Explore
Home 
Literature 
Links 
Posts 
Molecules 
Blogs 
Zeitgeist 
Markup Help 
News 
Everything Papers Books
In de novo drug design, computational strategies are used to generate novel molecules with good affinity to the desired biological target. In this work, we show that recurrent neural networks can be trained as generative models for molecular structures, similar to statistical language models in natural language processing. We demonstrate that the properties of the generated molecules correlate very well with the properties of the molecules used to train the model. In order to enrich libraries with molecules active toward a given biological target, we propose to fine-tune the model with small sets of molecules, which are known to be active against that target. Against Staphylococcus aureus, the model reproduced 14% of 6051 hold-out test molecules that medicinal chemists designed, whereas against Plasmodium falciparum (Malaria), it reproduced 28% of 1240 test molecules. When coupled with a scoring function, our model can perform the complete de novo drug design cycle to generate large sets of novel molecules for drug discovery.

Posts

Masato Sumita, Xiufeng Yang, Shinsuke Ishihara, Ryo Tamura, and Koji Tsuda (2018)Highlighted by Jan JensenFigure 1 from the paper. Reproduced under the CC-BY-NC-ND licenseSumita and co-workers combine Monte Carlo tree search (MCTS) and a recurrent neural...