Deep learning approaches for non-coding genetic variant effect prediction: current progress and future prospects
Problem
Most genetic variants are non-coding and their effects on gene regulation are hard to interpret; deep learning tools have been developed to predict these effects.
Why it matters
Non-coding variants make up over 90% of variants and are key to understanding gene regulation and disease mechanisms.
What the AI did
The paper reviews deep learning models built on bulk and single-cell sequencing data that predict non-coding variant effects and support downstream interpretation tasks.
Results
not stated in source
Impact
Documents current progress of deep learning approaches for non-coding variant interpretation; no new results.
Record
| Venue | Briefings in Bioinformatics |
|---|---|
| Published | 2024 |
| Work type | article |
| Authors | Xiaoyu Wang, Fuyi Li, Yiwen Zhang, Seiya Imoto, Hsin‐Hui Shen, Shanshan Li, Yuming Guo, Jian Xin Yang et al. |
| Citations | 29 (OpenAlex, at import time) |
| References | 98 |
| Model or method | not stated in source |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1093/bib/bbae446 |
| Open access | gold |
| Keywords | non-coding variants, deep learning, genomics, variant effect prediction, review |
Importance rating
significant — thousands to millions affected
Abstract states non-coding variants constitute over 90% of all variants and are key to gene regulation and disease mechanisms; broad genomics relevance.