PEDLA: predicting enhancers with a deep learning-based algorithmic framework
Problem
Systematically and precisely predicting transcriptional enhancers from massively heterogeneous genomic data remained a major challenge.
Why it matters
Enhancers play a central role in the spatiotemporal regulation of gene expression programs.
What the AI did
PEDLA, a deep learning-based framework, directly learns an enhancer predictor from heterogeneous data and generalizes across cell types/tissues.
Results
State-of-the-art performance relative to five existing enhancer prediction methods; trained on 1,114-dimensional features in H1 cells; extended to 22 training cell types/tissues.
Impact
PEDLA improves enhancer prediction across many cell types, aiding gene-regulation research.
Record
| Venue | Scientific Reports |
|---|---|
| Published | 2016 |
| Work type | article |
| Authors | Feng Liu, Hao Li, Chao Ren, Xiaochen Bo, Wenjie Shu |
| Citations | 102 (OpenAlex, at import time) |
| References | 80 |
| Model or method | PEDLA (deep learning-based framework) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1038/srep28517 |
| Open access | gold |
| Keywords | enhancer prediction, deep learning, PEDLA, genomics, gene regulation |
Importance rating
real but narrower advance
Enhancers centrally regulate gene expression per abstract, but no scale of lives/industry affected is given; a research-tool advance in regulatory genomics.