CoinFold: a web server for protein contact prediction and contact-assisted protein folding - PubMed (original) (raw)

. 2016 Jul 8;44(W1):W361-6.

doi: 10.1093/nar/gkw307. Epub 2016 Apr 25.

Affiliations

CoinFold: a web server for protein contact prediction and contact-assisted protein folding

Sheng Wang et al. Nucleic Acids Res. 2016.

Abstract

CoinFold (http://raptorx2.uchicago.edu/ContactMap/) is a web server for protein contact prediction and contact-assisted de novo structure prediction. CoinFold predicts contacts by integrating joint multi-family evolutionary coupling (EC) analysis and supervised machine learning. This joint EC analysis is unique in that it not only uses residue coevolution information in the target protein family, but also that in the related families which may have divergent sequences but similar folds. The supervised learning further improves contact prediction accuracy by making use of sequence profile, contact (distance) potential and other information. Finally, this server predicts tertiary structure of a sequence by feeding its predicted contacts and secondary structure to the CNS suite. Tested on the CASP and CAMEO targets, this server shows significant advantages over existing ones of similar category in both contact and tertiary structure prediction.

© The Author(s) 2016. Published by Oxford University Press on behalf of Nucleic Acids Research.

PubMed Disclaimer

Figures

Figure 1.

Figure 1.

Illustration of CoinFold workflow. Given an input protein sequence, CoinFold uses HHblits (22) and HHpred (23) to generate sequence profile and search for related protein families. Then CoinFold conducts joint evolutionary coupling analysis and supervised prediction of both contacts and secondary structure. Finally, CoinFold predicts 3D models using CNS.

Figure 2.

Figure 2.

TMscore comparison of the top models generated by CoinFold, ConFold, and EVfold. The top 1 and the best (in terms of TMscore) of top 5 models are evaluated. The 36 CASP10 targets, 49 from CASP11 targets and 47 CAMEO targets are shown in red square, blue diamond, and green triangle, respectively. (A and B) Head-to-head comparison of Top1 and Top5 best models by CoinFold (in X-axis) and ConFold (in Y-axis). (C and D) Head-to-head comparison of Top1 and Top5 best models by CoinFold (in X-axis) and EVfold (in Y-axis).

Figure 3.

Figure 3.

CoinFold server job submission. (A) The web interface for job submission has fields for job name (1), optional user email address (2), and sequences to be submitted (3). The sequences shall be in FASTA format and can also be submitted in a file (3). User can also click on the example link to see an example. Submit a job by clicking on the submit button (4). (B) An example for submission by a publicly available program Curl. Only ‘sequences’ and the submission URL (shown in underlines) are required and the others are optional. A job URL will be returned on screen after submission.

Figure 4.

Figure 4.

CoinFold server result page. The left part shows the predicted contact map (1), where the predicted score is displayed in greyscale, with a higher score represented by a darker color. The middle part shows the job status (the submitted, scheduled, and finished time) (2), as well as two downloading buttons for the predicted contact map (3) and 5 predicted 3D models (4). The right part contains a button to view alternative 3D models (5), a display bar for showing rank and score of the selected 3D model (6) and visualization of the selected 3D model (7).

Similar articles

Cited by

References

    1. Di Lena P., Nagata K., Baldi P. Deep architectures for protein contact map prediction. Bioinformatics. 2012;28:2449–2457. - PMC - PubMed
    1. Kim D.E., DiMaio F., Yu‐Ruei Wang R., Song Y., Baker D. One contact for every twelve residues allows robust and accurate topology‐level protein structure modeling. Proteins: Struct. Funct. Bioinform. 2014;82:208–218. - PMC - PubMed
    1. de Juan D., Pazos F., Valencia A. Emerging methods in protein co-evolution. Nat. Rev. Genet. 2013;14:249–261. - PubMed
    1. Marks D.S., Hopf T.A., Sander C. Protein structure prediction from sequence variation. Nat. Biotechnol. 2012;30:1072–1080. - PMC - PubMed
    1. Göbel U., Sander C., Schneider R., Valencia A. Correlated mutations and residue contacts in proteins. Proteins: Struct. Funct. Bioinform. 1994;18:309–317. - PubMed

Publication types

MeSH terms

Substances

LinkOut - more resources