DBpred: A web server for predicting DNA-binding residues in protein sequences

Reference: Patiyal S, Dhall A, Raghava GPS (2022) A deep learning-based method for the prediction of
DNA interacting residues in a protein. Brief Bioinform. 8:bbac322. doi: 10.1093/bib/bbac322.

DNA-protein interaction is one of the most crucial interactions in the biological system, which decide the fate of many processes such as transcription, regulation of gene expression, splicing, and many more. To explore the underlying mechanisms of the biological process, it is essential to recognize the specific residues in the protein sequences that interact with the DNA. Though many computational approaches exist that can predict the DNA interacting residues from the protein sequences, there is still a significant opportunity for improvement in terms of performance and accessibility. In this study, we are presenting a method, DBPred, that can predict the DNA-interacting residues in a protein from its primary structure.

Major Modules

Sequence based module: This module uses AAB, PCB information of protein sequences to predict DNA binding residue from its primary sequence.
PSSM based Module: This module utilize evolutionary information (in form of PSSM profile) of a protein to predict DNA binding residues in a protein.
Hybrid Module: This module utilize AAB, PCB and PSSM profile information of a protein to predict DNA binding residues in a protein.
Standalone Software: It has been developed using Python and will be freely available to users.
Datasets: All datasets used in this study will be available to public.