DAPTEV: Deep aptamer evolutionary modelling for COVID-19 drug design

Area of Science:

• Biotechnology and Pharmaceutical Sciences
• Computational Biology
• Molecular Biology

Background:

• Traditional drug discovery is expensive, slow, and prone to bias.
• Aptamers offer high affinity and specificity for molecular targets, but their development is challenging.
• Systematic Evolution of Ligands by Exponential Enrichment (SELEX) is a conventional, yet inefficient, aptamer development process.

Purpose of the Study:

• To develop an intelligent computational approach for aptamer sequence generation and evolution.
• To address the cost, time, and optimization limitations of conventional aptamer development.
• To support and accelerate aptamer-based drug discovery and development.

Main Methods:

• Development of a novel intelligent approach named DAPTEV.
• Utilizing computational methods for generating and evolving aptamer sequences.
• Testing the approach using the COVID-19 spike protein as a target molecule.

Main Results:

• DAPTEV demonstrates an ability to generate structurally complex aptamers.
• The generated aptamers exhibit strong binding affinities to the target.
• Computational results indicate significant improvements over traditional methods.

Conclusions:

• DAPTEV offers a promising intelligent solution for aptamer discovery.
• This approach can potentially reduce costs and time in aptamer-based drug development.
• The method shows efficacy in generating high-affinity aptamers for specific targets like the COVID-19 spike protein.