.png){kind=icon}
返回
Masked graph modeling for molecule generation
.png){kind=icon}
OA
AI
DOI：10.1038/s41467-021-23415-2.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
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 ones. We train and then sample from our model by iteratively masking and replacing different parts of initialized graphs. We evaluate our approach on the QM9 and ChEMBL datasets using the GuacaMol distribution-learning benchmark. We find that validity, KL-divergence and Frechet ChemNet Distance scores are anti-correlated with novelty, and that we can trade off between these metrics more effectively than existing models. On distributional metrics, our model outperforms previously proposed graph-based approaches and is competitive with SMILES-based approaches. Finally, we show our model generates molecules with desired values of specified properties while maintaining physiochemical similarity to the training distribution. Generating new sensible molecular structures is a key problem in computer aided drug discovery. Here the authors propose a graph-based molecular generative model that outperforms previously proposed graph-based generative models of molecules and performs comparably to several SMILES-based models.
Keyword:
DRUG DESIGN
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
15.7
论文数:
9.3W
被引数:
91.2W
机构
引用论文
The art and practice of structure-based drug design: A molecular modeling perspective基于结构的药物设计的艺术与实践: 分子建模视角
PREAI
分享收藏分享收藏Heterotopic Bone Formation With the Use of rhBMP2 in Posterior Minimal Access Interbody Fusion.png)
Spine
SpineIF0
PREAI
分享收藏Efficient learning of non-autoregressive graph variational autoencoders for molecular graph generation用于分子图生成的非自回归图变分自编码器的有效学习OAAI
OAAI分享收藏Generating Focused Molecule Libraries for Drug Discovery with Recurrent Neural Networks使用递归神经网络生成用于药物发现的聚焦分子库ACS CENTRAL SCIENCEOAAI
ACS CENTRAL SCIENCEIF10.4
OAAI分享收藏Frechet ChemNet Distance: A Metric for Generative Models for Molecules in Drug DiscoveryFrechet ChemNet距离: 药物发现中分子生成模型的度量OAAI
OAAI分享收藏
查看更多内容