MIRACN: a residual convolutional neural network for predicting cell line specific functional regulatory variants
Authors:
Open Access
- 4 March 2025
- journal article
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 26 (2)
Abstract
In post-genome-wide association study era, interpretation of noncoding variants remains a significant challenge due to their complexity and the limited understanding of their functions. Here, we developed MIRACN, a novel residual convolutional neural network designed to predict cell line-specific functional regulatory variants. By utilizing a substantial dataset from massively parallel reporter assays (MPRAs) and employing a multitask learning strategy, MIRACN was trained across seven distinct cell lines, attaining superior performance compared to existing methods, especially in predicting cell type specificity. Comparative evaluations on an independent MPRA test dataset demonstrated that MIRACN not only outperformed in identifying regulatory variants but also provided valuable insights into their cellular context-specific regulatory mechanisms. MIRACN is capable of not only providing scores for functional variants but also pinpointing the specific cell line in which these variants display their function. This enhancement has improved the resolution of current research on the functionality of noncoding variants and has paved the way for more precise diagnostic and therapeutic strategies.Keywords
Funding Information
- National Natural Science Foundation of China (32460159)
- Key Research and Development Program of Ningxia (2022BSB03043)
- Natural Science Foundation of Ningxia China (2023AAC03030, 2023AAC05006)
- Research and Development Program of Ningxia (2023BEG02009)
This publication has 27 references indexed in Scilit:
- A spectral approach integrating functional genomic annotations for coding and noncoding variantsNature Genetics, 2016
- Predicting effects of noncoding variants with deep learning–based sequence modelNature Methods, 2015
- Integrative analysis of 111 reference human epigenomesNature, 2015
- Diagnostic Clinical Genome and Exome SequencingNew England Journal of Medicine, 2014
- Functional annotation of noncoding sequence variantsNature Methods, 2014
- Systematic Localization of Common Disease-Associated Variation in Regulatory DNAScience, 2012
- The accessible chromatin landscape of the human genomeNature, 2012
- An operational definition of epigenetics: Figure 1.Genes & Development, 2009
- Initial sequencing and analysis of the human genomeNature, 2001
- dbSNP: a database of single nucleotide polymorphismsNucleic Acids Research, 2000