The Center for Bioinformatics and Intelligent Medicine team published a paper in Bioinformatics
October 15,2021 Editor:Centre for Bioinformatics and Intelligent Medicine
The lab team published "Autoencoder-based drug–target interaction prediction by preserving the consistency of chemical properties and functions of drugs" in Bioinformatics.
Exploring potential drug-target interactions (DTIs) is crucial in drug discovery and repurposing.
In recent years, predicting the probable DTIs through computational methods has gradually become a research hot spot.
However, most of the previous studies failed to judiciously consider the consistency between the chemical properties of a drug and its functions.
The changes in these relationships may lead to a severely negative effect on the prediction of DTIs.
The paper proposes an Autoencoder-based approach(AEFS) to predict potential drug-target interactions by maintaining a consistent
distribution of drug relevance in the chemical property space,molecular mechanism space, and clinical function space.
Experimental comparisons suggest that AEFS is significantly superior to several state-of-art DTI predition methods and is also
a robust DTI prediction method with inbalanced data.