LESS-PseU: A Language Model-Enhanced Semistacking Framework for RNA Pseudouridine Site Prediction
Journal of Chemical Information and Modeling · 09.11.2026 · 66 (21) · 14144-14158
DOI: 10.1021/acs.jcim.6c02817 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, online erschienen am 27.10.2026. Verfasst von Hao Yang und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Artificial Intelligence, Anhui Agricultural University, Hefei, Anhui230036, China. Hauptthemen laut MEDLINE: RNA, Pseudouridine, Computational Biology. Die Arbeit nennt 39 Literaturangaben. Gefördert von: University Natural Science Research Project of Anhui Province.
Abstract (Originalsprache)
Accurate prediction of RNA pseudouridine (Ψ) sites remains challenging because existing models often struggle to integrate interpretable handcrafted features with high-dimensional contextual representations from pretrained genomic language models. To address this issue, we propose LESS-PseU, a language model-enhanced semistacking framework that fuses the predicted probability features of primary learners with DNABERT2 embeddings for multiple species Ψ site prediction. Specifically, we first built three primary learners based on three kinds of hand-crafted features, including one-hot, k-mer, and nucleotide chemical property features. Instead of training a primary learner based on the embeddings extracted from DNABERT2, the embeddings were directly concatenated with the predicted probabilities of the three primary learners as the input features for a Logistic Regression meta-learner for final prediction. Under a leakage-aware cross-validation setting, our model was validated on the training sets of three species. Furthermore, on independent test sets from human, mouse, and yeast, LESS-PseU achieved AUC values of 0.9069, 0.8833, and 0.8820, respectively, which were higher than those of the compared models. A Friedman test indicated an overall difference (p = 0.029). Paired DeLong tests further showed that the AUC improvements over Meta-PseU were significant for the human and mouse data sets, while those over PseU-ST were significant for all three species. Ablation analysis, fusion-strategy comparison, and pretrained language-model comparison further demonstrate the effectiveness of the proposed framework. Additional evaluations on m5C and m7G benchmarks provided preliminary evidence that the framework may be applicable to other RNA modification prediction tasks.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- School of Artificial Intelligence, Anhui Agricultural University, Hefei, Anhui230036, China.
ORCID-Profile: Xiaolei Zhu
Förderung
- University Natural Science Research Project of Anhui Province
Zitieren
APA
Yang, H., Cheng, Z., He, S., Zhang, Y., & Zhu, X. (2026). LESS-PseU: A Language Model-Enhanced Semistacking Framework for RNA Pseudouridine Site Prediction. Journal of Chemical Information and Modeling, 66(21), 14144-14158. https://doi.org/10.1021/acs.jcim.6c02817
Vancouver
Yang H, Cheng Z, He S, Zhang Y, Zhu X. LESS-PseU: A Language Model-Enhanced Semistacking Framework for RNA Pseudouridine Site Prediction. Journal of Chemical Information and Modeling. 2026;66(21):14144-14158. doi:10.1021/acs.jcim.6c02817
BibTeX
@article{Yang2026,
author = {Yang, Hao and Cheng, Zhiwei and He, Sisi and Zhang, Yong and Zhu, Xiaolei},
title = {LESS-PseU: A Language Model-Enhanced Semistacking Framework for RNA Pseudouridine Site Prediction},
journal = {Journal of Chemical Information and Modeling},
year = {2026},
volume = {66},
number = {21},
pages = {14144--14158},
doi = {10.1021/acs.jcim.6c02817}
}
EUVIMED