TopModel: Template-Based Protein Structure Prediction at Low Sequence Identity Using Top-Down Consensus and Deep Neural Networks

2020 ◽  
Vol 16 (3) ◽  
pp. 1953-1967 ◽  
Author(s):  
Daniel Mulnaes ◽  
Nicola Porta ◽  
Rebecca Clemens ◽  
Irina Apanasenko ◽  
Jens Reiners ◽  
...  
Keyword(s):  
Neural Networks ◽  
Protein Structure ◽  
Protein Structure Prediction ◽  
Structure Prediction ◽  
Deep Neural Networks ◽  
Top Down ◽  
Sequence Identity

scholarly journals Protein structure prediction using multiple deep neural networks in the 13th Critical Assessment of Protein Structure Prediction (CASP13)

2019 ◽  
Vol 87 (12) ◽  
pp. 1141-1148 ◽  
Author(s):  
Andrew W. Senior ◽  
Richard Evans ◽  
John Jumper ◽  
James Kirkpatrick ◽  
Laurent Sifre ◽  
...  
Keyword(s):  
Neural Networks ◽  
Protein Structure ◽  
Protein Structure Prediction ◽  
Structure Prediction ◽  
Deep Neural Networks ◽  
Critical Assessment

scholarly journals Improved fragment sampling for ab initio protein structure prediction using deep neural networks

2019 ◽  
Vol 1 (8) ◽  
pp. 347-355 ◽  
Author(s):  
Tong Wang ◽  
Yanhua Qiao ◽  
Wenze Ding ◽  
Wenzhi Mao ◽  
Yaoqi Zhou ◽  
...  
Keyword(s):  
Neural Networks ◽  
Protein Structure ◽  
Ab Initio ◽  
Protein Structure Prediction ◽  
Structure Prediction ◽  
Deep Neural Networks

Optimal neural networks for protein-structure prediction

1993 ◽  
Vol 48 (2) ◽  
pp. 1502-1515 ◽  
Author(s):  
Teresa Head-Gordon ◽  
Frank H. Stillinger
Keyword(s):  
Neural Networks ◽  
Protein Structure ◽  
Protein Structure Prediction ◽  
Structure Prediction

scholarly journals QDeep: distance-based protein model quality estimation by residue-level ensemble error classifications using stacked deep residual neural networks

2020 ◽  
Vol 36 (Supplement_1) ◽  
pp. i285-i291 ◽  
Author(s):  
Md Hossain Shuvo ◽  
Sutanu Bhattacharya ◽  
Debswapna Bhattacharya
Keyword(s):  
Neural Networks ◽  
Protein Structure ◽  
Protein Structure Prediction ◽  
Structure Prediction ◽  
Residue Level ◽  
Supplementary Information ◽  
Model Quality ◽  
Quality Estimation ◽  
Distance Information ◽  
Protein Model

Abstract Motivation Protein model quality estimation, in many ways, informs protein structure prediction. Despite their tight coupling, existing model quality estimation methods do not leverage inter-residue distance information or the latest technological breakthrough in deep learning that has recently revolutionized protein structure prediction. Results We present a new distance-based single-model quality estimation method called QDeep by harnessing the power of stacked deep residual neural networks (ResNets). Our method first employs stacked deep ResNets to perform residue-level ensemble error classifications at multiple predefined error thresholds, and then combines the predictions from the individual error classifiers for estimating the quality of a protein structural model. Experimental results show that our method consistently outperforms existing state-of-the-art methods including ProQ2, ProQ3, ProQ3D, ProQ4, 3DCNN, MESHI, and VoroMQA in multiple independent test datasets across a wide-range of accuracy measures; and that predicted distance information significantly contributes to the improved performance of QDeep. Availability and implementation https://github.com/Bhattacharya-Lab/QDeep. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals QDeep: distance-based protein model quality estimation by residue-level ensemble error classifications using stacked deep residual neural networks

2020 ◽  
Author(s):  
Md Hossain Shuvo ◽  
Sutanu Bhattacharya ◽  
Debswapna Bhattacharya
Keyword(s):  
Neural Networks ◽  
Protein Structure ◽  
Protein Structure Prediction ◽  
Structure Prediction ◽  
Residue Level ◽  
Estimation Methods ◽  
Model Quality ◽  
Quality Estimation ◽  
Distance Information ◽  
Protein Model

AbstractMotivationProtein model quality estimation, in many ways, informs protein structure prediction. Despite their tight coupling, existing model quality estimation methods do not leverage inter-residue distance information or the latest technological breakthrough in deep learning that has recently revolutionized protein structure prediction.ResultsWe present a new distance-based single-model quality estimation method called QDeep by harnessing the power of stacked deep residual neural networks (ResNets). Our method first employs stacked deep ResNets to perform residue-level ensemble error classifications at multiple predefined error thresholds, and then combines the predictions from the individual error classifiers for estimating the quality of a protein structural model. Experimental results show that our method consistently out-performs existing state-of-the-art methods including ProQ2, ProQ3, ProQ3D, ProQ4, 3DCNN, MESHI, and VoroMQA in multiple independent test datasets across a wide-range of accuracy measures; and that predicted distance information significantly contributes to the improved performance of QDeep.Availabilityhttps://github.com/Bhattacharya-Lab/[email protected]

scholarly journals Real-Time Structure Search and Structure Classification for AlphaFold Protein Models

2021 ◽  
Author(s):  
Tunde Aderinwale ◽  
Vijay Bharadwaj ◽  
Charles Christoffer ◽  
Genki Terashi ◽  
Zicong Zhang ◽  
...  
Keyword(s):  
Neural Networks ◽  
Protein Structure ◽  
Real Time ◽  
Structure Prediction ◽  
Deep Neural Networks ◽  
Substantial Improvement ◽  
Time Structure ◽  
Molecular Surface ◽  
Structure Search ◽  
Protein Models

AlphaFold2 showed a substantial improvement in the accuracy of protein structure prediction. Following the release of the software, whole-proteome protein structure predictions by AlphaFold2 for 21 organisms were made publicly available. Here, we developed the infrastructure, 3D-AF-Surfer, to enable real-time structure-based search for the AlphaFold2 models by combining molecular surface representation with 3D Zernike descriptors and deep neural networks.

Sign in / Sign up

Export Citation Format

Share Document