Oncological drug discovery: AI meets structure-based computational research.

Area of Science:

• Computational biology
• Drug discovery
• Oncology

Background:

• Machine learning and structure-based computational methods are crucial for prioritizing drug targets and compounds.
• Neoplastic diseases present significant challenges due to their diverse nature, necessitating advanced research approaches.

Purpose of the Study:

• To review the application of integrated computational methods in oncological research.
• To explore six specific use-case scenarios for these integrated approaches.
• To highlight the potential of these methods in accelerating personalized cancer therapy development.

Main Methods:

• Review of integrated machine learning and structure-based computational methods.
• Analysis of six key use-case scenarios: driver prediction, computational mutagenesis, (off)-target prediction, binding site prediction, virtual screening, and allosteric modulation analysis.
• Discussion of integration approaches, individual method capabilities, and limitations.

Main Results:

• Integrated computational methods offer significant benefits in addressing the complexity of cancer.
• Six distinct use-case scenarios demonstrate the versatility of these approaches in drug discovery.
• The heterogeneity of integration strategies and methods is acknowledged, alongside their current constraints.

Conclusions:

• Integrated computational methods are vital for advancing oncological research and drug discovery.
• These approaches hold promise for overcoming limitations in current cancer therapy development.
• The potential exists to expedite the delivery of personalized cancer treatments to patients.