Research on Data Fusion Method for Drug-drug Interaction Prediction
HUANG An
XIE Xiaolan
PENG Shaoliang
Abstract：Drug-drug interaction prediction is critical to the safety of drug combination.At present,there are many calcula-tion methods for interaction prediction.However,these methods are usually limited to the use of drug similarity information,while ignoring other features of drugs.Therefore,a deep learning framework MDDI based on multi-information fusion is proposed,which uses multi-information of drugs to predict drug interaction events.MDDI extracts chemical molecular structure,target,metabolic enzyme and drug similarity to help predict.The experimental results on DrugBank dataset show that this method can effectively ex-tract the features of drugs and has better performance of interaction prediction.
Keywords：drug-drug interaction predictiondata fusiondeep learning
Publication Date：2025-10-20
Online Publishing Date：2026-01-16(First online date of this platform, not the publication date of the document)
Pages：6( 2754-2759 )