PepCleav: a classification method for evaluating the cleavability of peptide fragments presented by MHC class I
Jiang, D.; Zhu, W.; Tan, W.; Du, H.
Show abstract
Neoantigens, due to their tumor specificity and lack of central tolerance, are promising targets for cancer immunotherapy. Evaluating the cleavability of peptide fragments generated by proteasomes and aminopeptidases is crucial for neoantigen identification, but tools for this purpose are scarce. To address this, we developed PepCleav, a method for evaluating peptide cleavability by classifying the amino acids at the proteasome and aminopeptidase recognition sites of the C- and N-termini. By integrating C- and N-terminal cleavability, PepCleav accurately predicted the overall cleavability of peptide fragments in test datasets, correctly identifying 84-89% of cleavable peptides and 63-92% of non-cleavable peptides. We also found that highly cleavable peptides have a higher likelihood of being effective neoantigens, highlighting PepCleavs potential to improve neoantigen identification. PepCleavs source code is publicly available at https://github.com/Dulab2020/PepCleav.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- A random forest model for predicting exosomal proteins using evolutionary information and motifs 93%
- Prediction of peptide hormones using an ensemble of machine learning and similarity-based methods 93%
- Molecular characterization of triple negative breast cancer formaldehyde-fixed paraffin-embedded samples by data independent acquisition proteomics 92%
Similar papers in this journal
- Generation of SARS-CoV-2 S1 spike glycoprotein putative antigenic epitopes in vitro by intracellular aminopeptidases 94%
- PELSA-Decipher: a software tool for the processing and interpretation of ligand protein interaction dataset acquired by PELSA 94%
- Proximity-dependent biotinylation to elucidate the interactome of TNK2 non-receptor tyrosine kinase 93%
Similar papers in this journal
- Framework for analyzing MAE-derived immunopeptidomes from cell lines with shared HLA haplotypes 95%
- dagLogo: an R/Bioconductor package for identifying and visualizing differential amino acid group usage in proteomics data 93%
- Design of multi-epitope vaccine candidate against Brucella type IV secretion system (T4SS) 93%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.