iNucRes-ASSH:

Introduction

iNucRes-ASSH is a new structure-sequence hybrid computational predictor for identifying DNA-binding residues and RNA-binding residues in proteins. It uses the self-attention mechanism to learn the latent local patterns of protein structure from structural context and uses the bidirectional gated recurrent unit to integrate the learned structural features and the residue order information in sequence. To alleviate the cross-prediction problem, a multi-task learning framework is employed. It is an important complement to existing methods. The framework and working process of iNucRes-ASSH are shown in Fig. 1. For more information please refer to our paper.

Acknowledgments

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

(1) PSIBLAST - Generation of the position specific scoring matrixes (PSSMs);

(2) NCBR's database - The non-redundant database for usage of PSIBLAST to generate PSSMs;

(3) HHBlits - Generation of the hidden Markov model (HMM) based evolutionary profiles;

(4) HHsuite database - The non-redundant database for uasage of HHblits to generate HMM profiles;

(5) DSSP - Prediction of protein secondary structure and solvent accessibility respectively;

(6) MSMS - Prediction of half-sphere exposure and residue depth;

(7) Biopython - Protein data preprocessing;

(8) python 3.6.6 - Programming language and interpreter;

(9) PyTorch 1.1.0 - Libary for constructing neural networks and computing.

Stand-alone package

The stand-alone packages of iNucRes-ASSH based on python 3.6 can be download from below links:

[iNucRes-ASSH | README.txt]

Note: For the example of the command line of the stand-alone package and the guide of configuring the stand-alone package please refer to the above README file.

References

Upon the usage of this server the users are requested to use the following citation:

Zhang, J., Chen, Q. and Liu, B. iNucRes-ASSH: Identifying nucleic acid‐binding residues in proteins by using self‐attention‐based structure‐sequence hybrid neural network. Proteins: Structure, Function, and Bioinformatics, 2024, 92(3): 395-410.