Quantifying nanoscale forces using machine learning in dynamic atomic force microscopy

Chandrashekar, Abhilash; Belardinelli, Pierpaolo; Bessa, Miguel A.; Staufer, U.; Alijani, Farbod

doi:10.1039/d2na00011c

Cited by 18 publications

(11 citation statements)

References 57 publications

(105 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, AFM is a time-consuming technique in terms of measurement time and data analysis and often requires specialized personnel with a physical background. Fortunately, these limitations can be overcome by using high-speed (HS-) AFM and machine learning for data analysis ( Nievergelt et al, 2015 ; Wang et al, 2016 ; Dufrêne et al, 2017 ; Sokolov et al, 2018 ; Casuso et al, 2020 ; Dokukin and Dokukina, 2020 ; Ridolfi et al, 2020 ; Chandrashekar et al, 2022 ; Nguyen and Liu, 2022 ). To conclude, a further limitation of our work consists in the use of single exponential decays for fitting time-dependent curves such as those reported in Figure 2 .…”

Section: Discussionmentioning

confidence: 99%

Sensing red blood cell nano-mechanics: Toward a novel blood biomarker for Alzheimer’s disease

Nardini

Ciasca

Lauria

et al. 2022

Front. Aging Neurosci.

View full text Add to dashboard Cite

Red blood cells (RBCs) are characterized by a remarkable elasticity, which allows them to undergo very large deformation when passing through small vessels and capillaries. This extreme deformability is altered in various clinical conditions, suggesting that the analysis of red blood cell (RBC) mechanics has potential applications in the search for non-invasive and cost-effective blood biomarkers. Here, we provide a comparative study of the mechanical response of RBCs in patients with Alzheimer’s disease (AD) and healthy subjects. For this purpose, RBC viscoelastic response was investigated using atomic force microscopy (AFM) in the force spectroscopy mode. Two types of analyses were performed: (i) a conventional analysis of AFM force–distance (FD) curves, which allowed us to retrieve the apparent Young’s modulus, E; and (ii) a more in-depth analysis of time-dependent relaxation curves in the framework of the standard linear solid (SLS) model, which allowed us to estimate cell viscosity and elasticity, independently. Our data demonstrate that, while conventional analysis of AFM FD curves fails in distinguishing the two groups, the mechanical parameters obtained with the SLS model show a very good classification ability. The diagnostic performance of mechanical parameters was assessed using receiving operator characteristic (ROC) curves, showing very large areas under the curves (AUC) for selected biomarkers (AUC > 0.9). Taken all together, the data presented here demonstrate that RBC mechanics are significantly altered in AD, also highlighting the key role played by viscous forces. These RBC abnormalities in AD, which include both a modified elasticity and viscosity, could be considered a potential source of plasmatic biomarkers in the field of liquid biopsy to be used in combination with more established indicators of the pathology.

show abstract

Section: Discussionmentioning

confidence: 99%

Sensing red blood cell nano-mechanics: Toward a novel blood biomarker for Alzheimer’s disease

Nardini

Ciasca

Lauria

et al. 2022

Front. Aging Neurosci.

View full text Add to dashboard Cite

show abstract

“…34 Nowadays, these branches develop advanced methods and can be divided into four categories, that is, clas-sication, regression, clustering, and dimensionality reduction. [35][36][37][38][39][40][41][42][43][44] The algorithms for these branches include support vector machine (SVM), k-nearest neighbor (kNN), decision tree (DT), convolutional neural network (CNN), k-means, PCA, etc. [45][46][47][48][49][50] These algorithms have been well employed in SEIRA and SERS.…”

Section: Introductionmentioning

confidence: 99%

Machine learning-augmented surface-enhanced spectroscopy toward next-generation molecular diagnostics

Zhou

Ren

et al. 2023

Nanoscale Adv.

View full text Add to dashboard Cite

show abstract

“…[49][50][51] Recently, several theoretical and experimental contributions have illustrated the evolution trends followed in AM-AFM. [52][53][54][55][56][57][58][59][60][61][62][63][64] The dynamics of the tip motion in AM-AFM was far from intuitive. High spatial resolution images were obtained by either following a time-consuming trial and an error approach or by following a set of strict protocols.…”

Section: Introductionmentioning

confidence: 99%

Insights and guidelines to interpret forces and deformations at the nanoscale by using a tapping mode AFM simulator: dForce 2.0

Gisbert

García

2023

Soft Matter

View full text Add to dashboard Cite

show abstract

Quantifying nanoscale forces using machine learning in dynamic atomic force microscopy

Abstract: Dynamic atomic force microscopy (AFM) is a key platform that enables topological and nanomechanical characterization of novel materials. This is achieved by linking the nanoscale forces that exist between the...

Cited by 18 publications

References 57 publications

Sensing red blood cell nano-mechanics: Toward a novel blood biomarker for Alzheimer’s disease

Sensing red blood cell nano-mechanics: Toward a novel blood biomarker for Alzheimer’s disease

Machine learning-augmented surface-enhanced spectroscopy toward next-generation molecular diagnostics

Insights and guidelines to interpret forces and deformations at the nanoscale by using a tapping mode AFM simulator: dForce 2.0

Contact Info

Product

Resources

About