This record provides bibliographic details and links to the original research. An editorial study breakdown is not available.
What the researchers found
None of the models significantly outperformed random predictions for immunogenic peptides.
Why it matters
Improving predictions of T cell targets is crucial for developing effective vaccines and cancer therapies. Understanding model limitations can guide future research and model development.
How the study worked
The study systematically evaluated several publicly available models for predicting CD8+ T cell targets in the context of pathogens and cancers.
What this study cannot tell us
The study primarily focused on existing models without developing new predictive tools, and results may not directly translate to clinical settings.
Read the original research
Evaluating performance of existing computational models in predicting CD8+ T cell pathogenic epitopes and cancer neoantigens.
Briefings in bioinformatics, 23(3)
Citation
Buckley, Paul R; Lee, Chloe H; Ma, Ruichong; Woodhouse, Isaac; Woo, Jeongmin; Tsvetkov, Vasily O; Shcherbinin, Dmitrii S; Antanaviciute, Agne; Shughay, Mikhail; Rei, Margarida; Simmons, Alison; Koohy, Hashem. (2022). Evaluating performance of existing computational models in predicting CD8+ T cell pathogenic epitopes and cancer neoantigens.. Briefings in bioinformatics, 23(3). https://doi.org/10.1093/bib/bbac141