We applied the mixed prediction model (ImmuneApp-MA, integrates both mono- and multi-allelic ligands) as pre-trained model to employ deep transfer-learning on a new curated immunogenicity training data (>5,000 immunogenic epitopes), resulting in the creation of a novel immunogenicity predictor named ImmuneApp-Neo. ImmuneApp-Neo outperforms existing state-of-the-art methods in prioritizing immunogenic neoepitopes, yielding a notable 2.1-fold improvement in positive predictive value (PPV).

Important note: Each job may take 1-10 minutes to finish. You may retrive the results anytime using the Job Identifier (JID e.g., JOB1234_1234567890). Please do keep a record of the JID.

Example result: A quick example result page can be checked here