A research team led by Prof. ZHANG Fan and Prof. GU Hongcang from the Hefei Institutes of Physical Science of the Chinese Academy of Sciences has developed HelixDTA, a deep learning model for predicting drug-target affinity.
The model was designed to improve the prediction of interactions between drug molecules and target proteins.
"The analysis helped us understand which parts of drugs and proteins are important for their interactions," said Prof. ZHANG Fan.
The result was published in Journal of Chemical Information and Modeling.
Drug-target affinity prediction is an important step in AI-assisted drug discovery. It helps researchers evaluate whether a drug candidate can interact with a specific protein target. However, accurately predicting these interactions remains challenging because they are influenced by multiple factors, including molecular structures, protein sequences and three-dimensional conformations.
In this study, the team developed HelixDTA by bringing together information from drug molecules and target proteins. The model looks at drug structures, protein sequences and three-dimensional structural features to better understand how drugs interact with their target proteins. It then uses this information to predict the strength of these interactions.
The researchers tested HelixDTA on two widely used benchmark datasets, Davis and KIBA. The results showed that the model maintained stable prediction performance in standard evaluations.
They further examined its ability to handle more challenging cases, including interactions involving unfamiliar drug structures, evolutionarily distant protein sequences and new protein structures. HelixDTA continued to provide reliable predictions in these unseen situations.
Researchers also analyzed the model' s prediction process to better understand how different regions of drugs and proteins contribute to their interactions. The results showed that HelixDTA could identify regions related to drug binding and protein functions.
HelixDTA provides a computational approach for studying potential drug-target interactions, according to the team.
Framework of HelixDTA (Image by ZHANG Fan)