Natively Unstructured Loops Differ from Other Loops

By Avner Schlessinger, Jinfeng Liu, Burkhard Rost. 2007

99 citations recorded by the source corpus.

Natively unstructured or disordered protein regions may increase the functional complexity of an organism; they are particularly abundant in eukaryotes and often evade structure determination. Many computational methods predict unstructured regions by training on outliers in otherwise well-ordered structures. Here, we introduce an approach that uses a neural network in a very different and novel way. We hypothesize that very long contiguous segments with nonregular secondary structure (NORS regions) differ significantly from regular, well-structured loops, and that a method detecting such features could predict natively unstructured regions. Training our new method, NORSnet, on predicted information rather than on experimental data yielded three major advantages: it removed the overlap between testing and training, it systematically covered entire proteomes, and it explicitly focused on one particular aspect of unstructured regions with a simple structural interpretation, namely that they are loops. Our hypothesis was correct: well-structured and unstructured loops differ so substantially that NORSnet succeeded in their distinction. Benchmarks on previously used and new experimental data of unstructured regions revealed that NORSnet performed very well. Although it was not the best single prediction method, NORSnet was sufficiently accurate to flag unstructured regions in proteins that were previously not annotated. In one application, NORSnet revealed previously undetected unstructured regions in putative targets for structural genomics and may thereby contribute to increasing structural coverage of large eukaryotic families. NORSnet found unstructured regions more often in domain boundaries than expected at random. In another application, we estimated that 50%–70% of all worm proteins observed to have more than seven protein–protein interaction partners have unstructured regions. The comparative analysis between NORSnet and DISOPRED2 suggested that long unstructured loops are a major part of unstructured regions in molecular networks.

Subfields: 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 Molecular Biology

Citations in the corpus

Comprehensive comparative assessment of in-silico predictors of disordered regions. (2012, methodology): “Disorder predictors that were developed using regions identified by one experimental method could be less accurate for prediction of disorder characterized by other methods [[41]].”
Comprehensive review of methods for prediction of intrinsic disorder and its molecular functions (2017, background): “These inputs are divided into two types: 1) the outputs from four disorder predictors including NORSnet [76], IUPred [46], DISOPRED2 [71], and UCon [77]; and 2) other sequence-derived information including flexibility predicted with PROFbval [56], predicted secondary structure and solvent accessibil”
PredictProtein—an open resource for online prediction of protein structural and functional features (2014, unknown): “NORSnet (22) predicts disordered regions with NO Regular Secondary structure (NORS (46), i.e. long loops), separating very long disordered loops predicted by NORSp (47) from all other regions in the PDB (11).”
Improving protein disorder prediction by deep bidirectional long short‐term memory recurrent neural networks (2016, methodology): “…in many accurate predictors, such as DisEMBL (Linding et al. , 2003 a ), DISOPRED (Jones and Ward, 2003), DISpro (Cheng et al. , 2005), NORSnet (Schlessinger et al. , 2007 a ), the PONDR series (Romero et al. , 2001), PROFbval (Schlessinger et al. , 2006), RONN (Yang et al. , 2005), SPINE-D…”
PONDR-FIT: A Meta-Predictor of Intrinsically Disordered Amino Acids (2010, methodology): “These include the early PONDR series [19–21], DisEMBL [22], DISOPRED [23], and NORSnet [24], which used artificial neural networks; PONDR®VSL2 [21], DISOPRED2 [25], and POODLE [26], which employed support vector machines; and DISPro [27], which used a combination of neural networks and Bayesian meth”
Predict impact of single amino acid change upon protein structure (2012, methodology): “In addition, we used the following predicted structural and functional features: secondary structure [32,33] and solvent accessibility [24,25,32], protein flexibility [34], protein disorder [35-38], protein-protein interaction hotspots [39-41] and DNA-binding residues [42].”
Improved Disorder Prediction by Combination of Orthogonal Approaches (2009, methodology): “For both the C-terminal domains of cell-surface glycoprotein CD3 gamma chain and alkylmercury lyase, Ucon and NORSnet gave some signal of disorder (Fig.”
Improved sequence-based prediction of disordered regions with multilayer fusion of multiple information sources (2010, unknown): “Contact: lkurgan@ece.ualberta.ca”