A Hybrid Protocol for Identifying Comorbidity-Based Potential Drugs for COVID-19 Using Biomedical Literature Mining,...

Area of Science:

• Biomedical Informatics
• Computational Biology
• Infectious Diseases

Background:

• The COVID-19 pandemic, caused by SARS-CoV-2, presents a significant global health challenge despite extensive research.
• Existing treatments for COVID-19 require augmentation, particularly for patients with comorbidities such as type 2 diabetes mellitus (T2D), hypertension, and cardiovascular disease (CVD), which increase mortality risk.

Purpose of the Study:

• To develop and present a hybrid protocol for identifying potential therapeutic drugs for COVID-19.
• To leverage biomedical literature mining, omics data network analysis, and deep learning for drug discovery.

Main Methods:

• Biomedical literature mining to extract relevant information on COVID-19 and potential treatments.
• Network analysis of omics data to understand disease mechanisms and identify drug targets.
• Deep learning models to predict and identify the most promising drug candidates for COVID-19.

Main Results:

• The proposed hybrid protocol integrates multiple data sources and analytical techniques.
• The methodology facilitates the identification of potential drugs for COVID-19, with a focus on patient comorbidities.

Conclusions:

• A novel hybrid protocol combining literature mining, omics network analysis, and deep learning offers a promising strategy for COVID-19 drug discovery.
• This approach can accelerate the identification of effective treatments, especially for vulnerable patient populations with comorbidities.