EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Systematic Benchmarking of DNA Sequence Encoding Strategies for Predicting Regulatory Effects of Non-Coding SNPs

Hui Jin iD, Yihang Bao iD, Wenhao Li, Chengyi Yang, Weidi Wang, Wenxiang Cai, Zhe Liu, Guan Ning Lin iD

International Journal of Molecular Sciences · 25.07.2026 · 27 (15) · 6657

DOI: 10.3390/ijms27156657 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Molecular Sciences, online erschienen am 25.07.2026. Verfasst von Hui Jin und 7 weiteren Autor:innen. Beteiligte Einrichtung: School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai 200230, China. Hauptthemen laut MEDLINE: Polymorphism, Single Nucleotide, Sequence Analysis, DNA. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Shanghai.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Non-coding single nucleotide polymorphisms (SNPs) are key modulators of gene regulation and have been implicated in diverse complex traits and diseases. With the growing demand for accurate functional interpretation of non-coding variants, the choice of encoding strategies becomes critical in downstream predictive modeling. Despite recent advances, a systematic evaluation of encoding approaches tailored for non-coding SNPs remains lacking. To address this gap, we present a comprehensive benchmark that evaluates six representative encoding strategies, including categorical, semantic, and functional embeddings, across three quantitative trait loci (QTL)-related prediction tasks. The study encompasses nine machine learning and deep learning models and incorporates experimental controls and repeated trials to ensure robustness and reproducibility. We assess each strategy along multiple dimensions, such as interpretability, representation abundance, and computational efficiency. Rather than ranking individual methods, our analysis emphasizes the interaction between encoding strategies, model types, and preprocessing protocols, and highlights their collective influence on predictive performance. This work establishes a standardized framework for evaluating non-coding SNP representations and offers guidance for selecting and optimizing prediction pipelines in regulatory genomics.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Polymorphism, Single NucleotideSequence Analysis, DNAHumansQuantitative Trait LociBenchmarkingMachine LearningDeep LearningGenomicsComputational Biology

Stichwörter der Autor:innen

DNA methylationbenchmarkingdeep learningencoding strategiesnon-coding SNPsregulatory variants

Autor:innen und Institutionen

  • School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai 200230, China.
  • Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai 200237, China.

ORCID-Profile: Hui Jin, Yihang Bao, Guan Ning Lin

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Shanghai

Zitieren

APA

Jin, H., Bao, Y., Li, W., Yang, C., Wang, W., Cai, W., Liu, Z., & Lin, G. N. (2026). Systematic Benchmarking of DNA Sequence Encoding Strategies for Predicting Regulatory Effects of Non-Coding SNPs. International Journal of Molecular Sciences, 27(15), 6657. https://doi.org/10.3390/ijms27156657

Vancouver

Jin H, Bao Y, Li W, Yang C, Wang W, Cai W, et al. Systematic Benchmarking of DNA Sequence Encoding Strategies for Predicting Regulatory Effects of Non-Coding SNPs. International Journal of Molecular Sciences. 2026;27(15):6657. doi:10.3390/ijms27156657

BibTeX
@article{Jin2026,
  author = {Jin, Hui and Bao, Yihang and Li, Wenhao and Yang, Chengyi and Wang, Weidi and Cai, Wenxiang and Liu, Zhe and Lin, Guan Ning},
  title = {Systematic Benchmarking of DNA Sequence Encoding Strategies for Predicting Regulatory Effects of Non-Coding SNPs},
  journal = {International Journal of Molecular Sciences},
  year = {2026},
  volume = {27},
  number = {15},
  pages = {6657},
  doi = {10.3390/ijms27156657}
}
Kostenlos starten →