Search

Proteins in complex with small molecule ligands represent the core of structure-based drug discovery. However, three-dimensional representations are absent from most deep-learning-based generative models. We here present a graph-based generative modeling technology that encodes explicit 3D protein-ligand contacts within a relational graph architecture. The models combine a conditional variational autoencoder that allows for activity-specific molecule generation with putative contact generation that provides predictions of molecular interactions within the target binding pocket. We show that molecules generated with our 3D procedure are more compatible with the binding pocket of the dopamine D2 receptor than those produced by a comparable ligand-based 2D generative method, as measured by docking scores, expected stereochemistry, and recoverability in commercial chemical databases. Predicted protein-ligand contacts were found among highest-ranked docking poses with a high recovery rate. This work shows how the structural context of a protein target can be used to enhance molecule generation., Comment: 5 pages, 3 figures

The application of deep learning to generative molecule design has shown early promise for accelerating lead series development. However, questions remain concerning how factors like training, dataset, and seed bias impact the technology's utility to medicine and computational chemists. In this work, we analyze the impact of seed and training bias on the output of an activity-conditioned graph-based variational autoencoder (VAE). Leveraging a massive, labeled dataset corresponding to the dopamine D2 receptor, our graph-based generative model is shown to excel in producing desired conditioned activities and favorable unconditioned physical properties in generated molecules. We implement an activity swapping method that allows for the activation, deactivation, or retention of activity of molecular seeds, and we apply independent deep learning classifiers to verify the generative results. Overall, we uncover relationships between noise, molecular seeds, and training set selection across a range of latent-space sampling procedures, providing important insights for practical AI-driven molecule generation., Comment: 17 pages, 8 figures

Drug discovery is a multi-stage process that comprises two costly major steps: pre-clinical research and clinical trials. Among its stages, lead optimization easily consumes more than half of the pre-clinical budget. We propose a combined machine learning and molecular modeling approach that automates lead optimization workflow \textit{in silico}. The initial data collection is achieved with physics-based molecular dynamics (MD) simulation. Contact matrices are calculated as the preliminary features extracted from the simulations. To take advantage of the temporal information from the simulations, we enhanced contact matrices data with temporal dynamism representation, which are then modeled with unsupervised convolutional variational autoencoder (CVAE). Finally, conventional clustering method and CVAE-based clustering method are compared with metrics to rank the submolecular structures and propose potential candidates for lead optimization. With no need for extensive structure-activity relationship database, our method provides new hints for drug modification hotspots which can be used to improve drug efficacy. Our workflow can potentially reduce the lead optimization turnaround time from months/years to days compared with the conventional labor-intensive process and thus can potentially become a valuable tool for medical researchers.

The structural properties of the uranium-encapsulated nano-cage U@Au14 are predicted using density functional theory. The presence of the uranium atom makes the Au14 structure more stable than the empty Au14-cage, with a triplet ground electronic state for U@Au14. Analysis of the electronic structure shows that the two frontier single-occupied molecular orbital electrons of U@Au14 mainly originate from the 5f shell of the U atom after charge transfer. Meanwhile, the bonding orbitals have both the 5f and 6d components of the U atom, along with the 5d and 6s components of the Au atoms, indicating the covalent nature of the interaction between the U and Au atoms. Moreover, the charge population analysis shows that this nanostructure displays some unique electronic properties where the encapsulated atom gains electrons while the outer shell loses electrons. Therefore, this designed U@Au14 nano-cage structure is stabilized by ionocovalent interactions. The current findings provide theoretical basis for future syntheses and further study of actinide doped gold nanoclusters, which might subsequently facilitate applications of such structure in radio-labeling, nanodrug carrier and other biomedical applications.