EVEscape – a new artificial intelligence tool developed by researchers at Harvard Medical School and the University of Oxford. This EVEscape AI model is the latest innovation and scientists from across the globe consider it a historical milestone in the medical of epidemiology and public health.
EVEscape AI will revolutionize the field of vaccination research and development. Many experts say that once the EVEscape AI passes the clinical trial and research phase it will give precise solutions for developing vaccines for the deadliest and even for mutated viruses.
“EVEscape is a method for predicting the likelihood of antibody escape for viral mutations. EVEscape scores for individual mutations are found by combining three sources of information: a deep generative model for fitness prediction, structural information about the spike protein to estimate antibody binding potential, and chemical distances in charge and hydrophobicity between mutated and wild-type residues.”
EVEscape Artificial Intelligence tools have a substantial impact on the spread of infectious diseases, the effectiveness of vaccines, and the course of an epidemic or pandemic. The ability to predict which variants may arise and how they may behave will help scientists in preparing more effective solutions and prevention measurements for future pandemic outbreaks.
The official page says that “EVEscape antibody predictions for all SARS-CoV-2 strains in GISAID in order to flag potentially concerning strains from the first time they emerge. In silico mutational scans are provided to forecast potential variants to flagged strains and existing Variants of Concern.”
EVEscape AI tool has two elements: A model of evolutionary sequences that predicts changes that can occur to a virus, and detailed biological and structural information about the virus. Together, they allow EVEscape to make predictions about the variants most likely to occur as the virus evolves.
EVEscape Forecasting Viral Antibody Escape Tools: How it helps in the development of vaccines
EVEscape Forecasting Viral Antibody provides a download of mainly three reports based on which medical scientists and researchers can narrow their findings and learnings for the development of trial vaccines for clinical approval. The EVEscape AI tools provide three types of reports and they are:
To construct an AI tool capable of predicting viral variants, researchers would likely need to use a combination of machine learning techniques, such as deep learning and natural language processing, along with large datasets of viral genetic sequences and information on how past variants have behaved.
The fitness model used in this version of EVEscape is EVE, a Bayesian variational autoencoder, trained on historical coronavirus sequences and SARS-CoV-2 sequences through August. EVEscape scores for strains are sums of individual mutations from Wuhan in that strain.
Early prediction of antibody escape from deep generative sequence models, structural and biophysical constraints.
EVEscape assesses the likelihood of a mutation escaping the immune response on the basis of the probabilities of a given mutation maintaining viral fitness, occurring in an antibody epitope and disrupting antibody binding. The tool requires only information available early in a pandemic, before surveillance sequencing, antibody–antigen structures or experimental mutational scans are broadly available. This provides further early warning time critical for vaccine development. Read here the official document.
For further reading on EVEscape AI Tools check the link below:
Read EVEscape’s publication here
See new work using EVEscape to design infectious Spike proteins that forecast future neutralizing antibody escape on BioRxiv.
You can browse through the code at our repository on Github