Mining Chemogenomic Spaces for Prediction of Drug-Target Interactions

Area of Science:

• Computational chemistry
• Bioinformatics
• Drug discovery

Background:

• Drug discovery is a complex process with numerous stages.
• Drug-target interaction (DTI) determination is a critical step.
• Computational prediction of DTIs can significantly reduce experimental costs and timelines.

Purpose of the Study:

• To provide a comprehensive overview of machine learning algorithms for DTI prediction.
• To detail the stages involved in developing accurate DTI prediction models.
• To highlight the advantages of computational approaches in drug discovery.

Main Methods:

• Focus on machine learning algorithms for DTI prediction.
• Discussion of various stages in building predictive models.
• Exploration of network-centric approaches as an evolving alternative.

Main Results:

• Machine learning methods are widely adopted for DTI prediction.
• Computational prediction offers a viable alternative to experimental validation.
• The chapter outlines a systematic approach to developing predictive tools.

Conclusions:

• Machine learning-based DTI prediction is a key strategy in modern drug discovery.
• Accurate computational predictors streamline the identification of drug candidates.
• This work emphasizes the importance of computational approaches in accelerating drug development.