Artificial Intelligence in Aptamer–Target Binding Prediction

Abstract

Aptamers are short single-stranded DNA, RNA, or synthetic Xeno nucleic acids (XNA) molecules that can interact with corresponding targets with high affinity. Owing to their unique features, including low cost of production, easy chemical modification, high thermal stability, reproducibility, as well as low levels of immunogenicity and toxicity, aptamers can be used as an alternative to antibodies in diagnostics and therapeutics. Systematic evolution of ligands by exponential enrichment (SELEX), an experimental approach for aptamer screening, allows the selection and identification of in vitro aptamers with high affinity and specificity. However, the SELEX process is time consuming and characterization of the representative aptamer candidates from SELEX is rather laborious. Artificial intelligence (AI) could help to rapidly identify the potential aptamer candidates from a vast number of sequences. This review discusses the advancements of AI pipelines/methods, including structure-based and machine/deep learning-based methods, for predicting the binding ability of aptamers to targets. Structure-based methods are the most used in computer-aided drug design. For this part, we review the secondary and tertiary structure prediction methods for aptamers, molecular docking, as well as molecular dynamic simulation methods for aptamer–target binding. We also performed analysis to compare the accuracy of different secondary and tertiary structure prediction methods for aptamers. On the other hand, advanced machine-/deep-learning models have witnessed successes in predicting the binding abilities between targets and ligands in drug discovery and thus potentially offer a robust and accurate approach to predict the binding between aptamers and targets. The research utilizing machine-/deep-learning techniques for prediction of aptamer–target binding is limited currently. Therefore, perspectives for models, algorithms, and implementation strategies of machine/deep learning-based methods are discussed. This review could facilitate the development and application of high-throughput and less laborious in silico methods in aptamer selection and characterization.

Drug Discovery of DKK1 Inhibitors

“…With the gradual elucidation of nucleic-acid-related disease mechanisms and the advancement of drug delivery systems, significant achievements in clinical applications are expected. Aptamers, which are critical components of nucleic acid drugs, can be regarded as “chemical antibodies” owing to their high selectivity and specificity towards their targets, and their ease of access and more flexible recognition sites could further enable them to compete with antibodies ( He et al, 2019 ; Chen et al, 2021 ). To date, only two DKK1 aptamers, obtained by Zhou et al, have been reported for use in early diagnosis of HCC; therapeutic aptamers are still lacking ( Zhou et al, 2019 ).…”

Nucleic Acid Aptamers Emerging as Modulators of G-Protein-Coupled Receptors: Challenge to Difficult Cell Surface Proteins

“…The three out of five papers introduced here reportedly used HTS and/or bioinformatics tools [ 9 , 10 , 12 ]. Recently, there has been a notable trend toward the adoption of machine learning and artificial intelligence (AI) technologies for aptamer identification and aptamer design refinement [ 64 , 65 , 66 , 67 ]. Combined with appropriate data from wet analysis, such as counter selection and negative control to estimate false-positive sequences [ 12 ], aptamer identification is expected to become more efficient as a multidisciplinary technology.…”

Pheno-SELEX: Engineering Anti-Metastatic Aptamers through Targeting the Invasive Phenotype Using Systemic Evolution of Ligands by Exponential Enrichment

“…In the future, this could be explored using affinity chromatography and mass spectroscopy with aptamers as the selected material. Additionally, in silico approaches may be used to identify candidate targets that aptamers can bind [ 30 ]. However, a key concept and strength of this methodology are that is not necessary to know what structure the aptamer binds for it to be an effective therapeutic molecule.…”