Related Experiment Video
Updated: May 5, 2026
06:50
Author Spotlight: A Computational Approach to Decipher Amino Acid Preferences in Multispecific Protein-Protein Interactions
Published on: January 26, 2024
2.8K
Comprehensive evaluation of artificial intelligence-empowered approaches for protein-aptamer complex prediction
Jiani Zhao1, Kha Tram2, Hongbin Yan3,4
1Department of Computer Science, Brock University, 1812 Sir Isaac Brock Way, St. Catharines, L2S 3A1 Ontario, Canada.
Briefings in Bioinformatics
|May 4, 2026
Summary
Artificial intelligence (AI) tools show promise for designing aptamer drugs, but their accuracy in modeling protein-aptamer complexes needs further evaluation. This study benchmarks AI frameworks to guide future development in nucleic acid therapeutics.
Area of Science:
- Biomolecular modeling
- Computational drug discovery
- Nucleic acid therapeutics
Background:
- Drug discovery is costly and high-risk, with AI transforming small-molecule and protein therapeutic design.
- Aptamer drugs, while promising for diseases like cancer due to high affinity and specificity, face challenges in AI-driven design due to limited structural data and aptamer flexibility.
- Protein-aptamer complex structures are underrepresented in public databases, hindering AI-based modeling.
Purpose of the Study:
- To systematically evaluate current AI frameworks for predicting protein-aptamer complex structures.
- To assess the performance of AI models in estimating binding free energies for aptamer-protein interactions.
- To establish an independent benchmark for evaluating AI in aptamer drug design.
Main Methods:
- Systematic evaluation of AI frameworks: AlphaFold3, Chai-1, Boltz-2, and RoseTTAFold2NA.
- Comparison with a template-based approach for structure prediction.
- Development of an independent benchmark to assess structural accuracy, stability, and energetic consistency.
Main Results:
- Performance of AlphaFold3, Chai-1, Boltz-2, and RoseTTAFold2NA in predicting protein-aptamer complex structures was systematically benchmarked.
- Binding free energy estimation capabilities of the evaluated AI frameworks were assessed.
- The study established a benchmark for structural accuracy, stability, and energetic consistency in protein-aptamer complex modeling.
Conclusions:
- This study provides a foundational assessment of AI frameworks for protein-aptamer complex structure prediction.
- The established benchmark serves as a reference for future research in AI-driven aptamer drug design.
- Findings will guide the application of AI in developing novel nucleic acid therapeutics.
Related Concept Videos
02:04Protein-protein Interfaces
12.5K
Many proteins form complexes to carry out their functions, making protein-protein interactions (PPIs) essential for an organism's survival. Most PPIs are stabilized by numerous weak noncovalent chemical forces. The physical shape of the interfaces determines the way two proteins interact. Many globular proteins have closely-matching shapes on their surfaces, which form a large number of weak bonds. Additionally, many PPIs occur between two helices or between a surface cleft and a...
12.5K
01:49Conserved Binding Sites
4.1K
Many proteins’ biological role depends on their interactions with their ligands, small molecules that bind to specific locations on the protein known as ligand-binding sites. Ligand-binding sites are often conserved among homologous proteins as these sites are critical for protein function.
Binding sites are often located in large pockets, and if their location on a protein’s surface is unknown, it can be predicted using various approaches. The energetic method computationally...
Binding sites are often located in large pockets, and if their location on a protein’s surface is unknown, it can be predicted using various approaches. The energetic method computationally...
4.1K
02:26Protein Networks
3.7K
An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
3.7K