Drug Repositioning Based on the Enhanced Message Passing and Hypergraph Convolutional Networks

A general hypergraph learning algorithm for drug multi-task predictions in micro-to-macro biomedical networks

The powerful combination of large-scale drug-related interaction networks and deep learning provides new opportunities for accelerating the process of drug discovery. However, chemical structures that play an important role in drug properties and high-order relations that involve a greater number of nodes are not tackled in current biomedical networks. In this study, we present a general hypergraph learning framework, which introduces Drug-Substructures relationship into Molecular interaction Networks to construct the micro-to-macro drug centric heterogeneous network (DSMN), and develop a multi-branches HyperGraph learning model, called HGDrug, for Drug multi-task predictions. HGDrug achieves highly accurate and robust predictions on 4 benchmark tasks (drug-drug, drug-target, drug-disease, and drug-side-effect interactions), outperforming 8 state-of-the-art task specific models and 6 general-purpose conventional models. Experiments analysis verifies the effectiveness and rationality of the HGDrug model architecture as well as the multi-branches setup, and demonstrates that HGDrug is able to capture the relations between drugs associated with the same functional groups. In addition, our proposed drug-substructure interaction networks can help improve the performance of existing network models for drug-related prediction tasks.

Senolytic and senomorphic secondary metabolites as therapeutic agents in Drosophila melanogaster models of Parkinson's disease

Drosophila melanogaster is a valuable model organism for a wide range of biological exploration. The well-known advantages of D. melanogaster include its relatively simple biology, the ease with which it is genetically modified, the relatively low financial and time costs associated with their short gestation and life cycles, and the large number of offspring they produce per generation. D. melanogaster has facilitated the discovery of many significant insights into the pathology of Parkinson's disease (PD) and has served as an excellent preclinical model of PD-related therapeutic discovery. In this review, we provide an overview of the major D. melanogaster models of PD, each of which provide unique insights into PD-relevant pathology and therapeutic targets. These models are discussed in the context of their past, current, and future potential use for studying the utility of secondary metabolites as therapeutic agents in PD. Over the last decade, senolytics have garnered an exponential interest in their ability to mitigate a broad spectrum of diseases, including PD. Therefore, an emphasis is placed on the senolytic and senomorphic properties of secondary metabolites. It is expected that D. melanogaster will continue to be critical in the effort to understand and improve treatment of PD, including their involvement in translational studies focused on secondary metabolites.