Using computers to ESKAPE the antibiotic resistance crisis

Area of Science:

• Pharmacology and Drug Discovery
• Computational Chemistry
• Infectious Diseases

Background:

• Antibiotics revolutionized bacterial infection treatment but rising antibiotic resistance necessitates novel drug discovery approaches.
• Traditional drug discovery is slow, costly, and inefficient for developing new antibacterial agents.

Purpose of the Study:

• To review the application of cutting-edge in silico techniques, including machine learning (ML) and deep learning (DL), in drug discovery.
• To discuss the potential of quantum computing in advancing antibiotics research.
• To identify current limitations in computational drug discovery.

Main Methods:

• Review of current state-of-the-art computational approaches for drug discovery.
• Analysis of machine learning (ML) and deep learning (DL) applications.
• Discussion of quantum computing advancements and their relevance to antibiotic research.

Main Results:

• In silico methods, ML, and DL offer efficient and cost-effective alternatives for identifying drug candidates.
• Quantum computing holds significant promise for accelerating antibiotic research.
• Several bottlenecks currently impede the full advancement of computational drug discovery.

Conclusions:

• Computational approaches are crucial for overcoming the challenges posed by antibiotic resistance.
• Integrating advanced computational techniques like ML, DL, and quantum computing is vital for future antibiotic development.
• Addressing current bottlenecks is essential for maximizing the impact of computational drug discovery.