Related Experiment Video
Updated: Nov 15, 2025
Detection of SARS-CoV-2 Neutralizing Antibodies using High-Throughput Fluorescent Imaging of Pseudovirus Infection
Published on: June 5, 2021
Potential neutralizing antibodies discovered for novel corona virus using machine learning
Rishikesh Magar1, Prakarsh Yadav2, Amir Barati Farimani3,4,5
1Department of Mechanical Engineering, Carnegie Mellon University, Pittsburgh, PA, 15213, USA.
Abstract:
The fast and untraceable virus mutations take lives of thousands of people before the immune system can produce the inhibitory antibody. The recent outbreak of COVID-19 infected and killed thousands of people in the world. Rapid methods in finding peptides or antibody sequences that can inhibit the viral epitopes of SARS-CoV-2 will save the life of thousands. To predict neutralizing antibodies for SARS-CoV-2 in a high-throughput manner, in this paper, we use different machine learning (ML) model to predict the possible inhibitory synthetic antibodies for SARS-CoV-2. We collected 1933 virus-antibody sequences and their clinical patient neutralization response and trained an ML model to predict the antibody response. Using graph featurization with variety of ML methods, like XGBoost, Random Forest, Multilayered Perceptron, Support Vector Machine and Logistic Regression, we screened thousands of hypothetical antibody sequences and found nine stable antibodies that potentially inhibit SARS-CoV-2. We combined bioinformatics, structural biology, and Molecular Dynamics (MD) simulations to verify the stability of the candidate antibodies that can inhibit SARS-CoV-2.
Insights
Machine learning models identified nine stable synthetic antibodies capable of inhibiting SARS-CoV-2. This high-throughput approach accelerates the discovery of neutralizing antibodies to combat viral threats like COVID-19.
Area of Science:
- Immunology
- Computational Biology
- Virology
Background:
- Rapid virus mutations, like those in SARS-CoV-2, pose significant threats due to delayed immune responses.
- Developing effective neutralizing antibodies is crucial for controlling viral outbreaks and saving lives.
Purpose of the Study:
- To develop a high-throughput method for predicting neutralizing antibodies against SARS-CoV-2.
- To identify stable, synthetic antibody sequences with potential inhibitory effects on the virus.
Main Methods:
- Utilized machine learning (ML) models, including XGBoost, Random Forest, Multilayered Perceptron, Support Vector Machine, and Logistic Regression.
- Employed graph featurization on a dataset of 1933 virus-antibody sequences and clinical neutralization response data.
- Integrated bioinformatics, structural biology, and Molecular Dynamics (MD) simulations for candidate antibody validation.
Main Results:
- Screened thousands of hypothetical antibody sequences using various ML methods.
- Identified nine stable antibody sequences demonstrating potential to inhibit SARS-CoV-2.
- Validated the stability and inhibitory potential of candidate antibodies through multi-disciplinary approaches.
Conclusions:
- Machine learning offers a powerful tool for high-throughput prediction of neutralizing antibodies.
- The identified synthetic antibodies represent promising candidates for therapeutic development against SARS-CoV-2.
- Combining computational prediction with experimental validation accelerates the discovery of antiviral therapies.
