DeepCLIP
A context-aware neural network for modeling and predicting protein binding to nucleic acids using only sequence input.
About
- DeepCLIP is a neural network with shallow convolutional layers connected to a bidirectional LSTM layer.
- DeepCLIP can calculate binding profiles and pseudo position frequency matrices.
- Binding profiles show whether areas of sequences contain possible binding sites or whether they look like random genomic background.
- DeepCLIP outperforms current state-of-the-art RNA-binding protein motif discovery tools on curated CLIP datasets.
Online platform
We provide an easy-to-use web interface for DeepCLIP where you can train your own DeepCLIP models or use pre-trained models.
Go to web interface Read user guide
Stand-alone program
DeepCLIP is also available as a stand-alone Python program.
Cite
If you use DeepCLIP in your research, we kindly ask you to cite the following publication:
Grønning AGB, Doktor TK, et al. DeepCLIP: predicting the effect of mutations on protein-RNA binding with deep learning. Nucleic Acids Res. 2020 Jul 27;48(13):7099-7118.
Download from OUPContact
If you want to contact us regarding DeepCLIP, please contact us in the following order: