Improved protein model quality assessment by integrating sequential and pairwise features using deep learning

Jing, Xiaoyang; Xu, Jinbo

doi:10.1101/2020.09.30.321661

Cited by 12 publications

(18 citation statements)

References 43 publications

(54 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The benchmark dataset of geometries prediction network was constructed from SCOPe 2.07 (Fox et al, 2014) (deposited by November 30, 2018). To train the geometric constraints prediction neural network, the sequences with the sequence similarity of more than 40% with the dataset of model evaluation network are eliminated by CD-HIT-2D (Jing et al, 2020), and 166,025 sequences are retained. Then, the remaining sequences are limited to 50 to 500 residues and clustered by CD-HIT (Fu et al, 2012) with 30% sequence similarity to generate 9,091 representatives.…”

Section: Methodsmentioning

confidence: 99%

De novo protein structure prediction by incremental inter-residue geometries prediction and model quality assessment using deep learning

Liu

Zhao

et al. 2022

Preprint

View full text Add to dashboard Cite

Motivation: The successful application of deep learning has promoted progress in protein model quality assessment. How to use model quality assessment to further improve the accuracy of protein structure prediction, especially not reliant on the existing templates, is helpful for unraveling the folding mechanism. Here, we investigate whether model quality assessment can be introduced into structure prediction to form a closed-loop feedback, and iteratively improve the accuracy of de novo protein structure prediction. Results: In this study, we propose a de novo protein structure prediction method called RocketX. In RocketX, a feedback mechanism is constructed through the geometric constraint prediction network GeomNet, the structural simulation module, and the model quality evaluation network EmaNet. In GeomNet, the co-evolutionary features extracted from MSA that search from the sequence databases are sent to an improved residual neural network to predict the inter-residue geometric constraints. The structure model is folded based on the predicted geometric constraints. In EmaNet, the 1D and 2D features are extracted from the folded model and sent to the deep residual neural network to estimate the inter-residue distance deviation and per-residue lDDT of the model, which will be fed back to GeomNet as dynamic features to correct the geometries prediction and progressively improve model accuracy. RocketX is tested on 483 benchmark proteins and 20 FM targets of CASP14. Experimental results show that the closed-loop feedback mechanism significantly contributes to the performance of RocketX, and the prediction accuracy of RocketX outperforms that of the state-of-the-art methods trRosetta (without templates) and RaptorX. In addition, the blind test results on CAMEO show that although no template is used, the prediction accuracy of RocketX on medium and hard targets is comparable to the advanced methods that integrate templates.

show abstract

Section: Methodsmentioning

confidence: 99%

De novo protein structure prediction by incremental inter-residue geometries prediction and model quality assessment using deep learning

Liu

Zhao

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…In the 13th Critical Assessment of Protein Structure Prediction (CASP13), the inter-residue contact information and deep learning were the key for DeepRank 1 to achieve the best performance in ranking protein structural models with the minimum loss of GDT-TS score 2 . Recently, inter-residue distance predictions have been used with deep learning for the estimation of model accuracy 3,4,5 .…”

Section: Introductionmentioning

confidence: 99%

Protein Model Accuracy Estimation Empowered by Deep Learning and Inter-residue Distance Prediction in CASP14

Chen

Liu

Guo

et al. 2021

Preprint

View full text Add to dashboard Cite

The inter-residue contact prediction and deep learning showed the promise to improve the estimation of protein model accuracy (CASP13) in the 13th Critical Assessment of Protein Structure Prediction (CASP13). During the 2020 CASP14 experiment, we developed and tested several EMA predictors that used deep learning with the new features based on inter-residue distance/contact predictions as well as the existing model quality features. The average global distance test (GDT-TS) score loss of ranking CASP14 structural models by three multi-model MULTICOM EMA predictors (MULTICOM-CONSTRUCT, MULTICOM-AI, and MULTICOM-CLUSTER) is 0.073, 0.079, and 0.081, respectively, which are ranked first, second, and third places out of 68 CASP14 EMA predictors. The single-model EMA predictor (MULTICOM-DEEP) is ranked 10th place among all the single-model EMA methods in terms of GDT-TS score loss. The results show that deep learning and contact/distance predictions are useful in ranking and selecting protein structural models.

show abstract

“…Treating a protein structural model as a graph, ProteinGCN [13], GraphQA [14] and VoroCNN [15] applied graph convolutional networks (GCN) to estimate the model accuracy. ResNetQA [16] and DeepAccNet [17] used deep residue networks to address the problem.…”

Section: Introductionmentioning

confidence: 99%

“…In CSAP13, DeepRank [5] demonstrated that accurate residueresidue contacts (a simplified representation of distances between residues) predicted by deep learning improved the prediction of the quality of protein structural models, suggesting that more detailed residue-residue distance predictions could further improve EMA. However, only a few methods [6], [16], [17], use residue-residue distances to estimate the accuracy of protein structural models.…”

Section: Introductionmentioning

confidence: 99%

DISTEMA: distance map-based estimation of single protein model accuracy with attentive 2D convolutional neural network

Chen

Cheng

2021

Preprint

View full text Add to dashboard Cite

Estimation of the accuracy (quality) of protein structural models is important for both prediction and use of protein structural models. Deep learning methods have been used to integrate protein structure features to predict the quality of protein models. Inter-residue distances are key information for predicting protein's tertiary structures and therefore have good potentials to predict the quality of protein structural models. However, few methods have been developed to fully take advantage of predicted inter-residue distance maps to estimate the accuracy of a single protein structural model. We developed an attentive 2D convolutional neural network (CNN) with channel-wise attention to take only a raw difference map between the inter-residue distance map calculated from a single protein model and the distance map predicted from the protein sequence as input to predict the quality of the model. The network comprises multiple convolutional layers, batch normalization layers, dense layers, and Squeeze-and-Excitation blocks with attention to automatically extract features relevant to protein model quality from the raw input without using any expert-curated features. We evaluated DISTEMA's capability of selecting the best models for CASP13 targets in terms of ranking loss of GDT-TS score. The ranking loss of DISTEMA is 0.079, lower than several state-of-the-art single-model quality assessment methods. The work demonstrates that using raw inter-residue distance information alone with deep learning can predict the quality of protein structural models reasonably well.

show abstract

Improved protein model quality assessment by integrating sequential and pairwise features using deep learning

Cited by 12 publications

References 43 publications

De novo protein structure prediction by incremental inter-residue geometries prediction and model quality assessment using deep learning

De novo protein structure prediction by incremental inter-residue geometries prediction and model quality assessment using deep learning

Protein Model Accuracy Estimation Empowered by Deep Learning and Inter-residue Distance Prediction in CASP14

DISTEMA: distance map-based estimation of single protein model accuracy with attentive 2D convolutional neural network

Contact Info

Product

Resources

About