Cargando…
Masked graph modeling for molecule generation
De novo, in-silico design of molecules is a challenging problem with applications in drug discovery and material design. We introduce a masked graph model, which learns a distribution over graphs by capturing conditional distributions over unobserved nodes (atoms) and edges (bonds) given observed on...
Autores principales: | Mahmood, Omar, Mansimov, Elman, Bonneau, Richard, Cho, Kyunghyun |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8155025/ https://www.ncbi.nlm.nih.gov/pubmed/34039973 http://dx.doi.org/10.1038/s41467-021-23415-2 |
Ejemplares similares
-
Molecular Geometry Prediction using a Deep Generative Graph Neural Network
por: Mansimov, Elman, et al.
Publicado: (2019) -
NetTIME: a multitask and base-pair resolution framework for improved transcription factor binding site prediction
por: Yi, Ren, et al.
Publicado: (2022) -
Optimal tuning of weighted kNN- and diffusion-based methods for denoising single cell genomics data
por: Tjärnberg, Andreas, et al.
Publicado: (2021) -
NetQuilt: deep multispecies network-based protein function prediction using homology-informed network similarity
por: Barot, Meet, et al.
Publicado: (2021) -
Structure-based protein function prediction using graph convolutional networks
por: Gligorijević, Vladimir, et al.
Publicado: (2021)