EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Neur-Ally: a deep learning model for regulatory variant prediction based on genomic and epigenomic features in brain and its validation in certain neurological disorders

Anil Prakash iD, Moinak Banerjee iD

NAR Genomics and Bioinformatics · 2025

DOI: 10.1093/nargab/lqaf080 ↗

Kurz gefasst

Fachartikel in der Zeitschrift NAR Genomics and Bioinformatics, 2025. Verfasst von Anil Prakash und 1 weiteren Autor:innen. Beteiligte Einrichtung: Human Molecular Genetics Lab, Neurobiology and Genetics Division, BRIC-Rajiv Gandhi Centre for Biotechnology, Thiruvananthapuram, Kerala 695014, Indi…. Hauptthemen laut MEDLINE: Deep Learning, Polymorphism, Single Nucleotide, Brain, Nervous System Diseases. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Department of Biotechnology, Council of Scientific and Industrial Research.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large-scale quantitative studies have identified significant genetic associations for various neurological disorders. Expression quantitative trait locus (eQTL) studies have shown the effect of single-nucleotide polymorphisms (SNPs) on the differential expression of genes in brain tissues. However, a large majority of the associations are contributed by SNPs in the noncoding regions that can have significant regulatory function but are often ignored. Besides, mutations that are in high linkage disequilibrium with actual regulatory SNPs will also show significant associations. Therefore, it is important to differentiate a regulatory noncoding SNP with a nonregulatory one. To resolve this, we developed a deep learning model named Neur-Ally, which was trained on epigenomic datasets from nervous tissue and cell line samples. The model predicts differential occurrence of regulatory features like chromatin accessibility, histone modifications, and transcription factor binding on genomic regions using DNA sequence as input. The model was used to predict the regulatory effect of neurological condition-specific noncoding SNPs using in silico mutagenesis. The effect of associated SNPs reported in genome-wide association studies of neurological condition, brain eQTLs, autism spectrum disorder, and reported probable regulatory SNPs in neurological conditions were predicted by Neur-Ally.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningPolymorphism, Single NucleotideBrainNervous System DiseasesEpigenomicsHumansQuantitative Trait LociGenome-Wide Association StudyAutism Spectrum Disorder

Autor:innen und Institutionen

  • Human Molecular Genetics Lab, Neurobiology and Genetics Division, BRIC-Rajiv Gandhi Centre for Biotechnology, Thiruvananthapuram, Kerala 695014, India.
  • Department of Biotechnology, University of Kerala, Kariavattom, Thiruvananthapuram, Kerala 695581, India.

ORCID-Profile: Anil Prakash, Moinak Banerjee

Förderung

  • Department of Biotechnology
  • Council of Scientific and Industrial Research

Zitieren

APA

Prakash, A., & Banerjee, M. (2025). Neur-Ally: a deep learning model for regulatory variant prediction based on genomic and epigenomic features in brain and its validation in certain neurological disorders. NAR Genomics and Bioinformatics. https://doi.org/10.1093/nargab/lqaf080

Vancouver

Prakash A, Banerjee M. Neur-Ally: a deep learning model for regulatory variant prediction based on genomic and epigenomic features in brain and its validation in certain neurological disorders. NAR Genomics and Bioinformatics. 2025. doi:10.1093/nargab/lqaf080

BibTeX
@article{Prakash2025,
  author = {Prakash, Anil and Banerjee, Moinak},
  title = {Neur-Ally: a deep learning model for regulatory variant prediction based on genomic and epigenomic features in brain and its validation in certain neurological disorders},
  journal = {NAR Genomics and Bioinformatics},
  year = {2025},
  doi = {10.1093/nargab/lqaf080}
}
Kostenlos starten →