Deep‐learning contact‐map guided protein structure prediction in CASP13

Zheng, Wei; Li, Yang; Zhang, Chengxin; Pearce, Robin; Mortuza, S. M.; Zhang, Yang

doi:10.1002/prot.25792

Cited by 194 publications

(202 citation statements)

References 55 publications

Supporting

Mentioning

196

Contrasting

Order By: Relevance

“…The quality of the MSA is highly correlated with the predictive accuracy of a protein contact‐map, especially for TripletRes and ResTriplet due to their dependence on coevolutionary features derived directly from the MSA. In CASP13, we utilized DeepMSA to construct MSAs by searching across multiple databases using complementary sequence searching engines . To examine the impact of such pipeline on the final contact predictions, Figure A,B shows a head‐to‐head comparison of the top L long‐range predictions on the FM targets by TripletRes and ResTriplet using two different pipelines of MSA collection, one with DeepMSA and another with a routine approach of HHBlits searching through UniClust30 sequence database.…”

Section: Resultsmentioning

confidence: 99%

“…The overall pipelines for TripletRes and ResTriplet are shown in Figure . For a given query sequence, a multiple sequence alignment is generated by incrementally searching against multiple sequence databases using DeepMSA . Three coevolutionary matrix features are then extracted based on the obtained MSA, including the covariance matrix (COV), the precision matrix (PRE), and the coupling parameters of the Potts model by pseudolikelihood maximization (PLM).…”

Section: Methodsmentioning

confidence: 99%

“…Multiple sequence alignments are critical elements for contact‐map prediction based on coevolutionary analysis. DeepMSA is used to generate MSAs from three sequence databases and consists of three steps . First, HHblits is used to search against UniClust30 for three iterations with a minimal coverage equal to 50%.…”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Ensembling multiple raw coevolutionary features with deep residual neural networks for contact‐map prediction in CASP13

et al. 2019

Self Cite

View full text Add to dashboard Cite

We report the results of residue‐residue contact prediction of a new pipeline built purely on the learning of coevolutionary features in the CASP13 experiment. For a query sequence, the pipeline starts with the collection of multiple sequence alignments (MSAs) from multiple genome and metagenome sequence databases using two complementary Hidden Markov Model (HMM)‐based searching tools. Three profile matrices, built on covariance, precision, and pseudolikelihood maximization respectively, are then created from the MSAs, which are used as the input features of a deep residual convolutional neural network architecture for contact‐map training and prediction. Two ensembling strategies have been proposed to integrate the matrix features through end‐to‐end training and stacking, resulting in two complementary programs called TripletRes and ResTriplet, respectively. For the 31 free‐modeling domains that do not have homologous templates in the PDB, TripletRes and ResTriplet generated comparable results with an average accuracy of 0.640 and 0.646, respectively, for the top L/5 long‐range predictions, where 71% and 74% of the cases have an accuracy above 0.5. Detailed data analyses showed that the strength of the pipeline is due to the sensitive MSA construction and the advanced strategies for coevolutionary feature ensembling. Domain splitting was also found to help enhance the contact prediction performance. Nevertheless, contact models for tail regions, which often involve a high number of alignment gaps, and for targets with few homologous sequences are still suboptimal. Development of new approaches where the model is specifically trained on these regions and targets might help address these problems.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Ensembling multiple raw coevolutionary features with deep residual neural networks for contact‐map prediction in CASP13

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…“Davis‐EMAconsensus” estimates model accuracy purely based on consensus, by scoring the i th model by an average GDT‐TS to all other models in the pool as score i = 〈 N res, model / N res, target (GDT ‐ TS) i , model 〉 model . Z ‐score of top 1 GDT‐TS loss for “Davis‐EMAconsensus” is even higher than that of the best single‐model method in this category, “ModFOLD7_rank.” “GOAP,” a distance‐ and orientation‐dependent statistical potential, was also examined as a reference single‐model method, and performed above average in this CASP.…”

Section: Assessment Results and Discussionmentioning

confidence: 99%

“…This implies that there was higher consensus among CASP13 TS models compared to CASP12 for FM targets. The fraction of FM targets selected for EMA experiment also increased because higher‐accuracy models were generated for FM targets in CASP13 . The number of targets for which GDT‐TS of the best model >40, a criterion for EMA target, was 11 out of 15 single‐EU FM targets in CASP13, compared to 5 out of 13 in CASP12.…”

Section: Assessment Results and Discussionmentioning

confidence: 99%

Assessment of protein model structure accuracy estimation in CASP13: Challenges in the era of deep learning

et al. 2019

View full text Add to dashboard Cite

Scoring model structure is an essential component of protein structure prediction that can affect the prediction accuracy tremendously. Users of protein structure prediction results also need to score models to select the best models for their application studies. In Critical Assessment of techniques for protein Structure Prediction (CASP), model accuracy estimation methods have been tested in a blind fashion by providing models submitted by the tertiary structure prediction servers for scoring. In CASP13, model accuracy estimation results were evaluated in terms of both global and local structure accuracy. Global structure accuracy estimation was evaluated by the quality of the models selected by the global structure scores and by the absolute estimates of the global scores. Residue‐wise, local structure accuracy estimations were evaluated by three different measures. A new measure introduced in CASP13 evaluates the ability to predict inaccurately modeled regions that may be improved by refinement. An intensive comparative analysis on CASP13 and the previous CASPs revealed that the tertiary structure models generated by the CASP13 servers show very distinct features. Higher consensus toward models of higher global accuracy appeared even for free modeling targets, and many models of high global accuracy were not well optimized at the atomic level. This is related to the new technology in CASP13, deep learning for tertiary contact prediction. The tertiary model structures generated by deep learning pose a new challenge for EMA (estimation of model accuracy) method developers. Model accuracy estimation itself is also an area where deep learning can potentially have an impact, although current EMA methods have not fully explored that direction.

show abstract

Predicting the Real‐Valued Inter‐Residue Distances for Proteins

Ding

Gong

2020

Advanced Science

View full text Add to dashboard Cite

Predicting protein structure from the amino acid sequence has been a challenge with theoretical and practical significance in biophysics. Despite the recent progresses elicited by improved inter-residue contact prediction, contact-based structure prediction has gradually reached the performance ceiling. New methods have been proposed to predict the inter-residue distance, but unanimously by simplifying the real-valued distance prediction into a multiclass classification problem. Here, a lightweight regression-based distance prediction method is shown, which adopts the generative adversarial network to capture the delicate geometric relationship between residue pairs and thus could predict the continuous, real-valued inter-residue distance rapidly and satisfactorily. The predicted residue distance map allows quick structure modeling by the CNS suite, and the constructed models approach the same level of quality as the other state-of-the-art protein structure prediction methods when tested on CASP13 targets. Moreover, this method can be used directly for the structure prediction of membrane proteins without transfer learning.

show abstract

Deep‐learning contact‐map guided protein structure prediction in CASP13

Cited by 194 publications

References 55 publications

Ensembling multiple raw coevolutionary features with deep residual neural networks for contact‐map prediction in CASP13

Ensembling multiple raw coevolutionary features with deep residual neural networks for contact‐map prediction in CASP13

Assessment of protein model structure accuracy estimation in CASP13: Challenges in the era of deep learning

Predicting the Real‐Valued Inter‐Residue Distances for Proteins

Contact Info

Product

Resources

About