The Center for Bioinformatics and Intelligent Medicine team published a paper in Bioinformatics
November 01,2022 Editor：Centre for Bioinformatics and Intelligent Medicine
The lab team published “Drug–Protein interaction prediction by correcting the effect of Incomplete information in heterogeneous information” in Bioinformatics.
In recent years, computational methods for predicting drug-protein interactions have attracted more and more attention. The multi-source heterogeneous information can provide new perspectives and potentially improve the accuracy of drug-protein interaction prediction. However, the heterogeneous information available may be incomplete, and the existing methods do not distinguish between incomplete information and complete information, so they fail to fully weaken the negative impact of missing information.
In this paper, the drug-protein heterogeneous networks based on complete information and incomplete information are constructed successively. The negative effect of information incomplete on the prediction results of drug-protein interaction on the incomplete information network is weakened by the correction operation on the complete information network. The experimental results show that the method has better performance than the baselines in each evaluation metric.
