Author response for "DNSS2 : Improved ab initio protein secondary structure prediction using advanced deep learning architectures"

2020 ◽  
Author(s):  
Zhiye Guo ◽  
Jie Hou ◽  
Jianlin Cheng
Keyword(s):  
Deep Learning ◽  
Secondary Structure ◽  
Ab Initio ◽  
Structure Prediction ◽  
Secondary Structure Prediction ◽  
Protein Secondary Structure ◽  
Author Response ◽  
Protein Secondary Structure Prediction ◽  
Learning Architectures

scholarly journals DNSS2: improved ab initio protein secondary structure prediction using advanced deep learning architectures

2019 ◽  
Author(s):  
Jie Hou ◽  
Zhiye Guo ◽  
Jianlin Cheng
Keyword(s):  
Deep Learning ◽  
Secondary Structure ◽  
Ab Initio ◽  
Structure Prediction ◽  
Tertiary Structure ◽  
Secondary Structure Prediction ◽  
Protein Secondary Structure ◽  
Alpha Helix ◽  
Protein Secondary Structure Prediction ◽  
Learning Architectures

AbstractMotivationAccurate prediction of protein secondary structure (alpha-helix, beta-strand and coil) is a crucial step for protein inter-residue contact prediction and ab initio tertiary structure prediction. In a previous study, we developed a deep belief network-based protein secondary structure method (DNSS1) and successfully advanced the prediction accuracy beyond 80%. In this work, we developed multiple advanced deep learning architectures (DNSS2) to further improve secondary structure prediction.ResultsThe major improvements over the DNSS1 method include (i) designing and integrating six advanced one-dimensional deep convolutional/recurrent/residual/memory/fractal/inception networks to predict secondary structure, and (ii) using more sensitive profile features inferred from Hidden Markov model (HMM) and multiple sequence alignment (MSA). Most of the deep learning architectures are novel for protein secondary structure prediction. DNSS2 was systematically benchmarked on two independent test datasets with eight state-of-art tools and consistently ranked as one of the best methods. Particularly, DNSS2 was tested on the 82 protein targets of 2018 CASP13 experiment and achieved the best Q3 score of 83.74% and SOV score of 72.46%. DNSS2 is freely available at: https://github.com/multicom-toolbox/DNSS2.

Sign in / Sign up

Export Citation Format

Share Document