Enhancing tumor T cell antigen prediction by integrating deep protein representations

Area of Science:

• Immunology
• Computational Biology
• Bioinformatics

Background:

• Cancer immunotherapy is a promising treatment with high effectiveness and fewer side effects.
• Tumor T cell antigens (TTCA) are crucial targets for immunotherapy but are costly and time-consuming to identify experimentally.
• Developing efficient methods to predict TTCA is essential for advancing cancer treatment.

Purpose of the Study:

• To develop a novel computational framework, DEEPTHYBRID, for accurate prediction of tumor T cell antigens (TTCA).
• To integrate deep protein representations with chemical features for enhanced TTCA prediction.
• To provide a fast and scalable alternative to experimental methods for identifying TTCA candidates.

Main Methods:

• Utilized ProtBERT, a BERT-based language model, to extract deep protein representations from amino acid sequences.
• Incorporated chemically hand-designed features alongside deep protein embeddings.
• Employed an Inception-based neural network as the primary classifier within the DEEPTHYBRID framework.

Main Results:

• DEEPTHYBRID demonstrated superior performance across multiple datasets, outperforming existing TTCA predictors.
• Achieved an accuracy of 0.76 and an F1-score of 0.78 on one dataset, surpassing state-of-the-art methods.
• Combining deep protein embeddings with chemical attributes proved more effective than using either feature type alone.

Conclusions:

• DEEPTHYBRID offers a highly accurate and efficient computational method for predicting tumor T cell antigens.
• The framework significantly reduces the cost and time required for experimental validation of TTCA candidates.
• DEEPTHYBRID accelerates the discovery of potential targets for cancer immunotherapy development.