Related Experiment Video
Updated: Jun 30, 2026
09:47
DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data
Published on: December 15, 2023
Interpretable prediction and generation of ASC-speck aptamers using multiscale deep biological learning models
Mengting Niu1,2, Quan Zou1,2, Lei Xu3
1Institute of Fundamental and Frontier Sciences, University of Electronic Science and Technology of China, Chengdu 610054, China.
Bioinformatics Advances
|June 29, 2026
Summary
We developed ASC2BF, a novel DNA aptamer generation method using deep learning and optimization algorithms. This tool aids in discovering aptamers for challenging targets, advancing nucleic acid-based detection and therapeutics.
Area of Science:
- Biotechnology
- Bioinformatics
- Molecular Biology
Background:
- Aptamers are functional nucleic acids that can substitute monoclonal antibodies for ligand binding.
- Generating aptamers for certain protein targets can be challenging due to a lack of suitable DNA sequences.
- Novel methods are required to create new aptamer libraries for detecting previously unaddressable targets.
Purpose of the Study:
- To propose ASC2BF, an adaptive prediction and design method for DNA aptamer generation.
- To address the need for generating aptamers against targets lacking known binding sequences.
- To demonstrate the utility of deep learning in capturing sequential and functional semantic information for aptamer discovery.
Main Methods:
- ASC2BF utilizes a multiscale residual network for simultaneous aptamer prediction based on DNA-protein characteristics.
- The bacterial foraging optimization algorithm (BFOA) is employed to generate novel DNA aptamer sequences adhering to biophysical constraints.
- A neural network predictor screens initial seed sequences for the BFOA.
Main Results:
- ASC2BF was successfully applied to generate aptamer pools against apoptosis-associated speck-like proteins (ASC-speck).
- The study demonstrates deep learning's capability to capture sequential and functional semantic information in aptamer generation.
- Interpretability analysis provided insights into the model's learning process, aiding in biological function analysis.
Conclusions:
- ASC2BF offers an effective approach for DNA aptamer generation, particularly for challenging targets.
- The method enhances the discovery of functional aptamers by integrating prediction and optimization.
- The findings highlight the potential of AI-driven methods in advancing aptamer-based diagnostics and therapeutics.
