EUVIMEDEUVIMED entdecken
Crossref

PriMPT: Prior-Informed Multiscale Paired-Token Representation Learning for CRISPR/Cas9 Off-Target Cleavage Activity Prediction

Jiashun Fu, Ruijie Deng, Xiue Jiang, Wensheng Cai, Haohao Fu, Xueguang Shao

Journal of Chemical Information and Modeling · 04.11.2026

DOI: 10.1021/acs.jcim.6c02365 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, online erschienen am 04.11.2026. Verfasst von Jiashun Fu und 5 weiteren Autor:innen. Die Arbeit nennt 47 Literaturangaben. Gefördert von: Fundamental Research Funds for the Central Universities, Chinese Academy of Sciences, Natural Science Foundation of Tianjin City.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate prediction of CRISPR/Cas9 off-target cleavage activity requires molecular representations that explicitly capture the interaction compatibility between guide RNA and target DNA. This study presents PriMPT, a prior-informed multiscale paired-token representation learning framework that redesigns guide-target tokenization using 1-, 2-, and 3-gram paired tokens and injects mechanism-informed pair-prior descriptors into the corresponding embeddings through scale-specific gated injection, thereby incorporating RNA–DNA interaction information before contextual modeling and facilitating interaction-aware learning of guide-target compatibility. Across guide-disjoint cross-validation on six public data sets and a cross-data set external test, PriMPT achieved the numerically highest mean area under the precision-recall curve (AUPRC) among the evaluated models in each of the seven scenarios, with ablation studies identifying input-level pair-prior injection as the most consistent contributor and Integrated Gradients analysis yielding attribution patterns consistent with established aspects of Cas9 target recognition. These results suggest that PriMPT captures mechanism-relevant sequence-pair patterns and offers a mechanism-informed representation learning strategy for CRISPR/Cas9 off-target risk assessment.

Förderung

  • Fundamental Research Funds for the Central Universities
  • Chinese Academy of Sciences
  • Natural Science Foundation of Tianjin City
  • National Basic Research Program of China (973 Program)
  • National Natural Science Foundation of China (NSFC)

Zitieren

APA

Fu, J., Deng, R., Jiang, X., Cai, W., Fu, H., & Shao, X. (2026). PriMPT: Prior-Informed Multiscale Paired-Token Representation Learning for CRISPR/Cas9 Off-Target Cleavage Activity Prediction. Journal of Chemical Information and Modeling. https://doi.org/10.1021/acs.jcim.6c02365

Vancouver

Fu J, Deng R, Jiang X, Cai W, Fu H, Shao X. PriMPT: Prior-Informed Multiscale Paired-Token Representation Learning for CRISPR/Cas9 Off-Target Cleavage Activity Prediction. Journal of Chemical Information and Modeling. 2026. doi:10.1021/acs.jcim.6c02365

BibTeX
@article{Fu2026,
  author = {Fu, Jiashun and Deng, Ruijie and Jiang, Xiue and Cai, Wensheng and Fu, Haohao and Shao, Xueguang},
  title = {PriMPT: Prior-Informed Multiscale Paired-Token Representation Learning for CRISPR/Cas9 Off-Target Cleavage Activity Prediction},
  journal = {Journal of Chemical Information and Modeling},
  year = {2026},
  doi = {10.1021/acs.jcim.6c02365}
}
Kostenlos starten →