A Comparative Analytical Review on Machine Learning Methods in Drugtarget Interactions Prediction.

Area of Science:

• Computational chemistry and cheminformatics
• Pharmacology and drug discovery

Background:

• Predicting drug-target interactions (DTIs) is crucial for efficient drug discovery.
• In vitro studies for DTI prediction are costly and time-consuming, necessitating computational approaches.
• Machine learning (ML) methods offer a powerful chemogenomic strategy for DTI prediction.

Approach:

• This paper presents a novel comparative analytical framework for evaluating ML-based DTI prediction techniques.
• The framework involves categorizing ML methods, establishing evaluation criteria, and performing comparative analysis.
• Unlike previous surveys, this approach offers a systematic evaluation based on defined criteria.

Key Points:

• The research systematically reviews early, recent, and prominent DTI prediction techniques.
• It identifies the specific advantages and limitations of each reviewed approach.
• The framework facilitates the effective selection and enhancement of DTI prediction methodologies.

Conclusions:

• This work provides a comprehensive overview and guide for researchers in DTI prediction.
• The proposed analytical framework aids in selecting, comparing, and improving DTI prediction methods.
• It serves as a valuable reference for advancing computational drug discovery.