Deep Learning in the Quest for Compound Nomination for Fighting COVID-19

Area of Science:

• Biomedical research
• Computational biology
• Epidemiology

Background:

• The COVID-19 pandemic spurred rapid advancements in biomedical research and clinical response.
• Multidimensional data generated during the pandemic provided a rich framework for computational analysis.

Purpose of the Study:

• To review the application of deep learning and machine learning in COVID-19 research.
• To focus on research concerning COVID-19 targets, drug discovery, and symptom management.

Main Methods:

• Utilizing deep learning for data analysis and model building.
• Employing machine learning techniques for prediction-validation workflows.
• Reviewing computational strategies for drug identification and repurposing.

Main Results:

• Deep learning models have been instrumental in assessing outbreak spread, taxonomy, and population susceptibility.
• Significant progress has been made in diagnostics and drug discovery/repurposing within months.
• Computational approaches are yielding results in identifying therapeutic strategies.

Conclusions:

• Advanced machine learning techniques are crucial for understanding and combating the COVID-19 pandemic.
• Continued application of these methods is expected to yield further breakthroughs.
• Research is focusing on therapeutic targets and drug development to manage COVID-19.