EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

LOGOWheat: deep learning–based prediction of regulatory effects for noncoding variants in wheats

Lingpeng Kong, Hong Cheng, Kun Zhu, Bo Song iD

Briefings in Bioinformatics · 2024

DOI: 10.1093/bib/bbae705 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2024. Verfasst von Lingpeng Kong und 3 weiteren Autor:innen. Beteiligte Einrichtung: Agricultural Genomics Institute at Shenzhen, Chinese Academy of Agricultural Sciences, No. 97 Buxin Road, Dapeng New District, Shenzhen 518124, China. Hauptthemen laut MEDLINE: Triticum, Deep Learning. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 67 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Research Grants for Postdocs Settle in Shenzhen from Shenzhen Government.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Identifying the regulatory effects of noncoding variants presents a significant challenge. Recently, the accumulation of epigenomic profiling data in wheat has provided an opportunity to model the functional impacts of these variants. In this study, we introduce Language of Genome for Wheat (LOGOWheat), a deep learning–based tool designed to predict the regulatory effects of noncoding variants in wheat. LOGOWheat initially employs a self-attention-based, contextualized pretrained language model to acquire bidirectional representations of the unlabeled wheat reference genome. Epigenomic profiling data are also collected and utilized to fine-tune the model, enabling it to discern the regulatory code inherent in genomic sequences. The test results suggest that LOGOWheat is highly effective in predicting multiple chromatin features, achieving an average area under the receiver operating characteristic (AUROC) of 0.8531 and an average area under the precision–recall curve (AUPRC) of 0.7633. Two case studies illustrate and demonstrate the main functions provided by LOGOWheat: assigning scores and prioritizing causal variants within a given variant set and constructing a saturated mutagenesis map in silico to discover high-impact sites or functional motifs in a given sequence. Finally, we propose the concept of extracting potential functional variations from the wheat population by integrating evolutionary conservation information. LOGOWheat is available at http://logowheat.cn/.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

TriticumDeep LearningGenome, PlantEpigenomicsGenetic VariationSoftwareComputational Biology

Stichwörter der Autor:innen

deep learningnoncoding variantsself-attentionvariant score

Autor:innen und Institutionen

  • Agricultural Genomics Institute at Shenzhen, Chinese Academy of Agricultural Sciences, No. 97 Buxin Road, Dapeng New District, Shenzhen 518124, China.
  • State Key Laboratory of Crop Stress Adaptation and Improvement, School of Life Sciences, Henan University, No. 379 Mingli Road (North Section), Zhengzhou 450046, China.

ORCID-Profile: Bo Song

Förderung

  • Research Grants for Postdocs Settle in Shenzhen from Shenzhen Government

Zitieren

APA

Kong, L., Cheng, H., Zhu, K., & Song, B. (2024). LOGOWheat: deep learning–based prediction of regulatory effects for noncoding variants in wheats. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbae705

Vancouver

Kong L, Cheng H, Zhu K, Song B. LOGOWheat: deep learning–based prediction of regulatory effects for noncoding variants in wheats. Briefings in Bioinformatics. 2024. doi:10.1093/bib/bbae705

BibTeX
@article{Kong2024,
  author = {Kong, Lingpeng and Cheng, Hong and Zhu, Kun and Song, Bo},
  title = {LOGOWheat: deep learning–based prediction of regulatory effects for noncoding variants in wheats},
  journal = {Briefings in Bioinformatics},
  year = {2024},
  doi = {10.1093/bib/bbae705}
}
Kostenlos starten →