Assessment of protein disorder region predictions in CASP10
By Bohdan Monastyrskyy, Andriy Kryshtafovych, John Moult, Anna Tramontano, Krzysztof Fidelis. 2013
162 citations recorded by the source corpus.
The article presents the assessment of disorder region predictions submitted to CASP10. The evaluation is based on the three measures tested in previous CASPs: (i) balanced accuracy, (ii) the Matthews correlation coefficient for the binary predictions, and (iii) the area under the curve in the receiver operating characteristic (ROC) analysis of predictions using probability annotation. We also performed new analyses such as comparison of the submitted predictions with those obtained with a Naïve disorder prediction method and with predictions from the disorder prediction databases D2P2 and MobiDB. On average, the methods participating in CASP10 demonstrated slightly better performance than those in CASP9. Proteins 2014; 82(Suppl 2):127–137. © 2013 Wiley Periodicals, Inc.
Subfields: Artificial Intelligence, Molecular Biology
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Lukasz Kurgan
- Silvio C. E. Tosatto
- Zsuzsanna Dosztányi
- Vladimir N Uversky
- Jianzhu Ma
- Michele Vendruscolo
- Piero Fariselli
- Krzysztof Fidelis
In Molecular Biology
- Lukasz Kurgan
- Vladimir N Uversky
- Zsuzsanna Dosztányi
- Zhenling Peng
- Fanchi Meng
- Sheng Wang
- Andriy Kryshtafovych
- Jinbo Xu
Citations in the corpus
- Critical assessment of protein intrinsic disorder prediction (CAID) ‐ Results of round 2 (2023, methodology): “28 To overcome this problem, in CAID we leverage the annotation provided by the DisProt database which stores the position of IDRs along the protein sequence when there is experimental evidence in the literature.”
- MobiDB 2.0: an improved database of intrinsically disordered and mobile proteins (2014, methodology): “Many are quite accurate, as shown at the recent Critical Assessment of techniques for protein Structure Prediction (CASP-10) (12) and a large-scale assessment of disorder predictors (10).”
- DeepCNF-D: Predicting Protein Order/Disorder Regions by Weighted Deep Convolutional Neural Fields (2015, methodology): “PrDOS-CNF [15] and OnD-CRF [16] exploit this interdependency between adjacent order/disorder labels through a linear-chain Conditional Random Field structure [17], but they are unable to describe the long-range sequence information; (b) How to solve the label imbalance issue.”
- MobiDB‐lite: fast and highly specific consensus prediction of intrinsic disorder in proteins (2017, background): “A plethora of computational methods have been developed to predict ID, e.g. (Doszt anyi et al., 2010; He et al., 2009), with varying levels of accuracy (Monastyrskyy et al., 2014; Walsh et al., 2015).”
- The s2D method: simultaneous sequence-based prediction of the statistical populations of ordered and disordered regions in proteins. (2015, background): “Predictions of intrinsic disorder can be presented together with predictions of secondary or tertiary structure, as performed by some Web servers [22,26,27], to provide qualitative insights about the type and the stability of the structures formed by a given protein.”
- Comprehensive large-scale assessment of intrinsic protein disorder (2015, methodology): “Many are tuned for the disorder style used in the Critical Assessment of techniques for protein Structure Prediction (CASP), where the goal is to detect missing residues in the X-ray crystal (Monastyrskyy et al ., 2014).”
- High-throughput prediction of RNA, DNA and protein binding regions mediated by intrinsic disorder (2015, background): “Motivated by related works (30,31) we consider the disordered regions with at least 4 consecutive disordered residues.”
- CASP PREDICTION CENTER INFRASTRUCTURE AND EVALUATION MEASURES IN CASP10 AND CASP ROLL (2013, background): “13,14 In the DR category we also begun to require that prediction of a residue in a disordered state should be necessarily accompanied by a probability value in the range 0.5–1.0.”
- A comprehensive assessment of long intrinsic protein disorder from the DisProt database (2018, methodology): “In CASP, this situation has been acknowledged as being not optimal (Monastyrskyy et al. , 2014) and ultimately led to the discontinuing of the disorder prediction category.”
- Disorder Prediction Methods, Their Applicability to Different Protein Targets and Their Usefulness for Guiding Experimental Studies (2015, methodology): “For CASP10, the MCC score (Matthew’s correlation coefficient) was held as the main disorder prediction quality score, as it was deemed the most balanced of the three typical binary prediction scores used in CASP9 [58].”