August 13, 2023
Cancer is a complex and deadly disease that affects millions of people around the world. One of the biggest challenges in treating cancer is finding the right therapy for each patient, since every tumor is different and may respond differently to different drugs.
But what if we could use artificial intelligence (AI) to help us find the best way to fight cancer? That's what a team of engineers and cancer researchers from Johns Hopkins University are trying to do with their new technology called BigMHC.
BigMHC is a deep-learning method that can predict which protein fragments on cancer cells are most likely to trigger an immune response. These protein fragments, called neoantigens, are unique to each patient's tumor and can be used to create personalized cancer vaccines or immunotherapies to trigger T-cell response.
Immunotherapy is a type of treatment that boosts the body's natural defenses to kill cancer cells. However, not all neoantigens are equally effective in stimulating the immune system, and finding the best ones requires a lot of time and resources.
BigMHC aims to solve this problem by using a large amount of data from previous studies to train a set of neural networks, which are computer models that can learn from patterns and make predictions. BigMHC can then use these neural networks to analyze the genome of a patient's tumor and identify the most promising neoantigens.
The researchers tested BigMHC on data from 20 patients with melanoma, a type of skin cancer, and found that it was able to accurately predict the neoantigens that elicited an immune response. They also compared BigMHC with other existing methods and found that it performed better in terms of speed, accuracy, and reliability.
The researchers hope that BigMHC will help accelerate the development and testing of personalized cancer therapies and vaccines, as well as improve our understanding of how the immune system recognizes and fights cancer.
If you want to learn more about this exciting technology, you can read the full article here. And stay tuned for the latest news in artificial intelligence!