Abstract
Post-translational modifications (PTMs) are chemical changes added to proteins after translation. These changes affect protein function and regulation, and their disruption is linked to disease-associated mechanisms. Because experimentally validating all possible modification sites is impractical, many computational predictors have been developed for PTM site prediction. In this work, we study whether a shared model can represent common residue-background patterns while learning modification-specific background-to-positive offsets. We propose an anchor-guided rectified flow matching framework for multi-type PTM site prediction from protein language model embeddings. For each PTM-residue pair, the model builds residue-background anchors from PTM-compatible unannotated residues and positive anchors from experimentally annotated modified residues, and uses a rectified flow module to estimate a modification-conditioned background-to-positive offset. We evaluate the framework on a dbPTM-derived benchmark covering six commonly studied PTMs.
Cite this work
Download BibTeX · Download RIS · This record describes a preprint.
@article{pokharel2026ptm,
title = {Learning Shared Residue Backgrounds and Modification-Specific Offsets for PTM Site Prediction},
author = {Pokharel, Suresh and Bhusal, Bishnu},
journal = {bioRxiv},
year = {2026},
month = aug,
doi = {10.64898/2026.08.05.743079},
url = {https://doi.org/10.64898/2026.08.05.743079}
}