Accelerating AFM Characterization via Deep‐Learning‐Based Image Super‐Resolution

Kim, Young-Joo; Lim, Jaeheung; Kim, Do-Nyun

doi:10.1002/smll.202103779

Cited by 20 publications

(12 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At this point, it should be noted that there is some disagreement in the literature regarding the correct determination of persistence lengths from AFM images. There is a large body of works that measured the persistence lengths of semi-flexible biopolymers such as dsDNA, [56][57][58][59] protein filaments, [60][61][62][63] amyloid fibrils, [64][65][66][67] and DNA helix bundles [68][69][70][71] adsorbed at solid surfaces using s = 2 as we did in this work. However, it was also argued for dsDNA and dsRNA adsorbed at poly-l-lysine-coated mica surfaces that the immobilized molecules are not equilibrated but kinetically trapped at the surface, resulting in a situation better described by s = 1.…”

Section: Stability In Low-mg 2+ Environmentsmentioning

confidence: 99%

Environment‐Dependent Stability and Mechanical Properties of DNA Origami Six‐Helix Bundles with Different Crossover Spacings

Yang

Piskunen

Suma

et al. 2022

Small

View full text Add to dashboard Cite

The internal design of DNA nanostructures defines how they behave in different environmental conditions, such as endonuclease‐rich or low‐Mg2+ solutions. Notably, the inter‐helical crossovers that form the core of such DNA objects have a major impact on their mechanical properties and stability. Importantly, crossover design can be used to optimize DNA nanostructures for target applications, especially when developing them for biomedical environments. To elucidate this, two otherwise identical DNA origami designs are presented that have a different number of staple crossovers between neighboring helices, spaced at 42‐ and 21‐ basepair (bp) intervals, respectively. The behavior of these structures is then compared in various buffer conditions, as well as when they are exposed to enzymatic digestion by DNase I. The results show that an increased number of crossovers significantly improves the nuclease resistance of the DNA origami by making it less accessible to digestion enzymes but simultaneously lowers its stability under Mg2+‐free conditions by reducing the malleability of the structures. Therefore, these results represent an important step toward rational, application‐specific DNA nanostructure design.

show abstract

Section: Stability In Low-mg 2+ Environmentsmentioning

confidence: 99%

Environment‐Dependent Stability and Mechanical Properties of DNA Origami Six‐Helix Bundles with Different Crossover Spacings

Yang

Piskunen

Suma

et al. 2022

Small

View full text Add to dashboard Cite

show abstract

“…In AFM images (left column), bright dots represent the homogeneously monodispersed FNA nanovehicle, of which the height (right column) increases from about 2 to 4 nm upon the addition of K + . As we know, most of 3D DNA architectures usually differs from the 2D ones in their height in AFM images. − The height change of the FNA nanovehicle strongly suggests its 2D-to-3D transformation was induced by K + . Moreover, we employed a Cy3/Cy5 FRET pair to monitor the folding process of the FNA nanovehicle (Figure c).…”

Section: Resultsmentioning

confidence: 98%

Calcium-Differentiated Cellular Internalization of Allosteric Framework Nucleic Acids for Targeted Payload Delivery

et al. 2022

View full text Add to dashboard Cite

Target delivery systems have extensively shown promising applications in cancer therapy, and many of them function smartly by responding to the cancer cell microenvironment. Here, we for the first time report Ca 2+ -differentiated cellular internalization of 2D/3D framework nucleic acids (FNAs), enabling the engineering of a conceptually new target delivery system using an allosteric FNA nanovehicle. The FNA vehicle is subject to a 2D-to-3D transformation on the cancer cell surface via G-quadruplexes responding to environmental K + and thereby allows its cell entry to be more efficiently promoted by Ca 2+ . This design enables the FNA vehicle to target cancer cells and selectively deliver an antisense strand-containing cargo for livecell mRNA imaging. It would open new avenues toward targeted drug delivery and find extensive applications in precise disease treatment.

show abstract

“…By this we mean to recognize that there are alternative methods of accelerating DNA nanostructure identification and sorting. For example, some methods use ML to enhance AFM operation and image acquisition process while using MATLAB 51,52 and other scripting www.nature.com/scientificreports/ languages for structural identification. However, the current study distinguishes itself from other methods by eliminating reliance on certain criterion for consistent identification.…”

Section: Discussionmentioning

confidence: 99%

Rapid DNA origami nanostructure detection and classification using the YOLOv5 deep convolutional neural network

Chiriboga

Green

Hastman

et al. 2022

Sci Rep

View full text Add to dashboard Cite

The intra-image identification of DNA structures is essential to rapid prototyping and quality control of self-assembled DNA origami scaffold systems. We postulate that the YOLO modern object detection platform commonly used for facial recognition can be applied to rapidly scour atomic force microscope (AFM) images for identifying correctly formed DNA nanostructures with high fidelity. To make this approach widely available, we use open-source software and provide a straightforward procedure for designing a tailored, intelligent identification platform which can easily be repurposed to fit arbitrary structural geometries beyond AFM images of DNA structures. Here, we describe methods to acquire and generate the necessary components to create this robust system. Beginning with DNA structure design, we detail AFM imaging, data point annotation, data augmentation, model training, and inference. To demonstrate the adaptability of this system, we assembled two distinct DNA origami architectures (triangles and breadboards) for detection in raw AFM images. Using the images acquired of each structure, we trained two separate single class object identification models unique to each architecture. By applying these models in sequence, we correctly identified 3470 structures from a total population of 3617 using images that sometimes included a third DNA origami structure as well as other impurities. Analysis was completed in under 20 s with results yielding an F1 score of 0.96 using our approach.

show abstract

Accelerating AFM Characterization via Deep‐Learning‐Based Image Super‐Resolution

Cited by 20 publications

References 31 publications

Environment‐Dependent Stability and Mechanical Properties of DNA Origami Six‐Helix Bundles with Different Crossover Spacings

Environment‐Dependent Stability and Mechanical Properties of DNA Origami Six‐Helix Bundles with Different Crossover Spacings

Calcium-Differentiated Cellular Internalization of Allosteric Framework Nucleic Acids for Targeted Payload Delivery

Rapid DNA origami nanostructure detection and classification using the YOLOv5 deep convolutional neural network

Contact Info

Product

Resources

About