Discordant results among MHC binding affinity prediction tools
Nguyen, A.; Nellore, A.; Thompson, R. F.
Show abstract
A large number of machine learning-based Major Histocompatibility Complex (MHC) binding affinity (BA) prediction tools have been developed and are widely used for both investigational and therapeutic applications, so it is important to explore differences in tool outputs. We examined predictions of four popular tools (netMHCpan, HLAthena, MHCflurry, and MHCnuggets) across a range of possible peptide sources (human, viral, and randomly generated) and MHC class I alleles. We uncovered inconsistencies in predictions of BA, allele promiscuity and the relationship between physical properties of peptides by source and BA predictions, as well as quality of training data. Our work raises fundamental questions about the fidelity of peptide-MHC binding prediction tools and their real-world implications.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- Positional SHAP (PoSHAP) for Interpretation of Machine Learning Models Trained from Biological Sequences 95%
- An Integrated Approach to the Characterization of Immune Repertoires Using AIMS: An Automated Immune Molecule Separator 93%
- Predicted Impact of the Viral Mutational Landscape on the Cytotoxic Response against SARS-CoV-2 93%
Similar papers in this journal
- Current challenges for epitope-agnostic TCR interaction prediction and a new perspective derived from image classification 94%
- A simple workflow to identify novel Small Linear Motif (SLiM)-mediated interactions with AlphaFold 93%
- DeepImmuno: Deep learning-empowered prediction and generation of immunogenic peptides for T cell immunity 92%