.png){kind=icon}
返回
Kernel-elastic autoencoder for molecular design
.png){kind=icon}
OA
AI
DOI：10.1093/pnasnexus/pgae168.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
We introduce the kernel-elastic autoencoder (KAE), a self-supervised generative model based on the transformer architecture with enhanced performance for molecular design. KAE employs two innovative loss functions: modified maximum mean discrepancy (m-MMD) and weighted reconstruction ( L WCEL ). The m-MMD loss has significantly improved the generative performance of KAE when compared to using the traditional Kullback-Leibler loss of VAE, or standard maximum mean discrepancy. Including the weighted reconstruction loss L WCEL , KAE achieves valid generation and accurate reconstruction at the same time, allowing for generative behavior that is intermediate between VAE and autoencoder not available in existing generative approaches. Further advancements in KAE include its integration with conditional generation, setting a new state-of-the-art benchmark in constrained optimizations. Moreover, KAE has demonstrated its capability to generate molecules with favorable binding affinities in docking applications, as evidenced by AutoDock Vina and Glide scores, outperforming all existing candidates from the training dataset. Beyond molecular design, KAE holds promise to solve problems by generation across a broad spectrum of applications.
Keyword:
generative modeling
molecular optimization
molecular docking
期刊
P
IF:
3.8
论文数:
2.2K
被引数:
3.2K
机构
引用论文
Molecular generative model based on conditional variational autoencoder for de novo molecular design
OAAI
OAAI分享收藏Multi-constraint molecular generation based on conditional transformer, knowledge distillation and reinforcement learning基于条件变换器、知识蒸馏和强化学习的多约束分子生成
PREAI
分享收藏Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules使用数据驱动的分子连续表示的自动化学设计.png)
ACS CENTRAL SCIENCEOAAI
ACS CENTRAL SCIENCEIF10.4
OAAI分享收藏Extra precision glide: Docking and scoring incorporating a model of hydrophobic enclosure for protein-ligand complexes额外的精度滑行: 结合蛋白质-配体复合物的疏水外壳模型进行对接和评分OAAI
OAAI分享收藏
查看更多内容