Protein threading using residue co-variation and deep learning

Zhu, Jianwei; Wang, Sheng; Bu, Dongbo; Xu, Jinbo

doi:10.1093/bioinformatics/bty278

Cited by 70 publications

(101 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, 50% of the time RaptorX‐TBM finds the correct fold that is 10% more than that of our work (considering 20 full‐length targets). It should be noted here that RaptorX‐TBM uses inter‐residue distance maps that is considered more informative than inter‐residue contact maps in predicting protein 3D structure . Moreover, the comparison of our work with RaptorX‐TBM may not be fair since threading performance is directly dependent on the template library and RaptorX‐TBM potentially is based on a different template library compared to our work.…”

Section: Resultsmentioning

confidence: 88%

Does inclusion of residue‐residue contact information boost protein threading?

Bhattacharya

2019

Proteins

View full text Add to dashboard Cite

Template‐based modeling is considered as one of the most successful approaches for protein structure prediction. However, reliably and accurately selecting optimal template proteins from a library of known protein structures having similar folds as the target protein and making correct alignments between the target sequence and the template structures, a template‐based modeling technique known as threading, remains challenging, particularly for non‐ or distantly‐homologous protein targets. With the recent advancement in protein residue‐residue contact map prediction powered by sequence co‐evolution and machine learning, here we systematically analyze the effect of inclusion of residue‐residue contact information in improving the accuracy and reliability of protein threading. We develop a new threading algorithm by incorporating various sequential and structural features, and subsequently integrate residue‐residue contact information as an additional scoring term for threading template selection. We show that the inclusion of contact information attains statistically significantly better threading performance compared to a baseline threading algorithm that does not utilize contact information when everything else remains the same. Experimental results demonstrate that our contact based threading approach outperforms popular threading method MUSTER, contact‐assisted ab initio folding method CONFOLD2, and recent state‐of‐the‐art contact‐assisted protein threading methods EigenTHREADER and map_align on several benchmarks. Our study illustrates that the inclusion of contact maps is a promising avenue in protein threading to ultimately help to improve the accuracy of protein structure prediction.

show abstract

Section: Resultsmentioning

confidence: 88%

Does inclusion of residue‐residue contact information boost protein threading?

Bhattacharya

2019

Proteins

View full text Add to dashboard Cite

show abstract

“…CAMEO evaluates the structure predictions applying different scores for assessing different aspects of modeling, such as accuracy of a single protein chain, the homo‐oligomeric interface, or the binding site (Table ). Here, we categorized the data into the target domains “hard,” “medium,” and “easy.” The three best methods “Robetta,” “Raptor‐X,” and “IntFOLD5‐TS returned all hard targets (in total 62) with a very similar performance, both in average lDDT and SD, of 47.29±12.96, 45.25±13.57, and 44.79±12.82 (CAD‐scores: 0.55±0.09, 0.53±0.10, and 0.52±0.09), respectively. Although the performance is very similar on this specific target set, the response times vary greatly with “Raptor‐X” clearly in the lead (7.8 hours).…”

Section: Resultsmentioning

confidence: 97%

“…Here, we categorized the data into the target domains "hard," "medium," and "easy." The three best methods "Robetta," 19 "Raptor-X," 20 CAMEO analyses the accuracy of the binding-site residues ("lDDT-BS" 4 ), where on the current data set across 94 targets and 83 unique ligands (see Data S1), the top modeling groups are also producing good quality binding sites with lDDT-BS scores close to 70.…”

