Enhancing prediction of adverse drug event using drug-gene interaction - скачать в хорошем качестве

Enhancing prediction of adverse drug event using drug-gene interaction -

Abstract: Adverse drug events (ADEs) pose critical public health issues, affecting over 6% of hospitalized patients. While knowledge of potential drug-drug interactions (DDI) is necessary to prevent ADE, the rapid pace of drug discovery makes it challenging. We developed a novel literature-mining framework for enhancing the predictions of DDIs and ADE types by integrating drug-gene interactions (DGIs). We adapted ADE types from a DDI corpus. By using random forest classifier our approach achieves an F-score of 0.87 across the ADEs classification using only the DDI features. We then enhanced the performance of the classifier by including DGIs (F-score = 0.90), and applied the classification model trained with the DDI corpus to identify DDIs and ADEs for drugs used for treating cutaneous diseases. We successfully predict previously known ADEs and are also able to identify promising new ADEs.