New artificial intelligence models could help design antibodies that better protect the body from viruses and disease, a new study by researchers at UCL and the University of Surrey has found.
An AI model known as ImmunoMatch can predict and identify the correct combination of proteins within antibodies, potentially helping to strengthen the immune system.
In this unique study published in Nature Methods, scientists sought to understand whether artificial intelligence could be used to predict how the insides of antibodies are assembled in the body. Antibodies, made up of “heavy” and “light” protein chains, are produced by B cells in the immune system and protect against viruses and bacteria.
Co-lead author Professor Franca Fraternari, based at the Institute of Structural Molecular Biology, a joint UCL and Birkbeck institute, said: “Until now, it was widely thought that the pairing of heavy and light chains within antibodies occurs randomly. Using immunomatching, we show for the first time that this assembly is indeed highly specific.”
“Understanding these combinatorial rules is critical for predicting antibody stability and performance, opening the door to the rational design of more effective therapeutics.”
To learn more, the scientists created ImmunoMatch based on an antibody-specific language model and applied it to heavy and light chain antibody sequences collected from millions of single human B cells. The AI model was able to identify and predict chain combinations, giving scientists valuable insight into how antibodies bind.
The research team also showed that ImmunoMatch can accurately analyze antibody sequences in immune cells that actively respond to disease, such as B cells in blood cancers and solid tumors. These insights may accelerate the rational design of new therapeutic antibodies.
Co-author Professor Deborah Dunn-Walters, from the University of Surrey, said: “By using AI, we were able to discover that the combination of 'heavy' and 'light' chains is not as random as previously thought.”
“This information allows us to learn about the natural rules that govern how proteins combine to create functional antibodies.
“Antibodies are the largest class of modern therapeutics. About a quarter of newly approved therapeutics are monoclonal antibodies, so understanding how antibodies are made is critical to designing effective therapeutics.”
/Open to the public. This material from the original organization/author may be of a contemporary nature and has been edited for clarity, style, and length. Mirage.News does not take any institutional position or position, and all views, positions, and conclusions expressed herein are solely those of the authors. Read the full text here.
