Application of Machine Learning Approaches for the Design and Study of Anticancer Drugs

Area of Science:

• Computational chemistry
• Bioinformatics
• Drug discovery

Background:

• Cancer is a leading global cause of mortality, driving urgent research into novel anticancer drugs.
• The development of effective anticancer therapeutics is a critical area of medical research.

Purpose of the Study:

• To review the application of machine learning (ML) in predicting anticancer drug activity.
• To highlight ML's role in accelerating anticancer drug design and discovery.

Main Methods:

• Selected machine learning approaches including Linear Discriminant Analysis (LDA), Principal Component Analysis (PCA), Support Vector Machine (SVM), Random Forest (RF), k-Nearest Neighbor (kNN), and Naïve Bayes (NB).
• Examined examples of ML applications in the design and prediction of anticancer drug efficacy.

Main Results:

• Machine learning significantly contributes to anticancer drug design, offering time and cost efficiencies.
• ML serves as a powerful assisting tool, enhancing the capabilities of researchers in drug development.

Conclusions:

• Machine learning approaches are increasingly valuable in anticancer drug design and activity prediction.
• The integration of ML accelerates the identification and development of new anticancer agents.
• Ongoing research and available web servers support the advancement of ML in anticancer drug discovery.