RESUMO
Deep learning-based molecular generative models have successfully identified drug candidates with desired properties against biological targets of interest. However, syntactically invalid molecules generated from a deep learning-generated model hinder the model from being applied to drug discovery. Herein, we propose a conditional variational autoencoder (CVAE) as a generative model to propose drug candidates with the desired property outside a data set range. We train the CVAE using molecular fingerprints and corresponding GI50 (inhibition of growth by 50%) results for breast cancer cell lines instead of training with various physical properties for each molecule together. We confirm that the generated fingerprints, not included in the training data set, represent the desired property using the CVAE model. In addition, our method can be used as a query expansion method for searching databases because fingerprints generated using our method can be regarded as expanded queries.
RESUMO
Many fluorescent proteins (FPs) show fluorescence quenching by specific metal ions, which can be applied towards metal biosensor development. In this study, we investigated the significant fluorescence quenching of Dronpa by Co(2+) and Cu(2+) ions. Crystal structures of Co(2+) -, Ni(2+) - and Cu(2+) -bound Dronpa revealed previously unseen, unique, metal-binding sites for fluorescence quenching. These metal ions commonly interact with surface-exposed histidine residues (His194-His210 and His210-His212), and interact indirectly with chromophores. Structural analysis of the Co(2+) - and Cu(2+) - binding sites of Dronpa provides insight into FP-based metal biosensor engineering.