Comprehensive comparative assessment of in-silico predictors of disordered regions.

By Zhenling Peng, Lukasz Kurgan. 2012

176 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Molecular Biology

Citations in the corpus

IUPred2A: context-dependent prediction of protein disorder as a function of redox state and protein binding (2018, methodology): “While there are other methods that can achieve higher accuracies on particular datasets, IUPred still provides robust predictions with a favorable trade-off between speed and accuracy (22–24).”
DFLpred: High-throughput prediction of disordered flexible linker regions in protein sequences (2016, unknown): “These methods were built using crystallographic data that exclude disordered residues and thus they cannot accurately find disordered residues, which was shown in (Peng and Kurgan, 2012).”
Genome‐scale prediction of proteins with long intrinsically disordered regions (2014, methodology): “These predictors include 13 methods that were evaluated in a recent review 19 25 We divide these methods into those that are based on a single sequence, which are fast to compute, and those that utilize multiple sequence alignment, which comes with a higher computational cost.”
D2P2: database of disordered protein predictions (2012, unknown): “Because of the biases of structural resolution and the relative ease of task for disorder prediction methods compared with de novo fold prediction, many algorithms have been developed to discover novel regions of disorder from amino acid sequence alone (13,14).”
Comprehensive review of methods for prediction of intrinsic disorder and its molecular functions (2017, methodology): “Kurgan’s group [38], PONDR-VSL2B achieved the third highest AUC (0.”
High-throughput prediction of RNA, DNA and protein binding regions mediated by intrinsic disorder (2015, methodology): “Logistic regression is a probabilistic classification algorithm that was extensively used in related efforts including prediction of intrinsic disorder (6) and the ordered protein-RNA/DNA/-protein interactions that were annotated using crystal structures (48–51).”
Exceptionally abundant exceptions: comprehensive characterization of intrinsic disorder in all domains of life (2014, background): “Espritz and IUPred are competitive in terms of their predictive quality [38, 41], and they cover the main characteristics of the disorder including the three annotation types and two types of disordered segments.”