Published April 27, 2023
| Version v3
Dataset
Open
Multimodal learning of noncoding variant effects using genome sequence and chromatin structure
Description
ncVarPred-1D3D: pretrained models of Sei (PMID: 35817977) + our 3D structure embedding models are shared. The models are trained and validated using DeepSEA (PMID: 26301843) selected 200 bp regions (we extended to 4K bp neighboring) to predict the epigenetic profile containing 21907 epigenetic events Sei processed.
The pretrained DeepSEA (PMID: 26301843) and reproduced DanQ (PMID: 27084946) can be found in SOTA.tar.gz.
Files
Files
(34.0 GB)
| Name | Size | Download all |
|---|---|---|
|
md5:7b2adfbf9c9beed1cd72860cb35c0988
|
20.0 GB | Download |
|
md5:5693c612d9639bd69f0ea3a1135d6204
|
10.3 GB | Download |
|
md5:c4556f8571a3d3a467ebc333643dbdf2
|
3.6 GB | Download |
Additional details
References
- Tan, Wuwei, and Yang Shen. "Multimodal learning of noncoding variant effects using genome sequence and chromatin structure." bioRxiv (2022): 2022-12.