A web-based automated machine learning platform to analyze liquid biopsy data

Shen, Hanfei; Liu, Tony; Cui, Jesse; Borole, Piyush; Benjamin, Ari S.; Kording, Konrad; Issadore, David

doi:10.1039/d0lc00096e

Cited by 19 publications

(18 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the past decade, more and more attention has been paid to deep learning. Compared to traditional machine learning, deep learning has shown its merits in microbiological analysis [ 26 , 27 , 28 , 29 ], such as strong learning ability, good adaptability and excellent performance. A typical example of deep learning was reported by Kanakasabapathy et al [ 30 ] for the detection of embryos using inexpensive automated deep learning-based imaging systems, and more than 90% of embryos were successfully classified.…”

Section: Introductionmentioning

confidence: 99%

A Fluorescent Biosensor for Sensitive Detection of Salmonella Typhimurium Using Low-Gradient Magnetic Field and Deep Learning via Faster Region-Based Convolutional Neural Network

Wang

Duan

et al. 2021

Biosensors

View full text Add to dashboard Cite

In this study, a fluorescent biosensor was developed for the sensitive detection of Salmonella typhimurium using a low-gradient magnetic field and deep learning via faster region-based convolutional neural networks (R-CNN) to recognize the fluorescent spots on the bacterial cells. First, magnetic nanobeads (MNBs) coated with capture antibodies were used to separate target bacteria from the sample background, resulting in the formation of magnetic bacteria. Then, fluorescein isothiocyanate fluorescent microspheres (FITC-FMs) modified with detection antibodies were used to label the magnetic bacteria, resulting in the formation of fluorescent bacteria. After the fluorescent bacteria were attracted against the bottom of an ELISA well using a low-gradient magnetic field, resulting in the conversion from a three-dimensional (spatial) distribution of the fluorescent bacteria to a two-dimensional (planar) distribution, the images of the fluorescent bacteria were finally collected using a high-resolution fluorescence microscope and processed using the faster R-CNN algorithm to calculate the number of the fluorescent spots for the determination of target bacteria. Under the optimal conditions, this biosensor was able to quantitatively detect Salmonella typhimurium from 6.9 × 101 to 1.1 × 103 CFU/mL within 2.5 h with the lower detection limit of 55 CFU/mL. The fluorescent biosensor has the potential to simultaneously detect multiple types of foodborne bacteria using MNBs coated with their capture antibodies and different fluorescent microspheres modified with their detection antibodies.

show abstract

Section: Introductionmentioning

confidence: 99%

A Fluorescent Biosensor for Sensitive Detection of Salmonella Typhimurium Using Low-Gradient Magnetic Field and Deep Learning via Faster Region-Based Convolutional Neural Network

Wang

Duan

et al. 2021

Biosensors

View full text Add to dashboard Cite

show abstract

“…Interestingly, this approach allowed the researchers to predict recurrence-free survival (RFS). Shen et al . developed an automated web-based ML (AutoML) tool where models can be built without the user’s input.…”

Section: The Future: Automation and Artificial Intelligencementioning

confidence: 99%

“…Interestingly, this approach allowed the researchers to predict recurrence-free survival (RFS). Shen et al 118 developed an automated web-based ML (AutoML) tool where models can be built without the user's input. The approach was further validated by performing a meta-analysis on 11 independent published data sets and found that we had similar or better performance compared to those reported in the literature.…”

Section: ■ Challenges: Clinical Implementationmentioning

confidence: 99%

Microfluidics for Liquid Biopsies: Recent Advances, Current Challenges, and Future Directions

Belotti

Lim

2021

Anal. Chem.

View full text Add to dashboard Cite

“…[ 89 ] For example, an automated machine learning platform to analyze liquid biopsy data has been recently reported. [ 90 ] It was specifically designed for liquid biopsy data and has the very interesting capability to continuously improve itself as the quantity of the processed liquid biopsy data increases.…”

Section: Circulating Tumor Biomarkersmentioning

confidence: 99%

Photonic Technologies for Liquid Biopsies: Recent Advances and Open Research Challenges

Dell’Olio

Huser

et al. 2020

Laser & Photonics Reviews

View full text Add to dashboard Cite

The recent development of sophisticated techniques capable of detecting extremely low concentrations of circulating tumor biomarkers in accessible body fluids, such as blood or urine, could contribute to a paradigm shift in cancer diagnosis and treatment. By applying such techniques, clinicians can carry out liquid biopsies, providing information on tumor presence, evolution, and response to therapy. The implementation of biosensing platforms for liquid biopsies is particularly complex because this application domain demands high selectivity/specificity and challenging limit‐of‐detection (LoD) values. The interest in photonics as an enabling technology for liquid biopsies is growing owing to the well‐known advantages of photonic biosensors over competing technologies in terms of compactness, immunity to external disturbance, and ultrahigh spatial resolution. Some encouraging experimental results in the field of photonic devices and systems for liquid biopsy have already been achieved by using fluorescent labels and label‐free techniques and by exploiting super‐resolution microscopy, surface plasmon resonance, surface‐enhanced Raman scattering, and whispering gallery mode resonators. The current state‐of‐the‐art is critically reviewed here, starting from the requirements imposed by the detection of the most common circulating biomarkers. Open research challenges are considered together with competing technologies, and the most promising paths of improvement are discussed for future applications.

show abstract

A web-based automated machine learning platform to analyze liquid biopsy data

Abstract: We have developed a web-based, self-improving and overfitting-resistant automated machine learning tool tailored specifically for liquid biopsy data, where machine learning models can be built without the user's input.

Cited by 19 publications

References 37 publications

A Fluorescent Biosensor for Sensitive Detection of Salmonella Typhimurium Using Low-Gradient Magnetic Field and Deep Learning via Faster Region-Based Convolutional Neural Network

A Fluorescent Biosensor for Sensitive Detection of Salmonella Typhimurium Using Low-Gradient Magnetic Field and Deep Learning via Faster Region-Based Convolutional Neural Network

Microfluidics for Liquid Biopsies: Recent Advances, Current Challenges, and Future Directions

Photonic Technologies for Liquid Biopsies: Recent Advances and Open Research Challenges

Contact Info

Product

Resources

About