期刊论文详细信息
Journal of Cheminformatics
Mol-CycleGAN: a generative model for molecular optimization
Tomasz Danel1  Jan Kaczmarczyk1  Michał Warchoł1  Krzysztof Rataj1  Łukasz Maziarka1  Agnieszka Pocha2 
[1] Ardigen;Faculty of Mathematics and Computer Science, Jagiellonian University;
关键词: Drug design;    Molecular optimization;    Generative models;    Deep learning;   
DOI  :  10.1186/s13321-019-0404-1
来源: DOAJ
【 摘 要 】

Abstract Designing a molecule with desired properties is one of the biggest challenges in drug development, as it requires optimization of chemical compound structures with respect to many complex properties. To improve the compound design process, we introduce Mol-CycleGAN—a CycleGAN-based model that generates optimized compounds with high structural similarity to the original ones. Namely, given a molecule our model generates a structurally similar one with an optimized value of the considered property. We evaluate the performance of the model on selected optimization objectives related to structural properties (presence of halogen groups, number of aromatic rings) and to a physicochemical property (penalized logP). In the task of optimization of penalized logP of drug-like molecules our model significantly outperforms previous results.

【 授权许可】

Unknown   

  文献评价指标  
  下载次数:0次 浏览次数:5次