PrDOS: prediction of disordered protein regions from amino acid sequence

By Takashi Ishida, Kengo Kinoshita. Nucleic Acids Res., 2007

827 citations recorded by the source corpus.

PrDOS is a server that predicts the disordered regions of a protein from its amino acid sequence (http://prdos.hgc.jp). The server accepts a single protein amino acid sequence, in either plain text or FASTA format. The prediction system is composed of two predictors: a predictor based on local amino acid sequence information and one based on template proteins. The server combines the results of the two predictors and returns a two-state prediction (order/disorder) and a disorder probability for each residue. The prediction results are sent by e-mail, and the server also provides a web-interface to check the results.

Subfields: Materials Chemistry, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/bead22aea39653d1d6b9a1ff388b2228d20dc00a

How researchers see this paper

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

In Materials Chemistry

In Molecular Biology

Citations in the corpus

The Role of Balanced Training and Testing Data Sets for Binary Classifiers in Bioinformatics (2013, neutral): “The other three methods listed in Table 5 did not use available cost models in the machine learning methods they used, including LIBSVM (CBRC-Poodle) or SVMLight (Prdos2) or any form of weighting or oversampling in a neural network (Multicom-refine).”
MetaDisorder: a meta-server for the prediction of intrinsic disorder in proteins (2012, methodology): “…long disorder using an SVM. web service [29] PrDOS Predicts missing coordinates in 3D structure using SVM and PSSMs from PSI-BLAST. web service [30] Spritz Predicts long and short disorder (missing coordinates) using two separate SVMs. Utilizes secondary structure. web service [31] RONN…”
Disorder Prediction Methods, Their Applicability to Different Protein Targets and Their Usefulness for Guiding Experimental Studies (2015, methodology): “Uses DisEMBL (3 versions) [18], DISOPRED2 [3], DISpro [41], GlobPlot [28], iPDA [42], IUPred (2 versions) [39], Pdisorder, POODLE-S [43], POODLE-L [44], PrDOS [45], Spritz (2 versions) [46], and RONN [40].”
p53 Proteoforms and Intrinsic Disorder: An Illustration of the Protein Structure–Function Continuum Concept (2016, neutral): “pro/) [113], which represents the outputs of IUPred [114], PONDR® VLXT [115], PrDOS [116], PONDR® VSL2B [117,118], PV2 [113], and ESpritz [119].”
A comprehensive assessment of long intrinsic protein disorder from the DisProt database (2018, background): “Machine learning algorithms (neural networks and support-vector machines) are trained to recognize features that distinguish a collection of positive (disordered) sequences from negative (ordered) proteins (Ishida and Kinoshita, 2007; Jones and Cozzetto, 2015; Vullo et al., 2006; Wang et al., 2012, ”
DISOPRED3: precise disordered region predictions with annotated protein-binding activity (2014, background): “analyses also highlighted differences in the patterns of length, location and sequence conservation among IDRs, and machine-learning techniques have been trained to detect them (Eickholt and Cheng 2013; Hirose et al., 2007; Ishida and Kinoshita 2007; Liu and Rost 2003; Shimizu et al., 2007a,b; Ward ”
DeepCNF-D: Predicting Protein Order/Disorder Regions by Weighted Deep Convolutional Neural Fields (2015, methodology): “Examples include PrDOS [10], PONDR [11], POODLE [12], and MetaDisorder [13].”
D2P2: database of disordered protein predictions (2012, methodology): “The second predictor assumes the conservation of intrinsic disorder in homologous protein domain families (19,26) and is implemented using PSI-BLAST (22) and a novel measure of disorder (27).”
MFDp2 (2013, methodology): “27,45 The disorder prediction is part of the biannual Critical Assessment of techniques for protein Structure Prediction (CASP) experiments since 2002, 46 which further signifies interest in this area.”
APOD: accurate sequence-based predictor of disordered flexible linkers (2020, background): “According to a recent analysis, the second most commonly annotated function of IDPs/IDRs is entropic chain, behind only the molecular recognition function (Katuwawala et al., 2019a,b,c).”
Comprehensive large-scale assessment of intrinsic protein disorder (2015, methodology): “Machine learning, especially neural networks, has been widely used to predict protein disorder (Eickholt and Cheng, 2013; Hirose et al ., 2007; Ishida and Kinoshita, 2007; Linding et al. , 2003b; Walsh et al ., 2011, 2012; Ward et al ., 2004; Yang et al ., 2005).”
Insights into Coupled Folding and Binding Mechanisms from Kinetic Studies (2016, background): “These compositional differences form the basis for the identification of disordered regions using bioinformatics algorithms (14).”
Improving protein disorder prediction by deep bidirectional long short‐term memory recurrent neural networks (2016, neutral): “, 2007), PrDOS (Ishida and Kinoshita, 2007), Spritz (Vullo et al.”
PONDR-FIT: A Meta-Predictor of Intrinsically Disordered Amino Acids (2010, background): “In terms of AUC, the META-Disorder predictor improved the accuracy to 0.80 compared to IUPred at 0.76, while metaPrDOS achieved 0.90 compared to IUPred at 0.83.”
AUCpreD: proteome-level protein disorder prediction by AUC-maximized deep convolutional neural fields (2016, methodology): “Per-residue and per-protein performance on the CAMEO targets Methods Per-residue Per-protein Acc Sens Spec Mcc AUCpr AUC Acc Sens Spec Mcc P-value Predictors using sequence profile or template AUCpreDp 0.75 0.53 0.97 0.49 0.55 0.88 0.76 0.58 0.95 0.48 N/A DeepCNF-Dp 0.73 0.51 0.95 0.43 0.47 0.84 0.7”