iDRBP_MMC:

Introduction

A new sequence-based computational predictor for identifying DNA-binding proteins and RNA-binding proteins. In which, multi-label learning and a novel motif-based convolution neural network were employed. It reduced the cross prediction between DNA-binding proteins and RNA-binding proteins and improved the predictive perfermance for identification of DNA-binding proteins and RNA-binding proteins. It is a useful tool for nucleic acid binding protein prediction. The framework and working process of iDRBP_MMC are shown in Fig.1.

Data

The training dataset used in this study can be download from below link:

[Training dataset]

The test dataset TEST474 used in this study can be download from below link:

[Test dataset TEST474]

The test dataset PDB255 used in this study can be download from below link:

[Test dataset PDB255]

The dataset EZL used in this study can be download from below link:

[Dataset EZL]

The dataset DRBP206 used in this study can be download from below link:

[Dataset DRBP206]

The 467 structural motifs used in this study can be download from below link:

[Used structural motifs]

The predicted tomato DBPs and tomato RBPs can be download from below link:

[Predicted tomato nucleic acid binding proteins]

Acknowledgments

We acknowledge with thanks the following softwares used in this server:

NCBI-BLAST--For generating PSSM profile;

Tensorflow--For constructing multi-label neural network;

Biopython--For data processing.