Abstract
BackgroundContact-guided protein structure prediction methods are becoming more and more successful because of the latest advances in residue-residue contact prediction. To support contact-driven structure prediction, effective tools that can quickly build tertiary structural models of good quality from predicted contacts need to be developed.ResultsWe develop an improved contact-driven protein modelling method, CONFOLD2, and study how it may be effectively used for ab initio protein structure prediction with predicted contacts as input. It builds models using various subsets of input contacts to explore the fold space under the guidance of a soft square energy function, and then clusters the models to obtain the top five models. CONFOLD2 obtains an average reconstruction accuracy of 0.57 TM-score for the 150 proteins in the PSICOV contact prediction dataset. When benchmarked on the CASP11 contacts predicted using CONSIP2 and CASP12 contacts predicted using Raptor-X, CONFOLD2 achieves a mean TM-score of 0.41 on both datasets.ConclusionCONFOLD2 allows to quickly generate top five structural models for a protein sequence when its secondary structures and contacts predictions at hand. The source code of CONFOLD2 is publicly available at https://github.com/multicom-toolbox/CONFOLD2/.
Highlights
Contact-guided protein structure prediction methods are becoming more and more successful because of the latest advances in residue-residue contact prediction
On the PSICOV dataset, when best of 200 models are evaluated, CONFOLD2 achieves a mean TM-score of 0.57 compared to 0.55 of CONFOLD. This improvement in CONFOLD2 is statistically significant per paired t-test with a p-value of 4 × 10-8
To evaluate our model selection technique we compared our approach of model selection using clustering with the model ranking using contact satisfaction score only
Summary
We compared the performance of CONFOLD2 with the original CONFOLD method [3] on the 150 proteins in the PSICOV dataset [11] using the contacts predicted by the PSICOV method [11] (see Table 1). On the PSICOV dataset, when best of 200 models are evaluated, CONFOLD2 achieves a mean TM-score of 0.57 compared to 0.55 of CONFOLD. This improvement in CONFOLD2 is statistically significant per paired t-test with a p-value of 4 × 10-8 (see Additional file 1: Table S1 for a detailed comparison). We reconstructed models for the PSICOV150 dataset using contacts predicted by MetaPSICOV [13] and obtained a mean TM-score of 0.62 when best of top-five models are evaluated (see Additional file 1: Table S1 for detailed results), indicating that the improved contact prediction leads to the better tertiary structure reconstruction. For a more rigorous evaluation, on the PSICOV-150 dataset, we compared CONFOLD2’s performance with two other state-of-the-art modeling methods that use structural template fragments. It is worth noting that the latest results of RaptorX on the CASP12 targets are better which can be found in [17]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
