Drug repurposing for viral cancers: A paradigm of machine learning, deep learning, and virtual screening-based...

Area of Science:

• Oncology
• Virology
• Pharmacology

Background:

• Viral cancers represent a significant portion of human cancers, necessitating efficient treatment strategies.
• Traditional de novo drug discovery is lengthy, costly, and has a high clinical failure rate.
• Drug repurposing, identifying new uses for approved drugs, presents a viable alternative for accelerating viral cancer treatments.

Purpose of the Study:

• To critically review existing databases, tools, and computational approaches for drug repurposing in viral cancers.
• To present the mechanisms underlying viral oncogenesis.
• To provide case studies of drug repurposing for specific viral cancers and discuss limitations and future directions.

Main Methods:

• Comprehensive literature review of viral cancer databases and drug repurposing tools.
• Analysis of machine learning, deep learning, and virtual screening methodologies applied to viral cancer drug discovery.
• Examination of viral cancer mechanisms and case studies of successful drug repurposing.

Main Results:

• Identification of key databases and computational tools relevant to viral cancer drug repurposing.
• Overview of successful applications of AI and virtual screening in repurposing drugs for viral cancers.
• Detailed case studies illustrating the repurposing of specific drugs for distinct viral cancers.

Conclusions:

• Drug repurposing is a promising strategy to expedite the development of novel therapies for viral cancers.
• Integration of diverse computational approaches and understanding viral mechanisms can enhance repurposing success.
• Addressing current limitations and challenges will further optimize drug repurposing for viral oncology.