A machine learning model for classifying G-protein-coupled receptors as agonists or antagonists.

BACKGROUND: G-protein coupled receptors (GPCRs) sense and transmit extracellular signals into the intracellular machinery by regulating G proteins. GPCR malfunctions are associated with a variety of signaling-related diseases, including cancer and diabetes; at least a third of the marketed drugs target GPCRs. Thus, characterization of their signaling and regulatory mechanisms is crucial for the development of effective drugs. RESULTS: In this study, we developed a machine learning model to identify GPCR agonists and antagonists. We designed two-step prediction models: the first model identified the ligands binding to GPCRs and the second model classified the ligands as agonists or antagonists. Using 990 selected subset features from 5270 molecular descriptors calculated from 4590 ligands deposited in two drug databases, our model classified non-ligands, agonists, and antagonists of GPCRs, and achieved an area under the ROC curve (AUC) of 0.795, sensitivity of 0.716, specificity of 0.744, and accuracy of 0.733. In addition, we verified that 70% (44 out of 63) of FDA-approved GPCR-targeting drugs were correctly classified into their respective groups. CONCLUSIONS: Studies of ligand-GPCR interaction recognition are important for the characterization of drug action mechanisms. Our GPCR-ligand interaction prediction model can be employed in the pharmaceutical sciences for the efficient virtual screening of putative GPCR-binding agonists and antagonists.

Computational determination of hERG-related cardiotoxicity of drug candidates.

BACKGROUND: Drug candidates often cause an unwanted blockage of the potassium ion channel of the human ether-a-go-go-related gene (hERG). The blockage leads to long QT syndrome (LQTS), which is a severe life-threatening cardiac side effect. Therefore, a virtual screening method to predict drug-induced hERG-related cardiotoxicity could facilitate drug discovery by filtering out toxic drug candidates. RESULT: In this study, we generated a reliable hERG-related cardiotoxicity dataset composed of 2130 compounds, which were carried out under constant conditions. Based on our dataset, we developed a computational hERG-related cardiotoxicity prediction model. The neural network model achieved an area under the receiver operating characteristic curve (AUC) of 0.764, with an accuracy of 90.1%, a Matthews correlation coefficient (MCC) of 0.368, a sensitivity of 0.321, and a specificity of 0.967, when ten-fold cross-validation was performed. The model was further evaluated using ten drug compounds tested on guinea pigs and showed an accuracy of 80.0%, an MCC of 0.655, a sensitivity of 0.600, and a specificity of 1.000, which were better than the performances of existing hERG-toxicity prediction models. CONCLUSION: The neural network model can predict hERG-related cardiotoxicity of chemical compounds with a high accuracy. Therefore, the model can be applied to virtual high-throughput screening for drug candidates that do not cause cardiotoxicity. The prediction tool is available as a web-tool at http://ssbio.cau.ac.kr/CardPred .

In silico prediction of potential chemical reactions mediated by human enzymes.

BACKGROUND: Administered drugs are often converted into an ineffective or activated form by enzymes in our body. Conventional in silico prediction approaches focused on therapeutically important enzymes such as CYP450. However, there are more than thousands of different cellular enzymes that potentially convert administered drug into other forms. RESULT: We developed an in silico model to predict which of human enzymes including metabolic enzymes as well as CYP450 family can catalyze a given chemical compound. The prediction is based on the chemical and physical similarity between known enzyme substrates and a query chemical compound. Our in silico model was developed using multiple linear regression and the model showed high performance (AUC = 0.896) despite of the large number of enzymes. When evaluated on a test dataset, it also showed significantly high performance (AUC = 0.746). Interestingly, evaluation with literature data showed that our model can be used to predict not only enzymatic reactions but also drug conversion and enzyme inhibition. CONCLUSION: Our model was able to predict enzymatic reactions of a query molecule with a high accuracy. This may foster to discover new metabolic routes and to accelerate the computational development of drug candidates by enabling the prediction of the potential conversion of administered drugs into active or inactive forms.