|
Title
|
|
|
|
The pitfalls of negative data bias for the T-cell epitope specificity challenge
|
|
|
Author
|
|
|
|
|
|
|
Abstract
|
|
|
|
| Recently, Gao et al. introduced a combination of meta-learning and the neural Turing machine to tackle a very important but yet unsolved problem in immunology: the TCR–epitope binding prediction challenge for novel epitopes. All 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. 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. |
|
|
|
Language
|
|
|
|
English
|
|
|
Source (journal)
|
|
|
|
Nature Machine Intelligence
|
|
|
Publication
|
|
|
|
2023
|
|
|
ISSN
|
|
|
|
2522-5839
|
|
|
DOI
|
|
|
|
10.1038/S42256-023-00727-0
|
|
|
Volume/pages
|
|
|
|
5
:10
(2023)
, p. 1060-1062
|
|
|
ISI
|
|
|
|
001129678300003
|
|
|
Full text (Publisher's DOI)
|
|
|
|
|
|
|
Full text (open access)
|
|
|
|
|
|