Many therapeutic drugs are compounds that can be represented by simple chemical structures, which contain important determinants of affinity at the site of action. Recently, graph convolutional neural network (GCN) models have exhibited excellent results in classifying the activity of such compounds. For models that make quantitative predictions of activity, more complex information has been utilized, such as the three-dimensional structures of compounds and the amino acid sequences of their respective target proteins. As another approach, we hypothesized that if sufficient experimental data were available and there were enough nodes in hidden layers, a simple compound representation would quantitatively predict activity with satisfactory accuracy. In this study, we report that GCN models constructed solely from the two-dimensional structural information of compounds demonstrated a high degree of activity predictability against 127 diverse targets from the ChEMBL database. Using the information entropy as a metric, we also show that the structural diversity had less effect on the prediction performance. Finally, we report that virtual screening using the constructed model identified a new serotonin transporter inhibitor with activity comparable to that of a marketed drug in vitro and exhibited antidepressant effects in behavioural studies.
Recent studies suggest that peroxisome proliferator-activated receptor (PPAR) activation ameliorates metabolic disorders, including dyslipidemia. To identify an effective PPAR agonist, we screened the in vitro PPARα/γ activation ability of organic solvent extracts from food-oriented bacterial strains belonging to 5 genera and 32 species, including lactic acid bacteria, and of these, Lactobacillus amylovorus CP1563 demonstrated the highest PPARα/γ agonist activity. We also found that physical fragmentation of the strain could substitute organic solvent extraction for the expression of CP1563 activity in vitro. For functional food manufacturing, we selected the fragmented CP1563 and conducted subsequent animal experiments. In an obese mouse model, we found that treatment with fragmented CP1563 for 12 weeks decreased the levels of low-density lipoprotein (LDL)-cholesterol and triglyceride in plasma, significantly decreased the atherosclerosis index, and increased the plasma high-density lipoprotein (HDL)-cholesterol level. Thus, we conclude that fragmented CP1563 may be a candidate for the prevention and treatment of dyslipidemia.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.