The pitfalls of negative data bias for the T-cell epitope specificity challenge
00:46 Share

Link to bioRxiv paper: http://biorxiv.org/cgi/content/short/2023.04.06.535863v1?rss=1

Authors: Dens, C., Laukens, K., Bittremieux, W., Meysman, P.

Abstract: Even high-performing machine learning models can have problems when deployed in a real-world setting if the data used to train and test the model contains biases. TCR-epitope binding prediction for novel epitopes is a very important but yet unsolved problem in immunology. In this article, we describe how the technique used to create negative data for the TCR-epitope interaction prediction task can lead to a strong bias and makes that the performance drops to random when tested in a more realistic scenario.

Copy rights belong to original authors. Visit the link for more info

Podcast created by Paper Player, LLC