s2.0-85128871084 | - |
dc.type.rims | ART | - |
dc.citation.volume | 43 | - |
dc.citation.issue | 7 | - |
dc.citation.beginningpage | 934 | - |
dc.citation.endingpage | 936 | - |
dc.citation.publicationname | BULLETIN OF THE KOREAN CHEMICAL SOCIETY | - |
dc.identifier.doi | 10.1002/bkcs.12533 | - |
dc.identifier.kciid | ART002861215 | - |
dc.contributor.localauthor | Choi, Insung S. | - |
dc.contributor.nonIdAuthor | Jeong, Yoonho | - |
dc.contributor.nonIdAuthor | Kim, Yeji | - |
dc.description.isOpenAccess | N | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | adjacency matrix | - |
dc.subject.keywordAuthor | convolution filter | - |
dc.subject.keywordAuthor | deep learning | - |
dc.subject.keywordAuthor | graph convolutional network | - |
dc.subject.keywordAuthor | molecular representation | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.