How plesiosaurs swam underwater

Researchers are developing a new calculation model for generating aptames, with broad applications

Oligonucleotides are short, simple strands of synthetic DNA or RNA. Although small, these molecules play an important role in molecular and synthetic biology applications. One type of oligonucleotide – aptamers – can selectively bind to specific targets such as proteins, peptides, carbohydrates, viruses, toxins, metal ions and even living cells. Because they are similar to antibodies, they have a variety of uses in the areas of biosensors, therapy and diagnostics. However, compared to antibodies, aptamers do not induce an immune response in our bodies and are easy to synthesize and modify. In addition, an aptamer’s three-dimensional folding structure allows it to bind to a wider range of targets.

Aptamers are usually generated by one in vitro selection and amplification technology called systematic development of ligands by exponential enrichment, or SELEX. Briefly, SELEX is based on repeated cycles of binding, separation and amplification of nucleotides. This process results in an enriched pool of nucleotide sequences which are then analyzed for candidacy selection. High-throughput SELEX (HT-SELEX) can generate a large number of aptamer candidates, but current practical sequencing allows us to evaluate only a limited number of these candidates (approximately 106). Therefore, computational processes are important to optimize the detection of new aptamers.

Variational autoencoder (VAE, a type of machine learning method) -based assembly designs have been reported to be beneficial in the discovery of other small molecules. Now a team of researchers led by Professor Michiaki Hamada from the Graduate School of Advanced Science and Engineering at Waseda University, Japan, has introduced RaptGen, a UAE that can be used for aptamer generation. In their newspaper, which was published in Natural science on June 2, 2022, they describe how RaptGen uses a UAE with a profile-hidden Markov Model decoder to create latent spaces where sequences can form clusters. Using this latent representation, RaptGen was able to generate aptamers that were not even included in the original sequencing data or HT-SELEX data set.

Asked exactly how RaptGen could increase the discovery of aptamers, Professor Hamada says, “RaptGen first visualizes a latent space with a sequence motif and then generates several new aptamer sequences via this latent space. For example, it searches for optimized aptamer sequences in the latent space by consider additional information after analyzing the activity of a subset of sequences. In addition, RaptGen enables the design of truncated (or truncated) aptamer sequences. “

The team also successfully evaluated RaptGen’s performance using real-time data, exposing it to data from two independent HT-SELEX data sets. RaptGen could generate aptamer derivatives in an activity-controlled manner and provide opportunities to optimize its activities. “This is important because it means that RaptGen can generate sequences with desired properties, such as inhibition of certain enzymes or protein-protein interactions,” explains Professor Hamada. The use of these molecules may open many doors in the future.

Going forward, the team plans to conduct extensive studies to evaluate whether alternative models can improve the performance of RaptGen, and whether RaptGen could promote the generation of RNA aptams by using RNA sequences. The only disadvantages of using RaptGen are the high calculation cost and increased training time, both of which can be improved in further studies.

Professor Hamada concludes by saying: “As far as we know, RaptGen is the only data-driven method that can design and optimize truncated aptamers directly from HT-SELEX data. We believe that RaptGen will in time be recognized as a key tool for effective detection of aptamer. “

Story source:

Material provided by Waseda University. Note! The content can be edited for style and length.

#Researchers #developing #calculation #model #generating #aptames #broad #applications

Leave a Comment

Your email address will not be published.