Back

DRPBind: prediction of DNA, RNA and protein binding residues in intrinsically disordered protein sequences

Sharma, R.; Tsunoda, T.; Sharma, A.

2023-03-23 bioinformatics
10.1101/2023.03.20.533427 bioRxiv
Show abstract

DRPbind predicts three components: deoxyribonucleic acid (DNA) binding, ribonucleic acid (RNA) binding and protein-binding residues of query protein sequences. DRPbind utilizes independent sources of information encoded for each component predictor and relies on the information-rich profiles of protein evolutionary-based features, protein physicochemical-based features, and protein structural-based features. DRPbind employs protein profile-based features extracted from the bigrams of PSSM and HMM profiles. It also extracts features from physicochemical and structural attributes. DRPbind takes primary protein sequences as input, and through the Support Vector Machine (SVM) classifier, it provides the binding prediction. DRPbind is optimized based on a specific binding type and shown superior performance in terms of simultaneously predicting the DNA-binding, RNA-binding and protein-binding residues. The source code is available at https://github.com/roneshsharma/DNA-RNA-Protein-Binding/wiki

Matching journals

The top 7 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.