Transfer Learning for T-Cell Response Prediction

arXiv:2403.12117v1 Announce Type: cross
Abstract: We study the prediction of T-cell response for specific given peptides, which could, among other applications, be a crucial step towards the development of personalized cancer vaccines. It is a challenging task due to limited, heterogeneous training data featuring a multi-domain structure; such data entail the danger of shortcut learning, where models learn general characteristics of peptide sources, such as the source organism, rather than specific peptide characteristics associated with T-cell response.
Using a transformer …

abstract applications arxiv cancer cs.lg danger data development domain personalized prediction q-bio.cb shortcut study training training data transfer transfer learning type vaccines