Predicting Adverse Drug Reactions Using Computational Methods: An Analysis of Drug and Adverse Reaction Features and Representations

Identifying and controlling adverse drug reactions is a complex problem in the pharmacological field. Despite the studies done in di↵erent laboratory stages, some adverse drug reactions are recognized after being released, such as Rosiglitazone. Due to such experiences, pharmacists are now more interested in using computational methods to predict adverse drug reactions. In computational methods, finding and representing appropriate drug and adverse reaction features are one of the most critical challenges. Here, we assess fingerprint and target as drug features; and phenotype and unified medical language system as adverse reaction features to predict adverse drug reaction. Meanwhile, we show that drug and adverse reaction features represented by similarity vectors can improve adverse drug prediction computational methods. This article proposes four frameworks to analyze drug and adverse reaction features and representations in drug-adverse reaction association prediction. Two frameworks are based on random forest classification and neural networks as machine learning methods called F RF and F NN, respectively. Rest of them apply matrix factorization methods by improving the CS and TMF models. They are extended by considering target as a drug feature and phenotype as an adverse reaction feature. However, machine learning frameworks with fewer drug and adverse reaction features are more accurate than matrix factorization frameworks. In addition, the F RF framework performs significantly better than F NN with ACC = %۸۹.۱۵, AUC = %۹۶.۱۴ and AUPRC = %۹۲.۹. Next, we contrast F RF with some well-known models designed based on similarity vectors of drug and adverse reaction features. Unlike other methods, we do not remove rare reactions from the data set in our frameworks.

کلیدواژه ها:

Adverse drug reaction ، Machine learning ، Random Forest