Mol-CycleGAN: a generative model for molecular optimization

By Łukasz Maziarka, Agnieszka Pocha, Jan Kaczmarczyk, Krzysztof Rataj, Tomasz Danel, M. Warchoł. Journal of Cheminformatics, 2019

305 citations recorded by the source corpus.

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.

Subfields: Computational Theory and Mathematics, Materials Chemistry, Physical and Theoretical Chemistry

View Paper: https://www.semanticscholar.org/paper/90c97804c31287a35212538e85c5f34c0424341d

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

In Materials Chemistry

In Physical and Theoretical Chemistry

Citations in the corpus

MolGenSurvey: A Systematic Survey in Machine Learning Models for Molecule Design (2022, methodology): “Mol-CycleGAN [158] designs a cycle-GAN based model that translates input molecules to target molecules with a cycle-consistency loss [191].”
Artificial Intelligence in Cancer Research and Precision Medicine (2021, methodology): “Besides, generative adversarial networks (GAN), a combination of two networks—the generator and the discriminator—to build a stronger generator model, has also been commonly applied for molecule generation tasks (77, 78).”
Artificial intelligence in drug discovery: recent advances and future perspectives (2021, background): “Other popular deep-learning-based generative learning models, such as variational autoencoders [139], or generative adversarial networks [140,141] have also been commonly reported, as well as others based on graph convolutions [142,143].”