MoRFpred, a computational tool for sequence-based prediction and characterization of short disorder-to-order transitioning binding regions in proteins

By Fatemeh Miri Disfani, Wei-Lun Hsu, Marcin J. Mizianty, Christopher J. Oldfield, Bin Xue, A. Keith Dunker, Vladimir N Uversky, Lukasz Kurgan. 2012

340 citations recorded by the source corpus.

Motivation: Molecular recognition features (MoRFs) are short binding regions located within longer intrinsically disordered regions that bind to protein partners via disorder-to-order transitions. MoRFs are implicated in important processes including signaling and regulation. However, only a limited number of experimentally validated MoRFs is known, which motivates development of computational methods that predict MoRFs from protein chains. Results: We introduce a new MoRF predictor, MoRFpred, which identifies all MoRF types (α, β, coil and complex). We develop a comprehensive dataset of annotated MoRFs to build and empirically compare our method. MoRFpred utilizes a novel design in which annotations generated by sequence alignment are fused with predictions generated by a Support Vector Machine (SVM), which uses a custom designed set of sequence-derived features. The features provide information about evolutionary profiles, selected physiochemical properties of amino acids, and predicted disorder, solvent accessibility and B-factors. Empirical evaluation on several datasets shows that MoRFpred outperforms related methods: α-MoRF-Pred that predicts α-MoRFs and ANCHOR which finds disordered regions that become ordered when bound to a globular partner. We show that our predicted (new) MoRF regions have non-random sequence similarity with native MoRFs. We use this observation along with the fact that predictions with higher probability are more accurate to identify putative MoRF regions. We also identify a few sequence-derived hallmarks of MoRFs. They are characterized by dips in the disorder predictions and higher hydrophobicity and stability when compared to adjacent (in the chain) residues. Availability: http://biomine.ece.ualberta.ca/MoRFpred/; http://biomine.ece.ualberta.ca/MoRFpred/Supplement.pdf Contact: lkurgan@ece.ualberta.ca Supplementary information: Supplementary data are available at Bioinformatics online.

Subfields: Computational Theory and Mathematics, 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 Computational Theory and Mathematics

In Molecular Biology

Citations in the corpus

SPOT-Disorder2: Improved Protein Intrinsic Disorder Prediction by Ensembled Deep Learning (2019, methodology): “We have downloaded the Test and Test2012 datasets from the MoRFpred server [57] (http://biomine.cs.vcu.edu/servers/ MoRFpred/) for validation and independent testing, respectively.”
IUPred2A: context-dependent prediction of protein disorder as a function of redox state and protein binding (2018, methodology): “As a result, larger datasets were re-sorted to PDB complexes formed between short and longer segments, assuming that the short segments are usually associated with disorder (30).”
DFLpred: High-throughput prediction of disordered flexible linker regions in protein sequences (2016, positive): “They include methods that address protein binding (Disfani et al., 2012; Dosztanyi et al., 2009; Fang et al., 2013; Jones and Cozzetto, 2014; VC The Author 2016.”
DISOPRED3: precise disordered region predictions with annotated protein-binding activity (2014, methodology): “A set of 840 peptides, with lengths between 5 and 25 amino acids and solved in complex with globular protein domains, was initially obtained from a previous study (Disfani et al. , 2012).”
Improving protein disorder prediction by deep bidirectional long short‐term memory recurrent neural networks (2016, methodology): “Several machine-learning tools were developed specifically for prediction of binding sites in disorder (Garner et al. , 1999), such as alpha-MoRF (Oldfield et al. , 2005), MoRFpred (Disfani et al. , 2012), ANCHOR (Me´sz (cid:2) aros et al. , 2009) and DISOPRED3 (Jones and Cozzetto, 2015).”
High-throughput prediction of RNA, DNA and protein binding regions mediated by intrinsic disorder (2015, methodology): “Moreover, DisoRDPbind’s predictions of the disordered protein-binding residues are characterized by relatively high PCC > 0.5 with the outputs of ANCHOR and low correlation with MoRFpred and DISOPRED3.”
Comprehensive review of methods for prediction of intrinsic disorder and its molecular functions (2017, methodology): “This fairly sophisticated design results in an accurate prediction of MoRFs [126] but it also requires long runtime.”
Computational identification of MoRFs in protein sequences (2015, methodology): “However, in this study we focus only on computationally identifying MoRFs as defined initially by Mohan et al. (2006) and Disfani et al. (2012).”
MFSPSSMpred: identifying short disorder-to-order binding regions in disordered proteins based on contextual local evolutionary conservation (2013, methodology): “Because sequences longer than 1000 residues cannot be processed by MoRFpred [4], in our study, we also aimed to predict short MoRFs (5–25 residues).”