Transformer-based TransNRank model advances neoantigen prediction accuracy

Researchers have developed TransNRank, a novel deep learning framework utilizing the Transformer architecture for more accurate neoantigen prediction. This model addresses challenges like data scarcity and class imbalance by employing a self-attention mechanism to capture complex feature contexts and a positive-aware training objective. Experiments on NCI, TESLA, and HiTIDE datasets show TransNRank significantly improves the top 20 recall rate for neoantigen prediction while drastically reducing training time. The study also identified mutation at anchor and TCGA expression level as key predictive features. AI

IMPACT Advances neoantigen prediction accuracy and efficiency, potentially accelerating immuno-oncology research and personalized cancer treatments.

RANK_REASON The cluster describes a novel deep learning framework presented in a research paper, detailing its methodology and experimental results. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• HiTIDE House
• National Cancer Institute
• Tesla
• The Cancer Genome Atlas
• Transformer
• TransNRank
• XGBoost
• Yuenan Hou

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →