pipette
ENEnglish

Omics-scale decoding of protein N-glycosylation using protein language model embeddings

X. Zhou, X. Guan, Y. Zhou, J. Wang, Z. Peng, W. Ren, W. Wang, R. Xie, W. Li

PreprintAfirmaciones fuertes, leer con cuidado

En palabras de los autores

Protein language models (pLMs) learn rich sequence semantics from vast volume of protein sequences, yet the information encoded in their high-dimensional embeddings remains largely a black box, posing an interpretability challenge. Here we show that semantic features learned by pLMs can be decoded to reveal biologically meaningful signals using coevolutionary analysis without downstream supervised-training. Building on this insight, we developed MaskNGly, a zero-shot framework that identifies protein N-glycosylation sites directly from PLM-embeddings while achieving performance comparable to state-of-the-art supervised predictors. MaskNGly is computationally efficient and intrinsically transferable, enabling omics-scale characterization of protein glycosylation landscape. Applied across proteomes, it reveals that canonical N-X-S/T motifs gain higher glycosylation propensities with increasing organismal complexity and that glycosylation preferentially occurs at structured, solvent-exposed regions. Mutations altering high-scoring motifs are more frequently disease-associated. The framework also captures signatures of glycosylation-mediated protein allostery. These results establish an interpretable and scalable route to study glycobiology from pLM-embeddings.

Resultado principalEl resumen no menciona limitaciones.

Apareció: jueves, 5 de noviembre. bioRxiv. Preprint, todavía sin revisión por pares.

DOI: 10.64898/2026.11.02.763593