"Revolutionary Deep-Learning Tech Enhances Personalized Cancer Treatment"

Engineers and cancer researchers from Johns Hopkins have developed a deep-learning technology called BigMHC that can accurately predict protein fragments linked to cancer, which may trigger an immune system response. This technology could help in the creation of personalized immunotherapies and vaccines by identifying tumor-killing immune response-triggering neoantigens. The researchers trained BigMHC using transfer learning, leveraging massive data to build a model of antigen presentation and predict immunogenic antigens. BigMHC outperformed other methods in predicting antigen presentation and identifying neoantigens that trigger T-cell response. The team is now testing BigMHC in immunotherapy clinical trials to determine its effectiveness in filtering down to the most likely immunogenic neoantigens.