Skip to content
DraconiticResearch
Search Sources API
203,234 studies31 sourcesUpdated 4 min ago
Peer-reviewedCC BYNon-coding RNA Research

LncPNdeep: A long non-coding RNA classifier based on large language model with peptide and nucleotide embedding

  • Zongrui Dai1,2
  • Feiyang Deng1,2
  • Hsiao H. Sung3,4
4 affiliations
  1. 1Department of Biostatistics, University of Michigan, 1415 Washington Heights, Ann Arbor, MI, 48109, USA
  2. 2Department of Biostatistics, University of Michigan, Ann Arbor, MI 4809, USA
  3. 3Department of Oral and Maxillofacial Surgery, University of Michigan, 1011 N. University, Ave, Ann Arbor, MI, 48109, USA
  4. 4Experimental Rheumatology, Department of Rheumatology, Radboud University Medical Centre, Nijmegen, the Netherlands
Open at sourcePDFDOICite

Abstract

Accurate classification of long non-coding RNAs (lncRNAs) is essential for transcriptome annotation and understanding gene regulation. Existing computational methods predominantly rely on nucleotide sequence features, frequently overlooking biologically relevant peptide signals encoded within lncRNAs. To overcome this limitation, we developed LncPNdeep, an integrative deep learning framework that combines nucleotide and peptide embeddings extracted via masked language models, specifically utilizing contextual representations from BigBird, Longformer, and ProtTrans. By fusing both features in a concatenated neural architecture, LncPNdeep robustly captures complex sequence relationships and improves discrimination between lncRNAs and coding RNAs. Benchmarking on the human transcriptome achieved state-of-the-art performance with 97.1% accuracy, surpassing established lncRNA classification tools and baseline machine learning models. LncPNdeep also demonstrated superior generalization ability across cross-species datasets, maintaining consistently high accuracy and F1 scores. Permutation analysis highlighted the pivotal role of peptide embeddings, especially Average Peptide Embedding, in model performance, while t-SNE visualizations confirmed that integrating multiple embeddings markedly enhances the separation of lncRNAs from coding RNAs. These results position LncPNdeep as a versatile and powerful tool for transcriptomic research, facilitating lncRNA discovery, biomarker identification, and comparative genomics. The model and instructions are freely available at https://github.com/yatoka233/LncPNdeep.

Related

  1. An XGBoost-SHAP classifier to distinguish asymptomatic hyperuricemia from acute primary gouty arthritis
    Zilin Chen, Tao Peng, Feng Lin +5
    Scientific ReportsPeer-reviewedCC BY-NC-ND 4.0Full textGeneral medicineCrossref
  2. A machine learning classifier reveals hidden rare biallelic heterozygous variants in the coding regions of Meniere disease genome
    Sayedali A. Mohseni, Muhammad Hamza B. Khan, Pablo Cruz-Granados +3
    iSciencePeer-reviewedCC BY 4.0Full textNeurologyCell PressCrossrefEurope PMC
  3. Stage-Stratified Explainable Machine Learning Identifies a Reproducible Transcriptomic Classifier with Stage-Dependent Feature Importance in Colorectal Cancer: A Multi-Cohort Study with Saudi Population Contextualisation
    Asif Hassan Syed, Sultan Alhayyani, Nashwan Alromema +2
    BiomedicinesPeer-reviewedCC BYFull textGeneral medicineEurope PMC
  4. FRANK: a pan-cancer RNA-seq classifier for childhood tumors with data-efficient learning
    K. Sablauskas, T. Kiselova, L. Bardina +6
    medRxivPreprintCC BY-NC-NDFull textOncologymedRxiv
  5. Deep learning-based classifier for malignant plasma cell identification in myeloma
    Sarthak Satpathy, Marina E. Michaud, William C. Pilcher +2
    NPJ Precision OncologyPeer-reviewedCC BY-NC-ND 4.0Full textGeneral medicinePMC

Cite

BibTeXRIS
BibTeX
@article{dai2026lncpndeep,
  title = {{LncPNdeep: A long non-coding RNA classifier based on large language model with peptide and nucleotide embedding}},
  author = {Zongrui Dai and Feiyang Deng and Hsiao H. Sung},
  journal = {Non-coding RNA Research},
  year = {2026},
  month = aug,
  doi = {10.1016/j.ncrna.2026.06.004},
  url = {https://doi.org/10.1016/j.ncrna.2026.06.004},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - LncPNdeep: A long non-coding RNA classifier based on large language model with peptide and nucleotide embedding
AU  - Zongrui Dai
AU  - Feiyang Deng
AU  - Hsiao H. Sung
PY  - 2026
DA  - 2026/08/13
JO  - Non-coding RNA Research
DO  - 10.1016/j.ncrna.2026.06.004
UR  - https://doi.org/10.1016/j.ncrna.2026.06.004
AB  - Accurate classification of long non-coding RNAs (lncRNAs) is essential for transcriptome annotation and understanding gene regulation. Existing computational methods predominantly rely on nucleotide sequence features, frequently overlooking biologically relevant peptide signals encoded within lncRNAs. To overcome this limitation, we developed LncPNdeep, an integrative deep learning framework that combines nucleotide and peptide embeddings extracted via masked language models, specifically utilizing contextual representations from BigBird, Longformer, and ProtTrans. By fusing both features in a concatenated neural architecture, LncPNdeep robustly captures complex sequence relationships and improves discrimination between lncRNAs and coding RNAs. Benchmarking on the human transcriptome achieved state-of-the-art performance with 97.1% accuracy, surpassing established lncRNA classification tools and baseline machine learning models. LncPNdeep also demonstrated superior generalization ability across cross-species datasets, maintaining consistently high accuracy and F1 scores. Permutation analysis highlighted the pivotal role of peptide embeddings, especially Average Peptide Embedding, in model performance, while t-SNE visualizations confirmed that integrating multiple embeddings markedly enhances the separation of lncRNAs from coding RNAs. These results position LncPNdeep as a versatile and powerful tool for transcriptomic research, facilitating lncRNA discovery, biomarker identification, and comparative genomics. The model and instructions are freely available at https://github.com/yatoka233/LncPNdeep.
SN  - 2468-0540
SN  - 2468-2160
ER  -