Inferring gene regulatory networks from single-cell multiome data using atlas-scale external data
importance 6/10
ai assisted
Gene Regulatory Network Analysis genomics stage: research
Problem
Accurate context-specific gene regulatory network inference is impeded by limited independent data points and reliance on expression data alone.
Why it matters
Gene regulatory networks are crucial for understanding cellular mechanisms and disease.
What the AI did
LINGER, a deep learning-based method, infers GRNs from single-cell multiome data using atlas-scale external bulk data and transcription factor motif matching.
Results
not stated in source
Impact
A method is presented to improve GRN inference; measured outcomes not stated in source.
Record
| Venue | Nature Biotechnology |
|---|---|
| Published | 2024 |
| Work type | article |
| Authors | Qiuyue Yuan, Zhana Duren |
| Citations | 118 (OpenAlex, at import time) |
| References | 100 |
| Model or method | LINGER (deep learning neural network) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1038/s41587-024-02182-7 |
| Open access | hybrid |
| Keywords | gene regulatory networks, single-cell multiome, deep learning, chromatin accessibility |
Importance rating
6
significant — thousands to millions affected
GRN inference is called a crucial task in computational biology with disease relevance; 4-10x accuracy gain over existing methods, but abstract gives no scale of lives or systems affected.