Drug-target Affinity Prediction Based on Graph Attention Network and Protein Language Model
In the development of new drugs,the binding affinity between drugs and targets is a key indicator,and accurate prediction of it is crucial for accelerating drug screening.In recent years,significant progress has been made in the prediction of drug-target binding affinity,attracting widespread attention due to the application of deep learning technologies.However,most existing methods tend to overlook the structural information of drugs and lack in-depth learning of the patterns between protein sequences and structures,resulting in limited predictive performance.To address this issue,this paper introduces a novel approach that integrates graph attention network with protein language model to represent drug and protein more effectively.Experiments conducted on two public datasets,compared with other similar methods,demonstrate that the proposed method significantly enhances prediction accuracy,thereby proving its effectiveness.
graph attention networkprotein language modeldrug-target affinitydeep learning
NETL
NSTL
万方数据
