Research progress on Drug-Target Interactions in the last five years

Area of Science:

• Computational chemistry
• Bioinformatics
• Drug discovery

Background:

• Drug-Target Interaction (DTI) identification is vital for drug discovery and repositioning.
• Experimental validation of DTIs is costly and time-consuming.
• Computational approaches provide an economical and efficient alternative.

Purpose of the Study:

• To review and synthesize existing chemical genomic approaches for DTI prediction.
• To provide a comprehensive summary of prevalent DTI prediction databases and feature encodings.
• To discuss recent advancements and future directions in DTI prediction methods.

Main Methods:

• Literature review of chemical genomic approaches.
• Categorization of feature encodings for DTI prediction.
• Overview and comparison of prevalent DTI prediction methods (2020-2024), including network representation learning and graph neural networks.

Main Results:

• Synthesis of current DTI prediction databases and feature encoding strategies.
• Detailed discussion of strengths and weaknesses of recent DTI prediction methods.
• Evaluation of method performance across various datasets.

Conclusions:

• Computational DTI prediction is a rapidly evolving field with significant potential.
• Emerging methods like graph neural networks show promise for improving accuracy and efficiency.
• Future research should focus on integrating big data and advanced computing technologies to enhance DTI prediction.