DNA Origami Nanostructure Detection and Yield Estimation Using Deep Learning

Nie, Jinyan; Ma, Mingyuan; Shi, Xiaolong

doi:10.1021/acssynbio.2c00533

Cited by 3 publications

(2 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast, from traditional X-ray crystallography or cryo-EM, there are only ~ 200 thousand protein structures shared in the protein data bank (PDB). Specific to DNA nanotechnology, recent studies [28][29][30] showed the DNN is also a great solution for automatically recognizing nanostructure in atomic force microscopy or fluorescence microscopy with high accuracy, which provided a foundation to solving the DNA nanostructure identification problem. However, these works only demonstrated the feasibility of identifying static nanostructures from images and did not address the need for automated property characterization, which is necessary to overcome the characterization bottleneck for dynamic DNA nanodevices.…”

Section: Accelerating the Characterization Of Dynamic Dna Origami Dev...mentioning

confidence: 99%

Accelerating the characterization of dynamic DNA origami devices with deep neural networks

Wang,

Jin,

Castro

2023

Sci Rep

View full text Add to dashboard Cite

Mechanical characterization of dynamic DNA nanodevices is essential to facilitate their use in applications like molecular diagnostics, force sensing, and nanorobotics that rely on device reconfiguration and interactions with other materials. A common approach to evaluate the mechanical properties of dynamic DNA nanodevices is by quantifying conformational distributions, where the magnitude of fluctuations correlates to the stiffness. This is generally carried out through manual measurement from experimental images, which is a tedious process and a critical bottleneck in the characterization pipeline. While many tools support the analysis of static molecular structures, there is a need for tools to facilitate the rapid characterization of dynamic DNA devices that undergo large conformational fluctuations. Here, we develop a data processing pipeline based on Deep Neural Networks (DNNs) to address this problem. The YOLOv5 and Resnet50 network architecture were used for the two key subtasks: particle detection and pose (i.e. conformation) estimation. We demonstrate effective network performance (F1 score 0.85 in particle detection) and good agreement with experimental distributions with limited user input and small training sets (~ 5 to 10 images). We also demonstrate this pipeline can be applied to multiple nanodevices, providing a robust approach for the rapid characterization of dynamic DNA devices.

show abstract

Section: Accelerating the Characterization Of Dynamic Dna Origami Dev...mentioning

confidence: 99%

Accelerating the characterization of dynamic DNA origami devices with deep neural networks

Wang,

Jin,

Castro

2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…In contrast, from traditional X-ray crystallography or cryo-EM, there are only ~200 thousand protein structures shared in the protein data bank (PDB). Specific to DNA nanotechnology, recent studies [28]- [30] showed the DNN is also a great solution for automatically recognizing nanostructure in atomic force microscopy or fluorescence microscopy with high accuracy, which provided a foundation to solving the DNA nanostructure identification problem. However, these works only demonstrated the feasibility of identifying static nanostructures from images and did not address the need for automated property characterization, which is necessary to overcome the characterization bottleneck for dynamic DNA nanodevices.…”

Section: Introductionmentioning

confidence: 99%

Accelerating the Characterization of Dynamic DNA Origami Devices with Deep Neural Networks

Wang

Jin

Castro

2023

Preprint

View full text Add to dashboard Cite

Mechanical characterization of dynamic DNA nanodevices is essential to facilitate their use in applications like molecular diagnostics, force sensing, and nanorobotics that rely on device reconfiguration and interactions with other materials. A common approach to evaluate the mechanical properties of dynamic DNA nanodevices is by quantifying conformational distributions, where the magnitude of fluctuations correlates to the stiffness. This is generally carried out through manual measurement from experimental images, which is a tedious process and a critical bottleneck in the characterization pipeline. While many tools to support analysis of static of molecular structures, there is a need for tools to facilitate the rapid characterization of dynamic DNA devices that undergo large conformational fluctuations. Here, we develop a data processing pipeline based on Deep Neural Networks (DNNs) to address this problem. The YOLOv5 and Resnet50 network architecture were used for the two key subtasks: particle detection and pose (i.e. conformation) estimation. We demonstrate effective network performance (F1 score of 0.85 in particle detection) and good agreement with experimental distributions with limited user input and small training sets. We also demonstrate this pipeline can be applied to multiple nanodevices, providing a robust approach for the rapid characterization of dynamic DNA devices.

show abstract

Toward Precise Fabrication of Finite‐Sized DNA Origami Superstructures

Li,

Dong,

Zhou

et al. 2024

Small Methods

View full text Add to dashboard Cite

DNA origami enables the precise construction of 2D and 3D nanostructures with customizable shapes and the high‐resolution organization of functional materials. However, the size of a single DNA origami is constrained by the length of the scaffold strand, and since its inception, scaling up the size and complexity has been a persistent pursuit. Hierarchical self‐assembly of DNA origami units offers a feasible approach to overcome the limitation. Unlike periodic arrays, finite‐sized DNA origami superstructures feature well‐defined structural boundaries and uniform dimensions. In recent years, increasing attention has been directed toward precise control over the hierarchical self‐assembly of DNA origami structures and their applications in fields such as nanophotonics, biophysics, and material science. This review summarizes the strategies for fabricating finite‐sized DNA origami superstructures, including heterogeneous self‐assembly, self‐limited self‐assembly, and templated self‐assembly, along with a comparative analysis of the advantages and limitations of each approach. Subsequently, recent advancements in the application of these structures are discussed from a structure design perspective. Finally, an outlook on the current challenges and potential future directions is provided, highlighting opportunities for further research and development in this rapidly evolving field.

show abstract

DNA Origami Nanostructure Detection and Yield Estimation Using Deep Learning

Cited by 3 publications

References 45 publications

Accelerating the characterization of dynamic DNA origami devices with deep neural networks

Accelerating the characterization of dynamic DNA origami devices with deep neural networks

Accelerating the Characterization of Dynamic DNA Origami Devices with Deep Neural Networks

Toward Precise Fabrication of Finite‐Sized DNA Origami Superstructures

Contact Info

Product

Resources

About