Unknown

Dataset Information

0

COUSCOus: improved protein contact prediction using an empirical Bayes covariance estimator.


ABSTRACT: The post-genomic era with its wealth of sequences gave rise to a broad range of protein residue-residue contact detecting methods. Although various coevolution methods such as PSICOV, DCA and plmDCA provide correct contact predictions, they do not completely overlap. Hence, new approaches and improvements of existing methods are needed to motivate further development and progress in the field. We present a new contact detecting method, COUSCOus, by combining the best shrinkage approach, the empirical Bayes covariance estimator and GLasso.Using the original PSICOV benchmark dataset, COUSCOus achieves mean accuracies of 0.74, 0.62 and 0.55 for the top L/10 predicted long, medium and short range contacts, respectively. In addition, COUSCOus attains mean areas under the precision-recall curves of 0.25, 0.29 and 0.30 for long, medium and short contacts and outperforms PSICOV. We also observed that COUSCOus outperforms PSICOV w.r.t. Matthew's correlation coefficient criterion on full list of residue contacts. Furthermore, COUSCOus achieves on average 10% more gain in prediction accuracy compared to PSICOV on an independent test set composed of CASP11 protein targets. Finally, we showed that when using a simple random forest meta-classifier, by combining contact detecting techniques and sequence derived features, PSICOV predictions should be replaced by the more accurate COUSCOus predictions.We conclude that the consideration of superior covariance shrinkage approaches will boost several research fields that apply the GLasso procedure, amongst the presented one of residue-residue contact prediction as well as fields such as gene network reconstruction.

SUBMITTER: Rawi R 

PROVIDER: S-EPMC5159955 | biostudies-literature | 2016 Dec

REPOSITORIES: biostudies-literature

altmetric image

Publications

COUSCOus: improved protein contact prediction using an empirical Bayes covariance estimator.

Rawi Reda R   Mall Raghvendra R   Kunji Khalid K   El Anbari Mohammed M   Aupetit Michael M   Ullah Ehsan E   Bensmail Halima H  

BMC bioinformatics 20161215 1


<h4>Background</h4>The post-genomic era with its wealth of sequences gave rise to a broad range of protein residue-residue contact detecting methods. Although various coevolution methods such as PSICOV, DCA and plmDCA provide correct contact predictions, they do not completely overlap. Hence, new approaches and improvements of existing methods are needed to motivate further development and progress in the field. We present a new contact detecting method, COUSCOus, by combining the best shrinkage  ...[more]

Similar Datasets

| S-EPMC5860114 | biostudies-other
| S-EPMC3283699 | biostudies-literature
| S-EPMC3634008 | biostudies-literature
| S-EPMC5925776 | biostudies-literature
| S-EPMC8579053 | biostudies-literature
2024-06-05 | GSE32030 | GEO
| S-EPMC5286518 | biostudies-literature
| S-EPMC6472625 | biostudies-literature
| S-EPMC4222596 | biostudies-other
| S-EPMC6324825 | biostudies-literature