Machine learning-aided quantification of antibody-based cancer immunotherapy by natural killer cells in microfluidic droplets

Sarkar, Saheli; Kang, Wenjing; Jiang, Songyao; Li, Kunpeng; Ray, Somak; Luther, Ed; Ivanov, Alexander R.; Fu, Yun; Konry, Tania

doi:10.1039/d0lc00158a

Cited by 30 publications

(29 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Indeed, AI makes use of statistical, computational and mathematical capabilities. AI requires appropriate training datasets and algorithms to improve results before testing, similar to traditional statistical methods [ 213 , 214 , 215 , 216 , 217 ]. AI focuses on building automated decision systems, unlike traditional statistical approaches that rely on rule-based systems [ 215 , 218 ].…”

Section: The Future Of Microfluidicsmentioning

confidence: 99%

“…It is beyond the scope of this article to explore these three forms of learning approaches in detail. Instead, we focus on supervised learning as this is the most commonly used method in biopeptide prediction [ 217 , 219 ]. Supervised learning methods are used to build and train prediction models for data category values or continuous variables.…”

Section: The Future Of Microfluidicsmentioning

confidence: 99%

See 1 more Smart Citation

Microfluidics for Peptidomics, Proteomics, and Cell Analysis

et al. 2021

View full text Add to dashboard Cite

Microfluidics is the advanced microtechnology of fluid manipulation in channels with at least one dimension in the range of 1–100 microns. Microfluidic technology offers a growing number of tools for manipulating small volumes of fluid to control chemical, biological, and physical processes relevant to separation, analysis, and detection. Currently, microfluidic devices play an important role in many biological, chemical, physical, biotechnological and engineering applications. There are numerous ways to fabricate the necessary microchannels and integrate them into microfluidic platforms. In peptidomics and proteomics, microfluidics is often used in combination with mass spectrometric (MS) analysis. This review provides an overview of using microfluidic systems for peptidomics, proteomics and cell analysis. The application of microfluidics in combination with MS detection and other novel techniques to answer clinical questions is also discussed in the context of disease diagnosis and therapy. Recent developments and applications of capillary and microchip (electro)separation methods in proteomic and peptidomic analysis are summarized. The state of the art of microchip platforms for cell sorting and single-cell analysis is also discussed. Advances in detection methods are reported, and new applications in proteomics and peptidomics, quality control of peptide and protein pharmaceuticals, analysis of proteins and peptides in biomatrices and determination of their physicochemical parameters are highlighted.

show abstract

Section: The Future Of Microfluidicsmentioning

confidence: 99%

Section: The Future Of Microfluidicsmentioning

confidence: 99%

Microfluidics for Peptidomics, Proteomics, and Cell Analysis

et al. 2021

View full text Add to dashboard Cite

show abstract

“…In this work, cellular viability was determined in response to different concentrations of seven antibiotics. Sarkar and coworkers have extensive expertize in generating droplets on chip, including droplet formation for cell viability assessment used for the development of anticancer therapies (Sarkar et al, 2015;Sarkar et al, 2020). They first reported a microfluidic droplet generator for the encapsulation of single cancer cells and for the monitoring of the individual cells in presence of doxorubicin anticancer drug with live/dead staining.…”

Section: Droplet Microfluidicsmentioning

confidence: 99%

“…They evaluated the sensitivity of cells to the drug, by monitoring their viability (Sarkar et al, 2015). More recently, they used the same droplet technology to compare immunotherapy with Natural Killer cells with different cell types, and determined that the treatment based on the combination of herceptin and CD16 + Natural Killer cells was more effective for SKOV3 cells than for HER2 (Sarkar et al, 2020).…”

Section: Droplet Microfluidicsmentioning

confidence: 99%

“…A droplet microfluidics generator was used to trap a target cancer cell with a natural killer cell (1:1 ratio), and the interaction between them was accurately studied by time-lapse images, focusing on interaction duration, frequency and cell viability. With the obtained information, algorithms were developed for automatically interpreting the dynamics of natural killer cells as anticancer therapy (Sarkar et al, 2020).…”

Section: Automationmentioning

confidence: 99%

See 1 more Smart Citation

Advances in Microtechnology for Improved Cytotoxicity Assessment

2020

View full text Add to dashboard Cite

In vitro cytotoxicity testing is essential in the pharmaceutical and environmental industry to study the effects of potential harmful compounds for human health. Classical assays present several disadvantages: they are commonly based on live-death labelling, are highly time consuming and/or require skilled personnel to be performed. The current trend is to reduce the number of required cells and the time during the analysis, while increasing the screening capability and the accuracy and sensitivity of the assays, aiming single cell resolution. Microfabrication and surface engineering are enabling novel approaches for cytotoxicity assessment, offering high sensitivity and the possibility of automation in order to minimize user intervention. This review aims to overview the different microtechnology approaches available in this field, focusing on the novel developments for high-throughput, dynamic and real time screening of cytotoxic compounds.

show abstract

Application of Artificial Intelligence to In Vitro Tumor Modeling and Characterization of the Tumor Microenvironment

Lee

Goh

et al. 2023

Adv Healthcare Materials

View full text Add to dashboard Cite

In vitro tumor models have played vital roles in enhancing the understanding of the cellular and molecular composition of tumors, as well as their biochemical and biophysical characteristics. Advances in technology have enabled the evolution of tumor models from two-dimensional cell cultures to three-dimensional printed tumor models with increased levels of complexity and diverse output parameters. With the increase in complexity, the new generation of models is able to replicate the architecture and heterogeneity of the tumor microenvironment more realistically than their predecessors. In recent years, artificial intelligence (AI) has been used extensively in healthcare and research, and AI-based tools have also been applied to the precise development of tumor models. The incorporation of AI facilitates the use of high-throughput systems for real-time monitoring of tumorigenesis and biophysical tumor properties, raising the possibility of using AI alongside tumor modeling for personalized medicine. Here, the integration of AI tools within tumor modeling is reviewed, including microfluidic devices and cancer-on-chip models.

show abstract

Machine learning-aided quantification of antibody-based cancer immunotherapy by natural killer cells in microfluidic droplets

Abstract: Comparative proteomic profiling and development of convolution neural network algorithm for quantifying discrete target interaction by engineered NK cells in microfluidic droplets.

Cited by 30 publications

References 49 publications

Microfluidics for Peptidomics, Proteomics, and Cell Analysis

Microfluidics for Peptidomics, Proteomics, and Cell Analysis

Advances in Microtechnology for Improved Cytotoxicity Assessment

Application of Artificial Intelligence to In Vitro Tumor Modeling and Characterization of the Tumor Microenvironment

Contact Info

Product

Resources

About