rewire.it
Paper-reported evidence

The Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning

2024 · Peer-reviewed · journal full text in PMC

Paper-reported results. The values below come from this source, not an independent rewire.it run.

Open primary paper →DOI: 10.3390/antib13030074

Numeric result checked against Table 1 in primary full-text XML; journal/source: Antibodies.

1 verified numerical rows · source checked 2026-09-15

Paper-reportedAuthor's model

ESM-2 650M embeddings + classifier (esm2_t33_650m_UR50D)

antibody deamidation-site prediction

Reported score
0.944± 0.012
Metric
accuracy
Dataset / split
antibody peptide-mapping training dataset · fivefold stratified CV

global contextual embeddings only

Table 1, Global embeddings only row, Accuracy columnVerify at source →