MUFOLD-SS: New Deep Inception-Inside-Inception Networks for Protein Secondary Structure Prediction

By Chao Fang, Yingzi Shang, Dong Xu. 2018

157 citations recorded by the source corpus.

Protein secondary structure prediction can provide important information for protein 3D structure prediction and protein functions. Deep learning offers a new opportunity to significantly improve prediction accuracy. In this article, a new deep neural network architecture, named the Deep inception‐inside‐inception (Deep3I) network, is proposed for protein secondary structure prediction and implemented as a software tool MUFOLD‐SS. The input to MUFOLD‐SS is a carefully designed feature matrix corresponding to the primary amino acid sequence of a protein, which consists of a rich set of information derived from individual amino acid, as well as the context of the protein sequence. Specifically, the feature matrix is a composition of physio‐chemical properties of amino acids, PSI‐BLAST profile, and HHBlits profile. MUFOLD‐SS is composed of a sequence of nested inception modules and maps the input matrix to either eight states or three states of secondary structures. The architecture of MUFOLD‐SS enables effective processing of local and global interactions between amino acids in making accurate prediction. In extensive experiments on multiple datasets, MUFOLD‐SS outperformed the best existing methods and other deep neural networks significantly. MUFold‐SS can be downloaded from http://dslsrv8.cs.missouri.edu/~cf797/MUFoldSS/download.html.

Subfields: Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Molecular Biology

Citations in the corpus

High Quality Prediction of Protein Q8 Secondary Structure by Diverse Neural Network Architectures (2018, methodology): “ant study, CRRNN [38], which also reports results on CB513, is excluded from the table as its training set is twice as large as the one used by the other methods. Model Best Single Ensemble MUFOLD-SS [11] 70.5 70.6 NCCNN [3] 70.3 71.4 biRNN-CRF [17] 69.4 70.9 DeepMSCNN [2] 70.0 70.6 DCRNN [21] 69.4 ”
rawMSA: End-to-end Deep Learning Makes Protein Sequence Profiles and Feature Extraction obsolete (2018, methodology): “While most secondary structure and solvent accessibility prediction methods have been using 25-30% sequence identity as threshold to separate testing and training sets [51–54], this practice has been discouraged as it has been shown that it is not sufficient to avoid information leakage [55].”