Computational Model Development of Drug-Target Interaction Prediction: A Review

Area of Science:

• Biomedical Sciences
• Computational Biology
• Pharmacology

Background:

• Drug-target interactions are vital for disease diagnosis and treatment.
• Understanding these interactions aids in predicting biomolecular links, including drug-protein and protein-target correlations.
• Manual experimental methods for identifying drug-target relationships face limitations, driving the need for computational approaches.

Purpose of the Study:

• To review computational prediction models for drug-target connections developed in the last two years.
• To outline the advantages and disadvantages of these computational models.
• To identify promising future research directions in the field of drug-target interactions.

Main Methods:

• Literature review of computational drug-target interaction prediction models published within the past two years.
• Analysis and summarization of the methodologies, strengths, and weaknesses of identified models.
• Identification of emerging trends and potential research gaps.

Main Results:

• Several computational models for predicting drug-target interactions have emerged recently.
• These models offer varying advantages in terms of accuracy, efficiency, and data requirements.
• Each model also presents specific limitations that warrant further investigation.

Conclusions:

• Computational methods are increasingly favored for predicting drug-target relationships due to experimental limitations.
• The reviewed models provide valuable tools for accelerating drug discovery and understanding disease mechanisms.
• Further research is needed to refine existing models and explore novel computational strategies for drug-target interaction prediction.