Tag

Protein Fragments

All articles tagged with #protein fragments

"Breakthrough: Deep-Learning Predicts Cancer-Linked Protein Fragments with Unprecedented Accuracy"
healthtech3 years ago

"Breakthrough: Deep-Learning Predicts Cancer-Linked Protein Fragments with Unprecedented Accuracy"

Researchers at Johns Hopkins have developed a deep-learning technology called BigMHC that accurately predicts cancer-related protein fragments that can stimulate an immune response. This breakthrough has the potential to revolutionize personalized cancer therapy by aiding in the development of tailored immunotherapies and vaccines. BigMHC outperformed existing methods in predicting antigen presentation and identifying neoantigens responsible for triggering T-cell responses. The researchers aim to use BigMHC to guide the development of immunotherapies applicable to multiple patients or personalized vaccines. This integration of deep learning into clinical cancer research marks a significant step forward in the quest to conquer cancer through innovative technology and interdisciplinary collaboration.

"Revolutionary Deep-Learning Tech Enhances Personalized Cancer Treatment"
healthtech3 years ago

"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.