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.
Highlights
The fast and untraceable virus mutations take lives of thousands of people before the immune system can produce the inhibitory antibody
Enabling machine learning (ML) models to be used for high throughput screening of antibody sequences which is faster than traditional methods of computational protein design using Molecular Dynamics (MD) simulations
To better understand the diversity and similarity of the sequences that were used in the training set, we project the graph embeddings encoding the fingerprints of the molecules in the t-Distributed Stochastic Neighbor Embedding (t-SNE) space (Fig. 2a). t-SNE axes shows the directions of the maximum variance in the feature space of the dataset, the dimensionality of the data can be reduced to lower dimensions
Summary
The fast and untraceable virus mutations take lives of thousands of people before the immune system can produce the inhibitory antibody. ML can be used to learn a mapping between the viral epitope and effectiveness of its complementary antibody Once such mapping is learnt, it can be used to predict potentially neutralizing antibody for a given viral sequence enabling us to design novel a ntibodies[7]. ML can learn the complex antigen–antibody interactions much faster than human immune system This allows rapid generation of a library of synthetic inhibitory antibodies bridge, which can overcome the latency between viral infection and human immune system response. This bridge can potentially save the life of many people during the outbreak of novel viruses for which we lack treatment. With the availability of Scientific Reports | (2021) 11:5261
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
