The research team led by Weihong Tan, Xiaohong Fang, and Tao Bing at the Hangzhou Institute of Medical Sciences, Chinese Academy of Sciences, has introduced a groundbreaking method for analyzing nucleic acid aptamer sequences using machine learning. This innovative approach allows for the direct parsing of the secondary structure of nucleic acid aptamers from single-round screening data, eliminating the need for iterative enrichment. The findings, published in the open-access journal CCS Chemistry, promise to significantly accelerate the discovery and optimization of nucleic acid aptamers.
Nucleic acid aptamers are known for their ability to specifically recognize target molecules, thanks to their diverse and complex secondary structures. Traditional methods like SELEX generate numerous candidate sequences, yet identifying their functional secondary structures remains challenging. Conventional techniques such as electron microscopy and X-ray crystallography fall short in efficiently resolving these structures, hindering the optimization of nucleic acid aptamers.
Machine Learning: A New Frontier in Aptamer Analysis
To tackle these challenges, the research team developed a machine learning-based analytical method. This method employs unsupervised autoencoder clustering and deep learning to analyze core sequences within the aptamer family from a single round of screening. By using these core sequences as indices, the method extracts common secondary structural features of nucleic acid aptamers, facilitating rational truncation and performance optimization.
In their study, the researchers focused on the CD8 protein, using deep learning to analyze the family distribution patterns in single-round aptamer screening sequences. Despite the heterogeneous sequence background, they identified a common core sequence, “GTGAGGAGCTTGAAA,” enriched across most families. Traditional sequence alignment methods struggled to extract this key sequence due to the low homology background.
“Over 10,000 potentially active CD8-specific aptamers were successfully obtained,” the research team reported.
Verifying and Expanding the Method’s Applicability
To verify the core sequences, the team synthesized a library containing part of the core sequence and performed RE-SILEX. All screened nucleic acids contained core sequences consistent with those identified in the initial screening. Further analysis revealed that 62.4% of sequences formed stem-loop structures, while others formed different secondary structures. This insight allowed for the optimization of nucleic acid sequences, enhancing their affinity.
The method’s applicability was further tested on fibroblast activation protein (FAP) screening data. The results showed a conserved core sequence, suggesting a G-quadruplex structure, which was optimized to improve binding affinity. This demonstrates the method’s versatility across different structural types of aptamers.
Implications for Future Research and Applications
This novel approach reveals that single-round nucleic acid aptamer screening libraries contain rich structural information, previously thought to require multiple rounds of screening. By integrating high-throughput sequencing with machine learning, the study advances the field by decoding aptamer secondary structures and precisely locating target binding sites.
“This technique achieves rational truncation and optimization of nucleic acid aptamers, increasing affinity by more than tenfold,” the study highlights.
The implications of this research extend beyond aptamer discovery. It challenges traditional paradigms by emphasizing spatial conformation’s role in molecular recognition and opens new avenues for designing functional nucleic acids and exploring RNA-protein interactions. The potential for AI-driven virtual screening platforms for nucleic acid aptamers could drive rapid advancements in precision diagnostics and treatments.
Supported by various prestigious foundations, this research underscores the potential of machine learning in revolutionizing the field of nucleic acid aptamer technology. As the flagship journal of the Chinese Chemical Society, CCS Chemistry provides a platform for such groundbreaking work, promoting advancements across all areas of chemistry.
