EUVIMEDEUVIMED entdecken
Crossref

Accurate Prediction of CRISPR/Cas13a Guide Activity Using Feature Selection and Deep Learning

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

Journal of Chemical Information and Modeling · 14.04.2025 · 65 (7) · 3380-3387

DOI: 10.1021/acs.jcim.4c02438 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, online erschienen am 17.03.2025. Verfasst von Jiashun Fu und 6 weiteren Autor:innen. Beteiligte Einrichtung: Research Center for Analytical Sciences, College of Chemistry, Nankai University, Tianjin 300071, China. Hauptthemen laut MEDLINE: Deep Learning, CRISPR-Cas Systems, RNA, Guide, CRISPR-Cas Systems. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 39 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Haihe Laboratory of Sustainable Chemical Transformations, Nankai University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

CRISPR/Cas13a serves as a key tool for nucleic acid tests; therefore, accurate prediction of its activity is essential for creating robust and sensitive diagnosis. In this study, we create a dual-branch neural network model that achieves high prediction accuracy and classification performance across two independent CRISPR/Cas13a data sets, outperforming previously published models relying solely on sequence features. The model integrates direct sequence encoding with descriptive features and yields 99 key descriptive features out of 1553, extracted through statistical analysis, which critically influence guide-target interactions and Cas13a guide activity. By employing Shapley Additive Explanations and Integrated Gradients for feature importance analysis, we show that sequence composition, mismatch type and frequency, and the protospacer flanking site region are primary features. These findings underscore the importance of using descriptive features as complementary inputs to deep learning-based encoding and provide valuable insights into the mechanisms underlying guide-target interaction. All in all, this study not only introduces a reliable and efficient model for Cas13a guide activity prediction but also offers a foundation for future rational design efforts.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningCRISPR-Cas SystemsRNA, Guide, CRISPR-Cas SystemsNeural Networks, Computer

Substanzen

RNA, Guide, CRISPR-Cas Systems

Autor:innen und Institutionen

  • Research Center for Analytical Sciences, College of Chemistry, Nankai University, Tianjin 300071, China.
  • Haihe Laboratory of Sustainable Chemical Transformations, Tianjin 300192, China.
  • College of Biomass Science and Engineering, Healthy Food Evaluation Research Center, Sichuan University, Chengdu 610065, China.

ORCID-Profile: Jiashun Fu, Xuyang Liu, Ruijie Deng, Wensheng Cai, Haohao Fu, Xueguang Shao

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • Haihe Laboratory of Sustainable Chemical Transformations, Nankai University

Zitieren

APA

Fu, J., Liu, X., Deng, R., Jiang, X., Cai, W., Fu, H., & Shao, X. (2025). Accurate Prediction of CRISPR/Cas13a Guide Activity Using Feature Selection and Deep Learning. Journal of Chemical Information and Modeling, 65(7), 3380-3387. https://doi.org/10.1021/acs.jcim.4c02438

Vancouver

Fu J, Liu X, Deng R, Jiang X, Cai W, Fu H, et al. Accurate Prediction of CRISPR/Cas13a Guide Activity Using Feature Selection and Deep Learning. Journal of Chemical Information and Modeling. 2025;65(7):3380-3387. doi:10.1021/acs.jcim.4c02438

BibTeX
@article{Fu2025,
  author = {Fu, Jiashun and Liu, Xuyang and Deng, Ruijie and Jiang, Xiue and Cai, Wensheng and Fu, Haohao and Shao, Xueguang},
  title = {Accurate Prediction of CRISPR/Cas13a Guide Activity Using Feature Selection and Deep Learning},
  journal = {Journal of Chemical Information and Modeling},
  year = {2025},
  volume = {65},
  number = {7},
  pages = {3380--3387},
  doi = {10.1021/acs.jcim.4c02438}
}
Kostenlos starten →