Statistical Forecasting Of Drug-Drug Interactions Using Medicines' Physiological Similarity
Abstract
Taking several drugs at once is a typical practice that raises the possibility of side effects and drug interactions(DDIs). Ensuring patient safety and the effectiveness of treatment methods relies heavily on the prediction and detection of DDIs. To forecast DDIs from drug structures and/or functions, many computational approaches have been used. A computer technique for DDIs prediction based on drug functional similarity is shown here. We established the model using essential biological components such as transporters, targets, enzymes, and carriers (CTET). It We applied it to 21,189 authorized medications. DDIs were determine. We determined the DDIs by gathering all the CTETs associated with each medication and then constructing the corresponding binary vectors. molarity tests to identify DDIs. Inner product-based similarity measures (IPSMs) produced the best prediction values among the similarity approaches that were considered. Researchers looked at 2,394,766 possible drug-pair interactions in total. The program may predict more than 250,000 DDIs with unknown causes. We conclude that the present technique is a general in silico strategy for DDI identification that is both simple and rapid, and we recommend it. In the future, we want to see this suggested strategy implemented as a realistic methodology for DDI identification using pharmacological functional similarities.
Read the paper
Related studies
- The Prediction of the In Vitro Release Curves for PLGA-Based Drug Delivery Systems with Neural Networks
- Promising Ursolic Acid as a Novel Antituberculosis Agent: Current Progress and Challenges
- Proof of principle concept for the analysis and functional prediction of rare genetic variants in the CYP2C19 and CYP2D6 genes
- Fabrication, characterization, and docking studies of furosemide-loaded nanosponges using the emulsion solvent diffusion method
- The Effect of Concomitant Administration of Proton Pump Inhibitors on the Pharmacokinetics of CDK4/6 Inhibitors in Rats: Implications for the Evaluation of Hepatic and Transporter-Mediated Drug–Drug Interactions
- Mining the Metabolic Capacity of Clostridium sporogenes Aided by Machine Learning
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.