DSpace Repository

Embedding of Molecular Structure Using Molecular Hypergraph Variational Autoencoder with Metric Learning

Show simple item record

dc.contributor.author Koge, Daiki
dc.contributor.author Ono, Naoaki
dc.contributor.author Huang, Ming
dc.contributor.author Altaf‐Ul‐Amin, Md.
dc.contributor.author Kanaya, Shigehiko
dc.date.accessioned 2020-12-23T08:22:58Z
dc.date.available 2020-12-23T08:22:58Z
dc.date.issued 2020-11-08
dc.identifier.uri http://hdl.handle.net/10061/14170
dc.description.abstract Deep learning approaches are widely used to search molecular structures for a candidate drug/material. The basic approach in drug/material candidate structure discovery is to embed a relationship that holds between a molecular structure and the physical property into a low‐dimensional vector space (chemical space) and search for a candidate molecular structure in that space based on a desired physical property value. Deep learning simplifies the structure search by efficiently modeling the structure of the chemical space with greater detail and lower dimensions than the original input space. In our research, we propose an effective method for molecular embedding learning that combines variational autoencoders (VAEs) and metric learning using any physical property. Our method enables molecular structures and physical properties to be embedded locally and continuously into VAEs’ latent space while maintaining the consistency of the relationship between the structural features and the physical properties of molecules to yield better predictions. ja_JP
dc.language.iso en ja_JP
dc.publisher Wiley-VCH Verlag ja_JP
dc.relation.isreplacedby https://onlinelibrary.wiley.com/doi/full/10.1002/minf.202000203 ja_JP
dc.rights © 2020The Authors.Publishedby Wiley-VCHGmbH ja_JP
dc.title Embedding of Molecular Structure Using Molecular Hypergraph Variational Autoencoder with Metric Learning ja_JP
dc.type.nii Journal Article ja_JP
dc.contributor.transcription オノ, ナオアキ
dc.contributor.transcription カナヤ, シゲヒコ
dc.contributor.alternative 小野, 直亮
dc.contributor.alternative 金谷, 重彦
dc.textversion none ja_JP
dc.identifier.eissn 1868-1751
dc.identifier.jtitle Molecular Informatics ja_JP
dc.relation.doi 10.1002/minf.202000203 ja_JP
dc.identifier.NAIST-ID 73298960 ja_JP
dc.identifier.NAIST-ID 73292666 ja_JP
dc.identifier.NAIST-ID 73292500 ja_JP


Files in this item

Files Size Format View

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse

My Account