PLoS Computational Biology Issue Image | Vol. 22(8) September 2026
Abstract
Defining biologically grounded validation standards for deep learning-based post-translational modification (PTM) prediction: The CLASPP framework combines unsupervised sequence-space stratification with supervised contrastive learning in protein language model embedding space to predict 12 PTM types from a single model. Training and experimental validation were performed in humans, while out-of-distribution testing spanned diverse model organisms across the evolutionary tree shown. The model’s utility in phosphoproteomics workflows is demonstrated through the annotation of ubiquitination sites in the understudied DCLK3 kinase. By integrating evolutionary breadth, experimental validation, and behavioral testing, CLASPP establishes a framework for rigorous benchmarking of next-generation multi-PTM prediction models (Gravel et al., 2026).
Related
- PLoS Biology Issue Image | Vol. 24(8) September 2026
- PLoS Computational Biology Issue Image | Vol. 22(10) November 2026
- PLoS Computational Biology Issue Image | Vol. 22(9) October 2026
- PLoS Neglected Tropical Diseases Issue Image | Vol. 20(7) September 2026
- PLoS Medicine Issue Image | Vol. 23(8) September 2026
BibTeX
@article{anon2026plos,
title = {{PLoS Computational Biology Issue Image | Vol. 22(8) September 2026}},
journal = {PLoS Computational Biology},
year = {2026},
month = sep,
doi = {10.1371/image.pcbi.v22.i08},
url = {https://doi.org/10.1371/image.pcbi.v22.i08},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - PLoS Computational Biology Issue Image | Vol. 22(8) September 2026
PY - 2026
DA - 2026/09/21
JO - PLoS Computational Biology
DO - 10.1371/image.pcbi.v22.i08
UR - https://doi.org/10.1371/image.pcbi.v22.i08
AB - Defining biologically grounded validation standards for deep learning-based post-translational modification (PTM) prediction: The CLASPP framework combines unsupervised sequence-space stratification with supervised contrastive learning in protein language model embedding space to predict 12 PTM types from a single model. Training and experimental validation were performed in humans, while out-of-distribution testing spanned diverse model organisms across the evolutionary tree shown. The model’s utility in phosphoproteomics workflows is demonstrated through the annotation of ubiquitination sites in the understudied DCLK3 kinase. By integrating evolutionary breadth, experimental validation, and behavioral testing, CLASPP establishes a framework for rigorous benchmarking of next-generation multi-PTM prediction models (Gravel et al., 2026).
SN - 1553-7358
ER -