Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Enzyme-Linked Immunosorbent Assay

Enzyme-Linked Immunosorbent Assay

In 1971, Peter Perlman and Eva Engvall developed an Enzyme-linked immunosorbent assay (ELISA or EIA). ELISA differs from western blot in that the assays are conducted in microtiter plates or in vivo rather than on an absorbent membrane.
There are many different types of ELISAs, but they all involve an antibody molecule whose constant region binds an enzyme, leaving the variable region free to bind its specific antigen. Enzyme-substrate reaction allows the antigen to be visualized or...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Disordered protein LAT encodes relative levels of signaling pathways in T cell activation.

Science (New York, N.Y.)·2026

Same author

Evaluating Limits of Machine Learning-Assisted Raman Spectroscopy in Classification of Biological Samples.

bioRxiv : the preprint server for biology·2026

Same author

T cell costimulatory and inhibitory signals di4erentially modulate LAT condensate nucleation propensity after TCR ligation.

bioRxiv : the preprint server for biology·2025

Same author

A unifying model of LAT condensates in reconstitution experiments.

bioRxiv : the preprint server for biology·2025

Same author

Quantum-enhanced detection of viral cDNA via luminescence resonance energy transfer using upconversion and gold nanoparticles.

Nanophotonics (Berlin, Germany)·2025

Same author

Single-molecule biophysics in signaling: Functionality from stochastic effects.

Current opinion in cell biology·2025

Same journal

Physics-guided self-supervised learning for high-fidelity reconstruction in live-cell imaging.

Npj imaging·2026

Same journal

Complementary hyperpolarized <sup>13</sup>C and <sup>15</sup>N MRI reveal divergent signatures of hepatic injury and methyl-donor metabolism.

Npj imaging·2026

Same journal

Optical coherence tomography enables optical biopsy of endometrial tissue for early cancer detection.

Npj imaging·2026

Same journal

My Life as a "Theranostician": A commentary on the evolution of theranostics.

Npj imaging·2026

Same journal

Towards generalisable foundation models for brain MRI.

Npj imaging·2026

Same journal

Reliability of foundation models for image retrieval in histopathology.

Npj imaging·2026

See all related articles

Search research articles

Related Experiment Video

Updated: May 6, 2026

High-Throughput Automated Multiplex Immunofluorescence Assays for Translational Research

High-Throughput Automated Multiplex Immunofluorescence Assays for Translational Research

Published on: June 10, 2025

Homogeneous image-based digital immunoassays with high error tolerance.

Darren B McAffee¹, Qiang Hu², Assame Arnob²

¹ilytica, LLC., San Francisco, CA, USA. darren@ilytica.com.

|May 4, 2026

Summary

This summary is machine-generated.

Machine learning enhances image-based nanoparticle immunoassays for field diagnostics. This approach improves accuracy and sensitivity for detecting biomarkers like C-reactive protein and SARS-CoV-2 antibodies.

More Related Videos

Snap Chip for Cross-reactivity-free and Spotter-free Multiplexed Sandwich Immunoassays

Snap Chip for Cross-reactivity-free and Spotter-free Multiplexed Sandwich Immunoassays

Published on: November 13, 2017

Procedure and Key Optimization Strategies for an Automated Capillary Electrophoretic-based Immunoassay Method

Procedure and Key Optimization Strategies for an Automated Capillary Electrophoretic-based Immunoassay Method

Published on: September 10, 2017

Related Experiment Videos

Last Updated: May 6, 2026

High-Throughput Automated Multiplex Immunofluorescence Assays for Translational Research

High-Throughput Automated Multiplex Immunofluorescence Assays for Translational Research

Published on: June 10, 2025

Snap Chip for Cross-reactivity-free and Spotter-free Multiplexed Sandwich Immunoassays

Snap Chip for Cross-reactivity-free and Spotter-free Multiplexed Sandwich Immunoassays

Published on: November 13, 2017

Procedure and Key Optimization Strategies for an Automated Capillary Electrophoretic-based Immunoassay Method

Procedure and Key Optimization Strategies for an Automated Capillary Electrophoretic-based Immunoassay Method

Published on: September 10, 2017

Area of Science:

Biomedical Engineering
Nanotechnology
Machine Learning

Background:

Global health demands field-deployable in vitro diagnostics, requiring smaller sample volumes and tolerance for handling variability.
Current field diagnostics face limitations in sample processing and measurement capabilities compared to lab-based tests.
Enhancing error tolerance is crucial for successful design of assays for point-of-care and self-administered use.

Purpose of the Study:

To investigate machine learning (ML) strategies for improving error tolerance in image-based nanoparticle immunoassays.
To compare conventional image analysis with ML-enhanced approaches for assay performance.
To assess the feasibility of using ML for quantitative analyte detection in resource-limited settings.

Main Methods:

Image-based nanoparticle immunoassays were developed using microliter sample volumes.
Analyte concentrations were determined by analyzing nanoparticle appearance in images.
Three analysis methods were compared: conventional image analysis, hybrid ML-conventional segmentation, and end-to-end ML image regression.

Main Results:

The segmentation-based ML approach achieved 96% specificity and 90% sensitivity for binary classification of SARS-CoV-2 IgG.
The end-to-end regression ML model provided quantitative performance with a limit of detection of 5.2 ng/mL, comparable to ELISA.
ML approaches significantly improved dynamic range, sensitivity, and reproducibility compared to conventional methods, with reduced labeling effort.

Conclusions:

Machine learning significantly enhances the error tolerance and performance of image-based nanoparticle immunoassays for field applications.
End-to-end ML regression offers a powerful, label-efficient method for quantitative detection, approaching ELISA sensitivity.
These ML-driven advancements are vital for translating complex diagnostics to accessible point-of-care and self-administered formats.