Review and perspective on bioinformatics tools using machine learning and deep learning for predicting antiviral...

Area of Science:

• Biotechnology
• Bioinformatics
• Computational Biology

Background:

• Viruses pose a significant global health threat, necessitating novel therapeutic strategies.
• Antimicrobial peptides (AMPs) show promise for treating infections, with antiviral peptides (AVPs) specifically targeting viruses.
• Existing research on predicting AMPs using machine learning (ML) and deep learning (DL) is more advanced than that for AVPs.

Purpose of the Study:

• To review and summarize current ML and DL-based tools and methods for predicting antiviral peptides (AVPs).
• To highlight the potential of AVPs as pharmaceutical options for human and animal health.
• To address the scarcity of research tools for AVP prediction.

Main Methods:

• Literature review of AI-based tools and methods for AVP prediction.
• Analysis of ML and DL algorithms applied to peptide sequence data.
• Synthesis of current methodologies in the field of computational antiviral research.

Main Results:

• Identified and summarized various ML and DL tools and methods for AVP prediction.
• Highlighted the growing application of AI in deciphering patterns in amino acid sequences for biological functions.
• Demonstrated the potential of AI in accelerating the discovery of novel antiviral therapeutics.

Conclusions:

• AI, particularly ML and DL, offers powerful approaches for predicting AVPs.
• The development of AVP prediction tools is crucial for advancing antiviral drug discovery.
• Further research in this area can lead to effective pharmaceutical options for viral diseases.