hybridDBRpred (hybrid model for DNA-Binding Residue prediction)

HybridDBRpred is a webserver that implements a deep learner-based meta-predictor of DNA-binding amino acids in a protein sequence. It utilizes a modern custom-designed transformer network to combine predictions generated by DNAgenie, DNAPred and DisoRDPbind tools.

Please follow the three steps below to make predictions:

1. Copy and paste protein sequence into text area

The server accepts single FASTA formatted protein sequence. The sequence length is limited to between 21 and 1000 amino acids, which stems from the limitations of the input tools. Please enter the protein sequence in the following text field.

2. Provide your email address (optional)

Please enter your email address in the following text area or leave it blank. A link to prediction results will be sent to your email address once they are ready.

3. Predict

Click the Run button to launch the prediction.

Materials

here

Training dataset: Click here to download
Validation dataset: Click here to download
Test dataset: Click here to download

Training dataset: Click here to download
Validation dataset: Click here to download
Test dataset: Click here to download

References

Upon the usage the users are requested to use the following citation:

Zhang J, Basu S, Kurgan L. HybridDBRpred: improved sequence-based prediction of DNA-binding amino acids using annotations from structured complexes and disordered proteins. Nucleic Acids Research, gkad1131, 2023

Acknowledgments

We acknowledge with thanks the following software used as a part of this server:

DNAgenie - Predictor of DNA-type-specific binding residues in protein sequences
DisoRDPbind - Predictor of RNA-, DNA-, and protein-binding residues located in the intrinsically disordered regions in protein sequences
DNApred - Predictor of DNA-binding residues in protein sequences