[Dedicated to Prof. T. Okada and Prof. T. Nishioka: data science in chemistry]Classification of Alkaloid Compounds Based on Subring Skeleton (SRS) Profiling: On Finding Relationship of Compounds with Metabolic Pathways

Amino acid-derived defense metabolites from plants: A potential source to facilitate novel antimicrobial development

For millennia, humanity has relied on plants for its medicines, and modern pharmacology continues to reexamine and mine plant metabolites for novel compounds and to guide improvements in biological activity, bioavailability, and chemical stability. The critical problem of antibiotic resistance and increasing exposure to viral and parasitic diseases has spurred renewed interest into drug treatments for infectious diseases. In this context, an urgent revival of natural product discovery is globally underway with special attention directed toward the numerous and chemically diverse plant defensive compounds such as phytoalexins and phytoanticipins that combat herbivores, microbial pathogens, or competing plants. Moreover, advancements in “omics,” chemistry, and heterologous expression systems have facilitated the purification and characterization of plant metabolites and the identification of possible therapeutic targets. In this review, we describe several important amino acid–derived classes of plant defensive compounds, including antimicrobial peptides (e.g., defensins, thionins, and knottins), alkaloids, nonproteogenic amino acids, and phenylpropanoids as potential drug leads, examining their mechanisms of action, therapeutic targets, and structure–function relationships. Given their potent antibacterial, antifungal, antiparasitic, and antiviral properties, which can be superior to existing drugs, phytoalexins and phytoanticipins are an excellent resource to facilitate the rational design and development of antimicrobial drugs.

Classification of alkaloids according to the starting substances of their biosynthetic pathways using graph convolutional neural networks

BACKGROUND

Alkaloids, a class of organic compounds that contain nitrogen bases, are mainly synthesized as secondary metabolites in plants and fungi, and they have a wide range of bioactivities. Although there are thousands of compounds in this class, few of their biosynthesis pathways are fully identified. In this study, we constructed a model to predict their precursors based on a novel kind of neural network called the molecular graph convolutional neural network. Molecular similarity is a crucial metric in the analysis of qualitative structure-activity relationships. However, it is sometimes difficult for current fingerprint representations to emphasize specific features for the target problems efficiently. It is advantageous to allow the model to select the appropriate features according to data-driven decisions for extracting more useful information, which influences a classification or regression problem substantially.

RESULTS

In this study, we applied a neural network architecture for undirected graph representation of molecules. By encoding a molecule as an abstract graph and applying "convolution" on the graph and training the weight of the neural network framework, the neural network can optimize feature selection for the training problem. By incorporating the effects from adjacent atoms recursively, graph convolutional neural networks can extract the features of latent atoms that represent chemical features of a molecule efficiently. In order to investigate alkaloid biosynthesis, we trained the network to distinguish the precursors of 566 alkaloids, which are almost all of the alkaloids whose biosynthesis pathways are known, and showed that the model could predict starting substances with an averaged accuracy of 97.5%.

CONCLUSION

We have showed that our model can predict more accurately compared to the random forest and general neural network when the variables and fingerprints are not selected, while the performance is comparable when we carefully select 507 variables from 18000 dimensions of descriptors. The prediction of pathways contributes to understanding of alkaloid synthesis mechanisms and the application of graph based neural network models to similar problems in bioinformatics would therefore be beneficial. We applied our model to evaluate the precursors of biosynthesis of 12000 alkaloids found in various organisms and found power-low-like distribution.