VGAE-MCTS: A New Molecular Generative Model Combining the Variational Graph Auto-Encoder and Monte Carlo Tree Search.

Molecular generation is crucial for advancing drug discovery, materials science, and chemical exploration. It expedites the search for new drug candidates, facilitates tailored material creation, and enhances our understanding of molecular diversity. By employing artificial intelligence techniques such as molecular generative models based on molecular graphs, researchers have tackled the challenge of identifying efficient molecules with desired properties. Here, we propose a new molecular generative model combining a graph-based deep neural network and a reinforcement learning technique. We evaluated the validity, novelty, and optimized physicochemical properties of the generated molecules. Importantly, the model explored uncharted regions of chemical space, allowing for the efficient discovery and design of new molecules. This innovative approach has considerable potential to revolutionize drug discovery, materials science, and chemical research for accelerating scientific innovation. By leveraging advanced techniques and exploring previously unexplored chemical spaces, this study offers promising prospects for the efficient discovery and design of new molecules in the field of drug development.

A guide-tag system controlling client enrichment into Y15 peptide-based granules for an in-cell protein recruitment assay.

Self-assembling peptides (SAPs) are valuable building blocks for the fabrication of artificial supramolecules. We developed a guide-tag system that concentrates client proteins into SAP-based scaffolds in cellular environments at various enrichment levels. This system provides a tool to analyse the protein-protein interactions caused by protein clustering in cells.

Intracellular artificial supramolecules based on de novo designed Y15 peptides.

De novo designed self-assembling peptides (SAPs) are promising building blocks of supramolecular biomaterials, which can fulfill a wide range of applications, such as scaffolds for tissue culture, three-dimensional cell culture, and vaccine adjuvants. Nevertheless, the use of SAPs in intracellular spaces has mostly been unexplored. Here, we report a self-assembling peptide, Y15 (YEYKYEYKYEYKYEY), which readily forms ß-sheet structures to facilitate bottom-up synthesis of functional protein assemblies in living cells. Superfolder green fluorescent protein (sfGFP) fused to Y15 assembles into fibrils and is observed as fluorescent puncta in mammalian cells. Y15 self-assembly is validated by fluorescence anisotropy and pull-down assays. By using the Y15 platform, we demonstrate intracellular reconstitution of Nck assembly, a Src-homology 2 and 3 domain-containing adaptor protein. The artificial clusters of Nck induce N-WASP (neural Wiskott-Aldrich syndrome protein)-mediated actin polymerization, and the functional importance of Nck domain valency and density is evaluated.