GitHub Repository
Created On
Updated On
VaxOptiML is an integrated pipeline designed to enhance Cancer epitope prediction and prioritization. It employs 3 models for epitope prediction in cancer immunotherapy. Through advanced machine learning techniques and curated datasets, it can accurately predict epitopes, personalize HLA pairing, and prioritize targets based on immunogenicity. Rigorous evaluation showcases superior performance over existing approaches, with visual representations emphasizing our ensemble model's efficacy in expediting epitope discovery and vaccine design for cancer immunotherapy. First, the input protein will be chunked, and features of those peptides will be generated. Then, the peptides will be divided into epitopes and non-epitopes based on 0 and 1 annotations. Next, antigenic scores will be generated for those peptides. HLAs of those peptides will then be generated. Finally, based on the antigenic score and epitope nature, final probable epitopes will be generated along with starting and ending positions.

More details

Use Cases Limitations Evidence Owner's Insight

The VaxOptiML application can be utilized in several key use cases within the field of cancer immunotherapy:

  1. Cancer Epitope Prediction: The application uses advanced machine learning models to predict cancer epitopes, which are essential for designing effective cancer vaccines. Researchers can input sequence data to receive predictions on potential epitopes.

  2. Epitope Prioritization: By prioritizing epitopes based on their immunogenicity, the tool helps researchers focus on the most promising candidates for vaccine development, improving the efficiency and effectiveness of their research efforts.

  3. HLA Pairing Customization: The application customizes HLA (Human Leukocyte Antigen) pairing, which is crucial for personalized cancer immunotherapy. This ensures that the predicted epitopes are compatible with the patient's HLA types, enhancing the likelihood of a successful immune response.

  4. Performance Assessment: Researchers can use the application to compare the performance of different epitope prediction methods. The integrated pipeline provides thorough assessments and demonstrates improved performance over existing methods, helping researchers choose the best approach for their needs.

  5. Data Conversion and Report Generation: The application includes functionalities for converting data into CSV format and generating downloadable reports. This makes it easier for researchers to share their findings and collaborate with others in the field.

  6. Automated Notifications: The application has an email notification system that sends results and updates to users. This feature is useful for keeping researchers informed about the progress of their predictions and analyses without needing to constantly monitor the application.

  7. Educational Tool: The application can be used as an educational resource to teach students and new researchers about the processes and methodologies involved in cancer epitope prediction and prioritization using machine learning.

By integrating these functionalities, VaxOptiML serves as a comprehensive tool for advancing cancer vaccine research and development.

See owner's GitHub repository for more information:

This app is based on the paper:

Dhanushkumar, T., Sunila, B. G., Hebbar, S. R., Selvam, P. K., & Vasudevan, K. (2024). VaxOptiML: Leveraging machine learning for accurate prediction of MHC-I & II epitopes for optimized cancer immunotherapy. bioRxiv.

This application was not uploaded by the author, but through their publicly available Github repository,


Warning: Not intended for clinical use. Assume outputs are unsafe and unvalidated. Use carefully.

  • Favorites: 0
  • Executions: 2

  • Precision Medicine & Genomics


Kinal Patel

Member since