Section: General Performance Analysismentioning

confidence: 99%

Introducing “best single template” models as reference baseline for the Continuous Automated Model Evaluation (CAMEO)

et al. 2019

View full text Add to dashboard Cite

Critical blind assessment of structure prediction techniques is crucial for the scientific community to establish the state of the art, identify bottlenecks, and guide future developments. In Critical Assessment of Techniques in Structure Prediction (CASP), human experts assess the performance of participating methods in relation to the difficulty of the prediction task in a biennial experiment on approximately 100 targets. Yet, the development of automated computational modeling methods requires more frequent evaluation cycles and larger sets of data. The “Continuous Automated Model EvaluatiOn (CAMEO)” platform complements CASP by conducting fully automated blind prediction evaluations based on the weekly pre‐release of sequences of those structures, which are going to be published in the next release of the Protein Data Bank (PDB). Each week, CAMEO publishes benchmarking results for predictions corresponding to a set of about 20 targets collected during a 4‐day prediction window. CAMEO benchmarking data are generated consistently for all methods at the same point in time, enabling developers to cross‐validate their method's performance, and referring to their results in publications. Many successful participants of CASP have used CAMEO—either by directly benchmarking their methods within the system or by comparing their own performance to CAMEO reference data. CAMEO offers a variety of scores reflecting different aspects of structure modeling, for example, binding site accuracy, homo‐oligomer interface quality, or accuracy of local model confidence estimates. By introducing the "bestSingleTemplate" method based on structure superpositions as a reference for the accuracy of 3D modeling predictions, CAMEO facilitates objective comparison of techniques and fosters the development of advanced methods.

show abstract

“…In contrast, deep ResNet not only works very well on proteins without many sequence homologs, but also can directly predict interresidue or interatom distance. 8,9 In CASP12 and previous CAMEO tests we have demonstrated that deep ResNet can greatly improve contact prediction 6,10-12 and that without extensive conformation sampling, contacts predicted by deep ResNet can be used to build correct folds for (even membrane) proteins without detectable homology in PDB. 13 Afterwards, the power of deep convolutional neural network has been further validated by other research groups who have developed similar deep networks for contact prediction.…”

Section: Introductionmentioning

confidence: 93%

“…Prior to CASP13, we have extended our deep ResNet to protein distance prediction and showed that distance-based potential predicted by ResNet may significantly improve protein threading for targets without good templates in PDB. 8 We have developed a simple and efficient distance geometry algorithm that may quickly fold a protein sequence from distance and torsion angles predicted by deep ResNet. 9 Our deep ResNet not only can predict distance matrix from sequence and coevolutionary information, but also from template and alignment information.…”

Section: Introductionmentioning

confidence: 99%

Analysis of distance‐based protein structure prediction by deep learning in CASP13

Wang

2019

Proteins

Self Cite

134

View full text Add to dashboard Cite

This paper reports the CASP13 results of distance‐based contact prediction, threading, and folding methods implemented in three RaptorX servers, which are built upon the powerful deep convolutional residual neural network (ResNet) method initiated by us for contact prediction in CASP12. On the 32 CASP13 FM (free‐modeling) targets with a median multiple sequence alignment (MSA) depth of 36, RaptorX yielded the best contact prediction among 46 groups and almost the best 3D structure modeling among all server groups without time‐consuming conformation sampling. In particular, RaptorX achieved top L/5, L/2, and L long‐range contact precision of 70%, 58%, and 45%, respectively, and predicted correct folds (TMscore > 0.5) for 18 of 32 targets. Further, RaptorX predicted correct folds for all FM targets with >300 residues (T0950‐D1, T0969‐D1, and T1000‐D2) and generated the best 3D models for T0950‐D1 and T0969‐D1 among all groups. This CASP13 test confirms our previous findings: (a) predicted distance is more useful than contacts for both template‐based and free modeling; and (b) structure modeling may be improved by integrating template and coevolutionary information via deep learning. This paper will discuss progress we have made since CASP12, the strength and weakness of our methods, and why deep learning performed much better in CASP13.

show abstract

Protein threading using residue co-variation and deep learning

Cited by 70 publications

References 41 publications

Does inclusion of residue‐residue contact information boost protein threading?

Does inclusion of residue‐residue contact information boost protein threading?

Introducing “best single template” models as reference baseline for the Continuous Automated Model Evaluation (CAMEO)

Analysis of distance‐based protein structure prediction by deep learning in CASP13

Contact Info

Product

Resources

About