Surface plasmon resonance imaging (SPRi) in combination with machine learning for microarray analysis of multiple sclerosis biomarkers in whole serum

Malinick, Alexander S.; Stuart, Daniel D.; Lambert, Alexander; Cheng, Quan

doi:10.1016/j.biosx.2022.100127

Cited by 5 publications

(10 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…70% of the collected data was used for training from the endpoint results and the sensorgrams. The sensor showed a limit of detection below 7ng/mL in the 1-100 ng [19].…”

Section: Machine Learning To Improve Spr Biosensorsmentioning

confidence: 95%

Machine learning algorithms for surface plasmon resonance bio-detection applications, A short review

Zain¹,

Batumalay²,

Harith³

et al. 2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Surface plasmon resonance (SPR) sensors have many applications in detecting toxic gases, water pollutants, and biomarkers of many diseases. Surface plasmon resonance sensors are a good candidate for future sensing platforms due to their high sensitivity and fine resolution. However, the challenges of high cost, cross-sensitivity, and large amount of generated data need to be addressed to unlock surface plasmon resonance potential. Machine learning (ML) algorithms can address these challenges. In this short review, recent studies integrating the algorithms of Artificial Intelligence (AI) and Machine Learning (ML) with (SPR) sensing mechanisms for bio-detection applications are presented here. This short review shows how the integrated approach can help mitigate some of the challenges faced by traditional SPR sensing.

show abstract

“…70% of the collected data was used for training from the endpoint results and the sensorgrams. The sensor showed a limit of detection below 7ng/mL in the 1-100 ng [19].…”

Section: Machine Learning To Improve Spr Biosensorsmentioning

confidence: 95%

Machine learning algorithms for surface plasmon resonance bio-detection applications, A short review

Zain¹,

Batumalay²,

Harith³

et al. 2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

show abstract

“…CNNs are a kind of neural networks which employ filters and pooled layers in the architecture and often used if the size of the data set is large enough and if images are involved in the modeling [ 366 ]. Specifically, in the field of biophotonics, machine learning models using SERS can be efficiently classified into three domains: identification, classification, and quantification, with interests such as disease and molecular diagnosis [ 367 , 368 ]; microorganism classification, identification, etc. [ 369 , 370 , 371 , 372 ]; and cancer diagnosis [ 373 ], as shown in Figure 7 .…”

Section: Machine Learning In Sers-based Biosensingmentioning

confidence: 99%

Recent Trends in SERS-Based Plasmonic Sensors for Disease Diagnostics, Biomolecules Detection, and Machine Learning Techniques

2023

View full text Add to dashboard Cite

Surface-enhanced Raman spectroscopy/scattering (SERS) has evolved into a popular tool for applications in biology and medicine owing to its ease-of-use, non-destructive, and label-free approach. Advances in plasmonics and instrumentation have enabled the realization of SERS’s full potential for the trace detection of biomolecules, disease diagnostics, and monitoring. We provide a brief review on the recent developments in the SERS technique for biosensing applications, with a particular focus on machine learning techniques used for the same. Initially, the article discusses the need for plasmonic sensors in biology and the advantage of SERS over existing techniques. In the later sections, the applications are organized as SERS-based biosensing for disease diagnosis focusing on cancer identification and respiratory diseases, including the recent SARS-CoV-2 detection. We then discuss progress in sensing microorganisms, such as bacteria, with a particular focus on plasmonic sensors for detecting biohazardous materials in view of homeland security. At the end of the article, we focus on machine learning techniques for the (a) identification, (b) classification, and (c) quantification in SERS for biology applications. The review covers the work from 2010 onwards, and the language is simplified to suit the needs of the interdisciplinary audience.

show abstract

“…6 Although much knowledge has been gained on how the composition of planar lipid membrane affect biophysical interactions, 3,6,12 it is becoming more evident that curvature needs to be taken into account in the studies. 13−15 SAMs and SLBs have been effective in the examination of many types of biological interactions, 7,8,16 however, a large portion of these interactions and their properties still remains less investigated and poorly understood, especially in regards to the interactions that require curvature. [13][14][15]17,18 Several methods have been developed to investigate the properties of these interactions using specific interfaces on the biosensor's surface with surface functionalization.…”

Section: ■ Introductionmentioning

confidence: 99%

“…To date, a vast majority of membrane mimics have relied on the use of self-assembled monolayers (SAMs) and supported lipid bilayers (SLBs) to investigate these complex interactions. ,− While SAM and SLB are valuable models, especially as biomimetics, they have several drawbacks. Most notably is that both are planar surfaces, lacking in curvature or curvature tuning, which have led to misrepresentation when compared to the natural structure of cells and the interactions they attempt to mimic .…”

Section: Introductionmentioning

confidence: 99%

Curved Membrane Mimics for Quantitative Probing of Protein–Membrane Interactions by Surface Plasmon Resonance

Malinick,

Stuart,

Lambert

et al. 2023

ACS Appl. Mater. Interfaces

Self Cite

View full text Add to dashboard Cite

A majority of biomimetic membranes used for current biophysical studies rely on planar structures such as supported lipid bilayer (SLB) and self-assembled monolayers (SAMs). While they have facilitated key information collection, the lack of curvature makes these models less effective for the investigation of curvature-dependent protein binding. Here, we report the development and characterization of curved membrane mimics on a solid substrate with tunable curvature and ease in incorporation of cellular membrane components for the study of protein-membrane interactions. The curved membranes were generated with an underlayer lipid membrane composed of DGS-Ni-NTA and POPC lipids on the substrate, followed by the attachment of histidine-tagged cholera toxin (his-CT) as a capture layer. Lipid vesicles containing different compositions of gangliosides, including GA 1 , GM 1 , GT 1b , and GQ 1b , were anchored to the capture layer, providing fixation of the curved membranes with intact structures. Characterization of the curved membrane was accomplished with surface plasmon resonance (SPR), fluorescence recovery after photobleaching (FRAP), and nano-tracking analysis (NTA). Further optimization of the interface was achieved through principal component analysis (PCA) to understand the effect of ganglioside type, percentage, and vesicle dimensions on their interactions with proteins. In addition, Monte Carlo simulations were employed to predict the distribution of the gangliosides and interaction patterns with single point and multipoint binding models. This work provides a reliable approach to generate robust, component-tuning, and curved membranes for investigating protein interactions more pertinently than what a traditional planar membrane offers.

show abstract

Surface plasmon resonance imaging (SPRi) in combination with machine learning for microarray analysis of multiple sclerosis biomarkers in whole serum

Cited by 5 publications

References 49 publications

Machine learning algorithms for surface plasmon resonance bio-detection applications, A short review

Machine learning algorithms for surface plasmon resonance bio-detection applications, A short review

Recent Trends in SERS-Based Plasmonic Sensors for Disease Diagnostics, Biomolecules Detection, and Machine Learning Techniques

Curved Membrane Mimics for Quantitative Probing of Protein–Membrane Interactions by Surface Plasmon Resonance

Contact Info

Product

Resources

About